Product recommendation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to a product recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: constructing a user portrait corresponding to a requesting user according to dialogue text data; performing semantic analysis operation on the dialogue text data according to a large language model to obtain a real intention of a user and a product demand index; constructing a dynamic knowledge graph according to the user portrait, the real intention of the user and the product demand index; generating a product comparison set according to the dynamic knowledge graph; and performing a comparison operation on the to-be-selected products in the product comparison set according to an iterative comparison process to obtain a target recommended product. According to the method, through deep user portrait and multi-dimensional similarity calculation, dynamic comparison set generation and progressive accurate comparison, irrelevant information is effectively filtered, the cognitive burden of the user is reduced, and the accuracy of personalized recommendation is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a product recommendation method, device, computer equipment and storage medium. Background Art

[0002] Product push is to collect information about target users in the context of big data, relying on the powerful recording, transmission and sharing functions of the Internet, and to complete the analysis of user behavior through the integration and identification of information, so as to determine the user's past and potential needs for product push. For example, in the financial field, in order to maintain customer flow, insurance platforms push relevant news about some insurance products on the platform (such as product discounts, new product launches, etc.) to increase user stickiness to the platform.

[0003] The traditional product push method is to obtain user behavior and preference information, build a user profile based on the behavior and preference information, and push messages based on the user profile.

[0004] However, the user data obtained by this traditional method are generally all historical user data or all real-time data. When all the user data obtained are historical data, there is a data lag, which makes the accuracy of product push low. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a product recommendation method, device, computer equipment and storage medium to solve the problem of low accuracy in traditional product push methods.

[0006] In order to solve the above technical problems, the present application embodiment provides a product recommendation method, which adopts the following technical solution:

[0007] Receiving conversation text data sent by the requesting terminal;

[0008] Building a user profile corresponding to the requesting user based on the conversation text data;

[0009] Performing semantic analysis on the conversation text data according to the large language model to obtain the user's true intention and product demand indicators;

[0010] Construct a dynamic knowledge graph according to the user portrait, the user's real intention and the product demand index;

[0011] Generate a product comparison set according to the dynamic knowledge graph;

[0012] Performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result;

[0013] Outputting the comparison result to the requesting terminal;

[0014] receiving feedback information corresponding to the comparison result sent by the requesting terminal;

[0015] The product comparison set is filtered according to the feedback information, and the next round of iterative comparison operation is performed until the number of products in the product comparison set meets the preset number, and the target recommended product is obtained.

[0016] Furthermore, the step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps:

[0017] Obtaining a control product that does not match the dynamic knowledge graph;

[0018] Among the control products, the products with the most historical selection times are selected and added to the product comparison set.

[0019] Furthermore, the step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps:

[0020] Acquire exploration products according to the ε-greedy strategy;

[0021] The explored product is added to the product comparison set.

[0022] Furthermore, after the step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the following step is further included:

[0023] collecting micro-expression information of the requesting user when browsing the products in the comparison results using a camera device;

[0024] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0025] Performing an emotion analysis operation on the micro-expression information according to visual and emotional computing technology to obtain an emotion analysis result;

[0026] The product comparison set is filtered according to the sentiment analysis result and the feedback information.

[0027] Furthermore, after the step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the following step is further included:

[0028] Collecting behavior data of the requesting user when browsing the products in the comparison results, wherein the behavior data includes dwell time and mouse movement track;

[0029] constructing an attention heat map based on the behavioral data;

[0030] Acquire the product attention features of the requesting user according to the attention heat map;

[0031] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0032] The product comparison set is filtered according to the product focus feature and the feedback information.

[0033] Furthermore, the behavior data includes a click behavior sequence, and after the step of collecting the behavior data of the requesting user when browsing the products in the comparison results, the following steps are also included:

[0034] Performing a preference analysis operation on the click behavior sequence according to the sequence model to obtain interest preference features;

[0035] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0036] The product comparison set is filtered according to the interest preference characteristics and the feedback information.

