Product recommendation method and device, computer program product and electronic equipment

Abstract

The invention discloses a product recommendation method and device, a computer program product and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the following steps: obtaining transaction data and social behavior data of a target user in a preset period, the social behavior data comprising at least one of interaction data between the target user and other users, and operation data of the target user on a social platform; matching the transaction data and the social behavior data with a preset product recommendation rule base, and judging whether a target product recommendation rule is matched or not; under the condition that the target product recommendation rule is matched, determining a target product type associated with the target product recommendation rule; and obtaining identity information of the target user, determining a recommended product based on the identity information and the target product type, and recommending the recommended product to the target user. Through the method and the device, the problem of inaccurate product recommendation in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a product recommendation method, device, computer program product, and electronic device. Background Art

[0002] The product recommendation method in the related art is based on the user's historical transaction data, and recommends related products to the user by calculating the correlation between the user's historical transaction data. For example, if the user purchases product A, then the products B, C, D, etc. related to product A are recommended. However, the calculation of the correlation depends on the historical transaction data, and there is a problem that the user has already purchased the recommended related products, or the correlation with the user's needs is low, resulting in a poor user experience.

[0003] Currently, no effective solution has been proposed to the problem of inaccurate product recommendations in related technologies. Summary of the invention

[0004] The main purpose of this application is to provide a product recommendation method, device, computer program product and electronic device to solve the problem of inaccurate product recommendation in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a product recommendation method is provided. The method comprises: obtaining transaction data and social behavior data of a target user within a preset period, wherein the social behavior data comprises at least one of the following: interaction data between the target user and other users, and operation data of the target user on a social platform; matching the transaction data and social behavior data with a preset product recommendation rule library, and determining whether the target product recommendation rule is matched; if the target product recommendation rule is matched, determining the target product type associated with the target product recommendation rule; obtaining the identity information of the target user, determining the recommended product based on the identity information and the target product type, and recommending the recommended product to the target user.

[0006] Optionally, the preset product recommendation rule library is constructed in the following manner: determine multiple types of products of a financial institution, and for each type of product, determine the purchasing users of the product; obtain historical transaction data and historical social behavior data of the purchasing users within a target period of purchasing the product; extract multiple features from the historical transaction data and historical social behavior data, and for each feature, count the proportion of purchasing users who contain the feature in the historical transaction data and historical social behavior data in the purchasing user group to obtain the feature proportion; when the feature proportion is greater than or equal to a proportion threshold, determine the feature as an associated feature of the product; construct product matching rules based on the associated features of each type of product, and construct a preset product recommendation rule library based on the matching rules of multiple types of products of financial institutions.

[0007] Optionally, the method also includes: re-counting the feature proportions of the associated features of each product at every preset rule update cycle to obtain an updated feature proportion; when the updated feature proportion is less than a proportion threshold, removing the associated features corresponding to the updated feature proportion from the product matching rules; when the number of associated features of a product is less than a quantity threshold, obtaining the transaction data and social behavior data of users who purchased the product within the preset rule update cycle; extracting multiple features from the transaction data and social behavior data, and counting the feature proportion of each feature; when the feature proportion is greater than or equal to the proportion threshold, and the feature is not an associated feature of the product, determining the feature as a newly added associated feature of the product, and updating the product matching rules based on the newly added associated features.

[0008] Optionally, after determining whether the target product recommendation rule is matched, the method also includes: if the target product recommendation rule is not matched, obtaining the identity information of the target user; determining the customer group to which the target user belongs based on the identity information, and obtaining multiple recommended products for the customer group within a preset period; generating a product recommendation table based on the multiple recommended products, and pushing the product recommendation table to the target user.

[0009] Optionally, determining recommended products based on identity information and target product types includes: extracting identity features from the identity information, wherein the identity features include at least one of the following: age, gender, occupation, region and income; inputting the identity features and the target product type into a target model to obtain recommended products, wherein the target model is trained by multiple groups of training samples, each group of training samples including historical identity features, historical product types and historical recommended products.

[0010] Optionally, after recommending the recommended product to the target user, the method further includes: obtaining feedback data of the target user on the recommended product, wherein the feedback data includes at least one of the following: purchases, clicks, views and opinion feedback; adding the feedback data to the transaction data and social behavior data of the target user.

