CN111061831A - Method and device for switching machine customer service to manual customer service and electronic equipment - Google Patents
Method and device for switching machine customer service to manual customer service and electronic equipment Download PDFInfo
- Publication number
- CN111061831A CN111061831A CN201911039210.0A CN201911039210A CN111061831A CN 111061831 A CN111061831 A CN 111061831A CN 201911039210 A CN201911039210 A CN 201911039210A CN 111061831 A CN111061831 A CN 111061831A
- Authority
- CN
- China
- Prior art keywords
- customer service
- analysis result
- session
- machine
- session record
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000004458 analytical method Methods 0.000 claims abstract description 114
- 230000008451 emotion Effects 0.000 claims description 68
- 230000004044 response Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000036651 mood Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G10L15/26—Speech to text systems
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a method and a device for switching a machine customer service to an artificial customer service and an electronic device, wherein the method comprises the following steps: acquiring a target session record of machine customer service; analyzing the target session record to obtain a session analysis result; determining whether the session analysis result meets a customer service switching condition; and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service. The method determines whether to convert the machine customer service into the artificial customer service by analyzing the target session record, and can enable the conversion between the machine customer service and the artificial customer service to be more accurate by analyzing different angles of the target session record.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for switching from a machine customer service to a manual customer service, and an electronic device.
Background
With the continuous increase of the scale of mobile internet users, more and more enterprises have online intelligent customer service systems, and the application of virtual robots based on artificial intelligence in the field of enterprise user customer service is more and more extensive. Compared with manual customer service, the machine customer service has the advantages of strong memory, easy expansion of knowledge points, quick response, uninterrupted service within 24 hours and the like, but can not well process the user problems with specificity and outburst; compared with machine customer service, the manual customer service has the advantages of individuation, accurate service and the like, but is comfortable and slow in response and limited in energy. Obviously, for some unconventional user problems, the machine customer service is often difficult to provide a satisfactory answer for the user, so how to accurately and effectively convert the machine customer service into the manual customer service is a problem to be solved urgently.
Disclosure of Invention
In view of this, the embodiment of the present application provides a method and an apparatus for switching from a machine service to a manual service, and an electronic device, so as to improve the above defects.
In a first aspect, an embodiment of the present application provides a method for switching a machine customer service to a manual customer service, where the method includes: acquiring a target session record of machine customer service; analyzing the target session record to obtain a session analysis result; determining whether the session analysis result meets a customer service switching condition; and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service.
In a second aspect, an embodiment of the present application provides a device for switching from machine customer service to manual customer service, where the device includes: the system comprises a record acquisition module, a result determination module and a customer service switching module. The record acquisition module is used for acquiring a target session record of the machine customer service. And the result acquisition module is used for analyzing the target session record to obtain a session analysis result. And the result determining module is used for determining whether the session analysis result meets the customer service switching condition. And the customer service switching module is used for switching the machine customer service into the manual customer service if the session analysis result meets the customer service switching condition.
In a third aspect, an embodiment of the present invention provides an electronic device, including: one or more processors; a memory for storing one or more programs; one or more application programs; wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform a method of machine to manual customer service switching provided by any embodiment of the present application.
In a fourth aspect, embodiments of the present application provide a computer system, where a computer-readable storage medium has program code stored therein, where the program code may be invoked by a processor to execute a method for switching from machine customer service to manual customer service provided in any of the embodiments of the present application.
Compared with the prior art, the method, the device and the electronic equipment for switching the machine customer service to the manual customer service are provided, the method for switching the machine customer service to the manual customer service can firstly obtain a session record with the machine customer service, the session record is used as a target session record, then the target session record can be analyzed to obtain a session analysis result, and finally whether the session analysis result meets the customer service switching condition or not is determined, and if the session analysis result meets the customer service switching condition, the machine customer service is switched to the manual customer service. According to the method and the system, whether the machine customer service is converted into the manual customer service is determined through analysis of the target session record, and automatic switching of the customer service can be achieved as long as the customer service switching condition is met, so that the cost of customer service switching can be reduced, and the efficiency of customer service switching can be improved to a certain extent.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating a method for switching from a machine service to a manual service according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating a method for switching from machine customer service to manual customer service according to another embodiment of the present application;
fig. 3 is a flowchart illustrating step S230 in a method for switching from machine service to manual service according to another embodiment of the present application;
fig. 4 is a flowchart illustrating step S230 in a method for switching from machine service to manual service according to another embodiment of the present application;
fig. 5 is a flowchart illustrating step S230 in a method for switching from machine service to manual service according to another embodiment of the present application;
FIG. 6 is a schematic diagram illustrating emotion classification obtained by using an emotion analysis model in a method for switching from machine customer service to manual customer service according to another embodiment of the present application;
FIG. 7 is a flow chart illustrating a method for switching from machine customer service to manual customer service according to another embodiment of the present application;
fig. 8 is a flowchart illustrating a step S330 in a method for switching from machine service to manual service according to another embodiment of the present application;
fig. 9 is a flowchart illustrating a step S330 in a method for switching from machine service to manual service according to another embodiment of the present application;
fig. 10 is a block diagram illustrating a structure of a device for switching from a machine service to a manual service according to an embodiment of the present application;
fig. 11 shows a block diagram of an electronic device for executing a method for switching from machine customer service to manual customer service according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers or letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.