[0037] In order to solve the above technical problems, the embodiment of the present application further provides a product recommendation device, which adopts the following technical solution:

[0038] A dialogue text acquisition module, used for receiving dialogue text data sent by a requesting terminal;

[0039] A user portrait building module, used to build a user portrait corresponding to the requesting user according to the conversation text data;

[0040] A semantic analysis module, used to perform semantic analysis on the conversation text data according to a large language model to obtain the user's true intention and product demand indicators;

[0041] A knowledge graph construction module, used to construct a dynamic knowledge graph based on the user portrait, the user's real intention and the product demand index;

[0042] A product comparison set generation module, used to generate a product comparison set according to the dynamic knowledge graph;

[0043] A comparison module, used for performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result;

[0044] A comparison result output module, used to output the comparison result to the request terminal;

[0045] A feedback information acquisition module, used to receive feedback information corresponding to the comparison result sent by the requesting terminal;

[0046] The target product acquisition module is used to filter the product comparison set according to the feedback information and perform the next round of iterative comparison operation until the number of products in the product comparison set meets the preset number, thereby obtaining the target recommended product.

[0047] Furthermore, the product comparison set generation module includes:

[0048] A control product acquisition submodule, used to acquire control products that do not match the dynamic knowledge graph;

[0049] The control product adding submodule is used to select the products with the most historical selection times from the control products and add them to the product comparison set.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0051] It includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the product recommendation method as described above when executing the computer-readable instructions.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0053] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the product recommendation method described above are implemented.

[0054] The present application provides a product recommendation method, comprising: receiving conversation text data sent by a requesting terminal; constructing a user portrait corresponding to the requesting user according to the conversation text data; performing semantic analysis operations on the conversation text data according to a large language model to obtain the user's true intention and product demand indicators; constructing a dynamic knowledge graph according to the user portrait, the user's true intention and the product demand indicators; generating a product comparison set according to the dynamic knowledge graph; performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result; outputting the comparison result to the requesting terminal; receiving feedback information corresponding to the comparison result sent by the requesting terminal; filtering the product comparison set according to the feedback information, and performing the next round of iterative comparison operations until the number of products in the product comparison set meets the preset number, and obtaining the target recommended product. Compared with the prior art, the present application effectively filters irrelevant information, reduces the user's cognitive burden, and effectively improves the accuracy of personalized recommendations through deep user portraits and multi-dimensional similarity calculations, dynamic comparison set generation and progressive precision comparison. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0057] Figure 2 is a flowchart of the implementation of the product recommendation method provided in the embodiment of the present application;

[0058] Figure 3 is a schematic diagram of the structure of a product recommendation device provided in an embodiment of the present application;

[0059] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0061] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0062] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0063] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0064] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0065] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0066] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0067] It should be noted that the product recommendation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the product recommendation device is generally set in the server / terminal device.

[0068] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0069] Continue to refer Figure 2 , shows a flow chart of an embodiment of a product recommendation method according to the present application. The product recommendation method comprises: step S201, step S202, step S203, step S204, step S205, step S206, step S207, step S208 and step S209.

[0070] In step S201, the conversation text data sent by the requesting terminal is received.

[0071] In the embodiments of the present application, the user terminal refers to a terminal device used to execute the image processing method for preventing document abuse provided by the present application. The user terminal can be a mobile terminal such as a mobile phone, a smart phone, a laptop computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a navigation device, etc., as well as a fixed terminal such as a digital TV, a desktop computer, etc. It should be understood that the examples of user terminals here are only for the convenience of understanding and are not used to limit the present application.

[0072] In the embodiment of the present application, when a user inputs dialogue text data through a request terminal (such as a mobile phone APP, a web page, a chat robot, etc.), the system first receives this data. This data may include the user's inquiry, demand description, preference information, etc.

[0073] In step S202, a user portrait corresponding to the requesting user is constructed based on the conversation text data.

[0074] In the embodiment of the present application, the system uses machine learning or natural language processing technology to extract key information from the conversation text data, such as the user's age, gender, interests, occupation, etc., and constructs a user profile corresponding to the user. This user profile is the basis for subsequent recommendations and helps to more accurately understand user needs and preferences.

[0075] In step S203, a semantic analysis operation is performed on the conversation text data according to the large language model to obtain the user's real intention and product demand indicators.

