Product recommendation method and device, equipment, medium and product

Abstract

The invention discloses a product recommendation method and device, equipment, a medium and a product. The method comprises the following steps: acquiring user information and streaming media data of a target user; inputting the streaming media data into a trained network model to obtain product information corresponding to the streaming media data; and determining a recommended product of the target user based on the user information and the product information.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a product recommendation method, apparatus, device, medium and product. Background Art

[0002] With the development of computer computing, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into financial technology (Fintech). However, due to the security and real-time requirements of the financial industry, higher requirements are also put forward for technologies.

[0003] In the field of financial technology, financial products are usually recommended to users according to their search keywords. With the prevalence of streaming media, the streaming media information browsed by users can better reflect the product needs of users. However, in the related technologies, the business database cannot recommend corresponding financial products according to the streaming media data of users. Summary of the Invention

[0004] Embodiments of the present application provide a product recommendation method, apparatus, device, medium and product.

[0005] The technical solution of the embodiments of the present application is implemented as follows:

[0006] A product recommendation method, the method includes:

[0007] Obtain the user information and streaming media data of a target user;

[0008] Input the streaming media data into a trained network model to obtain product information corresponding to the streaming media data;

[0009] Determine a recommended product for the target user based on the user information and the product information.

[0010] In the above solution, before inputting the streaming media data into a trained network model to obtain product information corresponding to the streaming media data, it includes:

[0011] Obtain sample data; the sample data includes multiple groups of labeled streaming media data;

[0012] Input the sample data into a first sub-model of the network model to obtain a first product label for each group of the labeled streaming media data;

[0013] Input the first product label into a second sub-model of the network model to obtain a second product label for each group of the labeled streaming media data;

[0014] Adjust the parameters of the first sub-model based on the first product label, and adjust the parameters of the second sub-model based on the second product label to obtain the trained network model.

[0015] In the above solution, inputting the sample data into the first sub-model of the network model to obtain the first product label for each group of the marked streaming media data includes:

[0016] Construct the first sub-model of the network model;

[0017] Input the sample data into the first sub-model to extract the product industry characteristics of each group of the marked streaming media data;

[0018] Determine the first product label based on the product industry characteristics.

[0019] In the above solution, inputting the first product label into the second sub-model of the network model to obtain the second product label for each group of the marked streaming media data includes:

[0020] Construct the second sub-model of the network model;

[0021] Input the first product label into the second sub-model to extract the product category characteristics of each group of the marked streaming media data;

[0022] Determine the second product label based on the product industry characteristics.

[0023] In the above solution, inputting the streaming media data into the trained network model to obtain the product information corresponding to the streaming media data includes:

[0024] Input the streaming media data into the trained network model to obtain the second product label of the streaming media data;

[0025] Generate the product information based on the second product label.

[0026] In the above solution, determining the recommended products for the target user based on the user information and the product information includes:

[0027] Match the product information based on the user information to obtain a matching result;

[0028] Determine the recommended products for the target user based on the matching result.

[0029] A product recommendation device, the device includes:

[0030] An acquisition unit, configured to acquire the user information and streaming media data of the target user;

[0031] A processing unit, configured to input the streaming media data into the trained network model to obtain the product information corresponding to the streaming media data;

[0032] The processing unit is further configured to determine the recommended products for the target user based on the user information and the product information.

[0033] An electronic device includes: a processor and a memory for storing a computer program that can run on the processor,

[0034] wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of the above.

[0035] A storage medium stores a computer program thereon, and when the computer program is executed by a processor, it implements the steps of the method described in any one of the above.

[0036] A computer product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method described in any one of the above.