In order to better serve users, the existing intelligent customer service generally combines machine customer service and manual customer service, and the main reason is that the machine customer service cannot accurately and intelligently answer all the questions of the users. However, the basis for judging how the user arrives to be switched to the manual customer service is diversified, and the judgment of the switching condition is mostly incomplete, that is, the existing technology for switching the machine customer service to the manual customer service has the situation of false switching, which cannot meet the actual requirement of the user on the customer service switching.
Therefore, in order to overcome the above-mentioned drawback, as shown in fig. 1, an embodiment of the present application provides a method for switching from machine customer service to manual customer service, where the method includes steps S110 to S140.
Step S110: and acquiring a target session record with the machine customer service.
The embodiment of the application can be applied to any device with computing and storage capabilities, for example, a physical device or a logical device such as a mobile phone, a tablet PC (Personal Computer), a notebook, a server, a virtual machine, and the like; the functions of the embodiments of the present application may be implemented by two or more physical or logical devices sharing different responsibilities and cooperating with each other.
In one embodiment, the electronic device may obtain a target session record of the user and the machine service, the target session record refers to a session record generated by the user communicating with the machine service through a user terminal of the electronic device, and the user terminal refers to a port device/software used by the user when the user is in a session with the machine service. For example, a web page or an application running on an electronic device (e.g., a mobile phone or a tablet computer). Obviously, in this embodiment, the target session record not only includes the query information input by the user, but also includes the response information generated by the machine customer service in response to the query information input by the user, that is, after the machine customer service receives the query information input by the user, the response information may be generated according to the query information input by the user, and the information of the plurality of queries and the response information together form the target session record.
In this embodiment, the form of the target session record may be at least one of text, voice, or image, that is, the form of the query information input by the user may be text or voice, or may be any one of an image and a website, or may be any combination of these three forms. For example, the query entered by the user may be in the form of text "do you go trouble asking when my purchased mijia lock can be shipped? "the query information input by the user may also include a product image or a product link, etc. in order to express the intention of the user more clearly, the form of the target session record is specifically not limited explicitly here.
Step S120: and analyzing the target session record to obtain a session analysis result.
In an embodiment, after the electronic device obtains the target record, the electronic device may analyze the target session record to obtain a session analysis result. Specifically, the form of the target session record may be determined first, and then the corresponding analysis is performed according to different session record forms, because the target session records are different in form, the corresponding analysis methods are also different. When the form of the target session record is a text, the text recognition can be directly carried out on the target session record, namely, the processing such as sentence segmentation, keyword extraction, semantic analysis and the like is carried out on inquiry information input by a user; when the form of the target session record is voice, the query information input by the user may be firstly subjected to form conversion, that is, the voice information is converted into text information, and in a specific embodiment, the conversion from voice to text may be performed by ASR (Automatic Speech Recognition). Then, the text information is processed by sentence segmentation, keyword extraction, voice analysis and the like, or voice recognition can be directly carried out on inquiry information input by a user so as to obtain a voice recognition result; when the target session record is in the form of an image, the electronic device may perform image recognition on the image, and may perform denoising, filtering, and the like on the image before performing image recognition.
Step S130: and determining whether the session analysis result meets the customer service switching condition.
After obtaining the session analysis result, the electronic device may determine whether the session analysis result satisfies the customer service switching condition, if so, the step S140 is performed, and if not, the machine customer service is continuously used to communicate with the user. In this embodiment, the customer service switching condition may be "whether the number of times of occurrence of the specified keyword is greater than a preset threshold", or "whether the number of times of occurrence of the problem is greater than a preset threshold", or "whether the number of times of occurrence of the negative emotion of the user is greater than a preset threshold", or the like.
Step S140: and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service.
When the session analysis result meets the customer service switching condition, the electronic device can automatically switch the machine customer service to the manual customer service, or the machine customer service can be switched to the manual customer service through user permission, namely when the electronic device determines that the session analysis result meets the customer service switching condition, the electronic device can send a customer service switching prompt to the electronic device, if the electronic device sends 'whether to agree to switch to the manual customer service', and if the user chooses to agree, the machine customer service is switched to the manual customer service.
The embodiment of the application provides a method for switching from machine customer service to manual customer service, whether a user wants to perform customer service switching operation can be comprehensively analyzed by analyzing the session records of the machine customer service and the machine customer service, namely, the machine customer service can be switched into the manual customer service as long as the customer service switching condition is met, so that the customer service switching can be more intelligent, and the conversion between the machine customer service and the manual customer service can be more accurate to a certain extent.
Another embodiment of the present application provides a method for switching from machine service to manual service, please refer to fig. 2, and it can be seen from fig. 2 that the method includes steps S210 to S240.
Step S210: and acquiring a target session record with the machine customer service.
Step S220: and analyzing the target session record to obtain a session analysis result.
Step S230: and determining whether the session analysis result meets the customer service switching condition.
As shown in fig. 3, step S230 may include steps S231 to S233.
Step S231: and acquiring the occurrence times of specified keywords in the target session record according to the session analysis result to obtain first key times, wherein the specified keywords are used for indicating that the machine customer service is converted into a word of artificial customer service.
In an embodiment, after analyzing the target session record to obtain a session analysis result, the electronic device may obtain, according to the session analysis result, a number of times that a specified keyword in the target session record appears, to obtain a first number of times of the keyword, where the specified keyword is used to indicate that the machine customer service is changed into a word of the artificial customer service. Specifically, the specified keywords refer to keywords that express that the user wants to communicate with the artificial customer service when communicating with the machine customer service, and commonly used specified keywords may include: "manual customer service", "change manual" or "replace machine customer service", etc. In this embodiment, the designated keyword may include a plurality of keywords, as long as the semantic expression indicates that the user wants to convert the customer service from the machine customer service to the manual customer service, and the semantic meaning of the designated keyword may be obtained by performing semantic analysis on the target session record.
