WO2024142031A1 - A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant - Google Patents
A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant Download PDFInfo
- Publication number
- WO2024142031A1 WO2024142031A1 PCT/IB2024/050556 IB2024050556W WO2024142031A1 WO 2024142031 A1 WO2024142031 A1 WO 2024142031A1 IB 2024050556 W IB2024050556 W IB 2024050556W WO 2024142031 A1 WO2024142031 A1 WO 2024142031A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- feedback
- product
- module configured
- service
- Prior art date
Links
- 238000003058 natural language processing Methods 0.000 title claims description 17
- 230000001149 cognitive effect Effects 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims description 138
- 238000004458 analytical method Methods 0.000 claims description 55
- 230000000694 effects Effects 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 35
- 238000012790 confirmation Methods 0.000 claims description 31
- 230000004044 response Effects 0.000 claims description 27
- 125000001475 halogen functional group Chemical group 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 16
- 230000009471 action Effects 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 230000015572 biosynthetic process Effects 0.000 claims description 11
- 230000008901 benefit Effects 0.000 claims description 10
- 230000003340 mental effect Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 5
- 230000008520 organization Effects 0.000 claims description 4
- 230000000593 degrading effect Effects 0.000 claims description 3
- 230000004438 eyesight Effects 0.000 claims description 3
- 230000000116 mitigating effect Effects 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 230000033228 biological regulation Effects 0.000 claims description 2
- 230000007423 decrease Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000003780 insertion Methods 0.000 claims description 2
- 230000037431 insertion Effects 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 238000012986 modification Methods 0.000 claims description 2
- 230000004048 modification Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 238000009825 accumulation Methods 0.000 claims 2
- 238000001303 quality assessment method Methods 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 21
- 238000004891 communication Methods 0.000 abstract description 11
- 230000006378 damage Effects 0.000 abstract description 4
- 238000012552 review Methods 0.000 description 66
- 238000004590 computer program Methods 0.000 description 47
- 230000008451 emotion Effects 0.000 description 43
- 230000006399 behavior Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 12
- 230000001755 vocal effect Effects 0.000 description 11
- 239000003795 chemical substances by application Substances 0.000 description 10
- 238000007418 data mining Methods 0.000 description 10
- 230000010365 information processing Effects 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 10
- 238000003786 synthesis reaction Methods 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 8
- 230000002996 emotional effect Effects 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 7
- 238000007790 scraping Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 230000008909 emotion recognition Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000004873 anchoring Methods 0.000 description 4
- 230000003190 augmentative effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004630 mental health Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000000638 stimulation Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000008450 motivation Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000005562 fading Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000001976 improved effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000000275 quality assurance Methods 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 238000013518 transcription Methods 0.000 description 2
- 230000035897 transcription Effects 0.000 description 2
- 206010063659 Aversion Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/55—Rule-based translation
- G06F40/56—Natural language generation
Definitions
- H04N 21/475 - End-user interface for inputting end-user data, e.g. PIN [Personal Identification Number] or preference data [2011.01]
- the instant messaging method comprises: providing a graphical user interface; determining a selection of two or more existing messages; creating, on an instruction from the GUI, a relationship between the selected messages; and indicating, using links or edges on between the messages, the relationship between the messages. All related messages may be selected with a single selection and printed, stored, or deleted as a batch.
- a method includes performing computerized monitoring with a computer of at least one side of a telephone conversation, which includes spoken words, between a first person and a second person, automatically identifying at least one topic of the conversation, automatically performing a search for information related to the at least one topic, and outputting a result of the search. Also a system for performing the method.
- This patent represent a computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.
- a computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.
- a database includes statistics of human associations of human voice parameters with emotions.
- a voice signal is received. At least one feature of this voice signal is extracted. This extracted voice feature is then compared to the voice parameters in the database.
- An emotion is selected from the database based on the comparison of the extracted voice feature to the voice parameters.
- Input from the user is received. This input includes a user-determined emotion. The user-determined emotion is compared with the emotion selected from the database. The selected emotion is output and a determination as to whether the user-determined emotion matches the emotion selected from the database is made. A prize is then awarded to the user if the user-determined emotion is determined to match the selected emotion from the database.
- the invention comprises capturing a customer's speech, recognizing a key word in the customer's speech, searching a database, and retrieving information from the database.
- the retrieving is a real-time process, completed during a conversation involving the customer and a customer service representative. Examples include methods employing computerized speech recognition and key words to improve customer service, systems for executing methods of the present invention, and instructions on a computer-usable medium, or resident in a computer system, for executing methods of the present invention.
- a system which uses automatic speech recognition to provide dialogs with human speakers automatically detects one or more characteristics, which may be characteristics of a speaker, his speech, his environment, or the speech channel used to communicate with the speaker.
- the characteristic may be detected either during the dialog or at a later time based on stored data representing the dialog. If the characteristic is detected during the dialog, the dialog can be customized for the speaker at an application level, based on the detected characteristic.
- the customization may include customization of operations and features such as call routing, error recovery, call flow, content selection, system prompts, or system persona.
- Data indicative of detected characteristics can be stored and accumulated for many speakers and/or dialogs and analyzed offline to generate a demographic or other type of analysis of the speakers or dialogs with respect to one or more detected characteristics.
- a method and system is provided to monitor speech and detect keywords or phrases in the speech, such as for example, monitored calls in a call center or speakers/presenters using teleprompters, or the like.
- information associated with the keywords or phrases may be presented to a display device so that a user may dynamically receive new information as context of the speech progresses. This provides dynamic information as the context of the conversation develops.
- the information may be presented as links, cues, text, or similar formats.
- the detected keywords or phrases may also be associated with rules that govern the conditions and criteria for processing the detected keyword and presentation of the information.
- An information processing method includes the steps of: extracting speech data and sound data used for recognizing phonemes included in the speech data as words; identifying a section surrounded by pauses within a speech spectrum of the speech data; performing sound analysis on the identified section to identify a word in the section; generating prosodic feature values for the words; acquiring frequencies of occurrence of the word within the speech data; calculating a degree of fluctuation within the speech data for the prosodic feature values of high frequency words where the high frequency words are any words whose frequency of occurrence meets a threshold; and determining a key phrase based on the degree of fluctuation.
- the method includes receiving an audio recording of a call and a text transcription of the audio recording, identifying events which occur during the call by detecting characteristic audio patterns in the audio recording and selected keywords and phrases in the text transcription, determining, from the identified events, a first event which precedes sensitive data in the call and a second event which occurs after sensitive data in the call, determining a portion of the call containing sensitive data with a start time at the first event and an end time at the second event, and removing the portion of the call between the start time and end time from the audio recording.
- An agent may be located at an agent station having a display screen.
- a continuous audio feed of the conversation between a customer and an agent may be received.
- a customer emotion score may be calculated in real-time.
- a frequency at which calculated customer emotion scores equal or exceed an emotion score threshold during a specified time interval may be calculated in real-time during the conversation.
- the calculated frequency for the customer may be compared, in real-time, to a plurality of specified frequency thresholds.
- a visual representation corresponding to a highest of the plurality of specified frequency thresholds that is equaled or exceeded by the calculated frequency for the customer may be displayed in real-time on the display screen of the agent station.
- a system for supervised automatic code generation and tuning for natural language interaction applications comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module.
- Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs.
- Language recognition rules are generated by automated coding tools.
- Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules.
- the analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.
- a behavior change apparatus comprises: a contrivance determination for determining a contrivance for a user in a virtual space on the basis of a cognitive bias of the user; and a field installation unit for installing, in the virtual space, the contrivance determined by the contrivance determination unit.
- the contrivance determination unit may determine a contrivance by using a prediction model that predicts the degree of the user's behavior change by the contrivance by inputting the degree of the cognitive bias of the user.
- the contrivance may be a contrivance for guiding the user to predetermined content present in the virtual space.
- the determination of a contrivance by means of the contrivance determination unit may also be based on the attributes of the user.
- Facilitation module facilitates the processes of logging in, confirming a purchase, uploading a photo or video, editing or deleting a comment, or finding the right place to write a comment, and provide guidance and assistance to the users who may be confused about these processes.
- the visual feedback module is responsible for providing the video clip as a visual feedback for the product to the user.
- the visual feedback module can use multimedia and web technologies to display the video clip on the user’s device, and to enable the user to interact with the video clip, such as playing, pausing, rewinding, fast-forwarding, zooming, etc.
- the visual feedback module can also use natural language generation and speech synthesis techniques to provide verbal feedback and explanations to the user, based on the content and analysis of the video clip.
- the product lifetime estimator module is responsible for estimating the best life time span for the product based on the opinions of other users who have used the product in question.
- the product lifetime module can use web scraping and data mining techniques to collect and analyze the opinions of other users from different websites, and can use machine learning and artificial intelligence techniques to estimate the best life time span for the product based on the features and attributes of the product, and the usage patterns and preferences of the users.
- the buyer satisfaction module to measure the level of awareness and satisfaction of the previous buyers and those who had entered their last negative or positive comments about the previous similar product as soon as the new product is introduced in the market.
- This module can use web scraping and data mining techniques to access and extract the feedback data of the previous buyers from different websites, and can use natural language processing and sentiment analysis techniques to understand the feedback data and to calculate the awareness and satisfaction scores of the previous buyers.
- the follow-up module that monitors the user’s satisfaction with the new product during the follow-up period, and provides assistance and guidance to the user if the user is dissatisfied with the product for any reason.
- This module can use natural language processing and speech recognition techniques to understand the user’s input and output, and to provide verbal feedback and explanations to the user, based on the content and analysis of the product suggestion module.
- the module can also use graphical user interface elements to enable the user to interact with the system, such as rating, reviewing, commenting, etc.
- the system not only measures the level of awareness and satisfaction of the previous buyers and those who had entered their last negative or positive comments about the previous similar product as soon as the new product was released to the market but also suggests a new and similar product that has recently entered the market and has received good feedback, and finds out the reasons for dissatisfaction and or satisfaction with the previous similar product, and recommends the new product that has entered the market to the user, taking into account the new changes and their relationship with the user’s dissatisfaction, and monitors the user’s satisfaction with the new product during the follow-up period, and provides assistance and guidance to the user if the user is dissatisfied with the product for any reason.
- the dual-profile analysis module reaches two physical and mental profiles of the user. This module assesses the user’s characteristics and preferences by analyzing their feedback on various entities from different websites. It then finds out the relationship between the user’s feedback and their profile, including user behavior, preferences, satisfaction levels, cognitive biases, sentiments, interests, and emotions.
- the review submission module that facilitates the user to write and submit a review for their purchase on various entities from different websites.
- This module can use graphical user interface elements to simplify the review writing process, such as providing rating scales, checkboxes, text boxes, etc.
- the module can also use web scraping and data mining techniques to access and display the entities from different websites, and to enable the user to submit their review to multiple entities with a single click.
- the system not only enhances the user’s engagement and satisfaction with their purchase, but also increases the user’s participation and contribution to the online review community.
- the voice assistant not only personalizes the user’s shopping experience based on their feedback, but also helps the user find the best product or service that matches their needs and preferences.
- the feedback improvement module improves the quality and clarity of the user’s feedback or opinion.
- This module can use natural language generation and speech synthesis techniques to provide verbal feedback and explanations to the user, based on the content and analysis of the user’s feedback or opinion.
- the module can also use machine learning and artificial intelligence techniques to enhance the style and tone of the user’s feedback or opinion, such as correcting grammar, spelling, punctuation, etc., and adding emotions, expressions, etc.
- the system not only solves the challenges of users in writing feedback or their opinion about a product, service, or brand, but also facilitates this process and enhances the user’s experience and satisfaction.
- the feedback collection module to collect user feedback on various entities from different websites in an efficient and reliable way.
- This module can use web scraping and data mining techniques to access and extract user feedback data from different websites, such as ratings, reviews, comments, likes, dislikes, etc.
- the module can also use natural language processing and speech recognition techniques to understand the user feedback data and to convert it into a structured and standardized format.
- the feedback analysis module analyzes user feedback on various entities from different websites in a comprehensive and user-friendly way.
- This module can use machine learning and artificial intelligence techniques to perform various types of analysis on the user feedback data, such as sentiment analysis, topic modeling, aspect extraction, opinion summarization, etc.
- the module can also use natural language generation and speech synthesis techniques to provide verbal analysis results and explanations to the users, based on the content and analysis of the user feedback data.
- the feedback utilization module utilizes user feedback on various entities from different websites in a beneficial and personalized way.
- This module can use data mining and statistical techniques to identify the patterns, trends, and correlations among the user feedback data, and to provide insights and recommendations to the users and the entities based on the analysis results.
- the module can also use multimedia and web technologies to display the user feedback data and the analysis results on the user’s device, and to enable the user to access and interact with the user feedback data and the analysis results, such as filtering, sorting, searching, etc.
- the cognitive bias prevention module is a module that aims to reduce the impact of cognitive biases on customer decision-making and behavior.
- Cognitive biases are errors or distortions in thinking that affect how users perceive and interpret information, often leading to irrational or suboptimal choices.
- Some examples of cognitive biases are confirmation bias, anchoring bias, loss aversion, and bandwagon effect.
- the cognitive bias prevention module can use various techniques and technologies to detect, correct, and prevent cognitive biases, such as:
- the system can help the customer make more informed, rational, and satisfying decisions, and improve the customer experience and loyalty.
- This invention can help customers make better and more informed decisions, by providing them with objective and balanced information, personalized and relevant recommendations, and guidance and assistance throughout the feedback and suggestion process.
