CN114925275A

CN114925275A - Product recommendation method and device, computer equipment and storage medium

Info

Publication number: CN114925275A
Application number: CN202210579285.3A
Authority: CN
Inventors: 徐祥瑞
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-05-25
Filing date: 2022-05-25
Publication date: 2022-08-19

Abstract

The embodiment of the application belongs to the field of artificial intelligence and relates to a product recommendation method, a product recommendation device, computer equipment and a storage medium, wherein the method comprises the following steps: product investigation feedback information of a target customer is obtained and input into a characteristic prediction model, and first characteristic range information of an initial product is obtained; acquiring second characteristic range information of the initial product based on the product specification text; generating a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and respectively generating candidate products of the initial product according to the product feature combinations; calculating a product evaluation value of the candidate product based on the product characteristics of the candidate product; and screening each candidate product according to the product evaluation value, and recommending the screened candidate product as a target product to a target customer. In addition, the application also relates to a block chain technology, and the product survey feedback information can be stored in the block chain. The method and the device improve the accuracy of product recommendation.

Description

Product recommendation method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for recommending a product, a computer device, and a storage medium.

Background

As computers have evolved, it has become more common to perform specific problem solving and policy optimization through artificial intelligence related algorithms. For example, in the field of weiqi, *** developed Al phaGo has prevailed over the human world champion, showing the great advantage of artificial intelligence algorithms in applications in various fields.

Product recommendations are an extremely common activity in daily life. Products often have a plurality of characteristics, each characteristic has characteristic parameters, and specific characteristic parameters of the characteristics need to be determined when the products are designed and recommended. However, current product designs are usually based on manual experience and understanding, and due to the limitations of personal experience and visual field, it is often difficult to find products suitable for customers, so that the accuracy of product recommendation is low.

Disclosure of Invention

An object of the embodiments of the present application is to provide a product recommendation method, apparatus, computer device, and storage medium, so as to solve the problem of low product recommendation accuracy.

In order to solve the above technical problem, an embodiment of the present application provides a product recommendation method, which adopts the following technical solutions:

obtaining product investigation feedback information of a target client;

inputting the product investigation feedback information into a characteristic prediction model to obtain first characteristic range information of an initial product;

acquiring second characteristic range information of the initial product based on the product specification text;

generating a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and respectively generating candidate products of the initial product according to the product feature combinations;

for each candidate product, calculating a product evaluation value of the candidate product based on the product characteristics of the candidate product;

and screening each candidate product according to the product evaluation value, and recommending the screened candidate product as a target product to the target customer.

In order to solve the above technical problem, an embodiment of the present application further provides a product recommendation device, which adopts the following technical solutions:

the information acquisition module is used for acquiring product investigation feedback information of a target client;

the first acquisition module is used for inputting the product survey feedback information into a characteristic prediction model to obtain first characteristic range information of an initial product;

the second acquisition module is used for acquiring second characteristic range information of the initial product based on the product specification text;

a candidate generating module, configured to generate a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and generate candidate products of the initial product according to the product feature combinations respectively;

an evaluation value calculation module for calculating, for each candidate product, a product evaluation value of the candidate product based on a product feature of the candidate product;

and the candidate screening module is used for screening each candidate product according to the product evaluation value and recommending the screened candidate product as a target product to the target customer.

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

obtaining product investigation feedback information of a target client;

inputting the product survey feedback information into a characteristic prediction model to obtain first characteristic range information of an initial product;

In order to solve the foregoing technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:

obtaining product investigation feedback information of a target client;

acquiring second characteristic range information of the initial product based on a product specification text;

