CN116542779A

CN116542779A - Product recommendation method, device, equipment and storage medium based on artificial intelligence

Info

Publication number: CN116542779A
Application number: CN202310498104.9A
Authority: CN
Inventors: 林婷婷
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: 2023-05-05
Filing date: 2023-05-05
Publication date: 2023-08-04

Abstract

The embodiment of the application belongs to the field of artificial intelligence, and relates to a product recommendation method based on artificial intelligence, which comprises the following steps: acquiring user data; constructing a user tag based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended; acquiring a historical price inquiring record of a user, and determining the product preference type of the user based on the historical price inquiring record; screening a second product from the first product based on the product preference type; acquiring product information of the second product, processing the product information and historical product purchase information based on the purchase prediction model, and generating purchase probability of the second product purchased by the user; and determining a target product from the second product based on the purchase probability, and pushing the target product to the user. The application also provides a product recommendation device, computer equipment and a storage medium based on the artificial intelligence. In addition, the application also relates to a blockchain technology, and the target product can be stored in the blockchain. According to the recommendation method and device, the recommendation accuracy of the product can be improved.

Description

Product recommendation method, device, equipment and storage medium based on artificial intelligence

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to an artificial intelligence-based product recommendation method, apparatus, computer device, and storage medium.

Background

With the rapid development of insurance industry, the variety of insurance products is also becoming more and more. In the face of numerous insurance products and customers with a large number of different requirements, how to recommend the most suitable insurance products to the customers is a problem that insurance companies need to explore all the time.

Currently, when a user needs to purchase insurance, an insurance sales person manually judges the types of insurance that the user prefers to trade according to the needs and working experience of the user in a subjective judgment mode, and explains and recommends the types of insurance to the user. However, the manner of insurance recommendation by manually judging the user needs is mainly based on subjective judgment of insurance sales personnel, which is greatly dependent on personal experience of the insurance sales personnel, and easily causes large workload of insurance recommendation and low accuracy of recommended insurance products.

Disclosure of Invention

The embodiment of the application aims to provide a product recommendation method, device, computer equipment and storage medium based on artificial intelligence, so as to solve the technical problems that the conventional insurance recommendation mode through manual judgment of user requirements mainly aims at subjective judgment of insurance sales personnel, the personal experience of the insurance sales personnel is greatly relied on, the workload of insurance recommendation is easily caused to be large, and the accuracy of recommended insurance products is low.

In order to solve the above technical problems, the embodiments of the present application provide a product recommendation method based on artificial intelligence, which adopts the following technical scheme:

acquiring user data; wherein, the user data at least comprises basic information data and historical product purchase information of a user;

constructing a user tag of the user based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended;

acquiring a historical price inquiring record corresponding to the user, and determining a product preference type corresponding to the user based on the historical price inquiring record;

screening a second product from the first products based on the product preference type;

acquiring product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model, and generating purchase probability of the user purchasing the second product;

and determining a target product from the second product based on the purchase probability, and pushing the target product to the user.

Further, the step of constructing the user tag of the user based on the user data specifically includes:

Calling a preset user analysis model;

inputting the user data into the user analysis model;

and performing label matching processing on the user data through the user analysis model to generate a user label corresponding to the user.

Further, the step of obtaining the first product corresponding to the user tag from the product set to be recommended specifically includes:

acquiring a target label corresponding to the information type from the user label based on the preset information type;

determining a customer group type corresponding to the user based on the target tag;

and inquiring products matched with the customer group types from the product set to be recommended to obtain the first product.

Further, the step of determining the product preference type corresponding to the user based on the historical price inquiry record specifically comprises the following steps:

acquiring user evaluation information corresponding to the historical price inquiry record;

screening out evaluation content related to the product description from the user evaluation information;

and analyzing the evaluation content based on a preset analysis rule, and determining the product preference type corresponding to the user.

Further, before the step of processing the product information and the historical product purchase information based on the preset purchase prediction model to generate the purchase probability of the user purchasing the second product, the method specifically includes:

acquiring product purchase information of a target customer and acquiring specified product information of a preset product;

constructing a sample data set based on the product purchase information and the specified product information;

determining a training data set and a testing data set from the sample data set based on a preset proportion;

training a preset classification model by using the training data set to obtain an initial purchase prediction model;

and verifying the initial purchase prediction model by using the test set, if the obtained classification accuracy is greater than a preset accuracy threshold, finishing training, and taking the initial purchase prediction model as the purchase prediction model.

Further, the step of determining the target product from the second product based on the purchase probability specifically includes:

acquiring income information and family state information of the user from the user tag;

generating a purchase limit threshold of the user based on the income information and family state information;

Screening a third product smaller than the purchasing limit threshold value from the second products;

and taking the third product as the target product.

sorting the second products according to the order of the purchase probability from high to low to obtain corresponding sorting results;

determining a target number;

acquiring a fourth insurance of the target number from front to back in the sequencing result;

and taking the fourth insurance as the target insurance.

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

the first acquisition module is used for acquiring user data; wherein, the user data at least comprises basic information data and historical product purchase information of a user;

the first construction module is used for constructing a user tag of the user based on the user data and acquiring a first product corresponding to the user tag from a product set to be recommended;

the first determining module is used for acquiring a historical price inquiring record corresponding to the user and determining a product preference type corresponding to the user based on the historical price inquiring record;

A screening module for screening a second product from the first products based on the product preference type;

the processing module is used for acquiring the product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model and generating the purchase probability of the second product purchased by the user;

and the second determining module is used for determining a target product from the second products based on the purchase probability and pushing the target product to the user.

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

In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:

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

firstly, acquiring user data; then constructing a user tag of the user based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended; then, acquiring a historical price inquiring record corresponding to the user, and determining a product preference type corresponding to the user based on the historical price inquiring record; subsequently screening a second product from the first product based on the product preference type; further acquiring product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model, and generating purchase probability of the user purchasing the second product; and finally, determining a target product from the second product based on the purchase probability, and pushing the target product to the user. According to the method and the device for automatically selecting the product to be recommended, the user data of the user and the historical price inquiry records are analyzed to perform primary screening on the product set to be recommended, further products after primary screening are further screened based on the use of the purchase prediction model, and therefore target products meeting the purchase tendency of the user can be automatically and accurately generated and pushed.

Drawings

For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious 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 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 product recommendation method according to the present application;

FIG. 3 is a schematic structural view of one embodiment of an artificial intelligence based product recommendation device according to the present application;

FIG. 4 is a schematic structural diagram of one embodiment of a computer device according to 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 and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. 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 present 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 better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application 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 product recommendation method based on artificial intelligence provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the product recommendation device based on artificial intelligence is generally disposed 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 product recommendation method according to the present application is shown. The product recommendation method based on artificial intelligence comprises the following steps:

Step S201, obtaining user data; wherein the user data at least comprises basic information data of the user and historical product purchase information.

In this embodiment, the electronic device (e.g., the server/terminal device shown in fig. 1) on which the product recommendation method based on artificial intelligence operates may acquire the user 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. Wherein, the basic information data of the user at least comprises: customer name, ID card number, age, occupation, income information, property, life cycle, family status, etc., and the historical product purchase information at least comprises purchase product type, risk insurance, purchase date, etc.

Step S202, constructing a user tag of the user based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended.

In this embodiment, the scheme can be specifically applied to a service scenario recommended by an insurance product. The product set to be recommended can contain a plurality of insurance products. The specific implementation process of constructing the user tag of the user based on the user data and obtaining the first product corresponding to the user tag from the product set to be recommended is described in further detail in the following specific embodiments, which will not be described herein.

Step S203, a historical price inquiring record corresponding to the user is obtained, and the product preference type corresponding to the user is determined based on the historical price inquiring record.

In this embodiment, the specific implementation process of determining the product preference type corresponding to the user based on the historical price inquiry record will be described in further detail in the following specific embodiments, which will not be described herein.

Step S204, screening a second product from the first products based on the product preference type.

In this embodiment, the first product may be classified according to a category of a preset product type, and then a product matching with the product preference type may be selected from the classified first products as the second product.

Step S205, obtaining product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model, and generating a purchase probability of the user purchasing the second product.

In this embodiment, the purchase prediction model may be a classification type, and preferably a support vector machine model may be used. The expression of the specific vector machine model is as follows: Wherein P represents the purchase probability of the second product, W and b represent model coefficients, and f (x) represents the decision function of the support vector machine.

And step S206, determining a target product from the second products based on the purchase probability, and pushing the target product to the user.

In this embodiment, the target product may be pushed to the user by acquiring terminal contact information of the user and based on the terminal contact information. The specific implementation process of determining the target product from the second product based on the purchase probability will be described in further detail in the following specific embodiments, which will not be described herein.

Firstly, acquiring user data; then constructing a user tag of the user based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended; then, acquiring a historical price inquiring record corresponding to the user, and determining a product preference type corresponding to the user based on the historical price inquiring record; subsequently screening a second product from the first product based on the product preference type; further acquiring product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model, and generating purchase probability of the user purchasing the second product; and finally, determining a target product from the second product based on the purchase probability, and pushing the target product to the user. According to the method, the user data of the user and the historical price inquiry records are analyzed to conduct primary screening on the product set to be recommended, further products after primary screening are further screened based on the use of the purchase prediction model, and therefore target products meeting the purchase tendency of the user can be automatically and accurately generated and pushed.

In some alternative implementations, the constructing the user tag of the user based on the user data in step S202 includes the steps of:

and calling a preset user analysis model.

In this embodiment, a user model is predefined, which is composed of a plurality of tags, each tag describing one attribute of the user. Specifically, the tag means: to describe one or more attributes of a user, such as: age, sex, occupation, whether there is a house, whether there is a car, etc., each attribute is a label; the user analysis model refers to: by a set of tags, for example: a user analysis model is formed by a collection of tags of gender, age, occupation, annual income, whether rooms exist, whether vehicles exist, whether business trips frequently exist and the like.

Inputting the user data into the user analysis model.

In this embodiment, the user model may be automatically operated manually by a related person or periodically according to system settings at regular intervals, so as to match the user data with various tags in the user analysis model, and then lay the matched tags on the user data. After labeling, the user data can be stored in a relational database for subsequent display.

The method comprises the steps of calling a preset user analysis model; inputting the user data into the user analysis model; and subsequently, carrying out label matching processing on the user data through the user analysis model to generate a user label corresponding to the user. According to the method and the device for processing the user data based on the user analysis model, the user label corresponding to the user can be generated rapidly and accurately, the first product corresponding to the user label can be obtained from the product set to be recommended later, and accordingly rapid and intelligent obtaining of the first product is achieved.

In some optional implementations of this embodiment, the acquiring, in step S202, the first product corresponding to the user tag from the product set to be recommended includes the following steps:

and acquiring a target label corresponding to the information type from the user label based on the preset information type.

In the present embodiment, the above information type refers to a type corresponding to life cycle information.

And determining the client group type corresponding to the user based on the target label.

In this embodiment, the target tag refers to a life cycle tag in the user tags, and the users are divided into customer groups such as a single period, a family formation period, a family growth period, a family maturity period, and a retirement period according to the life cycle tags of different users in advance.

In this embodiment, the product set to be recommended is a pre-built set storing products respectively matched with each customer group, that is, a set in which products are pre-classified based on the types of the customer groups.

The method comprises the steps of obtaining a target label corresponding to an information type from the user label based on the preset information type; then determining a customer group type corresponding to the user based on the target label; and inquiring products matched with the customer group types from the product set to be recommended to obtain the first product. After the user tag of the user is obtained, the first products corresponding to the user tag can be quickly and intelligently obtained from the product set to be recommended based on the use of the user tag, so that the preliminary screening of all products in the product set to be recommended is finished, the first products only need to be processed subsequently to recommend accurate products of the user, and the processing workload of product recommendation is reduced.

In some alternative implementations, the determining, in step S203, a product preference type corresponding to the user based on the historical price inquiry record includes the steps of:

and acquiring user evaluation information corresponding to the historical price inquiry record.

In this embodiment, the user evaluation information may refer to evaluation information for a user, which is filled in by a product recommender in a product query performed by the user. Wherein the user rating information at least comprises preference information about the user for the product, the preference information about the user for the product may comprise that the user belongs to a price sensitive customer, that the user belongs to a solution sensitive customer, or that the user belongs to a balance type customer.

And screening out evaluation content related to the product description from the user evaluation information.

In this embodiment, the above-described evaluation content related to the product description refers to the preference information about the product of the user, which is filled in by the product recommender in the product price of the user.

In this embodiment, the target evaluation content with the largest occurrence number can be obtained by acquiring the evaluation content of the user for each product and then screening the evaluation content, and the target evaluation content is used as the product preference type corresponding to the user.

The user evaluation information corresponding to the historical price inquiry record is obtained; screening out evaluation content related to the product description from the user evaluation information; and then analyzing the evaluation content based on a preset analysis rule to determine the product preference type corresponding to the user. According to the method and the device, the historical price inquiring record of the user is analyzed and processed, the product preference type corresponding to the user can be rapidly and accurately determined, the subsequent screening of the second product from the first product can be facilitated based on the product preference type, and accordingly rapid and intelligent acquisition of the second product is achieved, primary screening of the first product is achieved, the second product is processed only for accurate product recommendation of the user, and processing workload of product recommendation is reduced.

In some alternative implementations, before step S205, the electronic device may further perform the following steps:

product purchase information of a target customer is obtained, and specified product information of a preset product is obtained.

In this embodiment, the target customer is preferably a customer with excellent purchasing power, and the product purchasing information includes at least a specific product purchased by the target customer in a preset period of time, and a specific product corresponding to a product type of the specific product not related to the purchase of the target customer in a next period of time in the preset period of time. The specified product information may include a product name of the specified product.

A sample dataset is constructed based on the product purchase information and the specified product information.

In the present embodiment, the feature vector of the product purchase information and the specified product information is extracted and used as a sample data set.

And determining a training data set and a testing data set from the sample data set based on a preset proportion.

In this embodiment, the value of the preset ratio is not particularly limited, and may be set according to actual use requirements. For example, it can be set to 8:2, namely randomly extracting 80% of data from the sample data set as a training data set, and randomly extracting 20% of data from the sample data set as a test data set.

Training a preset classification model by using the training data set to obtain an initial purchase prediction model.

In this embodiment, the selection of the classification model is not particularly limited, and for example, decision trees, random forests, GBDT, XGB, support vector machine models, and the like may be used, and support vector machine models are preferably used. Specifically, feature vectors in the training data set are input into the support vector machine model, so that the purchase probability of each corresponding appointed product is obtained. And adjusting model coefficients according to the purchase probability of each designated product and insurance products purchased by customers in the next period of time, so as to generate the purchase prediction model.

In this embodiment, the value of the accuracy threshold is not specifically limited, and may be set according to actual use requirements. If the obtained classification accuracy is not greater than a preset accuracy threshold, increasing the number of target clients and re-executing the training step until the accuracy is greater than or equal to the accuracy threshold, thereby obtaining a purchase prediction model meeting the requirements.

The method comprises the steps of obtaining product purchase information of a target customer and obtaining specified product information of a preset product; then constructing a sample data set based on the product purchase information and the specified product information; then determining a training data set and a testing data set from the sample data set based on a preset proportion; training a preset classification model by using the training data set to obtain an initial purchase prediction model; and finally, verifying the initial purchase prediction model by using the test set, if the obtained classification accuracy is greater than a preset accuracy threshold, finishing training, and taking the initial purchase prediction model as the purchase prediction model, so that the subsequent processing of the product information of the second product and the historical product purchase information based on the purchase prediction model is facilitated, the purchase probability of the second product purchased by the user is generated, and the target product can be determined from the second product based on the purchase probability, and the accuracy of the generated target product is ensured.

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

and acquiring income information and family state information of the user from the user tag.

In this embodiment, the user tag includes at least income information and family status information of the user.

And generating a purchase limit threshold of the user based on the income information and the family state information.

In this embodiment, the purchase limit threshold may refer to a user's affordable product purchase cost. The value range corresponding to the income information can be acquired first, and the purchase limit threshold corresponding to the income value range and the family state information is inquired from the purchase limit table by inquiring a preset purchase limit table. The purchase limit table is a data table constructed by carrying out data analysis on various client groups according to actual business rules (along with the improvement of income level, the adjustment from rigidity and basic guarantee to comprehensive high-end guarantee), and stores the association relationship among the income numerical value range, the family state information and the purchase limit threshold value. In addition, the home status information may include a single period, a home formation period, a home growth period, a home maturation period, a retirement period, and the like.

And screening a third product smaller than the purchase limit threshold from the second products.

And taking the third product as the target product.

The income information and the family state information of the user are obtained from the user tag; generating a purchase limit threshold of the user based on the income information and the family state information; and subsequently screening a third product which is smaller than the purchase limit threshold from the second products, and taking the third product as the target product. According to the method and the device, after the second product is determined from the product set to be recommended by analyzing the user data of the user and based on the use of the purchase prediction model, the second product is further screened based on the purchase limit threshold of the user to obtain a final target product, so that the target product which accords with the purchase tendency of the user can be automatically and accurately generated and pushed, compared with a manual recommendation mode, the recommendation accuracy of the product can be effectively improved, the workload of insurance recommending personnel can be reduced by the automatic processing mode, and the work efficiency of the insurance recommending personnel can be improved.

And sequencing the second products according to the order of the purchase probability from high to low, and obtaining corresponding sequencing results.

A target number is determined.

In this embodiment, the value of the target number is not particularly limited, and may be set according to actual use requirements. If the target number is one, acquiring the product with the forefront ordering as a target product; or when the target number is N and N is an integer greater than 1, acquiring N products which are ranked at the front as target products.

And acquiring a fourth insurance of the target number from front to back in the sequencing result.

And taking the fourth insurance as the target insurance.

The second products are ordered according to the order of the purchase probability from high to low, and corresponding ordering results are obtained; then determining the target quantity; and subsequently, acquiring a fourth insurance of the target number from front to back in the sorting result, and taking the fourth insurance as the target insurance. According to the method and the device, through analysis of the user data of the user and based on the use of the purchase prediction model, the target product which accords with the purchase tendency of the user can be automatically and accurately generated and pushed, compared with a manual recommendation mode, the recommendation accuracy of the product can be effectively improved, and the automatic processing mode can also reduce the workload of insurance recommending personnel, so that the work efficiency of the insurance recommending personnel can be improved.

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

The blockchain referred to in the application 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 product recommendation device, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.

As shown in fig. 3, the product recommendation device 300 based on artificial intelligence according to the present embodiment includes: a first acquisition module 301, a first construction module 302, a first determination module 303, a screening module 304, a processing module 305, and a second determination module 306. Wherein:

a first obtaining module 301, configured to obtain user data; wherein, the user data at least comprises basic information data and historical product purchase information of a user;

a first construction module 302, configured to construct a user tag of the user based on the user data, and obtain a first product corresponding to the user tag from a product set to be recommended;

a first determining module 303, configured to obtain a historical price query record corresponding to the user, and determine a product preference type corresponding to the user based on the historical price query record;

a screening module 304, configured to screen a second product from the first products based on the product preference type;

The processing module 305 is configured to obtain product information of the second product, process the product information and the historical product purchase information based on a preset purchase prediction model, and generate a purchase probability of the user purchasing the second product;

and a second determining module 306, configured to determine a target product from the second products based on the purchase probability, and push the target product to the user.

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

In some alternative implementations of the present embodiment, the first building block 302 includes:

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

an input sub-module for inputting the user data into the user analysis model;

and the first generation sub-module is used for carrying out label matching processing on the user data through the user analysis model to generate a user label corresponding to the user.

the first acquisition sub-module is used for acquiring a target label corresponding to the information type from the user label based on the preset information type;

a first determining submodule, configured to determine a customer group type corresponding to the user based on the target tag;

and the inquiring sub-module is used for inquiring the products matched with the customer group types from the product set to be recommended to obtain the first products.

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

the second acquisition sub-module is used for acquiring user evaluation information corresponding to the historical price inquiry records;

the first screening submodule is used for screening out evaluation contents related to the product description from the user evaluation information;

and the second determination submodule is used for analyzing the evaluation content based on a preset analysis rule and determining the product preference type corresponding to the user.

In some optional implementations of the present embodiments, the artificial intelligence based product recommendation device further includes:

the second acquisition module is used for acquiring product purchase information of the target customer and acquiring specified product information of a preset product;

a second construction module for constructing a sample data set based on the product purchase information and the specified product information;

a third determining module, configured to determine a training data set and a test data set from the sample data set based on a preset proportion;

the training module is used for training a preset classification model by using the training data set to obtain an initial purchase prediction model;

and the verification module is used for verifying the initial purchase prediction model by using the test set, and if the obtained classification accuracy is greater than a preset accuracy threshold, training is finished, and the initial purchase prediction model is used as the purchase prediction model.

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

a third obtaining sub-module, configured to obtain, from the user tag, income information and family status information of the user;

a second generation sub-module for generating a purchase amount threshold of the user based on the income information and the family status information;

a second screening sub-module, configured to screen a third product from the second products, where the third product is smaller than the purchase limit threshold;

and the third determining submodule is used for taking the third product as the target product.

the sorting sub-module is used for sorting the second products according to the order of the purchase probability from high to low to obtain corresponding sorting results;

a fourth determination submodule for determining a target number;

a fourth obtaining sub-module, configured to obtain a fourth insurance of a target number from front to back in the sorting result;

And a fifth determining submodule, configured to take the fourth insurance as the target insurance.

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 product 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 product 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, user data is acquired; then constructing a user tag of the user based on the user data, and acquiring a first product corresponding to the user tag from a product set to be recommended; then, acquiring a historical price inquiring record corresponding to the user, and determining a product preference type corresponding to the user based on the historical price inquiring record; subsequently screening a second product from the first product based on the product preference type; further acquiring product information of the second product, processing the product information and the historical product purchase information based on a preset purchase prediction model, and generating purchase probability of the user purchasing the second product; and finally, determining a target product from the second product based on the purchase probability, and pushing the target product to the user. According to the method and the device for automatically selecting the product to be recommended, the user data of the user and the historical price inquiry records are analyzed to perform primary screening on the product set to be recommended, further products after primary screening are further screened based on the use of the purchase prediction model, and therefore target products meeting the purchase tendency of the user can be automatically and accurately generated and pushed.

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 product 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 (such as ROM/RAM, magnetic disk, optical disk), comprising several 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 described in the embodiments of the present application.

It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present 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, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.

Claims

1. The product recommending method based on artificial intelligence is characterized by comprising the following steps of:

2. The method for recommending products based on artificial intelligence according to claim 1, wherein the step of constructing the user tag of the user based on the user data comprises the steps of:

Calling a preset user analysis model;

inputting the user data into the user analysis model;

3. The method for recommending products based on artificial intelligence according to claim 1, wherein the step of acquiring the first product corresponding to the user tag from the product set to be recommended specifically comprises:

4. The artificial intelligence based product recommendation method according to claim 1, wherein said step of determining a product preference type corresponding to said user based on said historical price inquiry record comprises:

5. The method for recommending products based on artificial intelligence according to claim 1, wherein before the step of processing the product information and the historical product purchase information based on a preset purchase prediction model to generate the purchase probability of the user purchasing the second product, the method specifically comprises:

6. The method for recommending products based on artificial intelligence according to claim 1, wherein the step of determining the target product from the second products based on the purchase probability comprises:

and taking the third product as the target product.

7. The method for recommending products based on artificial intelligence according to claim 1, wherein the step of determining the target product from the second products based on the purchase probability comprises:

determining a target number;

and taking the fourth insurance as the target insurance.

8. An artificial intelligence based product 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 product 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 product recommendation method according to any of claims 1 to 7.