[0037] The product recommendation method, device, equipment, medium and product provided by the embodiments of the present application; obtaining the user information and streaming media data of the target user; inputting the streaming media data into a trained network model to obtain the product information corresponding to the streaming media data; determining the recommended products for the target user based on the user information and the product information. That is to say, the present application obtains the user information and streaming media data of the target user; inputs the streaming media data into a trained network model to obtain the product information corresponding to the streaming media data; determines the recommended products for the target user based on the user information and the product information, so as to recommend products to the user according to the streaming media data browsed by the user, and solves the problem that the business database cannot recommend corresponding financial products according to the streaming media data of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic flowchart of a product recommendation method provided by an embodiment of the present application;

[0039] Figure 2 It is a schematic flowchart of model training provided by an embodiment of the present application;

[0040] Figure 3 It is a schematic flowchart of another product recommendation method provided by an embodiment of the present application;

[0041] Figure 4 It is a schematic structural diagram of a product recommendation device provided by an embodiment of the present application;

[0042] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be further elaborated in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be construed as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0044] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0045] The terms "first / second / third" involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0047] An embodiment of this application provides a product recommendation method. Referring to Figure 1 as shown, the method includes the following steps:

[0048] S101: Obtain the user information and streaming media data of the target user.

[0049] It can be understood that the user information can be collected through a financial service system, and the financial service system can include the financial service platforms of banks. For example: the mobile banking client, the customer service platform, and the offline counter. The streaming media data can include, but is not limited to, video data and audio data received by a User Equipment (UE).

[0050] In practical applications, the streaming media data on the UE can be obtained regularly. After the streaming media data is obtained, the streaming media data can be classified or aggregated. This application does not make specific limitations on this.

[0051] S102: Input the streaming media data into the trained network model to obtain the product information corresponding to the streaming media data.

[0052] It is understandable that the network model includes, but is not limited to, Deep Neural Networks (DNN), Recurrent Neural Network (RNN), Convolutional Neural Networks (CNN), Feed Forward (FF), and Generative Adversarial Network (GAN). This application does not make specific limitations in this regard. As an example, the network model can be a CNN.

[0053] In practical applications, the network model can be trained with labeled streaming media data. The network model can include a first-level model and a second-level model. The labeled streaming media data can be input into the first-level model to extract the product industry features of financial products in the streaming media data and generate first-level labels. For example, the sports sector features can be extracted from a football game video to generate sports industry labels. The sports industry labels are input into the second-level model to extract the product category features and generate second-level labels. For example, the sports culture category features are extracted based on the sports industry labels to generate sports culture labels. In this way, a trained network model is obtained. The corresponding products are searched in the business database according to the sports culture labels to generate product information.

[0054] S103: Determine the recommended products for the target user based on the user information and product information.

[0055] It is understandable that the user information can include the user's financial data, such as user attribute data, investment account data, purchased product data, asset value data, and transaction behavior data. The user attribute data can include data related to the user's basic attributes, such as gender, age, region, occupation, and education level. The investment account data can include, but is not limited to, the account opening duration, risk level, and account amount. The purchased product data can include, but is not limited to, the amount of purchased products, the total number of purchased products, and the categories of purchased products. The purchased product data can be divided according to the timeline. The asset value data can include, but is not limited to, the asset distribution and asset value. The transaction behavior data includes, but is not limited to, the user's average daily trading volume, periodic trading volume, trading price, and trading time. The user profile labels can be established based on the user information.

[0056] In practical applications, the matching financial products can be found in the product information according to the user profile labels to generate a product list, and the recommended products for the target user are screened out from the product list to improve the matching degree of user product recommendations.

[0057] As can be seen from the above, in the embodiments of the present application, user information and streaming media data of a target user are obtained; the streaming media data is input into a trained network model to obtain product information corresponding to the streaming media data; and a recommended product for the target user is determined based on the user information and the product information, so as to recommend products to the user according to the streaming media data browsed by the user, and solve the problem that the business database cannot recommend corresponding financial products according to the user's streaming media data.

[0058] In some embodiments of the present application, before inputting the streaming media data into a trained network model to obtain product information corresponding to the streaming media data, it includes:

[0059] Obtain sample data; the sample data includes multiple groups of labeled streaming media data;

[0060] Input the sample data into the first sub-model of the network model to obtain the first product label of each group of labeled streaming media data;

[0061] Input the first product label into the second sub-model of the network model to obtain the second product label of each group of labeled streaming media data;

[0062] Adjust the parameters of the first sub-model based on the first product label, and adjust the parameters of the second sub-model based on the second product label to obtain a trained network model.