[0011] Optionally, before obtaining the transaction data and social behavior data of the target user within a preset period, the method also includes: sending an authorization request to the target user, wherein the authorization request is used to request the target user to allow obtaining the transaction data and social behavior data of the target user; upon receiving a confirmation authorization indication from the target user for the authorization request, executing the step of obtaining the transaction data and social behavior data of the target user within the preset period; obtaining the transaction data and social behavior data of the target user within the preset period includes: obtaining the product purchase record, browsing record and search keywords of the target user within the preset period, and determining at least one of the following as the transaction data of the target user: product purchase record, browsing record and search keyword; obtaining the interaction data, comments, likes, sharing and follow data of the target user on the social platform within the preset period, and determining at least one of the following as the social behavior data of the target user: interaction data, comments, likes, sharing and follow data.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a product recommendation device is provided. The device includes: an acquisition unit, which is used to acquire the transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform; a matching unit, which is used to match the transaction data and social behavior data with the preset product recommendation rule library, and determine whether the target product recommendation rule is matched; a first determination unit, which is used to determine the target product type associated with the target product recommendation rule when the target product recommendation rule is matched; a recommendation unit, which is used to acquire the identity information of the target user, determine the recommended product based on the identity information and the target product type, and recommend the recommended product to the target user.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the product recommendation method described in each embodiment of the present application are implemented.

[0014] Through this application, the following steps are adopted: obtaining the transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform; matching the transaction data and social behavior data with the preset product recommendation rule library, and judging whether the target product recommendation rule is matched; in the case of matching the target product recommendation rule, determining the target product type associated with the target product recommendation rule; obtaining the identity information of the target user, determining the recommended product based on the identity information and the target product type, and recommending the recommended product to the target user, thereby solving the problem of inaccurate product recommendation in the related art. By matching the user's transaction data and social behavior data with the preset product recommendation rule library, if the target product recommendation rule is matched, the recommended product is determined based on the target product type associated with the target product recommendation rule and the user's identity information, and the recommended product is recommended to the target user, thereby improving the correlation between the recommended product and the target user, thereby achieving the effect of improving the accuracy of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for synchronizing information across systems is shown;

[0017] Figure 2 is a flowchart of a product recommendation method provided according to an embodiment of the present application;

[0018] Figure 3 is a schematic diagram of a product recommendation device provided according to an embodiment of the present application;

[0019] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] 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 drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0024] It should be noted that the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0025] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for synchronizing information across systems is shown. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as an MCU (Microcontroller Unit) or an FPGA (Field-Programmable Gate Array), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a USB (Universal Serial Bus) port (which may be included as one of the ports of a BUS (Business)), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0026] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0027] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the information synchronization method between systems in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned information synchronization method between systems. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0028] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] The display may be, for example, a touch screen liquid crystal display that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0030] The present invention is described below in conjunction with preferred implementation steps. Figure 2 is a flowchart of a product recommendation method provided according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0031] Step S201, obtaining transaction data and social behavior data of a target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on a social platform.

[0032] In step S201, transaction data is obtained from the relevant software authorized by the target user's mobile device through user authorization, and social behavior data is obtained from the social platform authorized by the target user to access. Transaction data may include information about products purchased by users, purchase time, purchase frequency, purchase amount, etc.; social behavior data may be interaction data between the target user and other users (such as comments, likes, shares, private messages, etc.), as well as the target user's operation data on the social platform (such as browsing history, search keywords, topics or groups followed, discussions participated in, etc.).

[0033] By analyzing the target user's transaction data and social behavior data, a more comprehensive user profile can be constructed, thereby more accurately predicting which related products the user may be interested in. For example, if the target user frequently discusses or pays attention to a certain topic on a social platform, and this topic is related to a product that the user has recently traded, then based on this change in social behavior, we can recommend expansion products or upgraded products related to the discussion topic to meet the user's potential consumption needs.

[0034] Step S202, matching the transaction data and social behavior data with a preset product recommendation rule library, and determining whether a target product recommendation rule is matched.

