CN116703515A

CN116703515A - Recommendation method and device based on artificial intelligence, computer equipment and storage medium

Info

Publication number: CN116703515A
Application number: CN202310677746.5A
Authority: CN
Inventors: 吴雪婧
Original assignee: Ping An Property and Casualty Insurance Company of China Ltd
Current assignee: Ping An Property and Casualty Insurance Company of China Ltd
Priority date: 2023-06-08
Filing date: 2023-06-08
Publication date: 2023-09-05

Abstract

The embodiment of the application belongs to the field of artificial intelligence and the field of financial science and technology, and relates to a recommendation method based on artificial intelligence, which comprises the following steps: determining a service merchant for the user based on the usage service data of the user; determining similar merchants of the service merchant from the merchants to be recommended based on the obtained first knowledge graph of the service merchant and the second knowledge graph of the merchants to be recommended; obtaining comment information of similar merchants; identifying invalid comment information from the comment information, and eliminating the comment information based on the invalid comment information to obtain effective comment information; generating merchant scores of merchants to be recommended based on the effective comment information; the target merchant is determined from the similar merchants based on the merchant score and pushed. The application also provides a recommendation device, computer equipment and a storage medium based on the artificial intelligence. In addition, the present application relates to blockchain technology in which merchant scores may be stored. The method and the device can be applied to merchant recommendation in the financial field, and accuracy and intelligence of merchant recommendation are improved.

Description

Recommendation method and device based on artificial intelligence, computer equipment and storage medium

Technical Field

The application relates to the technical field of artificial intelligence development and the technical field of finance, in particular to a recommendation method, a recommendation device, computer equipment and a storage medium based on artificial intelligence.

Background

With the continuous development of electronic commerce and the popularization of intelligent terminal equipment, more and more terminal users are connected to a service end such as an electronic commerce platform or an O2O platform through a browser or a client so as to realize online transaction activities. Because the information provided by the internet to the users is explosively increased, the demands of the users are also increasing, and how to timely and accurately acquire the interested business information required by the users from massive business information becomes a current urgent problem to be solved.

Taking an insurance company-butted vehicle maintenance platform as an example, a plurality of brand-linked merchants exist, the brand names and main products of the brand-linked merchants are very similar, a plurality of similar merchants often appear in the recommendation result when a user searches the merchant, and the user is required to automatically screen the recommendation result, so that the accuracy of the recommendation result of the merchant is low, and the user experience is poor.

Disclosure of Invention

The embodiment of the application aims to provide a recommendation method, a recommendation device, computer equipment and a storage medium based on artificial intelligence, so as to solve the technical problems that a large number of recommendation results are required to be screened by a user by the existing merchant recommendation method, so that the accuracy of the merchant recommendation results is low and the user experience is poor.

In order to solve the technical problems, the embodiment of the application provides an artificial intelligence-based recommendation method, which adopts the following technical scheme:

determining a service merchant for a user based on usage service data for the user;

acquiring a first knowledge graph corresponding to the service merchant and a second knowledge graph corresponding to a merchant to be recommended; wherein the number of merchants to be recommended includes a plurality of merchants;

determining similar merchants corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph;

obtaining comment information corresponding to the similar merchants;

identifying invalid comment information from the comment information based on a preset identification rule, and removing the comment information based on the invalid comment information to obtain effective comment information;

generating merchant scores of the merchants to be recommended based on the effective comment information;

and determining a target merchant from the similar merchants based on the merchant scores, and pushing the target merchant to the user.

Further, the step of determining, from the merchants to be recommended, similar merchants corresponding to the service merchant based on the first knowledge graph and the second knowledge graph specifically includes:

Acquiring first merchant features of the service merchant from the first knowledge graph; the method comprises the steps of,

acquiring second merchant characteristics of the merchant to be recommended from the second knowledge graph;

comparing the first merchant feature with the second merchant feature to generate a similarity between the first merchant feature and the second merchant feature;

judging whether the similarity is larger than a preset similarity threshold value or not;

if yes, determining the merchant to be recommended as a similar merchant of the service merchant, otherwise, determining the merchant to be recommended as a dissimilar merchant of the service merchant.

Further, the step of identifying invalid comment information from the comment information based on a preset identification rule specifically includes:

acquiring a preset standard comment template;

determining a matching numerical value between the comment information and the standard comment template;

judging whether the matching numerical value is larger than a preset matching numerical value threshold value or not;

if yes, determining the comment information as invalid comment information, otherwise, determining the comment information as normal comment information.

Calling a preset comment analysis model;

inputting the comment information into the comment analysis model;

analyzing the comment information through the comment analysis model to generate analysis data corresponding to the comment information;

determining an information type of the comment information based on the analysis data; the information type comprises invalid comments and normal comments.

Further, the step of generating the merchant score of the merchant to be recommended based on the valid comment information specifically includes:

acquiring a first quantity of the effective comment information;

counting the effective comment information to obtain a second number of good comments contained in the effective comment information;

and calling a preset calculation formula to calculate and obtain the merchant score of the merchant to be recommended based on the first quantity and the second quantity.

Further, the step of determining the target merchant from the similar merchants based on the merchant scores specifically includes:

sorting the similar merchants according to the order of the merchant scores from large to small to obtain corresponding sorting results;

acquiring a designated number;

acquiring the appointed number of appointed merchants from front to back in the sequencing result;

And taking the designated merchant as the target merchant.

Further, the step of pushing the target merchant to the user specifically includes:

acquiring communication information of the user;

obtaining merchant information of the target merchant;

constructing merchant push information based on the merchant information;

and pushing the merchant pushing information to the user based on the communication information.

In order to solve the technical problems, the embodiment of the application also provides a recommendation device based on artificial intelligence, which adopts the following technical scheme:

a first determining module, configured to determine a service merchant of a user based on usage service data of the user;

the first acquisition module is used for acquiring a first knowledge graph corresponding to the service merchant and acquiring a second knowledge graph corresponding to the merchant to be recommended; wherein the number of merchants to be recommended includes a plurality of merchants;

the second determining module is used for determining similar merchants corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph;

the second acquisition module is used for acquiring comment information corresponding to the similar merchants;

The first processing module is used for identifying invalid comment information from the comment information based on a preset identification rule and eliminating the comment information based on the invalid comment information to obtain effective comment information;

the generation module is used for generating merchant scores of the merchants to be recommended based on the effective comment information;

and the second processing module is used for determining a target merchant from the similar merchants based on the merchant scores and pushing the target merchant to the user.

In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:

obtaining comment information corresponding to the similar merchants;

In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:

obtaining comment information corresponding to the similar merchants;

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

the embodiment of the application firstly determines a service merchant of a user based on service data of the user; then, a first knowledge graph corresponding to the service merchant is obtained, and a second knowledge graph corresponding to the merchant to be recommended is obtained; determining similar merchants corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph; then comment information corresponding to the similar merchants is acquired; subsequently, invalid comment information is identified from the comment information based on a preset identification rule, and the comment information is removed based on the invalid comment information to obtain effective comment information; generating merchant scores of the merchants to be recommended based on the effective comment information; and finally, determining a target merchant from the similar merchants based on the merchant scores, and pushing the target merchant to the user. According to the method and the device for identifying the business score of the business to be recommended, the knowledge graph corresponding to the business can be used for rapidly determining the similar business corresponding to the service business from the business to be recommended, accuracy of the obtained similar business is guaranteed, and then the comment information of the similar business is screened to identify invalid comment information from the comment information so as to generate the valid comment information with high reliability, so that the business score of the business to be recommended can be accurately generated by using the valid comment information later, and further a target business is determined from the similar business based on the business score, so that the business meeting personal interests of the user can be pushed to the user, accuracy and intelligence of the business recommendation are improved, and use experience of the user is improved.

Drawings

In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow chart of one embodiment of an artificial intelligence based recommendation method in accordance with the present application;

FIG. 3 is a schematic diagram of one embodiment of an artificial intelligence based recommendation device in accordance with the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.

It should be noted that, the recommendation method based on artificial intelligence provided by the embodiment of the present application is generally executed by a server/terminal device, and correspondingly, the recommendation device based on artificial intelligence is generally set in the server/terminal device.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow chart of one embodiment of an artificial intelligence based recommendation method in accordance with the present application is shown. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs. The recommendation method based on artificial intelligence provided by the embodiment of the application can be applied to any scene needing to be recommended by merchants, and can be applied to products in the scenes, such as automobile maintenance merchant recommendation in the field of financial insurance. The recommendation method based on artificial intelligence comprises the following steps:

Step S201, determining a service merchant of the user based on the usage service data of the user.

In this embodiment, the electronic device (e.g., the server/terminal device shown in fig. 1) on which the recommendation method based on artificial intelligence operates may acquire the usage service data through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection. The usage service data may be indicative of merchant information records that have been previously consumed by the user. The service merchant may refer to a merchant that has been consumed by the user the last time the service merchant was currently. Merchants may refer to merchants who are able to provide users with mass hot car services, car insurance, car life, etc., and high-value insurance.

Step S202, a first knowledge graph corresponding to the service merchant is obtained, and a second knowledge graph corresponding to the merchant to be recommended is obtained; wherein the number of merchants to be recommended includes a plurality of merchants.

In this embodiment, the knowledge graph is a pre-constructed merchant knowledge graph extracted for a merchant service event, and four elements of service "person-vehicle-service effect-environment" are used as a core body. Based on the core entity, modeling is carried out, the ontology graph is expanded through knowledge extraction and manual verification, the entity hyponyms, relations and attributes thereof are judged manually, the knowledge graph is expanded and optimized and adjusted, and finally the formed entity and the relations thereof are stored by adopting a graph database Neo4 j. Wherein the node comprises: people, vehicles, service effects, and environment; the "people" node contains the entities: service personnel, store fronts, maintenance workers, etc., including entity attributes: duration of the time of the operation, sex; the "car" node contains the entities: classified by purpose, comprising entity attributes: general attributes including size, color, name, brand, model, etc.; the "serving" node contains the entities: service effect, comprising entity attributes: service products, duration, service effects, geographic locations, commodity categories, commodity prices, customer groups, and the like; an "environment" node contains entities: store facilities comprising entity attributes: category, normal action state, abnormal action state. Additionally, the identification and extraction of feedback event elements may include: feedback to stores can generally be divided into three elements of a knowledge graph: 1. feedback to service personnel: whether the service attitude is enthusiasm or not; 2. feedback on store environment: whether the store position is found well or not, and whether parking is convenient or not; 3. feedback on service effects: whether the service results are satisfactory. Recognition and labeling of feedback event trigger words: the types of events for personnel feedback may include: enthusiasm, profession, funny, careful, good, and not good; event types for environmental feedback may include: clean, spacious, good to find, good; event types for effect feedback may include: clean, recommended, convenient and good. In addition, the feedback fusion disambiguation and template filling process comprises the following steps: filling according to a basic representation template of the feedback event, and identifying and primarily confirming comment basic information: 1) Personnel feedback: (character name: e.g., master king) service attitude is very (), skill (); 2) Environmental feedback: decoration (), location (), environment (); 3) And (3) effect feedback: washing well (), servicing well (); and carrying out semantic confirmation on the identified event, and carrying out reasoning by combining negative words, anti-question sentences, suspicious questions and the like to realize secondary classification of the event.

Step S203, determining a similar merchant corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph.

In this embodiment, the specific implementation process of the similar merchant corresponding to the service merchant is determined from the merchants to be recommended based on the first knowledge graph and the second knowledge graph, which will be described in further detail in the following specific embodiments, and will not be described herein.

Step S204, comment information corresponding to the similar merchants is acquired.

In this embodiment, all relevant comment information corresponding to the similar merchant may be acquired from various comment channels.

Step S205, identifying invalid comment information from the comment information based on a preset identification rule, and eliminating the comment information based on the invalid comment information to obtain effective comment information.

In this embodiment, the preset recognition rule may include a recognition manner based on a standard comment template, or further include a recognition manner based on a comment analysis model. The specific implementation process of identifying the invalid comment information from the comment information based on the preset identification rule will be described in further detail in the following specific embodiments, which will not be described herein. The above-mentioned rejection processing means deleting the invalid comment information from the comment information to obtain valid comment information.

Step S206, generating merchant scores of the merchants to be recommended based on the effective comment information.

In this embodiment, the foregoing specific implementation process of generating the merchant score of the merchant to be recommended based on the valid comment information will be described in further detail in the following specific embodiments, which will not be described herein.

Step S207, determining a target merchant from the similar merchants based on the merchant scores, and pushing the target merchant to the user.

In this embodiment, the specific implementation process of determining the target merchant from the similar merchants based on the merchant score and pushing the target merchant to the user will be described in further detail in the following specific embodiments, which will not be described herein.

Firstly, determining a service merchant of a user based on service data of the user; then, a first knowledge graph corresponding to the service merchant is obtained, and a second knowledge graph corresponding to the merchant to be recommended is obtained; determining similar merchants corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph; then comment information corresponding to the similar merchants is acquired; subsequently, invalid comment information is identified from the comment information based on a preset identification rule, and the comment information is removed based on the invalid comment information to obtain effective comment information; generating merchant scores of the merchants to be recommended based on the effective comment information; and finally, determining a target merchant from the similar merchants based on the merchant scores, and pushing the target merchant to the user. According to the method and the device for identifying the business score of the business to be recommended, the knowledge graph corresponding to the business can be used for rapidly determining the similar business corresponding to the service business from the business to be recommended, accuracy of the obtained similar business is guaranteed, and then the comment information of the similar business is screened to identify invalid comment information from the comment information so as to generate the valid comment information with high reliability, so that the business score of the business to be recommended can be accurately generated by using the valid comment information later, and further a target business is determined from the similar business based on the business score, so that the business meeting personal interests of the user can be pushed to the user, accuracy and intelligence of the business recommendation are improved, and use experience of the user is improved.

In some alternative implementations, step S203 includes the steps of:

and acquiring first merchant features of the service merchant from the first knowledge graph.

In this embodiment, the specific content of the merchant features is not specifically limited, and only the first merchant feature of the service merchant and the second merchant feature of the merchant to be recommended need to be determined to have a corresponding relationship. For example, merchant characteristics may include characteristics of geographic location, merchandise category, merchandise price, customer group, business data, payment data, transaction data, and the like.

And acquiring second merchant characteristics of the merchant to be recommended from the second knowledge graph.

Comparing the first merchant feature with the second merchant feature to generate a similarity between the first merchant feature and the second merchant feature.

In this embodiment, a first representation vector of the service merchant may be generated based on the first merchant feature, and a second representation vector of the merchant to be recommended may be generated based on the second merchant feature, and then a distance between the first representation vector and the second representation vector may be calculated, resulting in a similarity between the first merchant feature and the second merchant feature. Wherein the characteristics of the merchant may be obtained in advance and entered into the model to generate a representation vector of the merchant from the model.

And judging whether the similarity is larger than a preset similarity threshold value.

In this embodiment, the value of the similarity threshold is not particularly limited, and may be set according to actual use requirements, for example, may be set to 0.9.

The first merchant characteristics of the service merchant are obtained from the first knowledge graph; obtaining second merchant characteristics of the merchant to be recommended from the second knowledge graph; comparing the first merchant feature with the second merchant feature to generate a similarity between the first merchant feature and the second merchant feature; subsequently judging whether the similarity is larger than a preset similarity threshold value or not; if yes, determining the merchant to be recommended as a similar merchant of the service merchant, otherwise, determining the merchant to be recommended as a dissimilar merchant of the service merchant. The method and the device can quickly and accurately determine the similar merchant corresponding to the service merchant from the merchants to be recommended based on the use of the merchant knowledge graph, ensure the accuracy of the obtained similar merchant, and subsequently recommend the target merchant to the user by screening the target merchant from the similar merchants corresponding to the service merchant of the user, thereby simplifying the computational complexity, automatically pushing the merchant conforming to the personal interests of the user, improving the accuracy of merchant recommendation and improving the use experience of the user.

In some optional implementations of this embodiment, the identifying, in step S205, invalid comment information from the comment information based on a preset identification rule includes the steps of:

and acquiring a preset standard comment template.

In this embodiment, the standard comment templates may specifically include a first standard comment template corresponding to a good comment level, a second standard comment template corresponding to a medium comment level, and a third standard comment template corresponding to a bad comment level. The field content contained in the standard comment template can be predetermined according to actual service requirements.

A matching numerical value between the comment information and the standard comment template is determined.

In this embodiment, the first field number of the same first key field contained in the comment information and the standard comment template is determined; and then, acquiring the first number and the second number of the key fields contained in the standard comment templates, calculating the ratio of the first number of the fields to the second number of the fields, and taking the ratio as a matching numerical value between the comment information and the standard comment templates.

And judging whether the matching numerical value is larger than a preset matching numerical value threshold value or not.

In this embodiment, the value of the matching numerical threshold is not particularly limited, and may be set according to actual use requirements, for example, may be set to 0.88.

In this embodiment, as long as it is detected that the matching value of the comment template and the comment information currently processed is greater than the matching value threshold, the comment information is identified as invalid comment information, so that the calculation complexity can be simplified, and the recognition efficiency can be improved.

The method comprises the steps of obtaining a preset standard comment template; then determining a matching numerical value between the comment information and the standard comment template; subsequently judging whether the matching numerical value is larger than a preset matching numerical value threshold value or not; if yes, determining the comment information as invalid comment information, otherwise, determining the comment information as normal comment information. According to the method and the system for identifying the target business based on the standard comment template, the invalid comment information can be identified from the comment information rapidly and accurately, and further effective comment information with high reliability is generated, so that the effective comment information is used for determining the target business from the similar business later, and the accuracy of the generated target business can be guaranteed.

In some optional implementations, the identifying, in step S205, invalid comment information from the comment information based on a preset identification rule includes the steps of:

and calling a preset comment analysis model.

In this embodiment, the training process of the comment analysis model may include: obtaining a plurality of comment text samples, comment object feature vectors and comment object feature vectors corresponding to the comment text samples, and adding labels to form training sample data; the items in the feature vector of the commented object comprise the number of user grades of the commented object and the number of times of commenting, and the items in the feature vector of the commented object comprise the number of commented corresponding to the commented object, the good evaluation rate and/or the average number of stars of the commented user; searching word vectors and emotion vectors corresponding to each word in the sample of the evaluation paper in a preset word vector library and emotion vector library, sequentially connecting the word vectors into a first input vector, and sequentially connecting the emotion vectors into a second input vector; acquiring a preset initial model, wherein the initial model uses a first convolutional neural network to extract a semantic feature vector of a first input vector, uses a second convolutional neural network to extract an emotion feature vector of a second input vector, and classifies the semantic feature vector, the emotion feature vector, the comment object feature vector and the comment object feature vector through a full connection layer and an activation function after linear connection; and training the initial model by adopting the training sample data to obtain the evaluation analysis model. And the initial model adopts a cross entropy loss function to carry out parameter training.

Inputting the comment information into the comment analysis model.

Analyzing the comment information through the comment analysis model to generate analysis data corresponding to the comment information.

In this embodiment, the analysis data is a numerical value output by an activation function in the comment analysis model.

In this embodiment, if the value output by the activation function in the comment analysis model is greater than a preset value, it is determined that the comment information belongs to an invalid comment, and if the value output is not greater than the preset value, it is determined that the comment information belongs to a normal comment. The value of the preset value is not particularly limited, and may be set according to actual use requirements.

The method and the device call a preset comment analysis model; inputting the comment information into the comment analysis model; analyzing the comment information through the comment analysis model to generate analysis data corresponding to the comment information; and determining the information type of the evaluation information based on the analysis data. According to the method and the system for identifying the target business based on the comment analysis model, the invalid comment information can be identified from the comment information rapidly and accurately, and further effective comment information with high reliability is generated, so that the effective comment information is used for determining the target business from the similar business later, and the accuracy of the generated target business can be guaranteed.

In some alternative implementations, step S206 includes the steps of:

and acquiring the first quantity of the effective comment information.

And counting the effective comment information to obtain a second number of the good comments contained in the effective comment information.

In this embodiment, the valid comment information includes a good comment, a medium comment, and a bad comment.

In this embodiment, the above-mentioned preset calculation formula includes: sorce = a/b, where Sorce is the merchant score, a is the number of good reviews, and b is the number of valid review information.

The method comprises the steps of obtaining a first quantity of the effective comment information; counting the effective comment information to obtain a second number of good comments contained in the effective comment information; and then, based on the first quantity and the second quantity, calling a preset calculation formula to calculate and obtain the merchant score of the merchant to be recommended so as to quickly and accurately generate the merchant score of the merchant to be recommended, and the method is beneficial to accurately determining the target merchant from the similar merchants based on the obtained merchant score.

In some optional implementations of this embodiment, the determining the target merchant from the similar merchants based on the merchant score in step S207 includes the steps of:

and sequencing the similar merchants according to the sequence of the merchant scores from large to small to obtain corresponding sequencing results.

A specified number is obtained.

In this embodiment, the specific number of values is not limited, and may be set according to actual use requirements.

And acquiring the designated number of designated merchants from front to back in the sorting result.

In this embodiment, if the specified number is one, the product with the top ranking result ranking is obtained as the target merchant; or when the target number is N and N is an integer greater than 1, acquiring N merchants with the top ranking as target merchants.

And taking the designated merchant as the target merchant.

According to the method, the similar merchants are ranked according to the order of the merchant scores from large to small, and corresponding ranking results are obtained; then acquiring the designated number; and subsequently acquiring the appointed number of appointed merchants from front to back in the sorting result, and taking the appointed merchants as the target merchants. According to the method, the target merchant with the highest evaluation is screened out from similar merchants based on merchant scores and pushed to the user, so that the target merchant meeting the personal requirements of the user is automatically and accurately generated and pushed, the data accuracy of the target merchant is improved, and the automation and the intelligence of merchant pushing are improved.

In some optional implementations of this embodiment, the pushing the target merchant to the user in step S207 includes the steps of:

and acquiring the communication information of the user.

In this embodiment, the communication information may include a mobile phone number or a mail address.

And acquiring merchant information of the target merchant.

In this embodiment, the merchant information may refer to a merchant name of a merchant, or may further include information such as a merchant introduction.

And constructing merchant push information based on the merchant information.

In this embodiment, the merchant pushing information is generated by filling the merchant information into a preset information template. The information template is a template which is created in advance according to actual use requirements. The push information is the information conforming to the communication information, so that the normal sending of the push information of the merchant can be ensured later. The merchant pushing information at least comprises merchant information.

In this embodiment, the merchant push information may be sent to a communication terminal of a user corresponding to the communication information through the communication information.

The application obtains the communication information of the user; then obtaining merchant information of the target merchant; then constructing merchant push information based on the merchant information; and pushing the merchant pushing information to the user based on the communication information. According to the method and the device for recommending the target merchant, the merchant pushing information corresponding to the target merchant is generated and pushed to the user, so that merchant intelligent recommendation of the user is achieved, the intelligence and the accuracy of merchant recommendation are improved, the user can review the merchant pushing information in time and conduct relevant follow-up processing, and the use experience of the user is improved.

It should be emphasized that to further ensure the privacy and security of the product transformation data, the product transformation data may also be stored in a blockchain node.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an artificial intelligence-based recommendation device, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device is particularly applicable to various electronic devices.

As shown in fig. 3, the recommendation device 300 based on artificial intelligence according to the present embodiment includes: a first determining module 301, a first acquiring module 302, a second determining module 303, a second acquiring module 304, a first processing module 305, a generating module 306 and a second processing module 307. Wherein:

A first determining module 301, configured to determine a service merchant of a user based on usage service data of the user;

a first obtaining module 302, configured to obtain a first knowledge graph corresponding to the service merchant and obtain a second knowledge graph corresponding to a merchant to be recommended; wherein the number of merchants to be recommended includes a plurality of merchants;

a second determining module 303, configured to determine, based on the first knowledge graph and the second knowledge graph, similar merchants corresponding to the service merchant from the merchants to be recommended;

a second obtaining module 304, configured to obtain comment information corresponding to the similar merchants;

the first processing module 305 is configured to identify invalid comment information from the comment information based on a preset identification rule, and reject the comment information based on the invalid comment information to obtain valid comment information;

a generating module 306, configured to generate a merchant score of the merchant to be recommended based on the valid comment information;

a second processing module 307 is configured to determine a target merchant from the similar merchants based on the merchant scores, and push the target merchant to the user.

In this embodiment, the operations performed by the modules or units respectively correspond to the steps of the artificial intelligence-based recommendation method in the foregoing embodiment one by one, which is not described herein again.

In some alternative implementations of the present embodiment, the second determining module 303 includes:

a first obtaining sub-module, configured to obtain a first merchant feature of the service merchant from the first knowledge-graph; the method comprises the steps of,

the second obtaining submodule is used for obtaining second merchant characteristics of the merchant to be recommended from the second knowledge graph;

a first generation sub-module for comparing the first merchant feature with the second merchant feature to generate a similarity between the first merchant feature and the second merchant feature;

the first judging submodule is used for judging whether the similarity is larger than a preset similarity threshold value or not;

and the first judging submodule is used for determining the merchant to be recommended as a similar merchant of the service merchant if yes, and determining the merchant to be recommended as a dissimilar merchant of the service merchant if not.

In some alternative implementations of the present embodiment, the first processing module 305 includes:

the third acquisition submodule is used for acquiring a preset standard comment template;

A first determining submodule for determining a matching numerical value between the comment information and the standard comment template;

the second judging sub-module is used for judging whether the matching numerical value is larger than a preset matching numerical value threshold value or not;

and the second judging submodule is used for determining the comment information as invalid comment information if yes, and determining the comment information as normal comment information if not.

In this embodiment, the operations performed by the modules or units respectively correspond to the steps of the recommendation method based on artificial intelligence in the foregoing embodiment one by one, which is not described herein again.

the calling sub-module is used for calling a preset comment analysis model;

an input sub-module for inputting the comment information into the comment analysis model;

the second generation submodule is used for analyzing the comment information through the comment analysis model and generating analysis data corresponding to the comment information;

a second determining sub-module for determining an information type of the evaluation information based on the analysis data; the information type comprises invalid comments and normal comments.

In some alternative implementations of the present embodiment, the generating module 306 includes:

a fourth obtaining sub-module, configured to obtain the first number of valid comment information;

the statistics sub-module is used for carrying out statistics on the effective comment information to obtain a second number of the comment comments contained in the effective comment information;

and the calculating sub-module is used for calling a preset calculating formula to calculate and obtain the merchant score of the merchant to be recommended based on the first quantity and the second quantity.

In some alternative implementations of the present embodiment, the second processing module 307 includes:

the sorting sub-module is used for sorting the similar merchants according to the order of the merchant scores from large to small to obtain corresponding sorting results;

a fifth acquisition sub-module for acquiring the specified number;

A sixth obtaining sub-module, configured to obtain, from front to back, a specified number of specified merchants in the ranking result;

and a third determining sub-module, configured to use the designated merchant as the target merchant.

a seventh obtaining sub-module, configured to obtain communication information of the user;

an eighth obtaining sub-module, configured to obtain merchant information of the target merchant;

a construction sub-module for constructing merchant push information based on the merchant information;

and the pushing sub-module is used for pushing the merchant pushing information to the user based on the communication information.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.

The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It should be noted that only computer device 4 having components 41-43 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 41 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various application software installed on the computer device 4, such as computer readable instructions of an artificial intelligence based recommendation method. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.

The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as executing computer readable instructions of the artificial intelligence based recommendation method.

The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.

in the embodiment of the application, firstly, a service merchant of a user is determined based on service data of the user; then, a first knowledge graph corresponding to the service merchant is obtained, and a second knowledge graph corresponding to the merchant to be recommended is obtained; determining similar merchants corresponding to the service merchant from the merchants to be recommended based on the first knowledge graph and the second knowledge graph; then comment information corresponding to the similar merchants is acquired; subsequently, invalid comment information is identified from the comment information based on a preset identification rule, and the comment information is removed based on the invalid comment information to obtain effective comment information; generating merchant scores of the merchants to be recommended based on the effective comment information; and finally, determining a target merchant from the similar merchants based on the merchant scores, and pushing the target merchant to the user. According to the method and the device for identifying the business score of the business to be recommended, the knowledge graph corresponding to the business can be used for rapidly determining the similar business corresponding to the service business from the business to be recommended, accuracy of the obtained similar business is guaranteed, and then the comment information of the similar business is screened to identify invalid comment information from the comment information so as to generate the valid comment information with high reliability, so that the business score of the business to be recommended can be accurately generated by using the valid comment information later, and further a target business is determined from the similar business based on the business score, so that the business meeting personal interests of the user can be pushed to the user, accuracy and intelligence of the business recommendation are improved, and use experience of the user is improved.

The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence-based recommendation method as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.

It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims

1. An artificial intelligence based recommendation method is characterized by comprising the following steps:

obtaining comment information corresponding to the similar merchants;

2. The method for recommending according to claim 1, wherein the step of determining a similar merchant corresponding to the service merchant from the merchants to be recommended based on the first knowledge-graph and the second knowledge-graph specifically comprises:

3. The recommendation method based on artificial intelligence according to claim 1, wherein the step of identifying invalid comment information from the comment information based on a preset identification rule specifically comprises:

acquiring a preset standard comment template;

4. The recommendation method based on artificial intelligence according to claim 1, wherein the step of identifying invalid comment information from the comment information based on a preset identification rule specifically comprises:

calling a preset comment analysis model;

inputting the comment information into the comment analysis model;

5. The artificial intelligence based recommendation method according to claim 1, wherein the step of generating a merchant score of the merchant to be recommended based on the valid comment information specifically comprises:

acquiring a first quantity of the effective comment information;

6. The artificial intelligence based recommendation method according to claim 1, wherein said step of determining a target merchant from said similar merchants based on said merchant score, in particular comprises:

acquiring a designated number;

and taking the designated merchant as the target merchant.

7. The artificial intelligence based recommendation method of claim 1, wherein the step of pushing the target merchant to the user specifically comprises:

acquiring communication information of the user;

obtaining merchant information of the target merchant;

constructing merchant push information based on the merchant information;

8. An artificial intelligence based recommendation device, comprising:

9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the artificial intelligence based recommendation method of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the artificial intelligence based recommendation method according to any of claims 1 to 7.