- This invention can help customers improve their satisfaction and loyalty, by providing them with feedback and suggestions that match their needs and preferences, by reducing the impact of cognitive biases on their decision-making and behavior, and by monitoring and addressing their dissatisfaction and concerns.
- This invention can help businesses enhance their reputation and brand image, by providing them with feedback and suggestions that reflect their strengths and weaknesses, by informing them about any user dissatisfaction and taking appropriate actions to address them, and by motivating and rewarding the customers for writing feedback and suggestions.
- This invention can help customers connect and socialize with other customers and entities, by providing them with feedback and suggestions that are engaging and interactive, by using various techniques and technologies to facilitate and improve the communication and collaboration process, such as graphical user interface, multimedia, web technologies, gamification, reward, social proof, persuasion, etc., and by creating and maintaining a community of feedback and suggestion providers and consumers.
- This invention can help customers save time and money, by providing them with feedback and suggestions that are efficient and reliable, by using various techniques and technologies to collect and compare feedback and suggestions from different websites, such as web scraping, data mining, etc., and by providing them with the best and most suitable feedback and suggestions for their needs and preferences
- This invention uses nudges and incentives to encourage the customer to explore different options, compare different attributes, and consider different perspectives, and educates the customer about the common cognitive biases and how they can affect their decisions and outcomes.
- the flow chart describes a platform that collects user comments from different websites about products, services, or brands and analyzes them using natural language processing.
- the flow chart describes a platform that uses a voice-based intelligent assistant to interact with the user and provide reports, recommendations, and feedback based on user comments and voice commands.
- the flow chart describes an intelligent system that uses a voice-based intelligent assistant to interact with the user and provide recommendations based on the user’s opinions and experiences with a product.
- the flow chart describes an intelligent system that manages user feedback about a product, brand, or service provider.
- the flow chart describes an intelligent system that integrates and displays feedback from two user groups: those who have purchased a product and those who provide services related to that product.
- the flow chart describes an intelligent system that collects and processes user feedback on different types of products.
- the flow chart describes a system for measuring the halo effect in online feedback, incorporating various modules for sentiment analysis, gamification, product selection, halo effect measurement, and feedback rating.
- the flow chart describes a system for detecting and mitigating the bandwagon effect in online feedback.
- the flow chart describes a system for detecting and reducing user negativity bias in online feedback.
- the platform stores and organizes the comments in a database based on their product, service, or brand name and their category name.
- the platform also displays the comments in a user interface in either graphical or textual format.
- the system comprises a user interface that receives questions and presents random queries about dissatisfaction imperceptibly, a monitoring module that analyzes responses to identify dissatisfaction root causes based on user characteristics, and a reporting module that notifies relevant parties if unsatisfactory feedback exceeds a threshold.
- the process involves receiving and analyzing user responses, identifying existing dissatisfaction, comparing the number of unsatisfactory feedbacks with a predetermined threshold, and notifying the seller, owner, manufacturer or any person/organization providing the product/service if the threshold is exceeded.
- the another module shows you different online shops that sell bicycles that match your preferences. Some of these shops are more popular or trustworthy than others, so they are shown at the top of the list. The platform has an agreement with these shops to promote them more.
- This module is the website selection module.
- This pop-up window is the user interface.
- the notification is from a computer program that helps you track and report the quality of the jeans.
- the program asks you if you want to join a project that collects and analyzes pictures of the jeans from different users. You agree to join the project and you open the program on your phone. This program is the follow-up module.
- a module also sends your pictures to another computer program that creates a video clip of the jeans.
- the program selects the most relevant and representative pictures of the jeans from different angles and time intervals.
- the program then arranges the pictures in a chronological order and adds some transitions and effects to make the video more smooth and appealing.
- the program also adds some text and audio to the video, such as the name, the description, and the price of the jeans, and your rating, review, or comment about them.
- the program then compresses the video to make it shorter and easier to watch.
- the video shows the quality of the jeans degrading over time, such as their color fading, their shape stretching, or their fabric tearing.
- This computer program is the video generator.
- a module collects your answers and sends them to a computer program that analyzes them.
- the program looks for any signs of confirmation bias in your answers.
- Confirmation bias is the tendency to search for, interpret, favor, and recall information in a way that confirms one’s preexisting beliefs or hypotheses. For example, you might only pay attention to the positive feedback that supports your preferences and opinions, and ignore or dismiss the negative feedback that contradicts them. Or you might only trust the feedback from users who have the same or similar preferences and opinions as you, and doubt or reject the feedback from users who have different or opposite preferences and opinions.
- the program also compares your answers with a fixed value that represents the acceptable level of confirmation bias. For example, the website might decide that if more than 50% of your answers show confirmation bias, then you need to be more open-minded and objective. The program then decides if you are suffering from confirmation bias or not based on your behavior and the fixed value.
- This computer program is the confirmation bias confirmation module.
- a module sends your answers to another computer program that helps you reduce your confirmation bias and improve your decision making.
- the program looks for the feedback from other users that are fair and balanced and that challenge your preferences and opinions. The program also considers other factors, such as the relevance, the credibility, and the diversity of the feedback. The program then shows you the feedback from other users that you might have missed or ignored because of your confirmation bias. The program also asks you to rate or review the feedback from other users and to explain why you agree or disagree with them. The program also gives you some tips and suggestions on how to overcome your confirmation bias and how to evaluate the feedback from other users more critically and rationally.
- This computer program is the confirmation bias reduction module.
- a module sends your answers to another computer program that displays several products that have been influenced by the halo effect of another product.
- the program looks for the products that have similar or different characteristics to the product that you are interested in, such as the brand, the model, the features, or the price.
- the program also considers other factors, such as the availability, the popularity, and the compatibility of the products.
- the program shows you the products that you might have overlooked or overrated because of the halo effect of another product.
- the program also asks you to rate or review the products and to explain why you like or dislike them.
- This computer program is the product selection module.
- a module helps you find and compare the best video games for you.
- the website also shows you the feedback from other users who bought the video games that you are interested in.
- the feedback includes ratings, reviews, and comments.
- the website also asks you some questions about your preferences and opinions.
- the website is the bandwagon effect detection module.
- a module e collects your answers and sends them to a computer program that analyzes them.
- the program looks for any signs of bandwagon effect in your answers.
- Bandwagon effect is a cognitive bias that causes you to conform to the opinion of others, regardless of your own beliefs, which you may ignore or override. For example, you might buy or like a video game because it is popular or trendy, even if it does not match your preferences or opinions. Or you might avoid or dislike a video game because it is unpopular or outdated, even if it does match your preferences or opinions.
- the program also proposes that you write an opinion that is contrary to the opinion of others and that provides a different point of view on the video game that everyone is praising or criticizing.
- This computer program is the feedback generation module.
- a module helps you find and compare the best coffee makers for you.
- the module also shows you the feedback from other users who bought the coffee makers that you are interested in.
- the feedback includes ratings, reviews, and comments.
- the module also asks you some questions about your preferences and opinions.
- the module is the negativity bias detection module.
- a module collects your answers and sends them to a computer program that analyzes them.
- the program looks for any signs of negativity bias in your answers.
- Negativity bias is a cognitive bias that causes you to focus more on negative than positive information, regardless of their frequency or importance. For example, you might pay more attention to the negative feedback that criticizes the coffee maker, and ignore or dismiss the positive feedback that praises the coffee maker. Or you might trust the negative feedback more than the positive feedback, and think that the positive feedback is biased or dishonest.
- the program also shows you the positive opinions of other users and different views on the coffee maker that you are reviewing. The program also explains why it is important to consider both the positive and negative aspects of the coffee maker and how they can benefit you and other users.
- This computer program is the feedback presentation module.
- a module collects your answers and sends them to a computer program that analyzes them.
- the program looks for any signs of sunk cost fallacy in your answers.
- Sunk cost fallacy is a cognitive bias that causes you to continue investing in a product or service that has already incurred a significant cost and does not provide satisfactory results. For example, you might keep using or buying a car that is expensive, old, or faulty, just because you have spent a lot of money, time, or effort on it. Or you might avoid using or buying a car that is cheap, new, or functional, just because you think that switching to a different car would be a waste of your previous investment.
- the program also examines the evidence of the sunk cost fallacy in the feedback that you provide later about the cars that you have bought or used. The program also explains why the sunk cost fallacy is irrational and harmful and how it can affect your decision making.
- This computer program is the fallacy identification module.
- the program lets you choose which websites you want to post your feedback on, such as social media, blogs, or forums.
- the program also adds some information to your feedback, such as your name, the car name, and the website where you bought it. This way, other users can see that you are a real customer and not a fake one.
- the program also shows you the feedback from other users who have the same or similar cars as you and who have posted their feedback on the same or different websites as you.
- the program also lets you interact with them and exchange your opinions and experiences.
- This computer program is the feedback display module.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
In this invention, we investigated the challenges of human-machine communication to enter feedback about the products he/she bought from an online store or the service he/she received from a platform, and we provided an appropriate solution for each of them. We hope that this invention will help the customers be satisfied with the products they have bought and not suffer any cognitive biases when buying a product. This invention will provide a suitable platform for human-machine interaction using a voice assistant. It will also intelligently check users' opinions to prevent any trend that will damage the brand's reputation and also to prevent any disputes by applying the legal laws of each country.
Description
Despite many strategies to get users' opinions in any possible way, many users refuse to express their opinions about the product they have purchased or the service they have received. They are confused when they want to put their feedback and share their experiences. They may have faced challenges on where, when, and how to write a comment that delivers the exact opinion about a service or product. A product that receives a lot of feedback due to its flaws is seen more than a product that does not receive positive feedback from users due to its high quality. There needs to be an interface to discover users' interests and direct them to a product that suits their needs. This invention is a platform to easily receive users' opinions with the help of natural language processing and an intelligent voice assistant, motivate users to post their comments about a product or service, and an artificially intelligent assistant to discover the real needs of users, and a guide in buying and using process, in which provides a personalized follow-up procedure.
G06N 3/02 – Neural networks [2006.01]
G06F 18/10 - Pre-processing; Data cleansing [2023.01]
G06Q 30/014 - Providing recall services for goods or products [2023.01]
G10L 13/00 - Speech synthesis; Text to speech systems [2006.01]
G16H 20/70 - relating to mental therapies, e.g. psychological therapy or autogenous training [2018.01]
G06T 13/00 - Animation [2011.01]
G06Q 50/18 - Legal services; Handling legal documents [2012.01]
H04N 21/475 - End-user interface for inputting end-user data, e.g. PIN [Personal Identification Number] or preference data [2011.01]
A61B - Diagnosis; surgery; Identification
US20110004624A1
Method for Customer Feedback Measurement in Public Places Utilizing Speech Recognition Technology
This patent shows A method, a system and a computer program product for enabling a customer response speech recognition unit to dynamically receive customer feedback. The customer response speech recognition unit is positioned at a customer location. The speech recognition unit is automatically initialized when one or more spoken words are detected. The response statements of customers are dynamically received by the customer response speech recognition unit at the customer location, in real time. The customer response speech recognition unit determines when the one or more spoken words of the customer response statement are associated with a score in a database. An analysis of the words is performed to generate a score that reflects the evaluation of the subject by the customer. The score is dynamically updated as new evaluations are received, and the score is displayed within graphical user interface (GUI) to be viewed by one or more potential customers.
US20060031361A1
Method and apparatus for conversational annotation for instant messaging systems
This invention relates to a method, apparatus, or computer program for conversation annotation for instant messaging systems. The instant messaging method comprises: providing a graphical user interface; determining a selection of two or more existing messages; creating, on an instruction from the GUI, a relationship between the selected messages; and indicating, using links or edges on between the messages, the relationship between the messages. All related messages may be selected with a single selection and printed, stored, or deleted as a batch.
US20080275701A1
System and method for retrieving data based on topics of conversation
A method includes performing computerized monitoring with a computer of at least one side of a telephone conversation, which includes spoken words, between a first person and a second person, automatically identifying at least one topic of the conversation, automatically performing a search for information related to the at least one topic, and outputting a result of the search. Also a system for performing the method.
US11076046B1
Voice and speech recognition for call center feedback and quality assurance
This patent represent a computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.
US11076046B1
Voice and speech recognition for call center feedback and quality assurance
A computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.
US6275806B1
System method and article of manufacture for detecting emotion in voice signals by utilizing statistics for voice signal parameters
A database is provided. The database includes statistics of human associations of human voice parameters with emotions. A voice signal is received. At least one feature of this voice signal is extracted. This extracted voice feature is then compared to the voice parameters in the database. An emotion is selected from the database based on the comparison of the extracted voice feature to the voice parameters. Input from the user is received. This input includes a user-determined emotion. The user-determined emotion is compared with the emotion selected from the database. The selected emotion is output and a determination as to whether the user-determined emotion matches the emotion selected from the database is made. A prize is then awarded to the user if the user-determined emotion is determined to match the selected emotion from the database.
US7058565B2
Employing speech recognition and key words to improve customer service
The invention comprises capturing a customer's speech, recognizing a key word in the customer's speech, searching a database, and retrieving information from the database. The retrieving is a real-time process, completed during a conversation involving the customer and a customer service representative. Examples include methods employing computerized speech recognition and key words to improve customer service, systems for executing methods of the present invention, and instructions on a computer-usable medium, or resident in a computer system, for executing methods of the present invention.
US7133828B2
Methods and apparatus for audio data analysis and data mining using speech recognition
The present invention provides an audio analysis intelligence tool that provides ad-hoc search capabilities using spoken words as an organized data form. The present invention provides an SQL like interface to process and search audio data and combine it with other traditional data forms.