[0063] It can be understood that the network model includes but is not limited to DNN, RNN, CNN, FF, GAN. The present application does not make specific limitations in this regard. As an example, the network model can be CNN. Refer to Figure 2 As shown, the network model can be trained with labeled streaming media data. The network model can include a first-level model and a second-level model. The first sub-model can be understood as the first-level model, and the second sub-model can be understood as the second-level model.

[0064] In practical applications, multiple groups of labeled streaming media data can be input into the first-level model to extract product industry features related to financial products in the streaming media data and generate first-level labels; for example: extract sports sector features from a football game video to generate a sports industry label; input the sports industry label into the second-level model to extract product category features and generate second-level labels; for example: extract sports culture category features according to the sports industry label to generate a sports culture label, and obtain a trained network model.

[0065] In some embodiments of the present application, inputting the sample data into the first sub-model of the network model to obtain the first product label of each group of labeled streaming media data includes:

[0066] Construct the first sub-model of the network model;

[0067] Input the sample data into the first sub-model to extract the product industry features of each group of labeled streaming media data;

[0068] Determine the first product label based on the product industry features.

[0069] In practical applications, after constructing the first sub-model, input the sample data into the first sub-model for self-supervised pre-training, enabling the first sub-model to learn product industry features at different abstraction levels from each group of labeled streaming media data, so as to generate the first product label more quickly and simultaneously have better generalization performance.

[0070] In some embodiments of the present application, input the first product label into the second sub-model of the network model to obtain the second product label of each group of labeled streaming media data, including:

[0071] Construct the second sub-model of the network model;

[0072] Input the first product label into the second sub-model to extract the product category features of each group of labeled streaming media data;

[0073] Determine the second product label based on the product industry features.

[0074] In practical applications, after constructing the second sub-model, input the first product label corresponding to each group of labeled streaming media data into the second sub-model, train the second sub-model, extract the product category features of each group of labeled streaming media data, and generate the second product label.

[0075] In some embodiments of the present application, input the streaming media data into the trained network model to obtain the product information corresponding to the streaming media data, including:

[0076] Input the streaming media data into the trained network model to obtain the second product label of the streaming media data;

[0077] Generate product information based on the second product label.

[0078] In practical applications, as shown in Figure 3 It is possible to regularly obtain the streaming media data on the UE, input the streaming media data into the first-level model, extract the product industry features related to financial products in the streaming media data, and generate the first-level label; for example: extract the sports sector features from a football game video to generate a sports industry label; input the sports industry label into the second-level model, extract the product category features, and generate the second-level label; for example: extract the sports culture category features based on the sports industry label to generate a sports culture label. Search for the corresponding product in the business database according to the second product label to generate product information.

[0079] In some embodiments of the present application, determining a recommended product for a target user based on user information and product information includes:

[0080] Match product information based on user information to obtain matching results;

[0081] Determine recommended products for target users based on the matching results.

[0082] In actual applications, user information may include financial data of users, such as user attribute data, investment account data, product purchase data, asset value data, and transaction behavior data. User profile tags can be established based on user information. By obtaining the user profile tags of the target user, matching financial products are found in the product information based on the user profile tags, and a product list is generated. The evaluation function can be used to filter out recommended products for the target user from the product list. For example, the evaluation function can be used to filter out products from the product list that match the customer's risk tolerance, or to filter out products from the product list that best match the customer's purchase similarity, thereby improving the matching degree of user product recommendations.

[0083] It can be seen from the above content that the embodiment of the present application obtains the user information and streaming media data of the target user; inputs the streaming media data into a trained network model to obtain product information corresponding to the streaming media data; determines the recommended products for the target user based on the user information and product information, so as to recommend products to the user based on the streaming media data browsed by the user, thereby solving the problem that the business database cannot recommend corresponding financial products based on the user's streaming media data.

[0084] Based on the same inventive concept as above, Figure 4 A schematic diagram of the structure of a product recommendation device provided by an embodiment of the present invention, the product recommendation device 400 includes:

[0085] The acquisition unit 401 is used to acquire user information and streaming media data of a target user.

[0086] The processing unit 402 is used to input the streaming media data into the trained network model to obtain product information corresponding to the streaming media data.