[0076] In an embodiment of the present application, a large language model (such as BERT, GPT, etc.) is used to perform deep semantic analysis on the conversation text data to identify the user's true intentions (such as purchase, consultation, comparison, etc.) and specific product demand indicators (such as price range, functional requirements, brand preferences, etc.).

[0077] In step S204, a dynamic knowledge graph is constructed based on the user portrait, the user's true intention, and the product demand indicators.

[0078] In the embodiment of the present application, a dynamic knowledge graph is constructed by combining user portraits, user intentions and product demand indicators. This graph contains various information nodes and relationships related to users, such as product information, user preferences, market trends, etc., which helps the system understand user needs more comprehensively.

[0079] In step S205, a product comparison set is generated based on the dynamic knowledge graph.

[0080] In the embodiment of the present application, based on the dynamic knowledge graph, the system screens out a series of products that best match the user's needs to form a product comparison set. These products may come from different brands, models or price ranges to meet the diverse needs of users.

[0081] In step S206, a comparison operation is performed on the candidate products in the product comparison set according to the iterative comparison process to obtain a comparison result.

[0082] In the embodiment of the present application, the system adopts an iterative comparison process to compare the selected products in the product comparison set one by one or in batches. The comparison content may include multiple dimensions such as price, performance, reputation, user evaluation, etc. to ensure that the recommended products meet user needs in all aspects.

[0083] In step S207, the comparison result is output to the requesting terminal.

[0084] In an embodiment of the present application, the comparison results are displayed to the requesting terminal where the user is located in an easy-to-understand manner (such as a list, chart, rating, etc.), helping the user to quickly understand the advantages and disadvantages of each product.

[0085] In step S208, feedback information corresponding to the comparison result sent by the requesting terminal is received.

[0086] In the embodiment of the present application, the user may give his or her own feedback based on the comparison results, such as preference for certain products, demand for specific functions, etc. The system receives this feedback information to further optimize the recommendation results.

[0087] In step S209, the product comparison set is filtered according to the feedback information, and the next round of iterative comparison operation is performed until the number of products in the product comparison set meets the preset number, and the target recommended product is obtained.

[0088] In the embodiment of the present application, the system filters the product comparison set according to the user's feedback to exclude products that do not meet the user's needs, and then performs the next round of iterative comparison operations to more accurately meet the user's needs.

[0089] In the embodiment of the present application, after multiple rounds of iterative comparison, when the number of products in the product comparison set is reduced to a preset number (such as 3-5), the system considers that these products are sufficient to meet the user's needs and displays them to the user as target recommended products. These recommended products are not only of moderate quantity, but also carefully screened and compared in all aspects, which helps users make wise purchasing decisions.

[0090] In an embodiment of the present application, a product recommendation method is provided, including: receiving conversation text data sent by a requesting terminal; constructing a user portrait corresponding to the requesting user according to the conversation text data; performing semantic analysis operations on the conversation text data according to a large language model to obtain the user's true intention and product demand indicators; constructing a dynamic knowledge graph according to the user portrait, the user's true intention and the product demand indicators; generating a product comparison set according to the dynamic knowledge graph; performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result; outputting the comparison result to the requesting terminal; receiving feedback information corresponding to the comparison result sent by the requesting terminal; filtering the product comparison set according to the feedback information, and performing the next round of iterative comparison operations until the number of products in the product comparison set meets the preset number, and obtaining the target recommended product. Compared with the prior art, the present application effectively filters irrelevant information, reduces the user's cognitive burden, and effectively improves the accuracy of personalized recommendations through deep user portraits and multi-dimensional similarity calculations, dynamic comparison set generation and progressive precision comparison.

[0091] In some optional implementations of the embodiments of the present application, the above step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps:

[0092] Obtain control products that do not match the dynamic knowledge graph;

[0093] Among the control products, select the products with the most historical selection times and add them to the product comparison set.

[0094] In the embodiments of the present application, mismatches can be based on a variety of factors, such as product price, functional characteristics, brand preference, user evaluation, etc., which are clearly represented in the dynamic knowledge graph. The mismatch criteria can be set according to the actual needs of users and market conditions to ensure that the selected control products are sufficiently diverse and representative.