[0035] In step S202, the acquired transaction data is cleaned and sorted, irrelevant information is removed, and key features are extracted, such as product type, purchase time, purchase frequency, etc. The social behavior data is deeply mined to analyze information such as user interests, social networks, and behavior patterns. For example, natural language processing technology is used to analyze user comments and discussions to identify hot topics of concern; graph algorithms are used to analyze users' social networks to obtain popular trends in their social circles. The processed transaction data and analyzed social behavior data are matched with a preset product recommendation rule library. The preset product recommendation rule library can contain a variety of recommendation rules based on expert knowledge and big data analysis, which associate the characteristics of transaction data and social behavior data with potential target products.

[0036] Determine whether the transaction data and social behavior data match the recommendation rules of one or some target products in the preset product recommendation rule library. If the match is successful, it means that the user is interested in a certain type of product, and the product of this type can be used as the recommended target product; if the match fails, further data analysis or optimization of the preset product recommendation rule library is required.

[0037] Step S203: when a target product recommendation rule is matched, determine the target product type associated with the target product recommendation rule.

[0038] In step S203, for each matched target product recommendation rule, the target product type is determined by parsing the product type information contained in the rule. The product recommendation rule can be based on the user's behavior pattern, interest preference, social network characteristics, etc. as the association condition of the target product type.

[0039] Based on the parsed product type information, the target product type that best matches the rule is selected. Based on the type selection, the target product type is further confirmed by combining the user's historical purchase records, browsing behavior, search keywords and other information. For example, if there are products associated with the recommendation rule in the user's historical purchase records, the same or complementary products can be given priority; if the user has recently browsed or searched for a certain type of product frequently, it can be included as part of the target product type.

[0040] Step S204, obtaining the identity information of the target user, determining the recommended product based on the identity information and the target product type, and recommending the recommended product to the target user.

[0041] In step S204, the identity information of the target user is obtained from the personal information authorized by the user. The identity information may include but is not limited to age, gender, occupation, income level, geographic location, hobbies, etc. This information helps to further refine the user portrait and achieve more personalized recommendations. According to the identity information of the target user and the target product type determined in the previous step, specific recommended products that meet the user's characteristics and needs are screened from the product database. For example, if the target user is a young woman and the target product type is sports equipment, some small loans can be recommended; if the target user is a high-income business person and the target product type is a fund, financial products corresponding to the target user's income level may be recommended.

[0042] Information about recommended products is pushed to target users through the financial institution's application on the user's terminal device. The push can be in the form of pop-up windows, message notifications, personalized recommendation lists, etc., to ensure that users can receive recommended information in a timely and convenient manner.

[0043] The product recommendation method provided in the embodiment of the present application solves the problem of inaccurate product recommendation in the related art by obtaining the transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform; matching the transaction data and social behavior data with the preset product recommendation rule library, and judging whether the target product recommendation rule is matched; in the case of matching the target product recommendation rule, determining the target product type associated with the target product recommendation rule; obtaining the identity information of the target user, determining the recommended product based on the identity information and the target product type, and recommending the recommended product to the target user. By matching the transaction data and social behavior data of the user with the preset product recommendation rule library, if the target product recommendation rule is matched, determining the recommended product based on the target product type associated with the target product recommendation rule and the identity information of the user, and recommending the recommended product to the target user, the correlation between the recommended product and the target user is improved, thereby achieving the effect of improving the accuracy of product recommendation.

[0044] In order to efficiently recommend products that better meet user needs to users, a preset product recommendation rule library is constructed. Optionally, in the product recommendation method provided in the embodiment of the present application, the preset product recommendation rule library is constructed in the following manner: determine multiple types of products of a financial institution, and for each type of product, determine the purchasing users of the product; obtain historical transaction data and historical social behavior data of the purchasing users within a target period of purchasing the product; extract multiple features from the historical transaction data and historical social behavior data, and for each feature, count the proportion of purchasing users who contain the feature in the historical transaction data and historical social behavior data in the purchasing user group to obtain the feature proportion; when the feature proportion is greater than or equal to a proportion threshold, determine the feature as an associated feature of the product; construct product matching rules based on the associated features of each type of product, and construct a preset product recommendation rule library based on the matching rules of multiple types of products of the financial institution.