In addition, the occurrence frequency of the specified keyword does not only refer to the occurrence frequency of a certain specific keyword, but also refers to the occurrence frequency of all words with similar semantics to the specified keyword. For example, the query information input by the user in the target session record includes' machine customer service answers are inaccurate, and people are asked to change to manual work; i want to communicate with the artificial customer service; please replace machine customer service! "obviously, the specified keywords in the target session record include" manual operation "," manual service ", and" replacement machine service ", and obviously, the number of times of occurrence of the specified keywords is 3 at this time, that is, the number of times of the first keyword is 3. It should be noted that, in the present embodiment, if a certain specified keyword appears repeatedly a plurality of times, the number of times of appearance of the specified keyword is recorded in terms of the number of times of repetition, instead of recording only once. For example, the query information input by the user is "i want to change to manual, please help i change to manual.
Step S232: and judging whether the first key frequency is greater than or equal to a first preset threshold value.
After obtaining the number of times of occurrence of the specified keyword in the target session record, the electronic device may determine whether the first key number is greater than or equal to a first preset threshold, if the first key number is greater than or equal to the first preset threshold, step S233 is entered, otherwise, it is determined whether the session analysis result meets other customer service switching conditions, and if none of the other customer service switching conditions is met, the machine customer service does not need to be converted into the manual customer service. In this embodiment, the first preset threshold may be preset, specifically, the first preset threshold may be set to 2, and then the process proceeds to step S233 when the first key number > is 2. The first preset threshold may also be set to other values according to practical situations, and the specific setting is not specifically limited herein.
Step S233: and if the first key times are larger than or equal to a first preset threshold value, determining that the session analysis result meets the customer service switching condition.
When the obtained first key times are larger than or equal to a first preset threshold value, the session analysis result is determined to meet the customer service switching condition, and at the moment, the machine customer service can be switched to the manual customer service.
As shown in fig. 4, step S230 may further include steps S234 to S236.
Step S234: and acquiring the number of times of unsolved problems in the target session record according to the session analysis result to obtain a second key number of times, wherein the unsolved problems comprise evaluation results of the user on the machine customer service problem reply.
In one embodiment, the session analysis result includes the number of times that the user clicks the unresolved button, and the number of times that the problem in the target session record is unresolved is obtained according to the session analysis result, including: and acquiring the times of clicking the problem unsolved button by the user in the analysis result, and taking the times as the times of unsolved problems. By the above description, it can be known that the target session record may include query information and machine response information input by the user, and the query information input by the user and the machine response information correspond to each other, that is, the user inputs a query information, and the machine customer service may output a response information according to the query information.
When the electronic device acquires the response information, the response information can be displayed, meanwhile, each response information can correspondingly display two buttons, the two buttons are respectively a problem unsolved button and a problem solved button, at this time, the electronic device can detect whether the user selects based on the two buttons, if so, the electronic device judges whether the selection of the user is based on the problem unsolved button, and if so, the selection times are recorded. Obviously, after the electronic device displays the two selection buttons, the user may click any one of the two selection buttons, or may skip directly without clicking and then continue to input the query information. The unresolved problem in this embodiment is one of the evaluation results of the response of the user to the machine service problem, and the evaluation result mainly means that the response information of the machine service is not satisfactory by the user, or that the response information made by the machine service does not really solve the user's question. The problem is solved, contrary to the problem which is not solved, the problem is also one of evaluation results returned by the user to the machine service problem, but the evaluation result mainly refers to that the user is satisfied with the response information of the machine service or that the response information made by the machine service solves the user's question.
It should be noted that the number of times of problem unresolved is not limited to the number of times of selection made by the user based on the "problem unresolved button", but may also include the number of times of occurrence of the keyword "unresolved" in the target session record. For example, if the electronic device obtains that the number of times the user clicks the "problem unresolved button" is 2 times and the number of times the keyword "unresolved" appears in the query information of the user is 1 time, the number of times the problem is unresolved is 3 times, and the situation that the keyword "unresolved" appears in the query information may be various. For example, "my question you did not solve, please answer again.
Step S235: and judging whether the second key frequency is greater than or equal to a second preset threshold value.
In an embodiment, after obtaining the second key number, the electronic device may determine whether the second key number is greater than or equal to a second preset threshold, if the second key number is greater than or equal to the second preset threshold, the step S236 is performed, otherwise, it is determined whether the session analysis result meets other customer service switching conditions, and if none of the other customer service switching conditions is met, the machine customer service does not need to be converted into the manual customer service. In this embodiment, the second preset threshold may be preset, specifically, the second preset threshold may be set to 3, and then the process proceeds to step S236 when the second key number > is 3. The second preset threshold may also be set to other values according to practical situations, and the specific setting is not specifically limited herein.
Step S236: and if the second key times are larger than or equal to a second preset threshold value, determining that the session analysis result meets the customer service switching condition.
When the obtained second key times are larger than or equal to a second preset threshold value, it is determined that the session analysis result meets the customer service switching condition, and at this time, the machine customer service can be switched to the manual customer service.
As shown in fig. 5, determining whether the session analysis result satisfies the customer service switching condition may further include step S237 to step S239.
Step S237: and determining the occurrence frequency of the negative emotions according to the emotion analysis result to obtain a third key frequency.