[0087] The processing unit 402 is further configured to determine recommended products for the target user based on the user information and the product information.

[0088] In some embodiments of the present application, the processing unit 402 is used to obtain sample data; the sample data includes multiple groups of marked streaming media data;

[0089] Input the sample data into the first sub-model of the network model to obtain the first product label of each group of labeled streaming media data;

[0090] Input the first product label into the second sub-model of the network model to obtain the second product label of each group of labeled streaming media data;

[0091] Adjust the parameters of the first sub-model based on the first product label, and adjust the parameters of the second sub-model based on the second product label to obtain a trained network model.

[0092] In some embodiments of the present application, the processing unit 402 is used to construct the first sub-model of the network model;

[0093] Input the sample data into the first sub-model to extract the product industry features of each group of labeled streaming media data;

[0094] Determine the first product label based on the product industry features.

[0095] In some embodiments of the present application, the processing unit 402 is used to construct the second sub-model of the network model;

[0096] Input the first product label into the second sub-model to extract the product category features of each group of labeled streaming media data;

[0097] Determine the second product label based on the product industry features.

[0098] In some embodiments of the present application, the processing unit 402 is used to input the streaming media data into the trained network model to obtain the second product label of the streaming media data;

[0099] Generate product information based on the second product label.

[0100] In some embodiments of the present application, the processing unit 402 is used to match the product information based on the user information to obtain a matching result;

[0101] Determine the recommended products for the target user based on the matching result.

[0102] Based on the foregoing embodiments, an embodiment of the present application provides an electronic device, Figure 5 This is a schematic hardware structure diagram of the electronic device according to the embodiment of the present invention. The electronic device 500 includes: at least one processor 501, a memory 502. Optionally, the electronic device 500 may further include at least one communication interface 503. Each component in the electronic device 500 is coupled together through a bus system 504. It can be understood that the bus system 504 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in Figure 5 all kinds of buses are labeled as the bus system 504.

[0103] Based on the hardware implementation of the above program modules, the communication interface 503 can interact with other communication devices for information;

[0104] The processor 501 is connected to the communication interface 503 to interact with other communication devices for information, and when running a computer program, it executes the methods provided by the above one or more technical solutions;

[0105] The memory 502 stores the computer program.

[0106] Specifically, the processor 501 is used to obtain the user information and streaming media data of the target user.

[0107] Input the streaming media data into the trained network model to obtain the product information corresponding to the streaming media data.

[0108] Determine the recommended products for the target user based on the user information and product information.

[0109] In some embodiments of the present application, the processor 501 is used to obtain sample data; the sample data includes multiple groups of labeled streaming media data;

[0110] Input the sample data into the first sub-model of the network model to obtain the first product label for each group of labeled streaming media data;

[0111] Input the first product label into the second sub-model of the network model to obtain the second product label for each group of labeled streaming media data;

[0112] Adjust the parameters of the first sub-model based on the first product label, and adjust the parameters of the second sub-model based on the second product label to obtain the trained network model.

[0113] In some embodiments of the present application, the processor 501 is used to construct the first sub-model of the network model;

[0114] Input the sample data into the first sub-model to extract the product industry characteristics of each group of labeled streaming media data;

[0115] Determine the first product label based on the product industry characteristics.

[0116] In some embodiments of the present application, the processor 501 is used to construct the second sub-model of the network model;

[0117] Input the first product label into the second sub-model to extract the product category characteristics of each group of labeled streaming media data;

[0118] Determine the second product label based on the product industry characteristics.

[0119] In some embodiments of the present application, the processor 501 is configured to input the streaming media data into the trained network model to obtain the second product label of the streaming media data;

[0120] Generate product information based on the second product label.

[0121] In some embodiments of the present application, the processor 501 is configured to match the product information based on the user information to obtain a matching result;

[0122] Determine the recommended products for the target user based on the matching result.

[0123] It can be understood that the memory 502 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), direct rambus random access memory (DRRAM).The memory 502 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0124] The memory 502 in the embodiments of the present invention is used to store various types of data to support the operation of the electronic device 500. Examples of such data include: any computer program for operating on the electronic device 500, and the program for implementing the method of the embodiments of the present invention may be included in the memory 502.

[0125] The method disclosed in the above embodiments of the present invention can be applied to or implemented by the processor 501. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or the instructions in the form of software. The above processor may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor, etc. Combining the steps of the method disclosed in the embodiments of the present invention, it can be directly embodied as being executed by the hardware decoding processor, or executed by the combination of the hardware and software modules in the decoding processor. The software module may be located in the storage medium, and this storage medium is located in the memory. The processor reads the information in the memory and combines its hardware to complete the steps of the foregoing method.

[0126] In an exemplary embodiment, the electronic device 500 can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontroller units (MCUs), microprocessors, or other electronic components, and is used to execute the above method.

[0127] Based on the foregoing embodiments, the embodiments of the present application further provide a computer product, including a computer program, and when the computer program is executed by a processor, it implements Figure 1 the steps in the product recommendation method provided in the corresponding embodiment.

[0128] Based on the foregoing embodiments, an embodiment of the present application further provides a storage medium storing computer-executable instructions configured to execute Figure 1 the product recommendation method provided by the corresponding embodiment.

[0129] It should be noted that the above computer storage medium may be a ROM, PROM, EPROM, EEPROM, FRAM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.; it may also be various electronic devices including one or any combination of the above memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0130] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or device including the element.

[0131] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), including several instructions for causing a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general computer, a special computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 means for the functions specified in one or more processes and / or boxes Figure 1 or boxes.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in Figure 1 one or more processes and / or boxes Figure 1 or boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more processes and / or boxes Figure 1 or boxes.

[0136] The above are only the preferred embodiments of this application, and do not limit the patent scope of this application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of this application.

[0137] The above are only the preferred embodiments of the present invention, and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A product recommendation method, characterized in that: The method comprises: Obtain user information and streaming media data of target users; Inputting the streaming media data into a trained network model to obtain product information corresponding to the streaming media data; Determine a recommended product for the target user based on the user information and the product information.

2. The method according to claim 1, characterized in that Before inputting the streaming media data into the trained network model to obtain product information corresponding to the streaming media data, the method includes: Acquire sample data; the sample data includes multiple groups of marked streaming media data; Inputting the sample data into a first sub-model of a network model to obtain a first product label for each group of the marked streaming media data; Inputting the first product label into the second sub-model of the network model to obtain a second product label for each group of the marked streaming media data; The parameters of the first sub-model are adjusted based on the first product label, and the parameters of the second sub-model are adjusted based on the second product label to obtain the trained network model.

3. The method according to claim 2, characterized in that The step of inputting the sample data into the first sub-model of the network model to obtain the first product label of each group of the marked streaming media data includes: Constructing a first sub-model of the network model; Inputting the sample data into the first sub-model to extract product industry features of each group of the marked streaming media data; The first product label is determined based on the product industry characteristics.

4. The method according to claim 2, characterized in that: Inputting the first product label into the second sub-model of the network model to obtain a second product label for each group of the marked streaming media data includes: constructing a second sub-model of the network model; Inputting the first product tag into the second sub-model to extract product category features of each group of the labeled streaming media data; The second product label is determined based on the product industry characteristics.

5. The method according to claim 2, characterized in that: The step of inputting the streaming media data into a trained network model to obtain product information corresponding to the streaming media data includes: Inputting the streaming media data into a trained network model to obtain a second product label for the streaming media data; The product information is generated based on the second product tag.

6. The method according to claim 1, characterized in that The determining the recommended product for the target user based on the user information and the product information includes: Match the product information based on the user information to obtain a matching result; Determine a recommended product for the target user based on the matching result.

7. A product recommendation device, characterized in that: The device comprises: An acquisition unit, used to acquire user information and streaming media data of a target user; A processing unit, used to input the streaming media data into a trained network model to obtain product information corresponding to the streaming media data; The processing unit is further used to determine the recommended product for the target user based on the user information and the product information.

8. An electronic device, characterized in that: include: a processor and a memory for storing a computer program capable of being executed on the processor, Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 1 to 6.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images