[0045] In some examples, first, multiple types of products provided or sold by financial institutions are determined, such as savings accounts, credit cards, investment and financial management, insurance products, loan services, etc. Then the purchasing user groups are divided. For each type of product, the user groups that have purchased or used the product are determined. These users can be existing customers of the financial institution or users who purchase related products through partner platforms. The historical transaction data and historical social behavior data of the above-mentioned purchasing user groups within the target period of purchasing the product are collected. These data may include transaction time, transaction amount, transaction frequency, transaction product type, as well as activity records, interest preferences, social relationship networks, etc. on social platforms.

[0046] Extract multiple features from historical transaction data and historical social behavior data, such as user income level, consumption habits, social activity, interest tags, etc. For each feature, calculate the proportion of purchasing users with this feature in the purchasing user group, that is, the feature proportion. Set a proportion threshold based on expert experience, and for those features whose feature proportion is greater than or equal to the threshold, determine them as related features related to the product type. Related features reflect the potential connection between product purchases and user behavior patterns to a certain extent.

[0047] Based on the associated features of each type of product, we use machine learning algorithms or expert rules to build product matching rules. When we receive new transaction data or social behavior data from users, we can quickly determine whether the user may be interested in a certain type of product. We integrate the matching rules of all types of products of financial institutions and build a preset product recommendation rule library to provide data and logic support for subsequent personalized product recommendations.

[0048] This embodiment forms a comprehensive and intelligent preset product recommendation rule library by performing feature extraction, statistical analysis and rule construction from a large amount of historical transaction data and historical social behavior data, so that product recommendations for users are more accurate and personalized.

[0049] In order to ensure the accuracy and timeliness of the associated features, it is necessary to regularly update the matching rules in the preset product recommendation rule library. Optionally, in the product recommendation method provided in the embodiment of the present application, the method also includes: re-counting the feature proportion of the associated features of each product at every preset rule update cycle to obtain an updated feature proportion; when the updated feature proportion is less than the proportion threshold, removing the associated features corresponding to the updated feature proportion from the product matching rules; when the number of associated features of the product is less than the quantity threshold, obtaining the transaction data and social behavior data of users who purchased the product within the preset rule update cycle; extracting multiple features from the transaction data and social behavior data, and counting the feature proportion of each feature; when the feature proportion is greater than or equal to the proportion threshold, and the feature is not an associated feature of the product, determining the feature as a newly added associated feature of the product, and updating the product matching rules based on the newly added associated features.

[0050] In some examples, a preset rule update cycle is set based on expert experience, such as quarterly or semi-annual, and is flexibly adjusted according to business needs and the frequency of data changes. Every preset rule update cycle, the feature proportion of each product's associated features in the purchasing user group is recounted to obtain updated feature proportion data. For the updated feature proportion, if it is found that the feature proportion of some associated features is less than the proportion threshold, it means that the relevance of these features to product purchases has weakened in the current cycle and no longer meets the recommendation conditions, so they are removed from the product matching rules.

[0051] In order to avoid too few associated features in the matching rules of products, resulting in a lower hit rate of the matching rules of products. The matching rules of products need to be updated regularly. For example, check the number of associated features in the matching rules of each product within the preset rule update cycle. If the number is less than the quantity threshold, it means that the rule may be too simple or outdated and needs to be re-evaluated and updated. By obtaining the transaction data and social behavior data of new users who purchased the product within the preset rule update cycle, a variety of potential features are extracted from them, and the feature proportion of each feature is counted. When the feature proportion is greater than or equal to the proportion threshold, if the feature has not been identified as an associated feature of the product, it is determined as a newly added associated feature of the product. Based on the newly added associated features, update the matching rules of the product to ensure that the preset product recommendation rule base can promptly reflect changes in the market and user behavior, and improve the accuracy and effectiveness of product recommendations.

[0052] This embodiment can continuously optimize the preset product recommendation rule library through a dynamic update mechanism for the preset product recommendation rule library, ensure that the matching rules in the preset product recommendation rule library are both comprehensive and accurate, and can adapt to the ever-changing user needs and market environment, thereby providing users with more personalized recommendation services, while creating higher product recommendation value and customer satisfaction for financial institutions.