In one embodiment, the target session record may include at least one sub-session record, and the sub-session record corresponds to a user emotion, the user emotion including a positive emotion, a negative emotion, or a neutral emotion. Analyzing the target session record to obtain a session analysis result, wherein the session analysis result comprises the following steps: obtaining the emotion of the user corresponding to the sub-session record to obtain an emotion analysis result, wherein the sub-session record can refer to query information of the user, and the emotion analysis refers to emotion judgment of a target session record, and generally, the emotion is divided into three types: positive (positive) mood, negative (negative) mood, and neutral mood. The electronic equipment can input the sub-session records into the emotion analysis model after acquiring the sub-session records, and the emotion category of each sub-session record can be calculated through the emotion analysis model. For example, the query entered by the user is "Mijia Lock has been placed a single for 1 more months, too slow! Why no one has yet installed it can be judged as a negative emotion by the emotion analysis model. The emotion analysis model in this embodiment can be implemented by using algorithms such as RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and the like.
The specific process of obtaining the emotion classification of the sub-session record by using the emotion analysis model is shown in fig. 6, and it can be seen from fig. 6 that after the user inputs query information, the query information can be converted into a sentence vector in an embedded manner, before that, whether the query information is in a text form or not can be judged, if the query information is in the text form, the query information is directly input into the emotion analysis model for emotion classification, and if the query information is not in the text form, the query information is converted into the text form, and then the emotion classification is performed. After the text is converted into a sentence vector, the sentence vector can be subjected to emotion classification, and a classification result is output, specifically, one result can be output from three possibilities of positive emotion/negative emotion/neutral emotion. Finally, the obtained result can be structured to obtain structured data, and the display of the structured data can comprise two parts, namely inquiry information and classification results. For example, { 'query': ' Home Lock has been released for 1 more months, too slowly! Why no one has yet installed the 'policy': 'negative'.
Through the above description, it can be known that the target session record may include at least one sub-session record, and each sub-session record corresponds to an emotion of a user, and the sub-session record mainly refers to query information input by the user, that is, through recognition of the query information input by the user, the emotion of the user as a whole can be determined. For example, the target session record includes three sub-session records, which are respectively "how the MIJI Lock is used," the MIJI Lock has been singled 1 for more than a month, too slow! Because no one has installed the target sub-session record and the target sub-session record is always the networking failure, the emotion analysis model is used for analyzing the target sub-session record, so that the emotion category corresponding to the first sub-session record is neutral emotion, the emotion categories corresponding to the second sub-session record and the third sub-session record are negative emotion, and the number of negative emotion occurrences in the target session record is 2 times, namely the third key number is 3 times.
Step S238: and judging whether the third key times is greater than or equal to a third preset threshold value.
In an embodiment, after obtaining the third key number, the electronic device may determine whether the third key number is greater than or equal to a third preset threshold, if the third key number is greater than or equal to the third preset threshold, step S239 is entered, otherwise, it is determined whether the session analysis result meets other customer service switching conditions, and if none of the other customer service switching conditions is met, the machine customer service does not need to be converted into the manual customer service. In this embodiment, the third preset threshold may be preset, specifically, the third preset threshold may be set to 3, and then the process proceeds to step S239 when the third key number > is 3. The third preset threshold may also be set to other values according to practical situations, and the specific setting is not specifically limited herein.
Step 239: and if the third key times are more than or equal to a third preset threshold value, determining that the session analysis result meets the customer service switching condition.
And when the acquired third key times are larger than or equal to a third preset threshold value, determining that the session analysis result meets the customer service switching condition, and switching the machine customer service to the manual customer service. According to the method and the device, the emotion of the user is analyzed through machine learning, the frequency of the negative emotion of the user in the target session record is obtained, and customer service switching can be more intelligent through statistics of the frequency of the negative emotion of the user.
Step S240: and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service.
Still another embodiment of the present application provides a method for switching from machine customer service to manual customer service, please refer to fig. 7, and it can be seen from fig. 7 that the method includes steps S310 to S340.
Step S310: and acquiring a target session record with the machine customer service.
Step S320: and analyzing the target session record to obtain a session analysis result.
Step S330: and determining whether the session analysis result meets the customer service switching condition.
As shown in fig. 8, step S330 may include steps S331 to S333.
Step S331: and acquiring the occurrence frequency of the hot spot products in the target session record according to the session analysis result to obtain a fourth key frequency.
The hot spot products may also be referred to as key products, which mainly aim at more important products or products with more strict customs, in some embodiments, the hot spot products may also be high-priced products or products with high sales volume, the system obtains pricing or sales volume of the products and ranks them, and determines the products with a certain percentage before the highest price or the products with a certain percentage before the highest sales volume as the hot spot products. The manufacturer has higher level of importance on the products. In this embodiment, the number of times of occurrence of the hotspot product may be determined by identifying the name of the hotspot product, that is, the number of times of occurrence of the hotspot product may be increased by one as long as the name of the hotspot product occurs in the target session record. In one embodiment, a plurality of hot spot products may exist at the same time, names of the hot spot products may be stored in a hot spot product list, and the embodiments of the present application may respectively count the number of times of occurrence of the hot spot products. For example, the target session records "what model the mijia smart door lock has; troublesome please give the installation instruction of the intelligent door lock of the Mijia; the target session record comprises two hot products, wherein the hot products are respectively generated 2 times and 1 time. In order to make the customer service switching more accurate, when a plurality of hot spot products exist in the target session record at the same time, the hot spot product with the largest occurrence frequency can be used as the target hot spot product, and the occurrence frequency of the target hot spot product is the fourth key frequency.