[0095] In the embodiment of the present application, once the mismatch criteria are defined, the system needs to search the extensive product database for products that do not meet these criteria. This involves a detailed analysis of the product information in the database to find options that do not match the user needs described in the dynamic knowledge graph.

[0096] In the present embodiment, after searching for a large number of control products, the system needs to perform a preliminary screening to exclude those products that obviously do not meet user needs or market trends. This step helps to reduce the burden of subsequent analysis and ensure that the control products finally screened have a certain quality and relevance.

[0097] In the embodiment of the present application, in order to determine which control products were most selected by users in the past, the system needs to access a database containing historical selection data. These data may come from previous user behavior records, sales data, user evaluations, etc.

[0098] In the embodiment of the present application, the system will analyze the control products after the preliminary screening and count the number of times each product is selected by the user. This step may involve processing and analyzing a large amount of data to ensure the accuracy and reliability of the results.

[0099] In the embodiment of the present application, after analyzing the historical selection times of all control products, the system needs to determine which product has been selected the most times. This may involve sorting and comparing the data to ensure that the product finally selected is a truly popular option.

[0100] In the embodiment of the present application, once the product with the most historical selection times is determined, the system needs to add it to the product comparison set. This step helps to increase the diversity and relevance of the product comparison set, and also provides users with more options to choose from.

[0101] In some optional implementations of the embodiments of the present application, if the system believes that the added new product can provide valuable information or suggestions to the user, it can also choose to update the dynamic knowledge graph to reflect this change. This helps the system better understand and meet user needs in the future.

[0102] Through the above operations, the system can ensure that the product comparison set contains not only products that are highly matched with user needs, but also products that are not completely matched but have wide recognition and popularity. This helps to provide users with more comprehensive choices and increase the diversity and accuracy of the recommendation system.

[0103] In some optional implementations of the embodiments of the present application, the above step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps:

[0104] Acquire exploration products according to the ε-greedy strategy;

[0105] Add the explored product to your comparison set.

[0106] In the embodiment of the present application, the ε-greedy strategy is a commonly used solution to the multi-armed bandit problem, which combines the ideas of exploration and exploitation. In this strategy, there is a parameter ε (epsilon), which determines the balance between exploration and exploitation. Usually, the value of ε is between 0 and 1.

[0107] In practical applications, the value of ε needs to be set according to the specific situation. If the system wants to explore more new possibilities, a higher ε value can be set; if the system wants to make more use of known information to make the best decision, a lower ε value can be set. Then, the system generates a random number between 0 and 1 for comparison with ε. If the generated random number is less than or equal to ε, the system chooses to explore; if the random number is greater than ε, the system chooses to exploit.

[0108] In the embodiment of the present application, in the exploration phase, the system needs to select one product from products that have not been fully explored or are completely unknown as an exploration product. This can be achieved by a variety of methods, such as random selection, selection based on certain heuristic rules, etc.

[0109] In the embodiment of the present application, through the ε-greedy strategy, the system can find a balance between exploration and utilization, which can not only continuously try new possibilities to discover better products, but also make full use of known information to make the best decision. This strategy helps to improve the diversity and accuracy of the recommendation system and provide users with a better experience.

[0110] In some optional implementations of the embodiments of the present application, after the above step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the following steps are further included:

[0111] Collecting micro-expression information of the requesting user when browsing products in the comparison results using a camera device;

[0112] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0113] Perform sentiment analysis on micro-expression information based on visual and emotional computing technology to obtain sentiment analysis results;

[0114] The product comparison set is filtered based on sentiment analysis results and feedback information.

[0115] In the embodiments of the present application, the user's emotional reactions and preferences can be understood more accurately, thereby providing more personalized product recommendations that meet the user's expectations.

[0116] In some optional implementations of the embodiments of the present application, after the step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the following steps are further included:

[0117] Collecting micro-expression information of the requesting user when browsing products in the comparison results using a camera device;

[0118] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0119] Perform sentiment analysis on micro-expression information based on visual and emotional computing technology to obtain sentiment analysis results;

[0120] The product comparison set is filtered based on sentiment analysis results and feedback information.

[0121] In the embodiment of the present application, through the above process, the system can more accurately understand the user's emotional response and preferences, thereby providing more personalized and user-expected product recommendations. At the same time, the system also pays attention to user privacy protection and compliance, ensuring the security and privacy of user data.