US7263489B2
Detection of characteristics of human-machine interactions for dialog customization and analysis
A system which uses automatic speech recognition to provide dialogs with human speakers automatically detects one or more characteristics, which may be characteristics of a speaker, his speech, his environment, or the speech channel used to communicate with the speaker. The characteristic may be detected either during the dialog or at a later time based on stored data representing the dialog. If the characteristic is detected during the dialog, the dialog can be customized for the speaker at an application level, based on the detected characteristic. The customization may include customization of operations and features such as call routing, error recovery, call flow, content selection, system prompts, or system persona. Data indicative of detected characteristics can be stored and accumulated for many speakers and/or dialogs and analyzed offline to generate a demographic or other type of analysis of the speakers or dialogs with respect to one or more detected characteristics.
US7672845B2
Method and system for keyword detection using voice-recognition
A method and system is provided to monitor speech and detect keywords or phrases in the speech, such as for example, monitored calls in a call center or speakers/presenters using teleprompters, or the like. Upon detection of the keywords of phrases, information associated with the keywords or phrases may be presented to a display device so that a user may dynamically receive new information as context of the speech progresses. This provides dynamic information as the context of the conversation develops. The information may be presented as links, cues, text, or similar formats. The detected keywords or phrases may also be associated with rules that govern the conditions and criteria for processing the detected keyword and presentation of the information.
US8204884B2
Method, apparatus and system for capturing and analyzing interaction based content
An apparatus and methods for capturing and analyzing customer interactions the apparatus comprising interaction information units, interaction meta-data information units associated with each of the interaction information units, a rule based analysis engine component for receiving the interaction information, an adaptive database, an interaction capture and storage component for capturing interaction information, a multi segment interaction capture device, an initial set up and calibration device and a pre processing and content extraction device.
US20040008828A1
Dynamic information retrieval system utilizing voice recognition
A dynamic information retrieval system for monitoring a conversation between two or more parties and automatically collecting a plurality of keywords used during the conversation. A priority is assigned to the plurality of keywords and an information database is automatically searched for information relevant to the conversation based on the plurality of keywords. A keyword list and an information list is displayed on a workstation display to allow an agent to directly select/deselect one or more of the plurality of keywords and/or information, wherein the priority of the one or more of the plurality of keywords and/or information may be adjusted. As keywords and/or information are selected/deselected, the keyword list and the information list are dynamically updated based on new priorities that may have been assigned to the plurality of keywords and information and/or how much time has passed since a keyword was mentioned. As the conversation progresses and time passes, the list of keywords and the information list are dynamically updated using the new or adjusted keywords.
US20120197644A1
Information processing apparatus, information processing method, information processing system, and program
An information processing apparatus, information processing method, and computer readable non-transitory storage medium for analyzing words reflecting information that is not explicitly recognized verbally. An information processing method includes the steps of: extracting speech data and sound data used for recognizing phonemes included in the speech data as words; identifying a section surrounded by pauses within a speech spectrum of the speech data; performing sound analysis on the identified section to identify a word in the section; generating prosodic feature values for the words; acquiring frequencies of occurrence of the word within the speech data; calculating a degree of fluctuation within the speech data for the prosodic feature values of high frequency words where the high frequency words are any words whose frequency of occurrence meets a threshold; and determining a key phrase based on the degree of fluctuation.
US20130266127A1
System and method for removing sensitive data from a recording
Systems and methods for, among other things, removing sensitive data from an recording. The method, in certain embodiments, includes receiving an audio recording of a call and a text transcription of the audio recording, identifying events which occur during the call by detecting characteristic audio patterns in the audio recording and selected keywords and phrases in the text transcription, determining, from the identified events, a first event which precedes sensitive data in the call and a second event which occurs after sensitive data in the call, determining a portion of the call containing sensitive data with a start time at the first event and an end time at the second event, and removing the portion of the call between the start time and end time from the audio recording.
US20140140497A1
Real-time call center call monitoring and analysis
Systems and methods are provided for analyzing conversations between customers and call center agents in real-time. An agent may be located at an agent station having a display screen. A continuous audio feed of the conversation between a customer and an agent may be received. For every second that the customer is speaking, a customer emotion score may be calculated in real-time. A frequency at which calculated customer emotion scores equal or exceed an emotion score threshold during a specified time interval may be calculated in real-time during the conversation. The calculated frequency for the customer may be compared, in real-time, to a plurality of specified frequency thresholds. A visual representation corresponding to a highest of the plurality of specified frequency thresholds that is equaled or exceeded by the calculated frequency for the customer may be displayed in real-time on the display screen of the agent station.
US20140220526A1
Customer sentiment analysis using recorded conversation
A system is configured to receive voice emotion information, related to an audio recording, indicating that a vocal utterance of a speaker is spoken with negative or positive emotion. The system is configured to associate the voice emotion information with attribute information related to the audio recording, and aggregate the associated voice emotion and attribute information with other associated voice emotion and attribute information to form aggregated information. The system is configured to generate a report based on the aggregated information and one or more report parameters, and provide the report.
US8892419B2
System and methods for semiautomatic generation and tuning of natural language interaction applications
A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.
US20150195406A1
Real-time conversational analytics facility
Methods and systems are provided for receiving a communication, analyzing the communication in real-time or near real-time using a computer-based communications analytics facility for at least one of a language characteristic and an acoustic characteristic, wherein for analyzing the language characteristic of voice communications, the communication is converted to text using computer-based speech recognition, determining at least one of the category, the score, the sentiment, or the alert associated with the communication using the at least one language and/or acoustic characteristic, and providing a dynamic graphical representation of the at least one category, score, sentiment, or alert through a graphical user interface.
US9661067B2
Systems and methods for facilitating dialogue mining
The disclosure is related to mining of text to derive information from the text that is useful for a variety of purposes. The text mining process can be implemented in a service oriented industry such as a call center, where a customer and an agent engage in a dialog, e.g., to discuss product/service related issues. The messages in dialogues between the customers and the agents are tagged with features that describe an aspect of the conversation. The text mining process can mine various dialogues and identify a set of features and messages based on prediction algorithms. The identified set of features and messages can be used to infer an intent of a particular customer for contacting the agent, and to generate a recommendation based on the determined intent.
US9799035B2
Customer feedback analyzer
A method and system for analyzing customer feedback is provided. The method includes accessing a keyword and word mapping database and receiving consumer feedback data associated with a product or service. The consumer feedback data includes feedback data groups. Each group is divided into segments based on word analysis. Each segment is analyzed with respect to the keyword and thesaurus database. A score is generated for each segment and a composite score is generated for each feedback data group. Each composite score is stored.
US10147427B1
Systems and methods to utilize text representations of conversations
A method for electronically utilizing content in a communication between a customer and a customer representative is provided. An audible conversation between a customer and a service representative is captured. At least a portion of the audible conversation is converted into computer searchable data. The computer searchable data is analyzed during the audible conversation to identify relevant meta tags previously stored in a data repository or generated during the audible conversation. Each meta tag is associated with the customer. Each meta tag provides a contextual item determined from at least a portion of one of a current or previous conversation with the customer. A meta tag determined to be relevant to the current conversation between the service representative and the customer is displayed in real time to the service representative currently conversing with the customer.
US20130290214A1
Method and apparatus for providing reviews and feedback for professional service providers
The present invention relates generally to a method and an apparatus for providing reviews and feedback for professional service providers (PSP). More particularly, the invention encompasses a method and an apparatus for providing reviews and feedback on customers or organizations by a professional service provider who has worked with the customer or the organization. The present invention is also directed to one or more data bases that are accessible to professional service providers either prior to or during or after performing a work assignment for a specific customer or organization. The present invention also encompasses a rating system and/or reviews by a professional service provider either prior to or during or after performing a work assignment for a specific customer, on not only for the job but also on the client or customer. Ads for generating income could also be displayed or transmitted during any communication.
US20230186906A1
Advanced sentiment analysis
Systems and methods are provided for generating call sentiment associated with a call. The call includes one or more utterances. An utterance includes one or more sentences. A sentence includes one or more words. The disclosed technology iteratively generates sentiment values associated with sentences based on sentiment associated with words in the sentences, sentiment values associated with utterances based on sentence sentiment, and the call sentiment. Determining sentiment includes use of one or more a trained neural network for predicting sentiment and weighted average of sentiment values associated sentences and utterances for aggregating sentiment values. The disclosed technology generates a sentiment momentum that trends sentiment that evolves over time during the call. A speaker sentiment indicates sentiment associated with a speaker who makes utterance during the call.
US20140280621A1
Conversation analysis of asynchronous decentralized media
The present disclosure provides a system that allows for the real-time and online monitoring of the exchanges between customers and a CRM team over social media. While crawling all messages exchanged over the social media by customers and CRM team, the system aggregates related messages exchanged between a given customer and the CRM team into a conversation. The system includes a linguistic framework for the analysis of conversations (based on the two linguistic theories of dialog acts and conversation analysis) to label the nature of the messages in a conversation or thread.
EP4233308
Systems and methods for generating video files of digital X-Ray imaging
An example method to generate a video from multiple cameras including a digital X-ray imaging device involves: initiating a recording session on an X-ray digital imaging device; capturing one or more images using a first one of a plurality of imaging sensors of the X-ray digital imaging device; capturing one or more videos using a second one of the plurality of imaging sensors; storing, on a machine readable storage device, two or more files corresponding to the one or more images and the one or more videos captured using the first and second ones of the plurality of imaging sensors; and combining the two or more files into a single video file representative of the recording session.
WO/2023/239562
Emotion Aware Voice Assistant
An interface customized to a detected emotional state of a user is provided. Audio signals are received from at least one microphone, the audio signals being indicative of spoken words, sentences, or commands. A wake-up word (WuW) is detected in the audio signals. An emotion is also detected in the audio signals containing the WuW. An emotion-aware processing system is configured according to the detected emotion. A voice control session is performed using the emotion-aware processing system configured according to the detected emotion.
US20230401031
Voice Assistant-Enabled Client Application With User View Context
Various embodiments discussed herein enable client applications to be heavily integrated with a voice assistant in order to both perform commands associated with voice utterances of users via voice assistant functionality and also seamlessly cause client applications to automatically perform native functions as part of executing the voice utterance. For example, some embodiments can automatically and intelligently cause a switch to a page the user needs and automatically and intelligently cause a population of particular fields of the page the user needs based on a user view context and the voice utterance.
CN115497458
Continouse learning method and device of intelligent voice assistant, electronic equipment and medium
The invention provides a continuous learning method and device of an intelligent voice assistant, electronic equipment and a storage medium, and relates to the technical fields of artificial intelligence, voice technologies and the like. The specific implementation scheme is as follows: acquiring voice input information of a user; obtaining feedback information of the user after the intelligent voice assistant responds based on the voice input information of the user; and controlling the intelligent voice assistant to learn based on the feedback information of the user. According to the technology disclosed by the invention, the continuous learning ability of the intelligent voice assistant can be effectively improved, and the performance of the intelligent voice assistant is optimized and improved.
AU2014233517
Training an at least partial voice command system
An electronic device with one or more processors and memory includes a procedure for training a digital assistant. In some embodiments, the device detects an impasse in a dialogue between the digital assistant and a user including a speech input. During a learning session, the device utilizes a subsequent clarification input from the user to adjust intent inference or task execution associated with the speech input to produce a satisfactory response. In some embodiments, the device identifies a pattern of success or failure associated with an aspect previously used to complete a task and generates a hypothesis regarding a parameter used in speech recognition, intent inference or task execution as a cause for the pattern. Then, the device tests the hypothesis by altering the parameter for a subsequent completion of the task and adopts or rejects the hypothesis based on feedback information collected from the subsequent completion.
US20210249013
Method and apparatus to provide comprehensive smart assistant services
An apparatus supports smart assistant services with a plurality of smart service providers. The apparatus includes an audio device that receives a speech signal having a user utterance, captures the user utterance when the user utterance includes a user wake word, and sends the captured utterance to a backend computing device. The backend computing device replaces the user wake word with specific wake words associated with different smart service providers. The processed utterances are then sent to selected smart service providers. The backend computing device subsequently constructs feedback to the user utterance based on voice responses from the different smart service providers. The backend computing device then passes a digital representation of the feedback to the audio device, and the audio device converts the digital representation to an audio reply to the user utterance.
IN202121036837
Method and system for user review bdased cognitive product recommendation
The present disclosure provides a user review based product recommendation system without any bias. Conventional methods are based on historical buying behavior and fails to consider subjective and qualitative nature of unrelated user search query without any bias. The system receives a user query pertaining to a product. The user query includes a plurality of subjective words indicating a sentiment of the user. A plurality of noun entities and subjective criteria are identified from the user query. Further, a first set of tuples are extracted from a polarity metadata repository based on the plurality of product category. Further, a second set of tuples are extracted from the first set of tuples based on the plurality of product features. Finally, a plurality of sorted tuples is obtained based on the subjective criteria. After sorting, a plurality of top n products is recommended based on the plurality of sorted tuples.
CN115456308
Bias index-based public opinion trend analysis application method, system and application
The invention belongs to the technical field of network space cognitive domains, and discloses a BIAS index-based public opinion trend analysis application method, system and application. The method comprises the following steps: calculating public opinion indexes of different periods to obtain BIAS credibility values, and visualizing the BIAS credibility values; establishing a BIAS credibility curve of different periods and a curve trend chart of public opinion indexes of different periods; the trend change of the public opinion indexes in different scenes is analyzed, then the trend of the public opinion trend is analyzed from multiple angles according to different scenes, and the public opinion is pre-warned and predicted. According to the method, the BIAS values in different periods are visualized, analysis is carried out from the perspective of BIAS credibility curve crossing conditions in different periods, possible trend changes of public opinion indexes in different scenes are summarized, and the method has certain guiding significance in early warning and prediction of public opinions.