It should be noted that when the hotspot product exists in the target session record in the form of text, text recognition may be directly performed to determine whether the target session record contains the name of the hotspot product, and when the hotspot product exists in the target session record in the form of image, product image recognition may be performed. Specifically, it may be determined whether the target session record includes a product image, and if the target session record includes a product image, the product image is identified to obtain an image identification result, and then it may be determined whether the product is a hot product according to the image identification result, and if the product is a hot product, the product is counted in the number of times of occurrence of the hot product. The image recognition result in this embodiment includes three cases, the first case is that the product image includes a hot product, the second case is that the product image includes a name of the hot product, and the third case is that the image of the hot product and the name of the hot product appear on the product image at the same time. If the product image belongs to any one of the three types, it is determined that a hot product exists in the target session record, and the occurrence frequency of the hot product can be added to the frequency of the hot product acquired by text recognition to obtain a fourth key frequency.
Step S332: and judging whether the fourth key frequency is greater than or equal to a fourth preset threshold value.
In an embodiment, after obtaining the fourth key number, the electronic device may determine whether the fourth key number is greater than or equal to a fourth preset threshold, if the fourth key number is greater than or equal to the fourth preset threshold, step S333 is entered, otherwise, it is determined whether the session analysis result meets other customer service switching conditions, and if none of the other customer service switching conditions is met, the machine customer service does not need to be converted into the manual customer service. In this embodiment, the fourth preset threshold may be preset, specifically, the fourth preset threshold may be set to 3, and then the process proceeds to step S333 when the fourth key number > is 3. The fourth preset threshold may also be set to other values according to practical situations, and the specific setting is not specifically limited herein.
Step S333: and if the fourth key frequency is larger than or equal to a fourth preset threshold value, determining that the session analysis result meets the customer service switching condition.
And when the acquired fourth key frequency is larger than or equal to a fourth preset threshold value, determining that the session analysis result meets the customer service switching condition, and switching the machine customer service to the manual customer service. According to the embodiment of the application, the key products can be monitored in real time through statistics of the occurrence times of the hot products, so that the satisfaction degree of a user on the hot products can be continuously improved, and meanwhile, the effectiveness of customer service switching can be improved.
In one embodiment, determining whether the session analysis result satisfies the customer service switching condition as shown in fig. 9 further includes steps S334 to S337.
Step S334: and acquiring the occurrence frequency of the hot spot products in the target session record according to the session analysis result to obtain a fourth key frequency.
Step S335: and judging whether the fourth key frequency is smaller than a fourth preset threshold and larger than or equal to a fifth preset threshold.
In order to make the customer service switching more accurate, the present embodiment may determine whether the session analysis result meets the customer service switching condition according to the number of times of the hot product and other times, where the other times may include the number of times of occurrence of the specified keyword, the number of times of unresolved problem, and the number of times of occurrence of negative emotion. When the fourth key count is less than the fourth preset threshold and greater than or equal to the fifth preset threshold, the process proceeds to step S336. For example, if the fourth preset threshold is 3, the fifth preset threshold is 1, and the fourth key time is 2, then the above condition is satisfied.
Step S336: if yes, determining whether at least one of the times of occurrence of the specified keywords, the times of unresolved problems and the times of occurrence of negative emotions in the target session record is greater than or equal to the fifth preset threshold.
When the fourth key frequency satisfies the condition of step S336, the electronic device may respectively obtain the frequency of occurrence of the specified keyword, the frequency of unresolved problems, and the frequency of occurrence of the negative emotion, and determine whether at least one of the frequencies is greater than or equal to a fifth preset threshold, if so, go to step S337. For example, if the fourth preset threshold is 3, the fifth preset threshold is 1, and the fourth key number is 2 at this time, the step is performed, and meanwhile, the number of times that the obtained problem is not solved is 2, obviously, the number of times is greater than or equal to the fifth preset threshold, at this time, the step S337 may be performed.
In the embodiment of the application, as long as one of the three keys of the number of times of occurrence of the specified keyword, the number of times of unsolved problems and the number of times of occurrence of negative emotions is greater than or equal to a fifth preset threshold, it is determined that the session analysis result meets the customer service switching condition. For example, if the hot product is a "mijia intelligent door lock", and the negative emotion of the "mijia intelligent door lock" in the target session record is greater than or equal to 2 times, the machine customer service is converted into the manual customer service. It should be noted that when the number of times of occurrence of the hotspot product does not satisfy the above condition, it may be determined whether the hotspot product appears in the target session record, and if the hotspot product appears, the hotspot product may be combined with the number of times of occurrence of the specified keyword, the number of times of unresolved problem, and the number of times of occurrence of the negative emotion to determine whether the customer service switching is required, and specific details are not repeated here.
Step S337: and if so, determining that the session analysis result meets the customer service switching condition.
According to the method and the device, whether customer service switching is carried out or not is comprehensively judged by combining the number of times of hot products, the number of times of specified keywords, the number of times of unsolved problems and the number of times of negative emotions, the requirement of users for customer service switching under different conditions can be fully considered, and the customer service switching is more accurate and effective.
Step S340: and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service.
Referring to fig. 10, a device 400 for switching from machine service to manual service according to an embodiment of the present application includes a record obtaining module 410, a result obtaining module 420, a result determining module 430, and a service switching module 440.
A record obtaining module 410, configured to obtain a target session record with a machine customer service.
Further, the target session record includes at least one of text, voice, and images.
And the result obtaining module 420 is configured to analyze the target session record to obtain a session analysis result.