[0053] For target users who do not match any product recommendation rules, recommended products of the customer group to which the target user belongs can be determined based on the target user's identity information, and a product recommendation table can be pushed to the target user based on users belonging to the same customer group. Optionally, in the product recommendation method provided in the embodiment of the present application, after determining whether the target product recommendation rules are matched, the method also includes: if the target product recommendation rules are not matched, obtaining the target user's identity information; determining the customer group to which the target user belongs based on the identity information, and obtaining multiple recommended products for the customer group within a preset period; generating a product recommendation table based on the multiple recommended products, and pushing the product recommendation table to the target user.

[0054] In some examples, the target user is divided into corresponding customer groups based on the target user's identity information. For example, users can be divided into different customer groups such as "young office workers", "middle-aged family customers", "high net worth investors", etc. according to age and income level. Obtain multiple recommended products for the customer group to which the target user belongs within a preset period (such as one week, one month). These recommended products can be selected by the product recommendation or product production department of the financial institution based on the general needs and preferences of the customer group and market trends. Generate a product recommendation table based on the selected multiple recommended products. Push the generated product recommendation table to the target user in the form of email, in-application message, personalized recommendation list, etc., to ensure that the user can receive these general recommendation information.

[0055] This embodiment provides a set of universal recommended products based on the user's identity information and the common needs of the customer group to which they belong when personalized recommendations cannot be made based on matching rules, thereby ensuring that valuable product recommendation information can be provided to the user in any case, thereby improving user satisfaction and the service quality of the financial institution.

[0056] After determining the target product type, recommended products can be obtained based on the target model. Optionally, in the product recommendation method provided in the embodiment of the present application, determining recommended products based on identity information and target product type includes: extracting identity features from the identity information, wherein the identity features include at least one of the following: age, gender, occupation, region and income; inputting the identity features and the target product type into the target model to obtain recommended products, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical identity features, historical product types and historical recommended products.

[0057] In some examples, a set of identity features are extracted from the identity information of the target user, including but not limited to age, gender, occupation, region, and income level. These features are important components of the user profile and can reflect the user's personal attributes and socioeconomic status. The extracted identity features and the previously determined target product type are input into the target model, which can be a model trained by machine learning to predict products that the user may be interested in.

[0058] The training of the target model is based on multiple sets of training samples, each set of training samples includes three parts of information: historical identity features, historical product types, and historical recommended products. Historical identity features and historical product types are the inputs of the model, and historical recommended products are the target outputs of model training. Through a large amount of training, the target model can learn the matching rules between recommended products and user preferences under different combinations of identity features and product types. After receiving the identity features and target product type inputs of the current target user, the target model outputs the recommended products as the prediction results based on the learned matching rules.

[0059] This embodiment generates personalized recommended products based on the target model based on machine learning and the identity information of the target user and the target product type, thereby improving the accuracy and personalization of product recommendations.

[0060] After each time a recommended product is recommended to a target user, feedback data of the target user is collected to update the target user's transaction data and social behavior data in the database of the financial institution in real time. Optionally, in the product recommendation method provided in an embodiment of the present application, after the recommended product is recommended to the target user, the method further includes: obtaining feedback data of the target user on the recommended product, wherein the feedback data includes at least one of the following: purchases, clicks, views, and feedback; and adding the feedback data to the target user's transaction data and social behavior data.

[0061] In some examples, after product recommendations, feedback data on the recommended products from target users needs to be collected. Such feedback data may include, but is not limited to, the following categories: whether the user has purchased the recommended product, the number of clicks, views, and any direct feedback that the user may provide, such as preferences or dissatisfaction expressed through evaluations, questionnaires, social media comments, etc. Among them, purchase feedback is the most direct feedback, indicating the user's actual interest in the recommended product; clicks and views reflect the user's initial attention and interest in the product; and feedback provides detailed information on the user's satisfaction with the product recommendation, which helps to understand the recommendation effect and user needs. The collected feedback data is integrated into the target user's transaction data and social behavior data to form a more comprehensive and real-time user data set.

[0062] This embodiment further optimizes the recommendation effect and improves the user experience by updating the user's data in real time and adjusting the recommendation strategy according to the user's real-time feedback.