Compared with the prior art, the embodiment of the application mainly has the following beneficial effects: firstly, product investigation feedback information reflecting the tendency and preference of a target customer product is obtained, the product investigation feedback information is input into a characteristic prediction model, and first characteristic range information of an initial product is obtained, wherein the first characteristic range information is a variation range of product characteristics obtained from a target customer level; the product specification text is a text for performing specification limitation on a product, and second characteristic range information is obtained according to the product specification text; determining all possible product feature combinations of the initial product according to an enumeration algorithm by taking the first feature range information and the second feature range information as limiting conditions, and adjusting the initial product according to the product feature combinations to obtain a plurality of candidate products; the product evaluation value of the candidate product is calculated according to the product characteristics of the candidate product, the product evaluation value represents the value and the recommendability of the product in the form of a numerical value, and the candidate product is selected as the target product according to the product evaluation value to recommend the product to the target client, so that the product with high pertinence and adaptability is automatically recommended to the target client, and the product recommendation accuracy is improved.

Drawings

In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.

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

FIG. 2 is a flow diagram of one embodiment of a product recommendation method according to the present application;

FIG. 3 is a schematic block diagram of one embodiment of a product recommendation device according to the present application;

FIG. 4 is a schematic block 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 application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase 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. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping application, a search 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 a smart phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture experts Group Audio Layer III, motion Picture experts compression standard Audio Layer 3), an MP4 player (Moving Picture experts Group Audio Layer IV, motion Picture experts compression standard Audio Layer 4), a laptop portable computer, a desktop computer, 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 provided in the embodiments of the present application is generally executed by a server, and accordingly, the product recommendation device is generally disposed in the server.

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 diagram of one embodiment of a product recommendation method in accordance with the present application is shown. The product recommendation method comprises the following steps:

and step S201, obtaining product survey feedback information of the target customer.

In this embodiment, the electronic device (for example, the server shown in fig. 1) on which the product recommendation method operates may communicate with the terminal through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G/5G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.

Wherein the product survey feedback information may be feedback information of the target customer in the product survey.

Specifically, product survey may be performed on the target customer in advance, and product survey feedback information of the target customer may be acquired. For example, when the product is an insurance product, the following dimensions of information can be gathered at the time of product investigation: the loan interest rate interval is accepted, the loan intention probability, whether credit is available, the loan purpose, the loan duration, the application mode (online/offline), the repayment capability, the repayment intention, the autonomous application capability and the like. And then using the collected information as product investigation feedback information.

It is emphasized that, to further ensure the privacy and security of the product survey feedback information, the product survey feedback information may also be stored in a node of a blockchain.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

Step S202, inputting the product survey feedback information into a characteristic prediction model to obtain first characteristic range information of the initial product.

The first characteristic range information can be value range information of product characteristics and can be obtained according to product survey feedback information. The initial product can be a certain type of product which is established in advance and comprises a plurality of product characteristics, and the values of the product characteristics can be set in a personalized way according to target customers.

Specifically, after the product survey feedback information is obtained, the product survey feedback information is input into the feature prediction model, and the feature prediction model is trained in advance and may include a plurality of sub models, and each sub model corresponds to one product feature. The submodels output possible ranges of product characteristics according to input product investigation feedback information, and output results of the submodels form first characteristic range information of the initial product.

Further, the step S202 may include: and inputting the product investigation feedback information into the trained characteristic prediction model to obtain first characteristic range information of the initial product, wherein the characteristic prediction model is a tree model.

Specifically, product survey feedback information is input into the trained feature prediction model. The feature prediction model may be a tree model, such as an XGBOOST, GBDT, or the like. The feature prediction model can predict all possible values of the product features according to the product survey feedback information.

The product characteristics may be various, for example, when the product is a loan product, the product characteristics may include a loan amount, a loan interest rate, an advertisement delivery channel, a customer manager's contribution, whether the product is a credit loan, a loan term, a repayment method, an application method, a collateral, a rating level, a risk level, and the like.

The feature prediction model can output all possible values of each product feature respectively, and all possible values of each product feature form first feature range information of the initial product.

In this embodiment, the feature prediction model is a tree model, and first feature range information suitable for a target customer can be accurately output according to product survey feedback information.

Step S203, second characteristic range information of the initial product is obtained based on the product specification text.

The product specification text may be a text for performing specification limitation on a product, such as relevant laws and regulations, regulatory information, or specification information inside a product provider.

Specifically, the setting of the product characteristics needs to satisfy a product specification text in addition to considering the intention of the target customer, and also needs to acquire the product specification text, and determine second characteristic range information of the initial product according to the product specification text.

And step S204, generating a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and respectively generating candidate products of the initial product according to the product feature combinations.

Specifically, the first feature range information and the second feature range information specify possible values of product features from two levels, a target customer and a product specification text. And combining all possible values of the product features through an enumeration algorithm based on the first feature range information and the second feature range information to obtain all product feature combinations.

And setting the product characteristics of the initial product according to the product characteristic combination to obtain a candidate product. The product characteristics of the candidate product take into account the willingness preferences of the target customer and the product specification text.

In step S205, for each candidate product, a product evaluation value of the candidate product is calculated based on the product characteristics of the candidate product.

Specifically, there are a plurality of candidate products obtained, and the candidate products need to be screened. The product evaluation value of the candidate product can be calculated, and the candidate product is screened according to the product evaluation value. The product evaluation value is a numerical value reflecting the value of the product to a product designer, a target customer, and the recommendability of a candidate product. In one embodiment, the higher the product valuation value, the better the candidate product is represented.

And S206, screening each candidate product according to the product evaluation value, and recommending the screened candidate product as a target product to a target customer.

Specifically, the product evaluation values are arranged in a descending order, a candidate product corresponding to the top N (N is a preset value, and N is a positive integer) product evaluation values can be selected as a target product, and then the target product is pushed to a target customer to complete product recommendation.

In the embodiment, product investigation feedback information reflecting the product tendency and preference of a target client is obtained first, and the product investigation feedback information is input into a characteristic prediction model to obtain first characteristic range information of an initial product, wherein the first characteristic range information is a variation range of product characteristics obtained from a target client level; the product specification text is a text for performing specification limitation on a product, and second characteristic range information is obtained according to the product specification text; determining all possible product feature combinations of the initial product according to an enumeration algorithm by taking the first feature range information and the second feature range information as limiting conditions, and adjusting the initial product according to the product feature combinations to obtain a plurality of candidate products; the product evaluation value of the candidate product is calculated according to the product characteristics of the candidate product, the product evaluation value represents the value and the recommendability of the product in the form of a numerical value, and the candidate product is selected as the target product according to the product evaluation value to recommend the product to the target client, so that the product with high pertinence and adaptability is automatically recommended to the target client, and the product recommendation accuracy is improved.

Further, after the step S201, the method may further include: acquiring client information of a target client; determining a client community to which the target client belongs based on the client characteristics in the client information; acquiring product characteristic statistical information corresponding to a product pool of a customer community; and determining first characteristic range information of the initial product according to the product characteristic statistical information.

The customer information may be information of a target customer, including various customer characteristics such as gender, age, region, income, work, and the like.

Specifically, the present application may also determine the first feature range information by another embodiment. The method comprises the steps of obtaining client information of a target client, and grouping the clients according to client characteristics in the client information to obtain a plurality of client communities. When the client society is divided, the larger the number of the selected client features is, the more the community is obtained. The purpose of dividing the client community is to recommend products, and many client communities can be set in order to improve the accuracy of product recommendation.

The client community to which the target client belongs has a product pool, which may be a collection of existing products of each client in the client community. And counting the product distribution in the product pool from the dimension of the product characteristics to obtain product characteristic statistical information. For example, according to the product feature of "interest rate", the product distribution in the product pool is counted to obtain that a% of the customer's existing product interest rates in the product pool are (c%, d%).

The product characteristic statistical information reflects the distribution and the preference of the existing products of the clients in the client community to which the target client belongs, and possible values of the product characteristics can be determined according to the product characteristic statistical information.

In the embodiment, the client community to which the target client belongs is determined, the product characteristic statistical information corresponding to the product pool of the client community is obtained, the product characteristic statistical information reflects the preference of the client community, the first characteristic range information is determined according to the product characteristic statistical information, and the adaptability of the first characteristic range information and the target client is ensured.

Further, the step of determining the first characteristic range information of the initial product according to the product characteristic statistical information may include: acquiring the product characteristics of an initial product; when the product features are category features, acquiring feature categories of the product features from the product feature statistical information; when the product characteristics are numerical characteristics, determining the value range of the product characteristics according to the product characteristic statistical information; and determining the acquired feature category or value range as first feature range information of the initial product.

Specifically, product characteristics of the initial product are respectively obtained, and the product characteristics can be classified into category characteristics and numerical characteristics according to types. The numerical characteristic is a characteristic that is itself numerical, and the category characteristic is a characteristic that is not numerical, for example, for a loan product, the repayment mode of the product characteristic is a category characteristic, and the loan amount is a numerical characteristic.

For the numerical features, all the feature categories that appear can be obtained from the product feature statistical information, and all the feature categories, or the feature categories of which the proportion exceeds a preset threshold value, are added to the first feature range information.

For numerical characteristics, the product characteristic statistical information can express the distribution of the product characteristics in normal distribution, an interval with a certain area can be selected on the horizontal axis, the value range of the product characteristics is obtained according to the horizontal coordinates of two endpoints of the interval, and the value range is added into the first characteristic range information. For example, (μ -2 σ, μ +2 σ) is taken from the normal distribution curve of the product characteristics a, the area of the section is 95.449974%, and a certain product characteristic of the product of 95.449974% of customers is distributed in the section, and the numerical value at both ends of the section is taken as the value range of the product characteristic.

In this embodiment, the first feature range information is determined in different ways according to the type of the product feature, so that the accuracy of the first feature range information is ensured.

Further, the step S203 may include: acquiring a product specification text; performing semantic analysis on the product specification text to obtain a semantic analysis result; and determining second characteristic range information of the initial product according to the semantic parsing result.

Specifically, a product specification text is obtained, and semantic analysis is performed on the product specification text to obtain a semantic analysis result. According to the semantic parsing result, which product features in the initial product are affected by the product specification text can be determined, and specific limits of the product specification text on the product features can be obtained according to the semantic parsing result. And according to the semantic parsing result, second characteristic range information of the initial product can be obtained. For example, if it is determined from the semantic analysis result that the collateral for a certain loan product cannot be B, the product feature of the collateral is indicated as "cannot be B" when the second feature range information is generated.

In one embodiment, the product specification text is time-sensitive, and the latest product specification text needs to be acquired to generate the second feature range information with the latest time-sensitivity.

In the embodiment, the semantic analysis is performed on the product specification text to automatically generate the second characteristic range information, so that the generation efficiency of the second characteristic range information is improved.

Further, the step S204 may include: calculating the intersection of the first characteristic range information and the second characteristic range information to obtain third characteristic range information; determining candidate values of the characteristics of the products through an enumeration algorithm based on the third characteristic range information; combining the candidate values of the product characteristics to obtain a product characteristic combination; and adjusting the initial product according to the product characteristic combination to obtain a candidate product.

Specifically, the first characteristic range information and the second characteristic range information are both limiting conditions of the initial product, and when the initial product is adjusted, the first characteristic range information and the second characteristic range information need to be satisfied at the same time. Therefore, the intersection of the first feature range information and the second feature range information may be obtained to obtain the third feature range information.