Further, the result obtaining module 420 is configured to obtain a user emotion corresponding to the sub-session record, so as to obtain an emotion analysis result. The target session record comprises at least one sub-session record, the sub-session record corresponds to a user emotion, and the user emotion comprises a positive emotion, a negative emotion or a neutral emotion.
And a result determining module 430, configured to determine whether the session analysis result satisfies a customer service switching condition.
Further, the result determining module 430 is configured to obtain, according to the session analysis result, a number of times that a specified keyword occurs in the target session record, to obtain a first key number, where the specified keyword is used to indicate that the machine customer service is converted into a word of the artificial customer service, to determine whether the first key number is greater than or equal to a first preset threshold, and if the first key number is greater than or equal to the first preset threshold, to determine that the session analysis result meets a customer service switching condition.
Further, the result determining module 430 is further configured to obtain, according to the session analysis result, the number of times that the problem in the target session record is not solved, to obtain a second key number, where the problem is not solved and includes an evaluation result replied by the user to the machine customer service problem, to determine whether the second key number is greater than or equal to a second preset threshold, and if the second key number is greater than or equal to the second preset threshold, determine that the session analysis result satisfies the customer service switching condition. In this embodiment, the obtaining the number of times that the problem is not solved in the target session record according to the session analysis result includes: and acquiring the times of clicking the problem unsolved button by the user in the analysis result, and taking the times as the times of unsolved problems.
Further, the result determining module 430 is further configured to determine, according to the emotion analysis result, the number of times of occurrence of the negative emotion to obtain a third number of times of key, determine whether the third number of times of key is greater than or equal to a third preset threshold, and if the third number of times of key is greater than or equal to the third preset threshold, determine that the session analysis result meets the customer service switching condition.
Further, the result determining module 430 is further configured to obtain, according to the session analysis result, the number of times of occurrence of hotspot products in the target session record, obtain a fourth key number, determine whether the fourth key number is greater than or equal to a fourth preset threshold, and if the fourth key number is greater than or equal to the fourth preset threshold, determine that the session analysis result meets the customer service switching condition. In addition, the result determining module 430 may be further configured to determine whether the target session record includes a product image, identify the product image if the target session record includes the product image to obtain an image identification result, determine whether the product is a hot product according to the image identification result, and count the hot product as the number of times of occurrence of the hot product if the product is the hot product.
Further, the result determining module 430 is further configured to obtain, according to the session analysis result, the number of times of occurrence of hotspot products in the target session record, to obtain a fourth key number, determine whether the fourth key number is smaller than a fourth preset threshold and greater than or equal to a fifth preset threshold, if so, determine whether at least one of the number of times of occurrence of a specified keyword, the number of times of unresolved problems, and the number of times of occurrence of negative emotions in the target session record is greater than or equal to the fifth preset threshold, and if so, determine that the session analysis result satisfies a customer service switching condition.
And a customer service switching module 440, configured to switch the machine customer service to the manual customer service if the session analysis result meets the customer service switching condition.
Fig. 11 is a block diagram of a hardware structure of an electronic device in a method for switching from machine customer service to manual customer service according to an embodiment of the present invention. Specifically, the electronic device may execute and implement any method for switching from machine customer service to manual customer service provided in the above method embodiments. As shown in fig. 11, the electronic device 1100 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 1110 (the processors 1110 may include but are not limited to processing devices such as a microprocessor MCU or a programmable logic device FPGA), a memory 1130 for storing data, and one or more storage media 1120 (e.g., one or more mass storage devices) for storing applications 1123 or data 1122. The memory 1130 and the storage medium 1120 may be, among other things, transient storage or persistent storage. The program stored in the storage medium 1120 may include one or more modules, each of which may include a series of instruction operations for a server. Still further, the processor 1110 may be configured to communicate with the storage medium 1120, and execute a series of instruction operations in the storage medium 1120 on the electronic device 1100. The electronic apparatus 1100 may also include one or more power supplies 1160, one or more wired or wireless network interfaces 1150, one or more input-output interfaces 1140, and/or one or more operating systems 1121, such as windows server, MacOSXTM, unix, linux, FreeBSDTM, and so forth.
The input output interface 1140 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the electronic device 1100. In one example, i/o interface 1140 includes a network adapter (NIC) that may be coupled to other network devices via a base station to communicate with the internet. In one example, the input/output interface 1140 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
It will be understood by those skilled in the art that the structure shown in fig. 11 is only an illustration and is not intended to limit the structure of the electronic device. For example, electronic device 1100 may also include more or fewer components than shown in FIG. 11, or have a different configuration than shown in FIG. 11. The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the method for switching from the machine customer service to the manual customer service, and can achieve the same technical effect, and is not described herein again to avoid repetition. The computer-readable storage medium may be a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Although the present application has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application, and all changes, substitutions and alterations that fall within the spirit and scope of the application are to be understood as being included within the following description of the preferred embodiment.
Claims (12)
1. A method for switching from machine customer service to manual customer service is characterized by comprising the following steps:
acquiring a target session record of machine customer service;
analyzing the target session record to obtain a session analysis result;
determining whether the session analysis result meets a customer service switching condition;
and if the session analysis result meets the customer service switching condition, switching the machine customer service to manual customer service.
2. The method of claim 1, wherein the determining whether the session analysis result satisfies a customer service switching condition comprises:
acquiring the occurrence times of specified keywords in the target session record according to the session analysis result to obtain first key times, wherein the specified keywords are used for indicating that the machine customer service is converted into a word of artificial customer service;
judging whether the first key frequency is greater than or equal to a first preset threshold value or not;
and if the first key times are larger than or equal to a first preset threshold value, determining that the session analysis result meets the customer service switching condition.