US20220366190
Augmented intelligence system impartiality assessment engine
A method, system and computer-readable storage medium for performing a cognitive information processing operation. The cognitive information processing operation includes: receiving data from a plurality of data sources; processing the data from the plurality of data sources to provide cognitively processed insights via an augmented intelligence system, the augmented intelligence system executing on a hardware processor of an information processing system, the augmented intelligence system and the information processing system providing a cognitive computing function; performing an impartiality assessment operation via an impartiality assessment engine, the impartiality assessment operation detecting a presence of bias in an outcome of the cognitive computing function; and, providing the cognitively processed insights to a destination, the destination comprising a cognitive application, the cognitive application enabling a user to interact with the cognitive insights.
IN202221021393
SEMI AUTOMATIC SEEDLING TRANSPLANTER
Semi automatic seedling transplanter
The association between the emotions leads to the understanding of emotion loss. In this Work we are trying to fill the gap between emotional recognition and emotional correlation mining through social media reviews of natural language text. The association between emotions, represented as the emotional uncertainty and evolution, is mainly triggered by cognitive bias in the human emotion. Three different types of features and two deep neural-network models are provided to mine the emotion co-relation from emotion detection using text. The rule on conflict of emotions is derived on a symmetric basis. TF-IDF, NLP Features and Co-relation features has been used for feature extraction as well as section and Recurrent Neural Network (RNN) and Hybrid deep learning algorithm for classification has been used to demonstrate the entire research experiments. Finally, evaluate the system performance with various existing systems and show the effectiveness of the proposed system. This work reviews and brings together the recent works carried out in the automatic stress detection looking over the measurements executed along the three main modalities, namely, psychological, physiological and behavioural modalities, along with contextual measurements, in order to give hints about the most appropriate techniques to be used and thereby, to facilitate the development of such a system.
US20220199249
system and method to self-determine a mental and emotional (non-physical) wellness score over time using deep learning algorithms (based on cognitive bias) which respond to various activities and events through a series of sensors, feedback, activities and conversational methods.
The vast majority of emphasis is still on physical health such as diet and exercise. Although some progress has been made in mental health, a new way of wellness can be achieved by extending the mental health space beyond relaxation techniques such as meditation. This is done by calculating a wellness score once we understand the cognitive/psychological bias of a person and knowing their past and present activities, events and their experiences. This wellness score is used as a basis to improve the emotional and mental health of the individual by recommending Next Best Actions (NBA.) NBA could include several activities that the user could perform beyond current relaxation methods. The pursuit of wellness obtained through this holistic approach proves it to be highly effective to address mental and emotional health rather than one solution fits all approaches that we see in the mental health industry.
US20220198297
Self-Monitoring cognitive bias mitigator in predictive systems
One or more embodiments described herein facilitate identification and mitigation of cognitive bias in data-driven models. In one embodiment, a deep-learning system can comprise a memory that stores computer executable components; and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise: an input component that receives data comprising primary task labels, secondary-identity attributes and a number of potential categories for one or more of the secondary-identity attributes; a machine-learning model that generates one or more predictions based on the received data; and a multi-objective learning component that trains the machine-learning model to mitigate bias from the one or more predictions.
US20200380597
Bias prediction and categorization in financial tools
A processor can obtain financial data for a user. The processor may process the financial data to generate feature data indicative of at least one feature. The processor may compare the at least one feature to at least one threshold value to determine that the user has a cognitive bias affecting a financial preference of the user and associated with the at least one threshold value. The at least one threshold value may denote a threshold for membership in a cluster of unlabeled users having the cognitive bias . In response to the comparing, the processor may identify a change applicable to a financial account of the user. The change may be associated with the cognitive bias . The processor may automatically cause the change to be implemented by a network-accessible financial service
US20220004898
Detection cognitive biases in intractions with analystics data
The present disclosure relates to methods, systems, and non-transitory computer-readable media for determining a cognitive, action-selection bias of a user that influences how the user will select a sequence of digital actions for execution of a task. For example, the disclosed systems can identify, from a digital behavior log of a user, a set of digital action sequences that correspond to a set of sessions for a task previously executed by the user. The disclosed systems can utilize a machine learning model to analyze the set of sessions to generate session weights. The session weights can correspond to an action-selection bias that indicates an extent to which a future session for the task executed by the user is predicted to be influenced by the set of sessions. The disclosed systems can provide a visual indication of the action-selection bias of the user for display on a graphical user interface.
KR102299031
Apparatus and method for providing diagnostic service of cognitive bias and decision rationality
The present invention relates to an apparatus and a method for providing a diagnosis service for cognitive bias and decision rationality through an online questionnaire. The apparatus for providing a diagnosis service for cognitive bias and decision rationality comprises: a questionnaire presentation unit presenting predetermined questionnaires for each field online in order to check the cognitive bias diagnosis flow; a response input unit receiving a response from an examiner to the questionnaires for each field presented in the questionnaire presentation unit; and a diagnosis unit diagnosing the level of cognitive bias based on the questionnaire response for each field received through the response input unit. The examiner can directly diagnose the problem situation, occurrence level, and evidence bias which may appear in their decision-making process, and as the concept of evidence bias and a guide to overcoming the same are provided, it is possible to prevent failure problems that may occur in the decision-making process and prevent loss.
EP3857452
Methods and systems for defining emotional machines
A method for training an intelligent agent is disclosed including creating a personality matrix, combining a cognitive bias matrix with the personality matrix and generating a behavioral function for a situation based on the combined cognitive bias matrix and personality matrix.
US20210097405
Bias indentification in cognitive computing systems
Mechanisms are provided to implement a bias identification engine that identifies bias in the operation of a trained cognitive computing system. A bias risk annotator is configured to identify a plurality of bias triggers in inputs and outputs of the trained cognitive computing system based on a bias risk trigger data structure that specifies terms or phrases that are associated with a bias. An annotated input and an annotated output of the trained cognitive computing system is received and processed by the bias risk annotator to determine if they comprise a portion of content that contains a bias trigger. In response to at least one of the annotated input or annotated output comprising a portion of content containing a bias trigger a notification is transmitted, to an administrator computing device, that specifies the presence of bias in the operation of the trained cognitive computing system.
KR102114907
Method for correcting cognitive bias using cognitive stimulation and device therof
Provided are a method for correcting cognitive bias using cognitive stimulation and a device thereof. In a method for correcting cognitive bias using cognitive stimulation performed by a computer, the method comprises the steps of : for each of a plurality of emotions subjected to correction in which emotions felt by a user are classified according to predetermined classification criteria, collecting the user prime;s emotion recognition information; based on the user prime;s emotion recognition information, evaluating the user prime;s emotion recognition ability for each of the plurality of emotions subjected to correction; determining the learning frequency of the user prime;s cognitive bias correction according to the user prime;s emotional recognition ability; reflecting the learning frequency for each of the plurality of emotions subjected to correction to provide conTExT information so as to apply cognitive stimulation to the user for a predetermined period of time and receiving the learning result of the user prime;s cognitive bias correction; and based on the learning result of the user prime;s cognitive bias correction, evaluating the level of the user prime;s cognitive bias correction for each of the plurality of emotions subjected to correction. Accordingly, the user can correct cognitive bias for specific emotions and accurately determine the degree of cognitive bias.
EP3977391
Bias Predection and Categorization in financial tools
A processor can obtain financial data for a user. The processor may process the financial data to generate feature data indicative of at least one feature. The processor may compare the at least one feature to at least one threshold value to determine that the user has a cognitive bias affecting a financial preference of the user and associated with the at least one threshold value. The at least one threshold value may denote a threshold for membership in a cluster of unlabeled users having the cognitive bias. In response to the comparing, the processor may identify a change applicable to a financial account of the user. The change may be associated with the cognitive bias. The processor may automatically cause the change to be implemented by a network-accessible financial service.
US20230101200
Cognitive bias detection and correction in self-repoted data
Embodiments are provided for cognitive bias detection and correction in self-reported data. In some embodiments, a system can include a processor that executes computer-executable components stored in memory. The computer-executable components include first components that creates an ontology of bias descriptor features to identify cognitive biases. The cognitive biases can include a combination of at least one device-induced cognitive bias, at least one testing-application-induced cognitive bias, or at least one study-design-induced cognitive bias.
JP2023067534
Anchoring personal characteristic estimation device
problem to be solved: to allow for estimating individual characteristics on anchoring by avoiding difficulty of experiments on cognitive bias called the anchoring effect that makes it impossible to guaranty independence if the same trial is repeated on the same experiment participant. Solution: Answers received by a first reception unit and values indicative of anchors are applied to a first estimation mode, second estimation model, and third estimation model to estimate a first personal characteristic value and a second personal characteristic value.
WO2023214484
Interest estimation device
The present invention addresses the problem of estimating a user’s interest in content on the basis of a cognitive bias of said user. An interest estimation device comprises: a storage unit that stores cognitive bias tendency information regarding a cognitive bias toward which users who indicate an interest in prescribed content have a tendency; an acquisition unit that acquires user cognitive bias information regarding a cognitive bias possessed by a target user, who is a user being targeted; and an estimation unit that estimates the target user’s interest in content on the basis of the cognitive bias tendency information stored in the storage unit and the user cognitive bias information acquired by the acquisition unit. The cognitive bias tendency information includes information regarding a cognitive bias toward which users who indicate an interest in content in a virtual world have a tendency, and the estimation unit may estimate the target user’s interest in content in the virtual world.
WO2023214483
Behavior Change Apparatus
The present invention addresses the problem of promoting the user's behavior change in a virtual space. A behavior change apparatus comprises: a contrivance determination for determining a contrivance for a user in a virtual space on the basis of a cognitive bias of the user; and a field installation unit for installing, in the virtual space, the contrivance determined by the contrivance determination unit. The contrivance determination unit may determine a contrivance by using a prediction model that predicts the degree of the user's behavior change by the contrivance by inputting the degree of the cognitive bias of the user. The contrivance may be a contrivance for guiding the user to predetermined content present in the virtual space. The determination of a contrivance by means of the contrivance determination unit may also be based on the attributes of the user.
The invention provides a platform that has the ability to accumulate all the opinions of users on different websites about a specific product, service, or brand and use natural language processing and natural language understanding to categorize comments about a product, service, or brand in the form of positive or negative, detailed or general, old or new, and can provide a vocal conversation-based approach in which the customer can easily manage a conversation with the system to and system is able to help customer in reaching an appropriate comment or feedback about a service or product. The platform further includes several features and systems that enhance the quality, reliability, and usefulness of the user feedback, such as ethical and legal issues prevention, text mining, rating system, bias detection, etc. This platform is able to help the user in buying a product or a service and provide him with valuable recommendations and reduce the user's cognitive biases.
Writing feedback or reviews is not always easy for customers. They may have different reasons to buy a product or service from various websites, but they may not have enough time, motivation, or information to share their opinions. They may also miss some important details or features of the product or service that could help other buyers or producers.
That's why there is a need for a smart and friendly voice assistant that can collect, analyze, and use user feedback in a better way. A voice assistant that can support both product and service reviews, and ask specific, customized, and unique questions based on the user's psychology, emotions, and preferences. A voice assistant that can adapt to the user's needs and suggest the best product or service for them based on their feedback on different websites. A voice assistant that can notify the user on their mobile phone and start a two-way conversation with them to encourage them to write a review for their purchase.
Customers also need more guidance and awareness when they choose a product or service. They need to know the latest updates, the expected lifetime, and the quality changes of the product or service. They need to overcome their cognitive biases and provide honest and fair assessments. Producers also need to know the user's feedback on the aspects of their product or service that may not be obvious or highlighted. New producers also need to reach more potential customers and showcase their brand.
All these needs and challenges can be solved by a voice assistant that can make writing feedback or reviews easier, faster, and more fun for customers.
Our invention is an integrated AI-based platform with many modules, and the aim is to make it easy for customers to collaborate in providing their reviews about the products they have bought and services they have taken and help them suggest the appropriate product or service.
Our invention is an integrated AI-based platform with many modules, and the aim is to make it easy for customers to collaborate in providing their reviews about the products they have bought and services they have taken and help them with suggesting the appropriate product or service.
To prepare an opportunity for producers or service providers to introduce their new product or service, we provide a module to create suggestions to diversify the brand in the customer's main product portfolio based on the feedback similarity and the criteria analysis, and a product suggestion module to suggest other products from those brands to the users, based on the users' preferences and needs and interests.
Another module of this invention help the user evaluate his arguments, and identify the points of view that may have been less noticed by the user, and analyze the sentences, and re-survey the parts that are ambiguous, and warn the user about the parts where the user’s opinion is exaggerated, and prompt the user to write a comment and invite him to take a fair assessment by an intelligent system that uses an opinion display module to display other opinions about the offered product or service from other sites and suppliers for the user, and an argument evaluation module to help the user evaluate his arguments by asking questions about his conclusion, criteria, standards, advantages, disadvantages, factors, and information, and requiring him to be honest and transparent about his reasoning process, and a point of view identification module to identify the points of view that may have been less noticed by the user by examining the opinions of the person and the general aspects of the product or service that can be examined, and a survey generation module to generate surveys about the specific aspects of the product or service, and a sentence analysis module to analyze the sentences of the user and re-survey the parts that are ambiguous to reach a clear survey, and a warning module to warn the user about the parts where the user’s opinion is exaggerated, and a comment prompt module to prompt the user to write a comment and invite him to take a fair assessment.