[0122] In some optional implementations of the embodiments of the present application, the behavior data includes a click behavior sequence, and after the step of collecting the behavior data of the requesting user when browsing the products in the comparison results, the following steps are also included:

[0123] Perform preference analysis on the click behavior sequence according to the sequence model to obtain interest preference characteristics;

[0124] The step of filtering the product comparison set according to the feedback information specifically includes the following steps:

[0125] The product comparison set is filtered according to interest preference characteristics and feedback information.

[0126] In the embodiment of the present application, through the above process, the system can more accurately understand the user's interests, preferences and needs, thereby providing more personalized and user-expected product recommendations. At the same time, the system also pays attention to the user's privacy protection and compliance, ensuring the security and privacy of user data.

[0127] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0128] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0130] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0131] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a product recommendation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0132] like Figure 3 As shown, the product recommendation device 200 of the embodiment of the present application includes:

[0133] The conversation text acquisition module 210 is used to receive the conversation text data sent by the requesting terminal;

[0134] A user portrait building module 220, for building a user portrait corresponding to the requesting user according to the conversation text data;

[0135] Semantic analysis module 230, used to perform semantic analysis on the conversation text data according to the large language model to obtain the user's true intention and product demand indicators;

[0136] A knowledge graph construction module 240 is used to construct a dynamic knowledge graph based on user portraits, user real intentions, and product demand indicators;

[0137] A product comparison set generation module 250, used to generate a product comparison set according to a dynamic knowledge graph;

[0138] A comparison module 260 is used to perform a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result;

[0139] A comparison result output module 270, configured to output the comparison result to the requesting terminal;

[0140] A feedback information acquisition module 280, configured to receive feedback information corresponding to the comparison result sent by the requesting terminal;

[0141] The target product acquisition module 290 is used to filter the product comparison set according to the feedback information and perform the next round of iterative comparison operation until the number of products in the product comparison set meets the preset number, thereby obtaining the target recommended product.

[0142] In an embodiment of the present application, a product recommendation device 200 is provided, including: a conversation text acquisition module 210, which is used to receive conversation text data sent by a requesting terminal; a user portrait construction module 220, which is used to construct a user portrait corresponding to the requesting user according to the conversation text data; a semantic analysis module 230, which is used to perform semantic analysis operations on the conversation text data according to a large language model to obtain the user's true intention and product demand indicators; a knowledge graph construction module 240, which is used to construct a dynamic knowledge graph according to the user portrait, the user's true intention and the product demand indicators; a product comparison set generation module 250, which is used to generate a product comparison set according to the dynamic knowledge graph; a comparison module 260, which is used to perform a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result; a comparison result output module 270, which is used to output the comparison result to the requesting terminal; a feedback information acquisition module 280, which is used to receive feedback information corresponding to the comparison result sent by the requesting terminal; a target product acquisition module 290, which is used to filter the product comparison set according to the feedback information, and perform the next round of iterative comparison operations until the number of products in the product comparison set meets the preset number, and the target recommended product is obtained. Compared with the existing technology, this application effectively filters out irrelevant information, reduces the user's cognitive burden, and effectively improves the accuracy of personalized recommendations through deep user profiling and multi-dimensional similarity calculation, dynamic comparison set generation and progressive precise comparison.

[0143] In some optional implementations of the embodiments of the present application, the product comparison set generation module includes:

[0144] A control product acquisition submodule is used to acquire control products that do not match the dynamic knowledge graph;

[0145] The control product adding submodule is used to filter out the products with the most historical selection times among the control products and add them to the product comparison set.

[0146] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0147] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0148] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0149] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions of the product recommendation method, etc. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0150] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions stored in the memory 310 or process data, such as computer-readable instructions for running the product recommendation method.

[0151] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0152] The computer device provided in this application effectively filters out irrelevant information, reduces the user's cognitive burden, and effectively improves the accuracy of personalized recommendations through deep user profiling and multi-dimensional similarity calculation, dynamic comparison set generation and progressive precision comparison.

[0153] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the product recommendation method as described above.