3. The method of claim 1, wherein the determining whether the session analysis result satisfies a customer service switching condition comprises:
obtaining the number of times of unsolved problems in the target session record according to the session analysis result to obtain a second key number of times, wherein the unsolved problems comprise evaluation results of user responses to machine customer service problems;
judging whether the second key frequency is greater than or equal to a second preset threshold value or not;
and if the second key times are larger than or equal to a second preset threshold value, determining that the session analysis result meets the customer service switching condition.
4. The method of claim 3, wherein the session analysis results include a number of times a user clicks a problem unresolved button;
the obtaining of the number of times of unsolved problems in the target session record according to the session analysis result includes:
and acquiring the times of clicking the problem unsolved button by the user in the analysis result, and taking the times as the times of unsolved problems.
5. The method of any of claims 1-4, wherein the target session record comprises at least one sub-session record, the sub-session record corresponding to a user emotion, the user emotion comprising a positive emotion, a negative emotion, or a neutral emotion;
the analyzing the target session record to obtain a session analysis result includes:
acquiring the user emotion corresponding to the sub-session record to obtain an emotion analysis result;
the determining whether the session analysis result meets the customer service switching condition includes:
determining the occurrence frequency of the negative emotion according to the emotion analysis result to obtain a third key frequency;
judging whether the third key times are larger than or equal to a third preset threshold value or not;
and if the third key times are more than or equal to a third preset threshold value, determining that the session analysis result meets the customer service switching condition.
6. The method according to any one of claims 1-4, wherein the determining whether the session analysis result satisfies a customer service switching condition comprises:
acquiring the occurrence frequency of hot spot products in the target session record according to the session analysis result to obtain a fourth key frequency;
judging whether the fourth key frequency is greater than or equal to a fourth preset threshold value or not;
and if the fourth key frequency is larger than or equal to a fourth preset threshold value, determining that the session analysis result meets the customer service switching condition.
7. The method of claim 6, wherein the obtaining of the number of occurrences of hotspot products in the target session record according to the session analysis result comprises:
determining whether a product image is contained in the target session record;
if the target session record contains the product image, identifying the product image to obtain an image identification result;
judging whether the product is a hot product or not according to the image identification result;
if the product is a hot product, the product is counted into the number of times of occurrence of the hot product.
8. The method of claim 1, wherein the determining whether the session analysis result satisfies a customer service switching condition further comprises:
acquiring the occurrence frequency of hot spot products in the target session record according to the session analysis result to obtain a fourth key frequency;
judging whether the fourth key frequency is smaller than a fourth preset threshold and larger than or equal to a fifth preset threshold;
if yes, determining whether at least one of the times of occurrence of the specified keywords, the times of unsolved problems and the times of occurrence of negative emotions in the target session record is greater than or equal to a fifth preset threshold value;
and if so, determining that the session analysis result meets the customer service switching condition.
9. The method of claim 1, wherein the target session record comprises at least one of text, speech, and images.
10. A device for switching from machine customer service to manual customer service, the device comprising:
the record acquisition module is used for acquiring a target session record of the machine customer service;
the result acquisition module is used for analyzing the target session record to obtain a session analysis result;
the result determining module is used for determining whether the session analysis result meets the customer service switching condition;
and the customer service switching module is used for switching the machine customer service into the manual customer service if the session analysis result meets the customer service switching condition.
11. An electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the machine to human customer service switching method of any of claims 1 to 9.
12. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the machine to manual customer service switching method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039210.0A CN111061831A (en) | 2019-10-29 | 2019-10-29 | Method and device for switching machine customer service to manual customer service and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911039210.0A CN111061831A (en) | 2019-10-29 | 2019-10-29 | Method and device for switching machine customer service to manual customer service and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111061831A true CN111061831A (en) | 2020-04-24 |
Family
ID=70298454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911039210.0A Pending CN111061831A (en) | 2019-10-29 | 2019-10-29 | Method and device for switching machine customer service to manual customer service and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111061831A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540358A (en) * | 2020-04-26 | 2020-08-14 | 云知声智能科技股份有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN111901487A (en) * | 2020-08-13 | 2020-11-06 | 周铭 | User voice calling system and method based on big data processing |
| CN112182149A (en) * | 2020-09-15 | 2021-01-05 | 中信银行股份有限公司 | Exception processing method and device, electronic equipment and computer readable storage medium |
| CN112269863A (en) * | 2020-10-15 | 2021-01-26 | 和美（深圳）信息技术股份有限公司 | Man-machine conversation data processing method and system of intelligent robot |