Negativity bias detection module detects the level of negativity bias effect in the user by using subtle tests based on psychological and behavioral principles, and a positive opinion presentation module to show the user the positive opinions of other users and different views on the product or service, and a pie chart generation module to show the user a large volume of positive opinions in a pie chart, and a feedback invitation module to invite the user to submit an opinion that is not affected by a negativity bias and provide guidance and assistance to the user on how to overcome the negativity bias effect in writing an appropriate review.
A store integrator module connect to different stores through API with a user-friendly environment and enable the users to send feedback to the stores, and a feedback synchronization module to synchronize the feedback data of the same product or service across different websites and prevent the users from getting confused.
Facilitation module facilitates the processes of logging in, confirming a purchase, uploading a photo or video, editing or deleting a comment, or finding the right place to write a comment, and provide guidance and assistance to the users who may be confused about these processes.
A question design and asking module generates questions for the user based on the product or service type and its salient features and keywords in the feedback data of other product buyers and asks the questions from the user and receive the answers and read and understand them using natural language processing and and natural language understanding.
A feedback analysis module identifys the extreme feedback (either positive or negative) about a product and combines the feedback data of the product buyers and the service providers, and displays and compares the feedback data to the users in a user-friendly and interactive manner.
A survey generation module creates a survey based on the product features and the feedback criteria and send the survey to the potential feedback providers who have bought the same product or a similar product but have not yet registered a feedback.
The user feedback module is responsible for collecting and analyzing the feedback of the users who use a product, such as ratings, reviews, comments, likes, dislikes, etc. The user feedback module can use web scraping and data mining techniques to access and extract user feedback data from different websites, and can use natural language processing and sentiment analysis techniques to understand the user feedback data and to identify the special events or outcomes that the users experience while using the product, such as defects, malfunctions, accidents, injuries, benefits, improvements, etc.
The notification module is responsible for sending and receiving notifications to and from other users who bought or reviewed the same product, based on the occurrence of a special event or outcome related to the product. The notification module can use push notifications and text messages to alert the other users about the special event or outcome that the user experienced while using the product, and to invite them to share their feedback or opinion on the product. The notification module can also use natural language generation and speech synthesis techniques to provide verbal notifications and explanations to the other users, based on the content and analysis of the user feedback module, and can use graphical user interface elements to enable the other users to respond to the notifications using various input methods, such as text, voice, rating, etc.
By integrating these modules, the follow-up system not only collects and analyzes the feedback of the users who use a product, but also notifies and engages other users who bought or reviewed the same product, based on the occurrence of a special event or outcome related to the product.
The bi-directional conversation module establishes a communication channel between the system and the user, and requesting and receiving a series of photos of the product from the user. The bi-directional conversation module can use natural language processing and speech recognition techniques to understand the user’s input and output, and can use graphical user interface elements to facilitate the photo uploading process.
The video processing module generates a video clip of the product quality changes. It shows the degradation of the product in its life span, based on the series of photos received from the user in a time interval. The video processing module can use image processing and computer vision techniques to analyze the features and attributes of the product in each photo and stitch the photos together to create a smooth and coherent video clip. The video processing module can also use machine learning and artificial intelligence techniques to enhance the quality and resolution of the video clip and add effects and annotations to highlight the changes and improvements of the product over time.
The visual feedback module is responsible for providing the video clip as a visual feedback for the product to the user. The visual feedback module can use multimedia and web technologies to display the video clip on the user’s device, and to enable the user to interact with the video clip, such as playing, pausing, rewinding, fast-forwarding, zooming, etc. The visual feedback module can also use natural language generation and speech synthesis techniques to provide verbal feedback and explanations to the user, based on the content and analysis of the video clip.
The product usage module is responsible for asking the user how long they are going to use the product, and receiving the user’s input. The product usage module can use natural language processing and speech recognition techniques to understand the user’s input and output, and can use graphical user interface elements to facilitate the input process.
The product lifetime estimator module is responsible for estimating the best life time span for the product based on the opinions of other users who have used the product in question. The product lifetime module can use web scraping and data mining techniques to collect and analyze the opinions of other users from different websites, and can use machine learning and artificial intelligence techniques to estimate the best life time span for the product based on the features and attributes of the product, and the usage patterns and preferences of the users.
The recommendation module is responsible for providing recommendations to the user on various entities from different websites, such as products, services, reviews, articles, videos, etc. The recommendation module can use natural language generation and speech synthesis techniques to provide verbal recommendations and explanations to the user, based on the content and analysis of the product lifetime module, and can use multimedia and web technologies to display the recommendations on the user’s device, and to enable the user to access and interact with the entities from different websites.
The buyer satisfaction module to measure the level of awareness and satisfaction of the previous buyers and those who had entered their last negative or positive comments about the previous similar product as soon as the new product is introduced in the market. This module can use web scraping and data mining techniques to access and extract the feedback data of the previous buyers from different websites, and can use natural language processing and sentiment analysis techniques to understand the feedback data and to calculate the awareness and satisfaction scores of the previous buyers.
The product suggestion module suggests a new and similar product that has recently released to the market and has received good feedback, and finds out the reasons for dissatisfaction and/or satisfaction with the previous similar product, and recommends the new product that has released to the market to the user, taking into account the new changes and their relationship with the user’s dissatisfaction. This module can use machine learning and artificial intelligence techniques to perform various types of analysis on the feedback data of the previous and the new products, such as feature extraction, aspect extraction, opinion summarization, etc. This module can also use natural language generation and speech synthesis techniques to provide verbal suggestions and explanations to the user, based on the content and analysis of the feedback data.
The follow-up module that monitors the user’s satisfaction with the new product during the follow-up period, and provides assistance and guidance to the user if the user is dissatisfied with the product for any reason. This module can use natural language processing and speech recognition techniques to understand the user’s input and output, and to provide verbal feedback and explanations to the user, based on the content and analysis of the product suggestion module. The module can also use graphical user interface elements to enable the user to interact with the system, such as rating, reviewing, commenting, etc.
By integrating these modules, the system not only measures the level of awareness and satisfaction of the previous buyers and those who had entered their last negative or positive comments about the previous similar product as soon as the new product was released to the market but also suggests a new and similar product that has recently entered the market and has received good feedback, and finds out the reasons for dissatisfaction and or satisfaction with the previous similar product, and recommends the new product that has entered the market to the user, taking into account the new changes and their relationship with the user’s dissatisfaction, and monitors the user’s satisfaction with the new product during the follow-up period, and provides assistance and guidance to the user if the user is dissatisfied with the product for any reason.
The dual-profile analysis module reaches two physical and mental profiles of the user. This module assesses the user’s characteristics and preferences by analyzing their feedback on various entities from different websites. It then finds out the relationship between the user’s feedback and their profile, including user behavior, preferences, satisfaction levels, cognitive biases, sentiments, interests, and emotions.
The product recommendation module utilizes the analyzed data to offer the best product options to the user. This module takes into account the user’s physical and mental profile to suggest products that align with their needs and preferences, thereby enhancing the user experience and satisfaction.
The user dissatisfaction module informs the entity about any user dissatisfaction detected through feedback analysis module. This module helps entities understand the user’s concerns and take appropriate actions to address them, such as improving product quality, adjusting services, or providing personalized customer support.
By integrating these modules, the system not only personalizes the shopping experience for the user but also aids entities in maintaining high customer satisfaction and loyalty.
The motivation module that motivates the user to write a review for their purchase on various entities from different websites. This module can use gamification and reward techniques to incentivize the user to write a review, such as offering points, badges, discounts, Prizes, etc. The module can also use social proof and persuasion techniques to influence the user to write a review, such as showing the number of reviews, ratings, and feedbacks from other users, highlighting the benefits and impacts of writing a review, etc.
The review submission module that facilitates the user to write and submit a review for their purchase on various entities from different websites. This module can use graphical user interface elements to simplify the review writing process, such as providing rating scales, checkboxes, text boxes, etc. The module can also use web scraping and data mining techniques to access and display the entities from different websites, and to enable the user to submit their review to multiple entities with a single click.
By integrating these modules, the system not only enhances the user’s engagement and satisfaction with their purchase, but also increases the user’s participation and contribution to the online review community.
The voice assistant that uses a request analysis module to adjust to the user’s request and guide them to the most similar product or service based on their feedback on various entities from different websites. This module can use natural language processing and speech recognition techniques to understand the user’s request and output, and to extract the relevant keywords and criteria from the user’s feedback.
The voice assistant also includes a similarity search module that searches for the most similar product or service based on the user’s feedback on various entities from different websites. This module can use web scraping and data mining techniques to collect and compare the feedback data of different products and services from different websites, and can use machine learning and artificial intelligence techniques to calculate the similarity score of each product or service based on the user’s feedback keywords and criteria.
Furthermore, the voice assistant features a guidance module that guides the user to the most similar product or service based on their feedback on various entities from different websites. This module can use natural language generation and speech synthesis techniques to provide verbal guidance and explanations to the user, based on the content and analysis of the similarity search module, and can use multimedia and web technologies to display the most similar product or service on the user’s device, and to enable the user to access and interact with the product or service from different websites.
By integrating these modules, the voice assistant not only personalizes the user’s shopping experience based on their feedback, but also helps the user find the best product or service that matches their needs and preferences.
The questionnaire generation module to provide specific, customized, unique questionnaires in each field of services, products, or brands based on users’ psychological behavior, sentiments, reactions, beliefs, emotions, interests, cognitive biases, etc. This module can use natural language processing and sentiment analysis techniques to understand the users’ feedback and emotions on various entities from different websites, and to extract the relevant topics and aspects from the feedback data. The module can also use machine learning and artificial intelligence techniques to generate specific, customized, unique questions for each user based on their psychological profile, which includes factors such as personality, motivation, attitude, preference, etc.
The questionnaire presentation module presents the specific, customized, unique questionnaires to the users in an engaging and interactive manner. This module can use graphical user interface elements to display the questionnaires on the users’ devices, and to enable the users to answer the questions using various input methods, such as text, voice, rating, etc. The module can also call the motivate module to use gamification and reward techniques to incentivize the users to complete the questionnaires, such as offering points, badges, discounts, coupons, prizes, etc.
The questionnaire analysis module analyzes the users’ responses to the specific, customized, unique questionnaires, and provides insights and recommendations to the users and the entities based on the analysis results. This module can use data mining and statistical techniques to analyze the users’ responses and identify the patterns, trends, and correlations among the users’ psychological behavior, sentiments, reactions, beliefs, emotions, interests, etc. The module can also use natural language generation and speech synthesis techniques to provide verbal insights and recommendations to the users and the entities, based on the content and analysis of the questionnaire data.
By integrating these modules, the system not only provides specific, customized, unique questionnaires in each field of services, products, or brands based on users’ psychological behavior, sentiments, reactions, beliefs, emotions, interests etc., but also helps the users and the entities to understand and improve their experiences and satisfaction levels.
The feedback facilitation module solves the challenges of users in writing feedback or their opinion about a product, service, or brand and facilitate this process. This module can use natural language processing and speech recognition techniques to understand the user’s input and output, and to provide guidance and assistance to the user on how to write a feedback or an opinion. The module can also use graphical user interface elements to simplify the feedback or opinion writing process, such as providing templates, suggestions, examples, etc.
The feedback improvement module improves the quality and clarity of the user’s feedback or opinion. This module can use natural language generation and speech synthesis techniques to provide verbal feedback and explanations to the user, based on the content and analysis of the user’s feedback or opinion. The module can also use machine learning and artificial intelligence techniques to enhance the style and tone of the user’s feedback or opinion, such as correcting grammar, spelling, punctuation, etc., and adding emotions, expressions, etc.
By integrating these modules, the system not only solves the challenges of users in writing feedback or their opinion about a product, service, or brand, but also facilitates this process and enhances the user’s experience and satisfaction.
The feedback collection module to collect user feedback on various entities from different websites in an efficient and reliable way. This module can use web scraping and data mining techniques to access and extract user feedback data from different websites, such as ratings, reviews, comments, likes, dislikes, etc. The module can also use natural language processing and speech recognition techniques to understand the user feedback data and to convert it into a structured and standardized format.
the feedback analysis module analyzes user feedback on various entities from different websites in a comprehensive and user-friendly way. This module can use machine learning and artificial intelligence techniques to perform various types of analysis on the user feedback data, such as sentiment analysis, topic modeling, aspect extraction, opinion summarization, etc. The module can also use natural language generation and speech synthesis techniques to provide verbal analysis results and explanations to the users, based on the content and analysis of the user feedback data.
The feedback utilization module utilizes user feedback on various entities from different websites in a beneficial and personalized way. This module can use data mining and statistical techniques to identify the patterns, trends, and correlations among the user feedback data, and to provide insights and recommendations to the users and the entities based on the analysis results. The module can also use multimedia and web technologies to display the user feedback data and the analysis results on the user’s device, and to enable the user to access and interact with the user feedback data and the analysis results, such as filtering, sorting, searching, etc.
By integrating these modules, the system not only collects, analyzes, and utilizes user feedback on various entities from different websites in an efficient, reliable, and user-friendly way, but also enhances the user’s experience and satisfaction, and improves the entity’s performance and quality.