[0063] Before obtaining the target user's transaction data and social behavior data, it is necessary to obtain the target user's authorization. Optionally, in the product recommendation method provided in the embodiment of the present application, before obtaining the target user's transaction data and social behavior data within a preset period, the method also includes: sending an authorization request to the target user, wherein the authorization request is used to request the target user to allow obtaining the target user's transaction data and social behavior data; upon receiving the target user's confirmation authorization indication for the authorization request, executing the step of obtaining the target user's transaction data and social behavior data within the preset period; obtaining the target user's transaction data and social behavior data within the preset period includes: obtaining the target user's product purchase records, browsing records and search keywords within the preset period, and determining at least one of the following as the target user's transaction data: product purchase records, browsing records and search keywords; obtaining the target user's interaction data, comments, likes, shares and follow-up data on the social platform within the preset period, and determining at least one of the following as the target user's social behavior data: interaction data, comments, likes, shares and follow-up data.

[0064] In some examples, an authorization request is sent to the target user to request the user to allow the acquisition of his / her transaction data and social behavior data within a preset period. The authorization request clearly states the purpose, scope and privacy protection measures of the data to ensure the user's right to know and data security. Wait for the target user to respond to the authorization request. If the user's confirmation authorization instruction is received, that is, the user agrees to share his / her data for optimizing product recommendation services, then the next step of data acquisition will be executed.

[0065] Obtain information such as product purchase records, browsing records, and search keywords within a preset period from the channels authorized by the target user. The acquisition of transaction data follows the scope of user authorization to ensure the legitimacy and privacy protection of the data. Obtain social behavior information such as interaction data (such as message sending and receiving), comments, likes, sharing, and follow data within a preset period from the social platforms authorized by the target user. The acquisition of social behavior data complies with the user privacy agreement and authorization scope.

[0066] This embodiment obtains transaction data and social behavior data authorized by the user on the basis of fully respecting the user's privacy and data protection, thereby providing data support for subsequent personalized product recommendations.

[0067] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0068] The embodiment of the present application also provides a product recommendation device. It should be noted that the product recommendation device of the embodiment of the present application can be used to execute the product recommendation method provided by the embodiment of the present application. The product recommendation device provided by the embodiment of the present application is introduced below.

[0069] Figure 3 Schematic diagram of a product recommendation device according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0070] The acquisition unit 301 is used to acquire the transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform;

[0071] A matching unit 302 is used to match the transaction data and social behavior data with a preset product recommendation rule library, and determine whether a target product recommendation rule is matched;

[0072] The first determination form 303 is used to determine the target product type associated with the target product recommendation rule when the target product recommendation rule is matched;

[0073] The recommendation unit 304 is used to obtain the identity information of the target user, determine the recommended product based on the identity information and the target product type, and recommend the recommended product to the target user.

[0074] The product recommendation device provided in the embodiment of the present application obtains the transaction data and social behavior data of the target user within a preset period through the acquisition unit 301, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform; the matching unit 302 matches the transaction data and social behavior data with the preset product recommendation rule library, and determines whether the target product recommendation rule is matched; the first determination unit 303 determines the target product type associated with the target product recommendation rule when the target product recommendation rule is matched; the recommendation unit 304 obtains the identity information of the target user, determines the recommended product based on the identity information and the target product type, and recommends the recommended product to the target user, thereby solving the problem of inaccurate product recommendation in the related art, and matching the user's transaction data and social behavior data with the preset product recommendation rule library. If the target product recommendation rule is matched, the recommended product is determined based on the target product type associated with the target product recommendation rule and the user's identity information, and the recommended product is recommended to the target user, thereby improving the correlation between the recommended product and the target user, thereby achieving the effect of improving the accuracy of product recommendation.

[0075] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: a second determination unit, used to determine multiple types of products of a financial institution, and for each type of product, determine the purchasing users of the product; a first data acquisition unit, used to obtain historical transaction data and historical social behavior data of purchasing users within a target period of purchasing products; a first extraction unit, used to extract multiple features from the historical transaction data and historical social behavior data, and for each feature, count the proportion of purchasing users containing the feature in the historical transaction data and historical social behavior data in the purchasing user group to obtain the feature proportion; a third determination unit, used to determine the feature as an associated feature of the product when the feature proportion is greater than or equal to a proportion threshold; a construction unit, used to construct product matching rules based on the associated features of each type of product, and construct a preset product recommendation rule library based on the matching rules of multiple types of products of financial institutions.