[0154] The computer-readable storage medium provided in this application effectively filters out irrelevant information, reduces the user's cognitive burden, and effectively improves the accuracy of personalized recommendations through deep user profiling and multi-dimensional similarity calculation, dynamic comparison set generation and progressive precision comparison.

[0155] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course 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, or the part that contributes to the prior art, can 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 a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0156] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A product recommendation method, characterized in that: The steps include: Receiving conversation text data sent by the requesting terminal; Building a user profile corresponding to the requesting user based on the conversation text data; Performing semantic analysis on the conversation text data according to the large language model to obtain the user's true intention and product demand indicators; Construct a dynamic knowledge graph according to the user portrait, the user's real intention and the product demand index; Generate a product comparison set according to the dynamic knowledge graph; Performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result; Outputting the comparison result to the requesting terminal; receiving feedback information corresponding to the comparison result sent by the requesting terminal; The product comparison set is filtered according to the feedback information, and the next round of iterative comparison operation is performed until the number of products in the product comparison set meets the preset number, and the target recommended product is obtained.

2. The product recommendation method according to claim 1, characterized in that: The step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps: Obtaining a control product that does not match the dynamic knowledge graph; Among the control products, the products with the most historical selection times are selected and added to the product comparison set.

3. The product recommendation method according to claim 1, characterized in that: The step of generating a product comparison set according to the dynamic knowledge graph specifically includes the following steps: Acquire exploration products according to the ε-greedy strategy; The explored product is added to the product comparison set.

4. The product recommendation method according to claim 1, characterized in that: After the step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the method further includes the following steps: collecting micro-expression information of the requesting user when browsing the products in the comparison results using a camera device; The step of filtering the product comparison set according to the feedback information specifically includes the following steps: Performing an emotion analysis operation on the micro-expression information according to visual and emotional computing technology to obtain an emotion analysis result; The product comparison set is filtered according to the sentiment analysis result and the feedback information.

5. The product recommendation method according to claim 1, characterized in that: After the step of outputting the comparison result to the requesting terminal and before the step of outputting the comparison result to the requesting terminal, the method further includes the following steps: Collecting behavior data of the requesting user when browsing the products in the comparison results, wherein the behavior data includes dwell time and mouse movement track; constructing an attention heat map based on the behavioral data; Acquire the product attention features of the requesting user according to the attention heat map; The step of filtering the product comparison set according to the feedback information specifically includes the following steps: The product comparison set is filtered according to the product focus feature and the feedback information.

6. The product recommendation method according to claim 5, characterized in that: The behavior data includes a click behavior sequence. After the step of collecting the behavior data of the requesting user when browsing the products in the comparison result, the following steps are also included: Performing a preference analysis operation on the click behavior sequence according to the sequence model to obtain interest preference features; The step of filtering the product comparison set according to the feedback information specifically includes the following steps: The product comparison set is filtered according to the interest preference characteristics and the feedback information.

7. A product recommendation device, characterized in that: include: A dialogue text acquisition module, used for receiving dialogue text data sent by a requesting terminal; A user portrait building module, used to build a user portrait corresponding to the requesting user according to the conversation text data; A semantic analysis module, used to perform semantic analysis on the conversation text data according to a large language model to obtain the user's true intention and product demand indicators; A knowledge graph construction module, used to construct a dynamic knowledge graph based on the user portrait, the user's real intention and the product demand index; A product comparison set generation module, used to generate a product comparison set according to the dynamic knowledge graph; A comparison module, used for performing a comparison operation on the selected products in the product comparison set according to an iterative comparison process to obtain a comparison result; A comparison result output module, used to output the comparison result to the request terminal; A feedback information acquisition module, used to receive feedback information corresponding to the comparison result sent by the requesting terminal; The target product acquisition module is used to filter the product comparison set according to the feedback information and perform the next round of iterative comparison operation until the number of products in the product comparison set meets the preset number, thereby obtaining the target recommended product.

8. The product recommendation device according to claim 7, characterized in that: The product comparison set generation module includes: A control product acquisition submodule, used to acquire control products that do not match the dynamic knowledge graph; The control product adding submodule is used to select the products with the most historical selection times from the control products and add them to the product comparison set.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the product recommendation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the product recommendation method according to any one of claims 1 to 6 are implemented.

Images