The cognitive bias prevention module is a module that aims to reduce the impact of cognitive biases on customer decision-making and behavior. Cognitive biases are errors or distortions in thinking that affect how users perceive and interpret information, often leading to irrational or suboptimal choices. Some examples of cognitive biases are confirmation bias, anchoring bias, loss aversion, and bandwagon effect. The cognitive bias prevention module can use various techniques and technologies to detect, correct, and prevent cognitive biases, such as:
Providing objective and balanced information about the products or services, such as features, benefits, drawbacks, alternatives, etc.
Offering personalized and relevant recommendations based on the customer’s needs, preferences, and goals, rather than on popularity, availability, or price.
Using nudges and incentives to encourage the customer to explore different options, compare different attributes, and consider different perspectives.
Educating the customer about the common cognitive biases and how they can affect their decisions and outcomes.
Asking the customer to reflect on their decisions and provide feedback on their satisfaction and experience.
By integrating this module, the system can help the customer make more informed, rational, and satisfying decisions, and improve the customer experience and loyalty.
This invention can help customers make better and more informed decisions, by providing them with objective and balanced information, personalized and relevant recommendations, and guidance and assistance throughout the feedback and suggestion process.
This invention can help customers improve their satisfaction and loyalty, by providing them with feedback and suggestions that match their needs and preferences, by reducing the impact of cognitive biases on their decision-making and behavior, and by monitoring and addressing their dissatisfaction and concerns.
This invention can help businesses increase their sales and revenue, by providing them with insights and recommendations based on the feedback and suggestions of the customers, by improving their product quality and service delivery, and by providing them with personalized customer support.
This invention can help businesses enhance their reputation and brand image, by providing them with feedback and suggestions that reflect their strengths and weaknesses, by informing them about any user dissatisfaction and taking appropriate actions to address them, and by motivating and rewarding the customers for writing feedback and suggestions.
This invention can help the online review community grow and thrive, by providing them with feedback and suggestions that are high-quality, clear, and consistent, by facilitating and improving the feedback and suggestion writing process, and by engaging and interacting with the customers and the entities in an efficient and reliable way.
This invention can help customers connect and socialize with other customers and entities, by providing them with feedback and suggestions that are engaging and interactive, by using various techniques and technologies to facilitate and improve the communication and collaboration process, such as graphical user interface, multimedia, web technologies, gamification, reward, social proof, persuasion, etc., and by creating and maintaining a community of feedback and suggestion providers and consumers.
This invention can help customers save time and money, by providing them with feedback and suggestions that are efficient and reliable, by using various techniques and technologies to collect and compare feedback and suggestions from different websites, such as web scraping, data mining, etc., and by providing them with the best and most suitable feedback and suggestions for their needs and preferences
This invention uses nudges and incentives to encourage the customer to explore different options, compare different attributes, and consider different perspectives, and educates the customer about the common cognitive biases and how they can affect their decisions and outcomes.
Examples
Imagine you want to buy a new bicycle online. You have some preferences, such as the color, the size, and the price of the bicycle. You enter these preferences into a module that helps you find the best bicycle for you. This module is the product specification module.
The another module shows you different online shops that sell bicycles that match your preferences. Some of these shops are more popular or trustworthy than others, so they are shown at the top of the list. The platform has an agreement with these shops to promote them more. This module is the website selection module.
You choose one of the shops and buy a bicycle from there. After you receive the bicycle, you want to share your opinion about it with other people who might be interested in buying a bicycle. You write a review and rate the bicycle on a scale of 1 to 5 stars. The module asks you if you want to post your review on other websites as well, such as social media or blogs. You can choose one or more websites where you want your review to appear. The module also adds some information to your review, such as your name, the bicycle model, and the shop where you bought it. This way, other people can see that you are a real customer and not a fake one. This module is the feedback insertion module.
The module also keeps track of all the reviews that are posted on different websites about the bicycles and the shops. It analyzes the reviews and looks for any signs of unfair or dishonest behavior. For example, some people might write bad reviews about a shop or a bicycle without actually buying it, just to hurt their reputation or to promote another shop or bicycle. These people are called attackers. The website can detect these attackers by checking if they have actually bought the product or service from the website they are reviewing. This module is the feedback analysis module.
The module also takes actions to stop these attackers and to protect the honest customers and shops. For example, it can remove the link to the product or service that is being attacked, so that other people cannot see the fake reviews. It can also report the profiles of the attackers to the websites where they posted the reviews, and send them warning messages to stop their behavior. It can also show more detailed and balanced reviews to the potential buyers, so that they can see the pros and cons of the product or service and make an informed decision. This module is the feedback management module.
Imagine you bought a new smartphone online and you are not happy with it. You think the screen is too small, the battery life is too short, and the camera quality is poor. You want to return the smartphone and get a refund.
You visit the website where you bought the smartphone and you see a pop-up window that asks you some questions. The questions are about your experience with the website, the delivery, the payment, and the product. Some of the questions are random and not related to the smartphone, such as your favorite color, your hobbies, or your pets. These questions are meant to make you feel more comfortable and to hide the real purpose of the survey, which is to find out why you are dissatisfied with the smartphone. This pop-up window is the user interface.
The website collects your answers and sends them to a computer program that analyzes them. The program looks for patterns and trends in your answers and compares them with other users who bought the same smartphone. The program tries to figure out what is the main reason that makes you unhappy with the smartphone. For example, it might find out that most of the users who complained about the smartphone have poor eyesight, and that the screen size is too small for them. Or it might find out that most of the users who complained about the smartphone use it for taking photos and videos, and that the camera quality is not good enough for them. The program also considers your personal information, such as your age, gender, location, and preferences, to understand your needs and expectations better. This computer program is the monitoring module.
The program also counts how many users are unhappy with the smartphone and how many users are happy with it. It compares these numbers with a fixed value that represents the acceptable level of dissatisfaction. For example, the website might decide that if more than 10% of the users are unhappy with the smartphone, then there is a problem that needs to be solved. If the program finds out that the number of unhappy users is higher than the fixed value, it sends a message to the people who are responsible for the smartphone, such as the seller, the owner, the manufacturer, and anyone else who is involved in providing the smartphone to the customers. The message tells them that there is a high level of dissatisfaction with the smartphone and what is the main cause of it. This way, they can take actions to improve the smartphone or to offer better alternatives to the customers. This message is the reporting module.
Imagine you bought a new book online and you are not happy with it. You think the book is boring, poorly written, and full of lies. You want to write a negative review and warn other people not to buy the book.
You visit the website where you bought the book and you see a pop-up window that asks you some questions. The questions are about your experience with the website, the delivery, the payment, and the book. Some of the questions are random and not related to the book, such as your favorite movie, your birthday, or your pets. These questions are meant to make you feel more comfortable and to hide the real purpose of the survey, which is to find out why you are dissatisfied with the book. This pop-up window is the user interface.
The module reads your review and compares it with the laws of the country where you live and where your readers are. The module looks for any mistakes or violations in your review, such as spelling errors, grammar errors, false information, defamation, hate speech, or incitement to violence. The website also checks if you have the right to use any images, videos, or quotes that you include in your review. The website marks any errors or violations with red color and explains why they are wrong or illegal. This module is the verification module.
The module also helps you fix your review and make it more legal and ethical. The module can introduce some errors into your review on purpose, such as changing some words or sentences, to make it less clear or convincing. This way, you can avoid being accused of spreading propaganda or influencing public opinion. The module can also suggest some alternative content that does not break the law or harm anyone, such as using different words, sources, or examples. The module shows you the original and the modified versions of your review and lets you choose which one you prefer. This module is the modification module.
The module warns you about the possible consequences of publishing your review, either the original or the modified one. The website tells you what kind of legal actions or penalties you might face if someone sues you or reports you to the authorities. The module also tells you how your review might affect your reputation, your audience, or your cause. The module asks you to confirm that you understand the risks and that you want to publish your review anyway. This module is the notification module.
Imagine you want to buy a new pair of shoes online. You have some preferences, such as the color, the size, and the style of the shoes. You tell these preferences to a website that helps you find the best shoes for you. You also tell the website how long you are going to use the shoes, such as for a day, a week, a month, or a year. This module is the voice-based intelligent assistant.
The database module collects your preferences and the duration of use and sends them to a computer program that stores and organizes the opinions and experiences of other users who bought the same or similar shoes. The module groups the users by the product name and the duration of use, such as users who bought red sneakers for a week, or users who bought black boots for a year. The module also analyzes the users’ feedback, such as their ratings, reviews, or complaints.
A computer program sends your preferences and the duration of use to another computer program that helps you choose the best shoes for you. The program looks for the users who have the same or similar preferences and the same or similar duration of use as you. The program compares the feedback of these users and finds the shoes that have the highest satisfaction, the lowest complaints, and the best quality. The program also considers other factors, such as the price, the availability, and the popularity of the shoes. The program then gives you some suggestions of the shoes that you might like and that suit your needs. This computer program is the recommendation engine.
A computer program also converts the suggestions into speech and tells them to you by voice. You can hear the name, the description, and the price of the shoes that the program recommends. You can also ask the program more questions about the shoes, such as their features, their benefits, or their drawbacks. The program can answer your questions by voice as well. This computer program is the speech synthesizer.
Imagine you bought a new pair of jeans online and you want to see how they look and fit over time. You also want to share your opinion and experience with other people who might be interested in buying the same jeans.
You receive a notification on your mobile phone a few days after you bought the jeans. The notification is from a computer program that helps you track and report the quality of the jeans. The program asks you if you want to join a project that collects and analyzes pictures of the jeans from different users. You agree to join the project and you open the program on your phone. This program is the follow-up module.
A module talks to you by voice and guides you through the process of taking and uploading pictures of the jeans. The module asks you to wear the jeans and to take pictures of them from different angles, such as the front, the back, the sides, and the details. The module also asks you to repeat this process at different time intervals, such as every week, every month, or every year. The module explains that this way, you can see how the jeans change over time, such as their color, their shape, their size, and their wear and tear. The module also tells you that your pictures will help other users who have the same or similar jeans to compare and evaluate them. This module is the voice-based intelligent assistant.
a module collects your pictures and sends them to a computer program that processes and analyzes them. The program looks for any changes or differences in the jeans based on the pictures. The program measures the dimensions, the colors, the textures, and the patterns of the jeans and compares them with the original pictures and the pictures from other users. The program also detects any signs of damage, such as holes, tears, stains, or fading. The program also considers your personal information, such as your height, weight, age, and preferences, to understand how the jeans fit and suit you better. This computer program is the image processing module.
A module also sends your pictures to another computer program that creates a video clip of the jeans. The program selects the most relevant and representative pictures of the jeans from different angles and time intervals. The program then arranges the pictures in a chronological order and adds some transitions and effects to make the video more smooth and appealing. The program also adds some text and audio to the video, such as the name, the description, and the price of the jeans, and your rating, review, or comment about them. The program then compresses the video to make it shorter and easier to watch. The video shows the quality of the jeans degrading over time, such as their color fading, their shape stretching, or their fabric tearing. This computer program is the video generator.
The module also stores and displays the video clip as a feedback record for the jeans. The website shows you the video and asks you if you want to share it with other users or not. You can also see the videos from other users who have the same or similar jeans and compare them with yours. You can also see the ratings, reviews, and comments from other users and give your own feedback. The module also gives you some suggestions of other jeans that you might like and that have better quality or durability. This module is the feedback recorder.
Imagine you want to buy a new laptop online and you want to read the feedback from other users who bought the same or similar laptops. You have some preferences, such as the brand, the model, the features, and the price of the laptop. You also have some opinions, such as which brand is better, which model is faster, which features are more useful, and which price is more reasonable.
A module helps you find and compare the best laptops for you. The module also shows you the feedback from other users who bought the laptops that you are interested in. The feedback includes ratings, reviews, and comments. The module also asks you some questions about your preferences and opinions. The module is the confirmation bias identification module.
A module collects your answers and sends them to a computer program that analyzes them. The program looks for any signs of confirmation bias in your answers. Confirmation bias is the tendency to search for, interpret, favor, and recall information in a way that confirms one’s preexisting beliefs or hypotheses. For example, you might only pay attention to the positive feedback that supports your preferences and opinions, and ignore or dismiss the negative feedback that contradicts them. Or you might only trust the feedback from users who have the same or similar preferences and opinions as you, and doubt or reject the feedback from users who have different or opposite preferences and opinions. The program also compares your answers with a fixed value that represents the acceptable level of confirmation bias. For example, the website might decide that if more than 50% of your answers show confirmation bias, then you need to be more open-minded and objective. The program then decides if you are suffering from confirmation bias or not based on your behavior and the fixed value. This computer program is the confirmation bias confirmation module.
A module sends your answers to another computer program that helps you reduce your confirmation bias and improve your decision making. The program looks for the feedback from other users that are fair and balanced and that challenge your preferences and opinions. The program also considers other factors, such as the relevance, the credibility, and the diversity of the feedback. The program then shows you the feedback from other users that you might have missed or ignored because of your confirmation bias. The program also asks you to rate or review the feedback from other users and to explain why you agree or disagree with them. The program also gives you some tips and suggestions on how to overcome your confirmation bias and how to evaluate the feedback from other users more critically and rationally. This computer program is the confirmation bias reduction module.
A module also collects your ratings and reviews and sends them to another computer program that adjusts the weight and the impact factor of your feedback in an opinion rating system. The opinion rating system is a system that calculates and displays the overall score and the popularity of the laptops based on the feedback from all the users. The program looks for the degree of confirmation bias in your feedback and compares it with the feedback from other users. The program then decides how much your feedback should influence the opinion rating system. For example, if your feedback shows a high degree of confirmation bias, then your feedback will have a lower weight and a lower impact factor than the feedback from users who show a low degree of confirmation bias. This way, the opinion rating system can reflect the feedback from all the users more accurately and fairly. This computer program is the feedback weighting module.
Imagine you want to buy a new smartphone online and you want to read the feedback from other users who bought the same or similar smartphones. You have some preferences, such as the brand, the model, the features, and the price of the smartphone. You also have some opinions, such as which brand is better, which model is faster, which features are more useful, and which price is more reasonable.
A module helps you find and compare the best smartphones for you. The module also shows you the feedback from other users who bought the smartphones that you are interested in. The feedback includes ratings, reviews, and comments. The module also asks you some questions about your feelings and opinions. The module is the sentiment analysis module.
A module collects your answers and sends them to a computer program that analyzes them. The program looks for any signs of halo effect in your answers. Halo effect is a cognitive bias that causes you to have a positive or negative impression of a product based on another product. For example, you might like or dislike a smartphone because of its brand name, regardless of its actual quality or performance. Or you might like or dislike a smartphone because of its appearance, regardless of its actual features or functionality. The program also rewards you for answering the questions and giving feedback by giving you points, badges, or prizes. The program also encourages you to give more feedback and to interact with other users. This computer program is the gamification module.
A module sends your answers to another computer program that displays several products that have been influenced by the halo effect of another product. The program looks for the products that have similar or different characteristics to the product that you are interested in, such as the brand, the model, the features, or the price. The program also considers other factors, such as the availability, the popularity, and the compatibility of the products. The program then shows you the products that you might have overlooked or overrated because of the halo effect of another product. The program also asks you to rate or review the products and to explain why you like or dislike them. This computer program is the product selection module.
A module collects your ratings and reviews and sends them to another computer program that measures the influence of the halo effect on your feedback. The program looks for any changes or differences in your feedback based on the products that you rated or reviewed. The program compares your feedback with the feedback from other users who have the same or similar preferences and opinions as you. The program also compares your feedback with the feedback from other users who have different or opposite preferences and opinions as you. The program then calculates how much your feedback is affected by the halo effect of another product. For example, the program might find out that you gave a higher rating to a smartphone because of its brand name, even though it had lower quality or performance than another smartphone. Or the program might find out that you gave a lower rating to a smartphone because of its appearance, even though it had higher features or functionality than another smartphone. This computer program is the halo effect measurement module.
A module sends your ratings and reviews to another computer program that adjusts the weight and the impact factor of your feedback in a rating system. The rating system is a system that calculates and displays the overall score and the popularity of the smartphones based on the feedback from all the users. The program looks for the degree of halo effect in your feedback and compares it with the feedback from other users. The program then decides how much your feedback should influence the rating system. For example, if your feedback shows a high degree of halo effect, then your feedback will have a lower weight and a lower impact factor than the feedback from users who show a low degree of halo effect. This way, the rating system can reflect the feedback from all the users more accurately and fairly. This computer program is the feedback rating module.
Imagine you want to buy a new video game online and you want to read the feedback from other users who bought the same or similar video games. You have some preferences, such as the genre, the graphics, the gameplay, and the price of the video game. You also have some opinions, such as which video game is more fun, more challenging, more realistic, or more worth buying.
A module helps you find and compare the best video games for you. The website also shows you the feedback from other users who bought the video games that you are interested in. The feedback includes ratings, reviews, and comments. The website also asks you some questions about your preferences and opinions. The website is the bandwagon effect detection module.
A module e collects your answers and sends them to a computer program that analyzes them. The program looks for any signs of bandwagon effect in your answers. Bandwagon effect is a cognitive bias that causes you to conform to the opinion of others, regardless of your own beliefs, which you may ignore or override. For example, you might buy or like a video game because it is popular or trendy, even if it does not match your preferences or opinions. Or you might avoid or dislike a video game because it is unpopular or outdated, even if it does match your preferences or opinions. The program also proposes that you write an opinion that is contrary to the opinion of others and that provides a different point of view on the video game that everyone is praising or criticizing. For example, you might write a positive review of a video game that has low ratings, or a negative review of a video game that has high ratings. The program also explains why it is important to have diverse and independent opinions and how they can benefit you and other users. This computer program is the feedback generation module.
A module also sends your opinion to another computer program that helps you mitigate your bandwagon effect and improve your decision making. The program encourages you to persist in your opposite opinion and to display the rejection or approval of your opinion by other users. The program also gives you some feedback and suggestions on how to improve your opinion and make it more convincing and informative. The program also shows you the opinions of other users who have the same or similar preferences and opinions as you, but who have different or opposite opinions on the video game that you rated or reviewed. The program also asks you to rate or review their opinions and to explain why you agree or disagree with them. The program also gives you some tips and suggestions on how to overcome your bandwagon effect and how to evaluate the opinions of other users more critically and rationally. This computer program is the feedback reinforcement module.
A module collects your opinion and sends it to another computer program that displays your opinion on one or more websites that sell the video game that you rated or reviewed. The program lets you choose which websites you want to post your opinion on, such as social media, blogs, or forums. The program also adds some information to your opinion, such as your name, the video game name, and the website where you bought it. This way, other users can see that you are a real customer and not a fake one. The program also shows you the opinions of other users who have the same or similar video games as you and who have posted their opinions on the same or different websites as you. The program also lets you interact with them and exchange your opinions and experiences. This computer program is the feedback display module.
Imagine you want to buy a new coffee maker online and you want to read the feedback from other users who bought the same or similar coffee makers. You have some preferences, such as the brand, the model, the features, and the price of the coffee maker. You also have some opinions, such as which coffee maker is more reliable, more convenient, more efficient, or more worth buying.
A module helps you find and compare the best coffee makers for you. The module also shows you the feedback from other users who bought the coffee makers that you are interested in. The feedback includes ratings, reviews, and comments. The module also asks you some questions about your preferences and opinions. The module is the negativity bias detection module.
A module collects your answers and sends them to a computer program that analyzes them. The program looks for any signs of negativity bias in your answers. Negativity bias is a cognitive bias that causes you to focus more on negative than positive information, regardless of their frequency or importance. For example, you might pay more attention to the negative feedback that criticizes the coffee maker, and ignore or dismiss the positive feedback that praises the coffee maker. Or you might trust the negative feedback more than the positive feedback, and think that the positive feedback is biased or dishonest. The program also shows you the positive opinions of other users and different views on the coffee maker that you are reviewing. The program also explains why it is important to consider both the positive and negative aspects of the coffee maker and how they can benefit you and other users. This computer program is the feedback presentation module.
A module sends your answers to another computer program that displays a large volume of positive opinions in a bar chart. The program looks for the positive opinions of other users who have the same or similar coffee makers as you. The program also considers other factors, such as the relevance, the credibility, and the diversity of the opinions. The program then shows you a bar chart that represents the number and the percentage of positive opinions for each coffee maker. The program also invites you to submit an opinion that is not affected by negativity bias and that reflects your true experience and satisfaction with the coffee maker. The program also gives you some tips and suggestions on how to overcome your negativity bias and how to write a fair and balanced opinion. This computer program is the feedback visualization module.
A module also collects your opinion and sends it to another computer program that displays your opinion on one or more websites that sell the coffee maker that you rated or reviewed. The program lets you choose which websites you want to post your opinion on, such as social media, blogs, or forums. The program also adds some information to your opinion, such as your name, the coffee maker name, and the website where you bought it. This way, other users can see that you are a real customer and not a fake one. The program also shows you the opinions of other users who have the same or similar coffee makers as you and who have posted their opinions on the same or different websites as you. The program also lets you interact with them and exchange your opinions and experiences. This computer program is the feedback display module.
Imagine you want to buy a new car online and you want to read the feedback from other users who bought the same or similar cars. You have some preferences, such as the brand, the model, the features, and the price of the car. You also have some opinions, such as which car is more reliable, more comfortable, more efficient, or more worth buying.
A module that helps you find and compare the best cars for you. The module also shows you the feedback from other users who bought the cars that you are interested in. The feedback includes ratings, reviews, and comments. The module also asks you some questions about your satisfaction and the cost of the cars that you have bought or used in the past. The module is the cost and satisfaction module.
A module collects your answers and sends them to a computer program that analyzes them. The program looks for any signs of sunk cost fallacy in your answers. Sunk cost fallacy is a cognitive bias that causes you to continue investing in a product or service that has already incurred a significant cost and does not provide satisfactory results. For example, you might keep using or buying a car that is expensive, old, or faulty, just because you have spent a lot of money, time, or effort on it. Or you might avoid using or buying a car that is cheap, new, or functional, just because you think that switching to a different car would be a waste of your previous investment. The program also examines the evidence of the sunk cost fallacy in the feedback that you provide later about the cars that you have bought or used. The program also explains why the sunk cost fallacy is irrational and harmful and how it can affect your decision making. This computer program is the fallacy identification module.
A module sends your answers and feedback to another computer program that helps you prevent and correct your sunk cost fallacy and improve your decision making. The program informs you about the sunk cost fallacy and offers you alternative suggestions at the time of action for the next purchase of cars that are similar to the ones that caused the fallacy. The program also gives you some feedback and suggestions on how to improve your feedback and make it more objective and informative. The program also shows you the feedback from other users who have the same or similar preferences and opinions as you, but who have avoided or overcome the sunk cost fallacy. The program also asks you to rate or review their feedback and to explain why you agree or disagree with them. The program also gives you some tips and suggestions on how to overcome your sunk cost fallacy and how to evaluate the feedback from other users more critically and rationally. This computer program is the fallacy correction module.
A module collects your feedback and sends it to another computer program that displays your feedback on one or more websites that sell the cars that you rated or reviewed. The program lets you choose which websites you want to post your feedback on, such as social media, blogs, or forums. The program also adds some information to your feedback, such as your name, the car name, and the website where you bought it. This way, other users can see that you are a real customer and not a fake one. The program also shows you the feedback from other users who have the same or similar cars as you and who have posted their feedback on the same or different websites as you. The program also lets you interact with them and exchange your opinions and experiences. This computer program is the feedback display module.
Industrial application
Claims (27)
- A platform comprising :
- a web crawler configured to access and extract user opinions from different websites related to a product or a service;
- a database configured to store and organize the extracted user opinions based on the product or service name, the website source, and the opinion sentiment; and
- a user interface configured to display the aggregated user opinions for a product or a service in a graphical or textual format.
- A platform comprising,
- a natural language processing unit configured to analyze user comments from different websites related to a product, a service, or a brand and classify them into categories based on their polarity, specificity, recency, and expertise;
- a database configured to store and organize the classified user comments based on the product, service, or brand name and the category name; and
- a user interface configured to display the categorized user comments for a product, a service, or a brand in a graphical or textual format.
- A platform comprising,
- a voice-based intelligent assistant configured to receive voice commands from a user and perform actions based on the voice commands;
- a report generator configured to create reports based on the user comments, categories, and products, services, or brands stored in the database;
- a speech synthesizer configured to convert the reports into speech and provide them to the user by voice;
- a speech analyzer configured to analyze the user’s voice feedback and adjust the presentation speed, skip reading a text, or react to the user’s expected word based on the feedback; and
- a recommendation engine configured to guide the user to the product or service that is most similar to his request by analyzing the user’s voice command and comparing it with the data stored in the database.
- A platform comprising,
- a questionnaire generator configured to create specific questionnaires in each field of services, products, or brands and present them to the user;
- a query processor configured to process the user’s responses to the questionnaires and limit the user’s searchable options in the same field based on the responses; and
- a data aggregator configured to provide accumulated data based on categories for the user’s searchable options from the database and display them to the user in a graphical or textual format.
- An intelligent system comprising,
- a notification module configured to send a notification to a user’s mobile phone;
- a voice-based intelligent assistant configured to initiate and maintain a bidirectional conversation with the user via the mobile phone; and
- a data processing module configured to process the user’s voice input and output and provide relevant information to the user via the voice-based intelligent assistant.
- An intelligent system comprising,
- a follow-up module configured to send a notification to a user’s mobile phone at different time intervals after the user has purchased a product;
- a voice-based intelligent assistant configured to communicate with the user via the mobile phone and record the user’s opinions and experiences with the product;
- a database configured to store and organize the user’s opinions and experiences based on the product name and the time interval; and
- a quality assessment module configured to create a time frame for each product and evaluate the quality of the product or the decline in the quality of the product based on the user’s opinions and experiences stored in the database.
- An intelligent system comprising,
- a profile generator configured to create two physical and mental profiles of a user based on the information received from the user over time;
- a correlation analyzer configured to find out the relationship between the user’s feedback in using a product, a service, or a brand and the physical and mental profile of the user;
- a recommendation engine configured to offer the best product, service, or brand to a user according to their physical and mental profile and prevent dissatisfaction in the future; and
- a feedback transmitter configured to inform the manufacturers, sellers, or the relevant brand about the user’s dissatisfaction with their product, service, or brand.
- An intelligent system comprising,
- a market monitor configured to measure the level of awareness of the previous buyers and those who had entered their last negative or positive comments about a previous similar product based on the time period that elapses from the time of introduction of a new product in the market;
- a follow-up module configured to send a notification to a user’s mobile phone at different time intervals after the user has purchased a product;
- a voice-based intelligent assistant configured to communicate with the user via the mobile phone and record the user’s feedback and satisfaction with the product;
- a recommendation engine configured to suggest to the user a new and similar product that has recently entered the market and has received good feedback, if the user is dissatisfied with the previous product for any reason, and to recommend the new product that has entered the market to the user, taking into account the new changes and their relationship with the user’s dissatisfaction with the previous similar product; and
- a feedback analyzer configured to understand the reasons for the user’s dissatisfaction or satisfaction with the previous similar product based on the user’s voice input and the last negative or positive comments entered by the previous buyers.
- An intelligent system comprising,
- a voice-based intelligent assistant configured to receive a voice command from a user and ask the user how long he is going to use a product;
- a database configured to store and organize the user opinions and experiences based on the product name and the duration of use;
- a recommendation engine configured to provide recommendations to the user based on the other users opinions and experiences stored in the database and the duration of use specified by the user; and
- a speech synthesizer configured to convert the recommendations into speech and provide them to the user by voice.
- An intelligent system comprising,
- a follow-up module configured to send a notification to a user’s mobile phone at different time intervals after the user has purchased a product;
- a voice-based intelligent assistant configured to communicate with the user via the mobile phone and ask the user to participate in the formation of the time range of product images by taking and uploading pictures of the product from different angles;
- an image processing module configured to automatically monitor the shape and product changes based on the uploaded pictures;
- a video generator configured to create a clip of a few seconds of the product quality degrading; and
- a feedback recorder configured to store and display the video clip as a video feedback record for the product.
- An intelligent system comprising,
- a sentiment analysis module configured to analyze the user’s feelings when he tries to write a negative or protesting feedback about a product, a brand, or a service provider;
- a two-way recognition module configured to recognize the service related to the product and the product related to the service that can be provided based on the user’s feedback;
- A recommendation engine configured to recommend the user to benefit from the service related to the product, with the aim of the user’s satisfaction in using the product increasing and the user’s dissatisfaction regarding the use of the product being resolved; and
- a feedback transmitter configured to inform the product, brand, or service provider about the user’s feedback and recommendation.
- An intelligent system comprising,
- a feedback integration module configured to integrate the feedback system of users who have bought a product with the feedback system of users who provide services related to the product;
- a database configured to store and organize the integrated feedback based on the product name and the service name; and
- a user interface configured to display the integrated feedback for a product and a service in a graphical or textual format.
- An intelligent system comprising,
- a feedback analysis module configured to identify the accumulation of extreme feedback about a product based on the polarity and intensity of the feedback;
- a survey generator configured to create a survey and send it to users who have bought the same product or a similar product but have not yet registered a feedback;
- a database configured to store and organize the survey responses based on the product name and the feedback polarity; and
- a balance creator configured to create a balance in the feedback distribution for a product based on the survey responses and display it to the user in a graphical or textual format.
- An intelligent system comprising,
- a question designer configured to design a number of questions and ask the user based on the type of product and its salient features and keywords in the feedback sent by others who have purchased the product;
- a sentence generator configured to design a sentence by itself based on the user’s answers to the questions and read it to the user;
- a feedback recorder configured to record the feedback about the product with the final approval of the user;
- a feature extractor configured to extract the most obvious features of the product based on the feedback from different users; and
- a feature display configured to display a large number of features that can be commented on for the product in a graphical or textual format.
- An intelligent system comprising,
- a variable value slider module configured to present a series of variable value sliders for different attributes and variables related to a product;
- a user input module configured to receive the user’s input by changing the sliders and expressing the intensity of the attributes for the variables;
- a sentence generator configured to design a sentence based on the user’s input and the attributes of the variables and read it to the user; and
- a feedback recorder configured to record the feedback about the product based on the sentence designed by the sentence generator.
- An intelligent system comprising,
- an API connector configured to connect to different stores through API and access the product or service information and the user feedback from the stores;
- a user-friendly environment module configured to facilitate the possibility of sending feedback to different stores through a single interface and prevent the user from getting confused when writing feedback about the same product or service on different websites;
- a login module configured to facilitate the processes of logging in, confirming a purchase, uploading a photo or video, editing or deleting a comment, or finding the right place to write a comment that users may be confused about; and
- a feedback transmitter configured to send the user feedback to the relevant store through API.
- An intelligent system comprising,
- a feature analysis module configured to understand the accumulation of similar features of a product based on the user feedback and question other prominent features of the product that may have been seen less;
- a feedback registration module configured to check the degree of similarity between the user feedback and other feedbacks and show the user a feedback with a high percentage of similarity that has combined that feedback with the attributes that are less noticeable;
- a speech synthesizer configured to convert the feedback into speech and provide it to the user by voice;
- a user input module configured to receive the user’s confirmation or rejection of the feedback by clicking on an I agree or I disagree option; and
- a feedback counter configured to display a counter in the corner of the feedback bubble that increases by one number after the user clicks on the I agree option.
- A system for tracking and reporting user dissatisfaction with a product or service, comprising,
- a user interface configured to receive questions from users and to present random questions related to user dissatisfaction with the product or service in an imperceptible manner;
- a monitoring module configured to analyze the user responses to the questions and to identify the root cause of dissatisfaction based on user characteristics (e.g., users whose vision is damaged may constitute the largest part of the group of complaining users);
- a reporting module configured to compare the number of feedbacks that are not satisfactory with a predetermined threshold and to notify the seller, the owner, the manufacturer, and any person or organization that provides the product or service about the existing dissatisfaction if the threshold is exceeded.
- A system for verifying and modifying written text according to legal regulations, comprising,
- a text input module configured to receive written text from a user;
- a verification module configured to check the written text and to detect any errors or violations of existing laws;
- a modification module configured to introduce errors into the text if needed and to suggest alternative content that avoids legal prosecutions;
- a notification module configured to display a message to the user indicating the legal consequences of inserting the original or modified content and to request the final approval from the user.
- A system for displaying and managing user feedback on different websites that sell a product or provide a service, comprising:
- a product specification module configured to receive product specifications from a user and to identify the product or service;
- a website selection module configured to display the websites that sell the product or provide the service to the user, wherein the websites are prioritized based on a contract between the system and the websites, and to request the user to choose one or more websites where the user’s feedback will be displayed;
- a feedback insertion module configured to insert the user’s feedback on the chosen website or websites, wherein the feedback is preceded by a statement indicating the user’s identity, the product or service purchased, and the website from where the purchase was made;
- a feedback analysis module configured to monitor and evaluate the feedback on different websites and to detect any unfair attacks on a website by users who have not purchased the product or service from that website;
- a feedback management module configured to take actions to prevent unfair attacks, such as suspending the link related to the product, identifying and reporting the profiles of the attackers, sending warning messages to the attackers, and displaying comprehensive feedback that covers all aspects of the product or service to potential buyers.
- A system for generating and displaying user feedback on a product or service based on user preferences, comprising:
- a text mining module configured to extract a set of features that are emphasized in the user comments about the product or service;
- a user interface configured to present a slider for each feature and to allow the user to determine the intensity of the feature by dragging the slider to the left or right, wherein the intensity can be: very low, low, medium, high, very high;
- a rating module configured to assign a score to each feature based on the intensity selected by the user and to generate a text based on the score and the feature;
- a sentence generator configured to design a sentence by itself based on the user’s answers to the questions and read it to the user;
- a speech synthesizer configured to convert the feedback into speech and provide it to the user by voice;
- a user input module configured to receive the user’s confirmation or rejection of the feedback by clicking on an I agree or I disagree option;
- a feedback display module configured to insert the final feedback on one or more websites that sell the product or provide the service, wherein the websites are selected by the user.
- A system for detecting and reducing user confirmation bias in online feedback, comprising:
- a confirmation bias identification module configured to present a few extreme opinions to the user and to measure the user’s agreement or disagreement with the opinions;
- a confirmation bias confirmation module configured to determine if the user is suffering from confirmation bias based on the user’s behavior and a predefined threshold;
- a confirmation bias reduction module configured to display other users’ opinions that are fair and balanced and to measure the user’s reaction to approve or disapprove them;
- a feedback weighting module configured to adjust the weight and the impact factor of the user’s feedback in an opinion rating system based on the degree of confirmation bias exhibited by the user.
- A system for measuring user halo effect in online feedback, comprising:
- a sentiment analysis module configured to scrutinize the user’s feelings and to aggregate his or her opinions;
- a gamification module configured to implement a gamification system that rewards the user for providing feedback;
- a product selection module configured to display several products that have been influenced by the halo effect of another product, wherein the halo effect is a cognitive bias that causes the user to have a positive or negative impression of a product based on another product;
- a halo effect measurement module configured to measure the influence of the user from the halo effect based on the user’s feedback on the displayed products;
- a feedback rating module configured to consider the halo effect influence in the rating system of the user’s feedback.
- A system for detecting and mitigating user bandwagon effect in online feedback, comprising:,
- a bandwagon effect detection module configured to use subtle tests to measure the extent of the bandwagon effect in the user, wherein the bandwagon effect is a cognitive bias that causes the user to conform to the opinion of others;
- A feedback generation module configured to propose that the user write an opinion that is contrary to the opinion of others and that provides a different point of view on the product or service that everyone is praising or criticizing;
- a feedback reinforcement module configured to encourage the user to persist in his or her opposite opinion and to display the rejection or approval of his or her opinion by other users;
- a feedback display module configured to insert the user’s personal opinion on one or more websites that sell the product or provide the service, wherein the websites are selected by the user.
- A system for detecting and reducing user negativity bias in online feedback, comprising:,
- a negativity bias detection module configured to use subtle tests to measure the level of negativity bias in the user, wherein the negativity bias is a cognitive bias that causes the user to focus more on negative than positive information;
- a feedback presentation module configured to show the user the positive opinions of other users and different views on the product or service that the user is reviewing;
- a feedback visualization module configured to show the user a large volume of positive opinions in a bar chart and to invite the user to submit an opinion that is not affected by negativity bias;
- a feedback display module configured to insert the user’s unbiased opinion on one or more websites that sell the product or provide the service, wherein the websites are selected by the user.
- A system for preventing and correcting user sunk cost fallacy in online feedback, comprising:
- a cost and satisfaction module configured to check the appropriateness of the cost and the customer’s satisfaction regarding the products he or she has bought or the services he or she has received, and to detect the repetition of the purchase of an expensive product or service by the user and his or her continued dissatisfaction;
- a fallacy identification module configured to examine the evidence of the sunk cost fallacy in the feedback that the user provides later about the purchased product or the service received, wherein the sunk cost fallacy is a cognitive bias that causes the user to continue investing in a product or service that has already incurred a significant cost and does not provide satisfactory results;
- a fallacy correction module configured to inform the user about the sunk cost fallacy and to offer alternative suggestions at the time of action for the next purchase of products or services that are similar to the ones that caused the fallacy;
- a feedback display module configured to insert the user’s feedback on one or more websites that sell the product or provide the service, wherein the websites are selected by the user.
- A system for suggesting brand diversification and product expansion to a user based on user feedback, comprising:
- a feedback similarity module configured to process the similarity of feedbacks about a specific product from different brands and to take into account the user’s main criteria for evaluating the product;
- a brand diversification module configured to create suggestions to diversify the brand in the user’s main product portfolio based on the feedback similarity and the user’s criteria;
- a product expansion module configured to suggest other products from the same or different brands that are related to the specific product or that meet the user’s needs and preferences;
- a user interface configured to display the suggestions to the user and to receive the user’s feedback on the suggestions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2024/050556 WO2024142031A1 (en) | 2024-01-20 | 2024-01-20 | A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2024/050556 WO2024142031A1 (en) | 2024-01-20 | 2024-01-20 | A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024142031A1 true WO2024142031A1 (en) | 2024-07-04 |
Family
ID=91716755
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2024/050556 WO2024142031A1 (en) | 2024-01-20 | 2024-01-20 | A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2024142031A1 (en) |
-
2024
- 2024-01-20 WO PCT/IB2024/050556 patent/WO2024142031A1/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10672012B2 (en) | Brand personality comparison engine | |
US8396741B2 (en) | Mining interactions to manage customer experience throughout a customer service lifecycle | |
US11315149B2 (en) | Brand personality inference and recommendation system | |
US11544135B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
US20130185291A1 (en) | Online rating and feedback system | |
US10395258B2 (en) | Brand personality perception gap identification and gap closing recommendation generation | |
US11562013B2 (en) | Systems and methods for improvements to user experience testing | |
US11909100B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
WO2020223409A1 (en) | Systems and methods for improvements to user experience testing | |
US10432793B2 (en) | Systems and methods to enroll users for real time communications connections | |
Haaland et al. | Measuring what is top of mind | |
Lee et al. | Artificial intelligence applications to customer feedback research: A review | |
WO2024142031A1 (en) | A natural language processing and ai-based platform for user feedback collection and product recommendation and follow-up with personalized vocie assistant | |
WO2021030636A1 (en) | Systems and methods for the analysis of user experience testing with ai acceleration | |
Stolard | Business intelligence: the influence of sentiment analysis on small businesses | |
Sabuncu et al. | Creating Brand Image Profile by Social Media Analysis | |
Zhang | The power of online opinion leaders in negative e-WOM dissemination | |
US11935518B2 (en) | Joint works production method and server using collective intelligence | |
EP4375912A1 (en) | Systems and methods for improved user experience results analysis | |
Ridley | Folk Theories, Recommender Systems, and Human-Centered Explainable Artificial Intelligence (HCXAI) | |
US20230090695A1 (en) | Systems and methods for the generation and analysis of a user experience score | |
Roth et al. | Measuring What Is Top of Mind | |
McTaggart | Unpacking a Hierarchy of Trust: The Impacts of Trust in Mediating User Experiences with AI Avatar Technology | |
Park | Essays on User Behavior in Online Platforms | |
Lai | Deception Identification: A Machine-in-the-Loop Approach |