| CN112365894A (en) * | 2020-11-09 | 2021-02-12 | 平安普惠企业管理有限公司 | AI-based composite voice interaction method and device and computer equipment |
| CN112700781A (en) * | 2020-12-24 | 2021-04-23 | 江西台德智慧科技有限公司 | Voice interaction system based on artificial intelligence |
| CN114117157A (en) * | 2021-11-19 | 2022-03-01 | 招联消费金融有限公司 | Session processing method, device, computer equipment and storage medium |
| CN115017291A (en) * | 2022-08-04 | 2022-09-06 | 太平金融科技服务(上海)有限公司深圳分公司 | Hotspot problem analysis method and device, computer equipment and storage medium |
| CN116362759A (en) * | 2023-03-27 | 2023-06-30 | 广州联欣信息科技有限公司 | Mobile Internet order management system |
| TWI807569B (en) * | 2022-01-03 | 2023-07-01 | 中華電信股份有限公司 | Auto-reply system and auto-reply method based on instant message service |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120155630A1 (en) * | 2010-12-17 | 2012-06-21 | Sridhar Raghavan | System, Method, and Computer Program Product for Detecting Redundancies in Information Provided by Customers in a Customer Service System |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN109145101A (en) * | 2018-09-06 | 2019-01-04 | 北京京东尚科信息技术有限公司 | Interactive method, device and computer readable storage medium |
-
2019
- 2019-10-29 CN CN201911039210.0A patent/CN111061831A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120155630A1 (en) * | 2010-12-17 | 2012-06-21 | Sridhar Raghavan | System, Method, and Computer Program Product for Detecting Redundancies in Information Provided by Customers in a Customer Service System |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN109145101A (en) * | 2018-09-06 | 2019-01-04 | 北京京东尚科信息技术有限公司 | Interactive method, device and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 小小青龙: "《一洽智能客服机器人怎么转人工？》", 《公开网址：HTTPS://WWW.ZHIHU.COM/QUESTION/316550655?UTM_ID=0》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111540358A (en) * | 2020-04-26 | 2020-08-14 | 云知声智能科技股份有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN111901487B (en) * | 2020-08-13 | 2021-05-21 | 山东泰盈科技有限公司 | User voice calling system and method based on big data processing |
| CN111901487A (en) * | 2020-08-13 | 2020-11-06 | 周铭 | User voice calling system and method based on big data processing |
| CN112182149A (en) * | 2020-09-15 | 2021-01-05 | 中信银行股份有限公司 | Exception processing method and device, electronic equipment and computer readable storage medium |
| CN112269863A (en) * | 2020-10-15 | 2021-01-26 | 和美（深圳）信息技术股份有限公司 | Man-machine conversation data processing method and system of intelligent robot |
| CN112365894A (en) * | 2020-11-09 | 2021-02-12 | 平安普惠企业管理有限公司 | AI-based composite voice interaction method and device and computer equipment |
| CN112365894B (en) * | 2020-11-09 | 2024-05-17 | 青岛易蓓教育科技有限公司 | AI-based composite voice interaction method and device and computer equipment |
| CN112700781A (en) * | 2020-12-24 | 2021-04-23 | 江西台德智慧科技有限公司 | Voice interaction system based on artificial intelligence |
| CN112700781B (en) * | 2020-12-24 | 2022-11-11 | 江西台德智慧科技有限公司 | Voice interaction system based on artificial intelligence |
| CN114117157A (en) * | 2021-11-19 | 2022-03-01 | 招联消费金融有限公司 | Session processing method, device, computer equipment and storage medium |
| CN114117157B (en) * | 2021-11-19 | 2024-04-09 | 招联消费金融股份有限公司 | Session processing method, apparatus, computer device and storage medium |
| TWI807569B (en) * | 2022-01-03 | 2023-07-01 | 中華電信股份有限公司 | Auto-reply system and auto-reply method based on instant message service |
| CN115017291A (en) * | 2022-08-04 | 2022-09-06 | 太平金融科技服务(上海)有限公司深圳分公司 | Hotspot problem analysis method and device, computer equipment and storage medium |
| CN116362759A (en) * | 2023-03-27 | 2023-06-30 | 广州联欣信息科技有限公司 | Mobile Internet order management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111061831A (en) | Method and device for switching machine customer service to manual customer service and electronic equipment | |
| US20220391421A1 (en) | Systems and methods for analyzing entity profiles | |
| US11645321B2 (en) | Calculating relationship strength using an activity-based distributed graph | |
| US8997117B1 (en) | System and method for creating personal connection alerts | |
| US20150006442A1 (en) | Facilitating machine learning in an online social network | |
| CN111026971A (en) | Content pushing method and device and computer storage medium | |
| US11238132B2 (en) | Method and system for using existing models in connection with new model development | |
| US10901992B2 (en) | System and method for efficiently handling queries | |
| Moro et al. | A divide‐and‐conquer strategy using feature relevance and expert knowledge for enhancing a data mining approach to bank telemarketing | |
| US10706359B2 (en) | Method and system for generating predictive models for scoring and prioritizing leads | |
| CN112231533A (en) | Data processing method, device, equipment and storage medium | |
| US11900320B2 (en) | Utilizing machine learning models for identifying a subject of a query, a context for the subject, and a workflow | |
| CN111310035A (en) | Recommendation method and device based on psychological and behavioral characteristics | |
| CN111046082A (en) | Data source determination method, device, server and storage medium | |
| US20220222688A1 (en) | Methodology of analyzing consumer intent from user interaction with digital environments | |
| CN110543635A (en) | information detection method and device based on deep learning and computer storage medium | |
| JP6750838B1 (en) | Procedure definition device for business automation processing and procedure definition system for business automation processing | |
| CN113158037A (en) | Object-oriented information recommendation method and device | |
| RU182968U1 (en) | DEVICE FOR AUTOMATED EXPERT ASSESSMENT OF PROJECT RISK FACTORS | |
| CN112148939A (en) | Data processing method and device and electronic equipment | |
| CN112052353A (en) | Advertisement video retrieval method and intelligent terminal | |
| US20240202212A1 (en) | Contextualizing data to augment processes using semantic technologies and artificial intelligence | |
| US20180189803A1 (en) | A method and system for providing business intelligence | |
| CN117422473A (en) | Transaction switching method and device, storage medium and electronic equipment | |
| CN116610581A (en) | Test result generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |