CN114663198A

CN114663198A - Product recommendation method, device and equipment based on user portrait and storage medium

Info

Publication number: CN114663198A
Application number: CN202210439883.0A
Authority: CN
Inventors: 孙裕
Original assignee: Weikun Shanghai Technology Service Co Ltd
Current assignee: Weikun Shanghai Technology Service Co Ltd
Priority date: 2022-04-25
Filing date: 2022-04-25
Publication date: 2022-06-24

Abstract

The invention relates to an artificial intelligence technology, and discloses a product recommendation method based on a user portrait, which comprises the following steps: acquiring user information of a training user, and determining a plurality of training user labels with different dimensions according to the user information; constructing a user portrait of a training user according to a plurality of training user labels; acquiring product information corresponding to a training user, constructing a training sample according to the product information and the user portrait, and performing machine learning on the training sample to obtain a prediction model of a user recommended product; acquiring a user portrait of a user to be recommended and a preset recommended product set, and inputting the user portrait of the user to be recommended and the recommended product set into a prediction model to obtain a recommended product prediction result of the user portrait; and recommending the product to the user to be recommended corresponding to the user image according to the product prediction result. The invention also provides a product recommendation device, equipment and a storage medium based on the user portrait. The invention can improve the precision of product recommendation to the user.

Description

Product recommendation method, device and equipment based on user portrait and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a product recommendation method, device and equipment based on user portrait and a storage medium.

Background

With the development of big data technology and the diversification of people's demands, all industries begin to analyze the data of enterprises and clients, improve the popularization degree of products, screen out users who accord with the products from a large amount of users to recommend the products, and then achieve the effects of improving user satisfaction and adjusting industrial structures, wherein, the analysis method of user portraits gradually plays more and more important roles in the fields of product recommendation and the like.

At present, the user portrait analysis method mainly analyzes historical information and basic information of a target user, and then matches an analysis result with characteristics of an enterprise product to achieve the purpose of pushing the product. The existing product recommendation technology is mostly based on single characteristics to realize the matching of users and products, and further carries out product recommendation on the users. For example, applicable products are recommended to users of different age groups based on age attributes. In practical application, different users have multiple factors which can influence requirements, and only considering a single attribute may result in too single product recommendation mode, so that the accuracy of product recommendation for the users is low.

Disclosure of Invention

The invention provides a product recommendation method, a product recommendation device, product recommendation equipment and a storage medium based on user portrait, and mainly aims to solve the problem of low product recommendation accuracy of a user.

In order to achieve the above object, the present invention provides a product recommendation method based on a user portrait, comprising:

acquiring user information of a training user, and determining a plurality of training user labels with different dimensions according to the user information;

constructing a user portrait of the training user according to a plurality of training user labels;

acquiring product information corresponding to the training user, constructing a training sample according to the product information and the user portrait, and performing machine learning on the training sample to obtain a prediction model of a user recommended product;

acquiring a user portrait of a user to be recommended and a preset recommended product set, and inputting the user portrait of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user portrait;

and recommending the product for the user to be recommended corresponding to the user portrait according to the product prediction result.

Optionally, the constructing a user representation of the training user according to the plurality of training user tags includes:

obtaining label characters corresponding to a plurality of labels of the training users, and analyzing the label characters to obtain an incidence relation among the labels of the training users;

and connecting the plurality of training user labels according to the incidence relation to obtain a user portrait of the training user represented by the tree structure.

Optionally, the performing machine learning on the training samples to obtain a prediction model of a product recommended by a user includes:

acquiring a pre-constructed initialization prediction model, and sequentially introducing a training sample into the initialization prediction model;

carrying out forward propagation calculation on the training sample by using an initial activation function in the initialized prediction model to obtain a calculation result;

calculating a loss value between the calculation result and a value corresponding to the training sample according to a cross entropy algorithm;

according to a gradient descent method, minimizing the loss value to obtain a function parameter when the loss value is minimum;

performing back propagation on the function parameters, and updating the model parameters of the initialized prediction model to obtain an updated prediction model;

recording the loss value, and judging whether the loss value is converged;

when the loss value is not converged, returning to the step of sequentially introducing a training sample into the initialized prediction model;

and when the loss value is converged, outputting the updated prediction model updated for the last time to obtain the prediction model.

Optionally, the inputting the user representation of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user representation includes:

configuring the prediction model by using a preset recommended product set, and performing feature extraction on the user portrait of the user to be recommended by using a feature extraction network in the configured prediction model to obtain a feature sequence set;

and performing matching calculation on the feature sequence set by using an operation layer in the prediction model to obtain a tendency prediction value corresponding to each recommended product in the recommended product set by the user to be recommended.

Optionally, the determining a plurality of training user labels of different dimensions according to the user information includes:

extracting information characteristics of the user information;

and identifying the information category of the information characteristic, and determining a plurality of training user labels with different dimensions according to the information category.

Optionally, the recommending a product to a user to be recommended corresponding to the user representation according to the product prediction result includes:

selecting a product of which the product prediction result is greater than a preset threshold value as a recommended product of the user to be recommended;

and arranging the recommended products into a recommended list, and displaying the recommended products according to the sequence in the recommended list according to preset time.

Optionally, after the product is recommended to the user to be recommended corresponding to the user representation according to the product prediction result, the method further includes:

obtaining feedback data of a result of recommending the product by the user to be recommended, and determining a feedback type of the feedback data;

and marking the user portrait of the user to be recommended according to the feedback type to obtain an updated user portrait.

In order to solve the above problem, the present invention further provides a product recommendation apparatus based on a user profile, the apparatus comprising:

the training user label generation module is used for acquiring user information of a training user and determining a plurality of training user labels with different dimensions according to the user information;

the user portrait construction module is used for constructing a user portrait of the training user according to the plurality of training user labels;

the prediction model generation module is used for acquiring product information corresponding to the training user, constructing a training sample according to the product information and the user portrait, and performing machine learning on the training sample to obtain a prediction model of a user recommended product;

the recommended product prediction result generation module is used for acquiring a user portrait of a user to be recommended and a preset recommended product set, and inputting the user portrait of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user portrait;

and the product recommendation module is used for recommending the product to the user to be recommended corresponding to the user portrait according to the product prediction result.

In order to solve the above problem, the present invention also provides an electronic device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the user representation-based product recommendation method described above.

In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the user representation-based product recommendation method described above.

According to the embodiment of the invention, the user information is acquired, the user tags with different dimensions are determined according to the user information, and the user tags with different dimensions are established by identifying the user information, so that the accuracy of subsequent user images is improved conveniently; the method comprises the steps that machine learning is carried out on user portraits and corresponding product information, a prediction model of a user recommended product with a recommended product prediction result and the user portraits as influence factors is constructed, and an enterprise can know which products in a preset recommended product set conform to the user portraits through the prediction model and the user portraits of users to be recommended; in addition, the prediction model of the user recommended product has higher accuracy and efficiency. Therefore, the product recommendation method and device based on the user portrait, the electronic equipment and the computer readable storage medium provided by the invention can solve the problem of low product recommendation accuracy for the user.

Drawings

FIG. 1 is a flowchart illustrating a method for user representation based product recommendation according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart illustrating a process of generating a predictive model of a user-recommended product according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating a method for generating a predicted result of a recommended product of a user representation according to an embodiment of the invention;

FIG. 4 is a functional block diagram of a user representation-based product recommendation device according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device implementing the user representation-based product recommendation method according to an embodiment of the present invention.

The objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a product recommendation method based on a user portrait. The execution subject of the product recommendation method based on the user portrait includes, but is not limited to, at least one of the electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the user representation-based product recommendation method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Referring to fig. 1, a flowchart of a product recommendation method based on a user portrait according to an embodiment of the present invention is shown. In this embodiment, the user profile-based product recommendation method includes the following steps S1-S5:

s1, obtaining user information of the training user, and determining a plurality of training user labels with different dimensions according to the user information.

In the embodiment of the present invention, the user information refers to basic information of a user, user behaviors such as access, browsing, and purchasing on a preset platform, an active time period of the user, and the like. For example, wherein the basic information comprises: gender, age, living city, etc. of the user; the active time period is as follows: a high frequency interaction time interval of the user; the basic information includes: browsing behavior, accumulation behavior, etc.

Specifically, the user information of the training user can be obtained by performing data embedding on a webpage, a product page and registration information.

In the embodiment of the invention, the user information can be called from a pre-constructed storage area for storing the user information of the training user through a preset external interface or through a computer script with a data grabbing function, such as a java script or python. In detail, the storage area includes, but is not limited to: database, block chain node, network cache.

In detail, the determining a plurality of training user labels of different dimensions according to the user information includes:

extracting information characteristics of the user information;

In an embodiment of the invention, the information features are key information extracted based on user information, for example, a user a purchases an xx brand car insurance and consumes xx elements in total, the information features can be a purchase, an enterprise brand, an insurance type and a consumption amount, and redundant data can be reduced through information feature extraction so as to improve the speed of subsequently generating the label.

In another embodiment of the present invention, the information category may also be a category to which user information identified based on information features belongs, for example, a B user browses disease insurance and car insurance on a preset insurance platform, purchases a car insurance, and pays off after selling the car insurance, and may identify the information category as three categories of insurance browsing, insurance purchasing, and insurance selling, and may determine a plurality of user tags with different dimensions according to different information categories.

In another embodiment of the present invention, after determining a plurality of training user labels with different dimensions according to the user information, the method further includes: and deleting the abnormal value and the null value in the training user label to obtain the training user label with the abnormal value and the null value deleted.

In the embodiment of the invention, the data quality of the training user labels can be improved by cleaning the data of the training user labels with different dimensions, and the deletion of the abnormal values and the null values can be realized by a normal distribution algorithm.

And S2, constructing a user portrait of the training user according to the plurality of training user labels.

In the embodiment of the invention, the user image means that the image of the training user is embodied by using the label of the training user, and the characteristic of the training user can be reflected.

In detail, the constructing a user representation of the training user according to the plurality of training user tags includes:

In an embodiment of the present invention, the training user tags may be input to a preset converter (e.g., a able converter) to obtain characters corresponding to the training user tags, and the tag characters are analyzed by a preset association algorithm (e.g., Apriori algorithm) to obtain association relationships among a plurality of training user tags. For example, the plurality of training user labels may be basic information such as name, age, occupation, etc., behavior information such as browsing, purchasing, after-sales, etc., and then the association between the name, age, occupation, and basic information, and the association between the browsing, purchasing, after-sales, behavior information are determined by Apriori algorithm.

In another embodiment of the invention, the user portrait can be obtained by connecting according to the association relationship and the tree structure. For example, the name, age and occupation labels are respectively connected to the basic information, the browsing, purchasing and after-sale labels are respectively connected to the behavior information, and then the basic information and the behavior information are connected to the user portrait to obtain the user portrait of the training user represented by the tree structure.

And S3, obtaining product information corresponding to the training user, constructing a training sample according to the product information and the user portrait, and performing machine learning on the training sample to obtain a prediction model of the user recommended product.

In the embodiment of the invention, in order to construct a model capable of predicting the selection tendency of a user on each product, a set of user portrait and product information is required to be used as an influence factor of model prediction, and a recommended product prediction result is used as a prediction result of the model, so that the embodiment of the invention can construct a key value pair by using the set of the user portrait and various product information as a key and using the product information corresponding to a training user as a key value, thereby obtaining a training sample.

In the embodiment of the invention, one training user corresponds to one training sample, and in order to construct a prediction model of a user recommended product, a plurality of training users and corresponding training samples need to be obtained.

In the embodiment of the invention, the prediction model can be a logistic regression judgment model based on a neural network, and comprises an input layer, an operation layer and an output layer.

Referring to fig. 2, in the embodiment of the present invention, the performing machine learning on the training samples to obtain the prediction model of the user recommended product includes steps S21 to S27:

s21, obtaining a pre-constructed initialization prediction model, and sequentially introducing a training sample into the initialization prediction model;

s22, performing forward propagation calculation on the training sample by using an initial activation function in the initialized prediction model to obtain a calculation result;

s23, calculating a loss value between the calculation result and a value corresponding to the training sample according to a cross entropy algorithm;

s24, minimizing the loss value according to a gradient descent method to obtain a function parameter when the loss value is minimum;

s25, performing back propagation on the function parameters, and updating the model parameters of the initialized prediction model to obtain an updated prediction model;

s26, recording the loss value, and judging whether the loss value is converged;

when the loss value does not converge, returning to S21;

and when the loss value is converged, executing S27, and outputting the updated prediction model updated last time to obtain the prediction model.

In the embodiment of the present invention, the initial activation function is located in the operation layer, and the initial activation function is a gaussian normal distribution function:

X～N(μ，σ²)

in the formula, the value X of the random variable X_iAnd its corresponding probability value P (X ═ X)_i) Satisfy the normal distribution, i ═ 1, 2, 3 … …, mu, sigma²Are model parameters.

In the embodiment of the invention, the initial activation function is utilized to analyze the user portrait in a training sample to obtain a calculation result, and then the calculation result is compared with a value (course selection behavior) corresponding to the training sample through a cross entropy algorithm to obtain a loss value. In order to make the difference between the calculation result and the value smaller, in the embodiment of the present invention, a minimization operation is performed on the loss value to obtain a function parameter when the loss value is the minimum, so that the function parameter is used to update the model parameter of the initialized prediction model to obtain an updated prediction model, so that the training process of one training sample is completed, and the step of S21 is returned to perform the training of the next training sample. The cross entropy algorithm is a method for solving the difference between a target and a predicted value, and can also avoid the problem of the decline of the learning rate when the gradient declines.

In the embodiment of the invention, when the variation amplitude of the loss value is small (i.e. convergence), the model parameters of the initialized prediction model are gradually stable, and an updated prediction model is obtained, otherwise, training is continued.

S4, obtaining a user portrait of a user to be recommended and a preset recommended product set, and inputting the user portrait of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user portrait.

In the embodiment of the present invention, the preset recommended product set refers to various products included in an enterprise.

Referring to fig. 5, in the embodiment of the present invention, the step of inputting the user representation of the user to be recommended and the recommended product set into the prediction model to obtain the recommended product prediction result of the user representation includes steps S31-S32:

s31, configuring the prediction model by using a preset recommended product set, and performing feature extraction on the user portrait of the user to be recommended by using a feature extraction network in the configured prediction model to obtain a feature sequence set;

and S32, performing matching calculation on the feature sequence set by using an operation layer in the prediction model to obtain a tendency prediction value corresponding to each recommended product in the recommended product set by the user to be recommended.

In the embodiment of the invention, the output layer of the prediction model is configured by using the recommended product set, then the feature extraction network in the prediction model is used for performing feature extraction operations such as convolution, pooling, full connection and the like on the user portrait of the user to be recommended to obtain a feature sequence set, then the feature sequence set is subjected to feature identification to obtain an identification result, and finally the identification result is matched with each recommended product in the recommended product set through the operation layer to obtain a tendency prediction value corresponding to each recommended product, wherein the tendency prediction value is the recommended product prediction result of the user portrait.

And S5, recommending the product to the user to be recommended corresponding to the user portrait according to the product prediction result.

In an embodiment of the present invention, recommending a product to a user to be recommended corresponding to the user portrait according to the product prediction result includes:

and sorting the recommended products into a recommended list, and displaying the recommended products according to the preset time and the sequence in the recommended list.

In an embodiment of the present invention, after recommending a product to a user to be recommended corresponding to the user representation according to the product prediction result, the method further includes:

Specifically, the feedback type may include positive feedback and negative feedback, and the embodiment of the present invention may add the feedback type to the user portrait in the form of an additional field, so as to complete the user portrait; or the feedback type can be recorded as a label and added to the user portrait in a label form, so that the user portrait of the user to be recommended is perfected; or the user representation of the user to be recommended, the feedback type and the product recommendation result can be input into the prediction model for training, and the prediction model is updated to realize the product recommendation of other subsequent users to be recommended.

According to the embodiment of the invention, the user information is obtained, the user labels with different dimensions are determined according to the user information, and the user labels with different dimensions are established by identifying the user information, so that the accuracy of the subsequent user picture is improved conveniently; the method comprises the steps that machine learning is carried out on user portraits and corresponding product information, a prediction model of a user recommended product with a recommended product prediction result and the user portraits as influence factors is constructed, and an enterprise can know which products in a preset recommended product set conform to the user portraits through the prediction model and the user portraits of users to be recommended; in addition, the prediction model of the user recommended product has higher accuracy and efficiency. Therefore, the product recommendation method based on the user portrait can solve the problem that the product recommendation accuracy of the user is low.

FIG. 4 is a functional block diagram of a product recommendation device based on a user representation according to an embodiment of the present invention.

The product recommendation device 100 based on user portrait can be installed in an electronic device. According to the realized functions, the product recommending device 100 based on the user portrait can comprise a training user label generating module 101, a user portrait constructing module 102, a prediction model generating module 103, a recommended product prediction result generating module 104 and a product recommending module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions of the respective modules/units are as follows:

the training user label generating module 101 is used for acquiring user information of a training user and determining a plurality of training user labels with different dimensions according to the user information;

the user portrait construction module 102 is configured to construct a user portrait of the training user according to a plurality of training user tags;

the prediction model generation module 103 is configured to obtain product information corresponding to the training user, construct a training sample according to the product information and the user portrait, and perform machine learning on the training sample to obtain a prediction model of a user recommended product;

the recommended product prediction result generation module 104 is configured to obtain a user portrait of a user to be recommended and a preset recommended product set, and input the user portrait of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user portrait;

and the product recommending module 105 is configured to recommend a product to the user to be recommended corresponding to the user figure according to the product predicting result.

In detail, in the embodiment of the present invention, when the modules in the product recommendation device 100 based on a user profile are used, the same technical means as the product recommendation method based on a user profile described in fig. 1 to 5 is adopted, and the same technical effects can be produced, which is not described herein again.

Fig. 5 is a schematic structural diagram of an electronic device for implementing a user-portrait-based product recommendation method according to an embodiment of the present invention.

The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a user representation-based product recommendation program, stored in the memory 11 and executable on the processor 10.

In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory 11 (for example, executing a product recommendation program based on a user profile, etc.) and calling data stored in the memory 11.

The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of a product recommendation program based on a user profile, but also to temporarily store data that has been output or is to be output.

The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The user-image-based product recommendation program stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:

Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.

Further, the integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:

and recommending the product to the user to be recommended corresponding to the user portrait according to the product prediction result.

In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain 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.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

Furthermore, it will be obvious that the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the same, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A user representation-based product recommendation method, the method comprising:

2. The user representation-based product recommendation method of claim 1, wherein said constructing a user representation of said training user based on a plurality of said training user tags comprises:

3. The user representation-based product recommendation method of claim 1, wherein the performing machine learning on the training samples to obtain a predictive model of a user recommended product comprises:

recording the loss value, and judging whether the loss value is converged;

4. The user representation-based product recommendation method of claim 1, wherein said inputting the user representation of the user to be recommended and the recommended product set into the prediction model to obtain a recommended product prediction result of the user representation comprises:

5. The user representation-based product recommendation method of claim 1, wherein said determining a plurality of training user labels of different dimensions from said user information comprises:

extracting information characteristics of the user information;

6. The method of claim 1, wherein recommending a product to a user to be recommended that corresponds to the user representation based on the product forecast comprises:

7. The user representation-based product recommendation method of any one of claims 1-6, wherein after performing product recommendation on the user to be recommended corresponding to the user representation according to the product prediction result, the method further comprises:

8. A user representation based product recommendation device, the device comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the user representation-based product recommendation method of any of claims 1-7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the user representation-based product recommendation method of any one of claims 1-7.