[0076] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: a statistical unit, used to re-count the feature proportions of the associated features of each product at every preset rule update cycle to obtain an updated feature proportion; a removal unit, used to remove the associated features corresponding to the updated feature proportions from the matching rules of the product when the updated feature proportions are less than a proportion threshold; a second data acquisition unit, used to obtain the transaction data and social behavior data of users who purchased the product within the preset rule update cycle when the number of associated features of the product is less than a quantity threshold; a second extraction unit, used to extract multiple features from the transaction data and social behavior data, and count the feature proportions of each feature; an updating unit, used to determine the feature as a newly added associated feature of the product when the feature proportion is greater than or equal to the proportion threshold and the feature is not an associated feature of the product, and update the matching rules of the product based on the newly added associated features.

[0077] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: an information acquisition unit, used to obtain the identity information of the target user when the target product recommendation rule is not matched; a fourth determination unit, used to determine the customer group to which the target user belongs based on the identity information, and obtain multiple recommended products for the customer group within a preset period; a push unit, used to generate a product recommendation table based on multiple recommended products, and push the product recommendation table to the target user.

[0078] Optionally, in the product recommendation device provided in the embodiment of the present application, the recommendation unit 304 includes: an extraction module, used to extract identity features from the identity information, wherein the identity features include at least one of the following: age, gender, occupation, region and income; an input module, used to input the identity features and the target product type into the target model to obtain recommended products, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical identity features, historical product types and historical recommended products.

[0079] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: a feedback acquisition unit, used to obtain feedback data of the target user on the recommended product, wherein the feedback data includes at least one of the following: purchases, clicks, views and opinion feedback; an adding unit, used to add the feedback data to the transaction data and social behavior data of the target user.

[0080] Optionally, in the product recommendation device provided in the embodiment of the present application, the device also includes: a request unit, used to send an authorization request to the target user, wherein the authorization request is used to request the target user to allow the acquisition of the target user's transaction data and social behavior data; an execution unit, used to execute the step of acquiring the target user's transaction data and social behavior data within a preset period upon receiving the target user's confirmation authorization indication for the authorization request; the acquisition unit 301 includes: a first acquisition module, used to acquire the target user's product purchase records, browsing records and search keywords within a preset period, and determine at least one of the following as the target user's transaction data: product purchase records, browsing records and search keywords; a second acquisition module, used to acquire the target user's interaction data, comments, likes, shares and follow-up data on the social platform within the preset period, and determine at least one of the following as the target user's social behavior data: interaction data, comments, likes, shares and follow-up data.

[0081] The product recommendation device includes a processor and a memory. The acquisition unit 301, matching unit 302, first confirmation unit 303 and recommendation unit 304 are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

[0082] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the accuracy of product recommendations can be improved by adjusting kernel parameters.

[0083] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0084] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, and the program implements a product recommendation method when executed by a processor.

[0085] An embodiment of the present invention provides a processor, which is used to run a program, wherein the product recommendation method is executed when the program is running.

[0086] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. Figure 4As shown, the electronic device 401 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining the transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on the social platform; matching the transaction data and social behavior data with the preset product recommendation rule library, and determining whether the target product recommendation rule is matched; in the case of matching the target product recommendation rule, determining the target product type associated with the target product recommendation rule; obtaining the identity information of the target user, determining the recommended product based on the identity information and the target product type, and recommending the recommended product to the target user. The device in this article can be a server, PC, PAD, mobile phone, etc.

[0087] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining transaction data and social behavior data of a target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on a social platform; matching the transaction data and social behavior data with a preset product recommendation rule library, and determining whether a target product recommendation rule is matched; if a target product recommendation rule is matched, determining a target product type associated with the target product recommendation rule; obtaining identity information of the target user, determining a recommended product based on the identity information and the target product type, and recommending the recommended product to the target user.

[0088] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0089] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0090] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0092] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0093] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0094] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0095] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0096] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0097] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A product recommendation method, characterized in that: include: Acquire transaction data and social behavior data of the target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on a social platform; Matching the transaction data and the social behavior data with a preset product recommendation rule library, and determining whether a target product recommendation rule is matched; In the case where the target product recommendation rule is matched, determining the target product type associated with the target product recommendation rule; The identity information of the target user is obtained, a recommended product is determined based on the identity information and the target product type, and the recommended product is recommended to the target user.

2. The method according to claim 1, characterized in that The preset product recommendation rule base is constructed in the following way: Determine multiple types of products of the financial institution, and for each type of product, determine the purchasing users of the product; Acquire historical transaction data and historical social behavior data of the purchasing user within the target period of purchasing the product; Extracting multiple features from the historical transaction data and the historical social behavior data, and for each feature, counting the proportion of purchasing users whose historical transaction data and the historical social behavior data contain the feature in the purchasing user group to obtain a feature proportion; When the feature proportion is greater than or equal to the proportion threshold, the feature is determined as an associated feature of the product; The matching rules of the products are constructed based on the associated features of each type of product, and the preset product recommendation rule library is constructed based on the matching rules of multiple types of products of the financial institution.

3. The method according to claim 2, characterized in that The method further comprises: Recalculate the feature proportion of each product's associated features every preset rule update cycle to obtain an updated feature proportion; When the updated feature proportion is less than the proportion threshold, the associated features corresponding to the updated feature proportion are removed from the matching rules of the product; When the number of associated features of the product is less than a quantity threshold, obtaining transaction data and social behavior data of users who purchased the product within the preset rule update period; Extracting multiple features from the transaction data and the social behavior data, and calculating the feature proportion of each feature; When the feature proportion is greater than or equal to the proportion threshold and the feature is not an associated feature of the product, the feature is determined as a newly added associated feature of the product, and the matching rule of the product is updated based on the newly added associated feature.

4. The method according to claim 1, characterized in that: After determining whether the target product recommendation rule is matched, the method further includes: If the target product recommendation rule is not matched, obtaining the identity information of the target user; Determine the customer group to which the target user belongs based on the identity information, and obtain a plurality of recommended products for the customer group within the preset period; A product recommendation table is generated based on the multiple recommended products, and the product recommendation table is pushed to the target user.

5. The method according to claim 1, characterized in that Determining the recommended product based on the identity information and the target product type includes: Extracting identity features from the identity information, wherein the identity features include at least one of the following: age, gender, occupation, region, and income; The identity features and the target product type are input into a target model to obtain the recommended product, wherein the target model is trained by multiple groups of training samples, each group of training samples includes historical identity features, historical product types and historical recommended products.

6. The method according to claim 1, characterized in that After recommending the recommended product to the target user, the method further includes: Acquire feedback data of the target user on the recommended product, wherein the feedback data includes at least one of the following: purchase, click, browse times and opinion feedback; The feedback data is added to the transaction data and social behavior data of the target user.

7. The method according to claim 1, characterized in that Before obtaining the transaction data and social behavior data of the target user within a preset period, the method further includes: Sending an authorization request to a target user, wherein the authorization request is used to request the target user to allow obtaining the target user's transaction data and social behavior data; Upon receiving a confirmation authorization indication from the target user for the authorization request, executing the step of acquiring the transaction data and social behavior data of the target user within a preset period; Acquiring the target user's transaction data and social behavior data within a preset period includes: Acquire the product purchase record, browsing record and search keyword of the target user within a preset period, and determine at least one of the following as the transaction data of the target user: the product purchase record, the browsing record and the search keyword; The interaction data, comments, likes, shares and attention data of the target user on the social platform within a preset period are obtained, and at least one of the following is determined as the social behavior data of the target user: the interaction data, the comments, the likes, the shares and the attention data.

8. A product recommendation device, characterized in that: include: An acquisition unit, configured to acquire transaction data and social behavior data of a target user within a preset period, wherein the social behavior data includes at least one of the following: interaction data between the target user and other users, and operation data of the target user on a social platform; A matching unit, used to match the transaction data and the social behavior data with a preset product recommendation rule library, and determine whether a target product recommendation rule is matched; A first determining unit, configured to determine a target product type associated with the target product recommendation rule when the target product recommendation rule is matched; The recommendation unit is used to obtain the identity information of the target user, determine the recommended product based on the identity information and the target product type, and recommend the recommended product to the target user.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the product recommendation method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the product recommendation method described in any one of claims 1 to 7.

Images