The third characteristic range information records possible values of each product characteristic, and enumerates all possible values of the product characteristic for each product characteristic to obtain a plurality of candidate values of the product characteristic. For the numerical value characteristics, enumeration fluctuation values of the product characteristics are predefined, and a plurality of candidate values are determined according to the enumeration fluctuation values. For example, the maximum value range of the product characteristic C is [8,10], and the enumeration fluctuation value of the product characteristic C is preset to be 0.2, that is, the interval of the product characteristic C needs to be changed according to 0.2 every time, so that a plurality of candidate value intervals of the product characteristic C are exhausted according to an enumeration algorithm.

And combining the candidate values of the product characteristics in an enumeration manner to obtain a plurality of product characteristic combinations, and respectively adjusting the candidate products according to the product characteristic combinations to obtain a plurality of candidate products.

In this embodiment, an intersection of the first feature range information and the second feature range information is calculated to obtain third feature range information, candidate values of product features are determined through an enumeration algorithm, and candidate values of product features are combined to obtain a product feature combination, so that all possible candidate products are obtained, and abundant candidate products are provided for product screening.

Further, the step S205 may include: for each candidate product, calculating a first gain evaluation value and a second gain evaluation value of the candidate product based on the product characteristics of the candidate product; and calculating a product evaluation value of the candidate product according to the first gain evaluation value and the second gain evaluation value.

Specifically, the product evaluation value may be measured in the form of a numerical value for the candidate product, and generally, the larger the product evaluation value, the better the candidate product is represented. The candidate product in the present application may be a loan product, an insurance product, and the like, and the product evaluation value is calculated by the first gain evaluation value and the second gain evaluation value.

The first gain evaluation value is an evaluation value of a gain of the candidate product to the product provider, for example, when the candidate product is a loan product, the first gain evaluation value may be a profit of the candidate product to the insurance company; the second gain estimate may be an estimate of the gain to the target customer, for example, when the candidate product is an insurance product, the second gain estimate may be the maximum gain available to the target customer. The calculation of the first gain estimation value and the second gain estimation value is related to the specific design and business logic of the product, and a specific calculation process is not carried out here.

A product evaluation value of the candidate product may be calculated based on the first gain evaluation value and the second gain evaluation value. In actual calculation, corresponding weights may be added to the first gain evaluation value and the second gain evaluation value, and then the weighted gain evaluation values are subjected to linear operation to obtain a product evaluation value.

In this embodiment, the candidate products are measured by the first gain evaluation value and the second gain evaluation value, and the product evaluation value is calculated according to the first gain evaluation value and the second gain evaluation value, so that the candidate products can be reasonably screened.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a 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, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a 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 according to the present embodiment includes: an information acquisition module 301, a first acquisition module 302, a second acquisition module 303, a candidate generation module 304, an evaluation value calculation module 305, and a candidate filtering module 306, wherein:

the information acquisition module 301 is configured to acquire product survey feedback information of a target customer.

The first obtaining module 302 is configured to input the product survey feedback information into the feature prediction model to obtain first feature range information of the initial product.

The second obtaining module 303 is configured to obtain second feature range information of the initial product based on the product specification text.

And the candidate generating module 304 is configured to generate a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and generate candidate products of the initial product according to the product feature combinations.

An evaluation value calculation module 305 for calculating, for each candidate product, a product evaluation value of the candidate product based on the product characteristics of the candidate product.

And the candidate screening module 306 is configured to screen each candidate product according to the product evaluation value, and perform product recommendation on the target customer by using the screened candidate product as a target product.

In some optional implementations of this embodiment, the first obtaining module 302 may be further configured to: and inputting the product investigation feedback information into the trained characteristic prediction model to obtain first characteristic range information of the initial product, wherein the characteristic prediction model is a tree model.

In some optional implementations of this embodiment, the product recommendation device 300 may further include: the system comprises an acquisition module, a community determination module, a statistic acquisition module and a first determination module, wherein:

and the acquisition module is used for acquiring the client information of the target client.

And the community determining module is used for determining the client community to which the target client belongs based on the client characteristics in the client information.

And the statistic acquisition module is used for acquiring the product characteristic statistic information corresponding to the product pool of the customer community.

And the first determining module is used for determining first characteristic range information of the initial product according to the product characteristic statistical information.

In some optional implementations of this embodiment, the first determining module may include: the device comprises a feature acquisition submodule, a category acquisition submodule, a range acquisition submodule and a first determination submodule, wherein:

and the characteristic acquisition submodule is used for acquiring the product characteristics of the initial product.

And the category obtaining submodule is used for obtaining the feature category of the product feature from the product feature statistical information when the product feature is the category feature.

And the range acquisition submodule is used for determining the value range of the product characteristics according to the product characteristic statistical information when the product characteristics are numerical characteristics.

And the first determining submodule is used for determining the acquired feature category or value range as first feature range information of the initial product.

In this embodiment, the first feature range information is determined in different manners according to the type of the product feature, so that the accuracy of the first feature range information is ensured.

In some optional implementations of this embodiment, the second obtaining module 303 may include: the text acquisition sub-module, the text analysis sub-module and the second determination sub-module, wherein:

and the text acquisition submodule is used for acquiring the product specification text.

And the text analysis submodule is used for carrying out semantic analysis on the product specification text to obtain a semantic analysis result.

And the second determining submodule is used for determining second characteristic range information of the initial product according to the semantic analysis result.

In this embodiment, the product specification text is subjected to semantic parsing to automatically generate the second feature range information, so that the generation efficiency of the second feature range information is improved.

In some optional implementations of this embodiment, the candidate generating module 304 may include: the device comprises an intersection calculation submodule, a candidate value determination submodule, a candidate value combination submodule and an initial adjustment submodule, wherein:

and the intersection calculation submodule is used for calculating the intersection of the first characteristic range information and the second characteristic range information to obtain third characteristic range information.

And the candidate value determining submodule is used for determining a candidate value of each product characteristic through an enumeration algorithm based on the third characteristic range information.

And the candidate value combination submodule is used for combining the candidate values of the product characteristics to obtain a product characteristic combination.

And the initial adjustment submodule is used for adjusting the initial product according to the product characteristic combination to obtain a candidate product.

In some optional implementations of the present embodiment, the evaluation value calculating module 305 may include: a gain calculation sub-module and an evaluation value calculation sub-module, wherein:

and the gain calculation sub-module is used for calculating a first gain evaluation value and a second gain evaluation value of each candidate product based on the product characteristics of the candidate product.

And the evaluation value calculation sub-module is used for calculating the product evaluation value of the candidate product according to the first gain evaluation value and the second gain evaluation value.

In order to solve the technical problem, the embodiment of the application further provides computer equipment. Referring to fig. 4, fig. 4 is a block diagram of a basic structure 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 is noted that only computer device 4 having components 41-43 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

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

The memory 41 includes at least one type of readable storage medium including flash memory, hard disks, multimedia cards, card-type 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 disks, optical disks, etc. In some embodiments, the memory 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 memory Card (Flash Card), and the like, provided on the computer device 4. Of course, the memory 41 may also include both internal and external storage devices of the computer device 4. In this embodiment, the memory 41 is generally used for storing an operating system installed in the computer device 4 and various application software, such as computer readable instructions of a product recommendation method. Further, the memory 41 may also 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 (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 computer readable instructions for executing the product recommendation method.

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

The computer device provided in this embodiment may execute the product recommendation method described above. Here, the product recommendation method may be the product recommendation method of each of the above embodiments.

The present application further provides another embodiment, which is to provide 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 product recommendation method as described above.

In the embodiment, product survey feedback information reflecting the product tendency and preference of a target customer is obtained first, and the product survey feedback information is input into a characteristic prediction model to obtain first characteristic range information of an initial product, wherein the first characteristic range information is a variation range of product characteristics obtained from a target customer level; the product specification text is a text for performing specification limitation on a product, and second characteristic range information is obtained according to the product specification text; determining all possible product feature combinations of the initial product according to an enumeration algorithm by taking the first feature range information and the second feature range information as limiting conditions, and adjusting the initial product according to the product feature combinations to obtain a plurality of candidate products; the product evaluation value of the candidate product is calculated according to the product characteristics of the candidate product, the product evaluation value represents the value and the recommendability of the product in the form of a numerical value, and the candidate product is selected as the target product according to the product evaluation value to recommend the product to the target client, so that the product with high pertinence and adaptability is automatically recommended to the target client, and the product recommendation accuracy is improved.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.

Claims

1. A method of recommending products, comprising the steps of:

acquiring product survey feedback information of a target client;

for each candidate product, calculating a product evaluation value of the candidate product based on the product features of the candidate product;

2. The product recommendation method of claim 1, wherein the step of inputting the product survey feedback information into a feature prediction model to obtain first feature range information of an initial product comprises:

and inputting the product investigation feedback information into a trained characteristic prediction model to obtain first characteristic range information of the initial product, wherein the characteristic prediction model is a tree model.

3. The product recommendation method according to claim 1, further comprising, after the step of obtaining product survey feedback information of the target customer:

acquiring customer information of the target customer;

determining a client community to which the target client belongs based on the client characteristics in the client information;

obtaining product characteristic statistical information corresponding to a product pool of the customer community;

and determining first characteristic range information of the initial product according to the product characteristic statistical information.

4. The product recommendation method according to claim 3, wherein the step of determining the first feature range information of the initial product according to the product feature statistical information comprises:

acquiring the product characteristics of the initial product;

when the product features are category features, acquiring feature categories of the product features from the product feature statistical information;

when the product characteristics are numerical characteristics, determining the value range of the product characteristics according to the product characteristic statistical information;

and determining the acquired feature category or value range as first feature range information of the initial product.

5. The product recommendation method according to claim 1, wherein the step of obtaining second feature range information of the initial product based on the product specification text comprises:

acquiring a product specification text;

performing semantic analysis on the product specification text to obtain a semantic analysis result;

and determining second characteristic range information of the initial product according to the semantic analysis result.

6. The product recommendation method according to claim 1, wherein the step of generating a product feature combination of the initial product by an enumeration algorithm based on the first feature range information and the second feature range information, and generating candidate products of the initial product according to the respective product feature combinations comprises:

calculating the intersection of the first characteristic range information and the second characteristic range information to obtain third characteristic range information;

determining a candidate value of each product characteristic through an enumeration algorithm based on the third characteristic range information;

combining the candidate values of the product characteristics to obtain a product characteristic combination;

and adjusting the initial product according to the product characteristic combination to obtain a candidate product.

7. The product recommendation method according to claim 1, wherein the step of calculating, for each candidate product, a product evaluation value of the candidate product based on the product feature of the candidate product comprises:

for each candidate product, calculating a first gain evaluation value and a second gain evaluation value of the candidate product based on the product characteristics of the candidate product;

and calculating a product evaluation value of the candidate product according to the first gain evaluation value and the second gain evaluation value.

8. A product recommendation device, comprising:

the information acquisition module is used for acquiring product survey feedback information of a target client;

the first acquisition module is used for inputting the product investigation feedback information into a characteristic prediction model to obtain first characteristic range information of an initial product;

a candidate generating module, configured to generate a product feature combination of the initial product through an enumeration algorithm based on the first feature range information and the second feature range information, and generate candidate products of the initial product according to the product feature combinations, respectively;

and the candidate screening module is used for screening each candidate product according to the product evaluation value, and recommending the screened candidate product as a target product to the target customer.

9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the product recommendation method of any of claims 1-7.

10. A computer-readable storage medium having computer-readable instructions stored thereon which, when executed by a processor, implement the steps of the product recommendation method of any of claims 1-7.