Method and device for determining to-be-recommended product and electronic equipment

Abstract

The invention discloses a to-be-recommended product determination method and device and electronic equipment. The method relates to the field of financial science and technology, and comprises the following steps: receiving product demand information sent by a target user through a user side, and obtaining a product type from the product demand information; acquiring historical user time sequence information of the target user in a historical time period, acquiring associated time sequence information associated with the product type from the historical user time sequence information, and determining target behavior information of the target user in the historical time period according to the associated time sequence information; obtaining product information of each preset product under the product type to obtain M pieces of product information; and determining a target matching degree between the target behavior information and each piece of product information, determining a to-be-recommended product from the M preset products according to the target matching degree, and sending the to-be-recommended product to the user side. Through the method and the device, the problem of relatively low accuracy of product recommendation for the user in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, and electronic device for determining a product to be recommended. Background Technology

[0002] As financial institutions offer an increasing variety and number of financial products, some users are unable to determine which product best suits their needs when making a purchase. Consequently, they need to review the details of each product individually, increasing the complexity of the purchase process.

[0003] To reduce the complexity and time required for users to purchase financial products, financial institutions often recommend new products based on the financial products that users have previously purchased. This helps users select products when they have a need to buy them, thereby improving the efficiency of their product purchase.

[0004] However, as user needs are constantly changing, the products a user has purchased in the past may not match their current needs. This results in a lower accuracy rate for financial institutions to recommend new products based on the user's past purchases, thus affecting the user's product purchase efficiency.

[0005] There is currently no effective solution to the problem of low accuracy in product recommendations for users in related technologies. Summary of the Invention

[0006] The main objective of this application is to provide a method, apparatus, and electronic device for determining products to be recommended, in order to solve the problem of low accuracy in product recommendations to users in related technologies.

[0007] To achieve the above objectives, according to one aspect of this application, a method for determining products to be recommended is provided. The method includes: receiving product demand information sent by a target user through a user terminal, and obtaining a product type from the product demand information; obtaining historical user time-series information of the target user within a historical time period, and obtaining associated time-series information related to the product type from the historical user time-series information, and determining the target user's target behavior information within the historical time period based on the associated time-series information; obtaining M preset products under the product type, and obtaining product information for each preset product, resulting in M ​​product information, where M is a positive integer; determining the matching degree between the target behavior information and each product information, obtaining M target matching degrees, and determining the product to be recommended from the M preset products based on the M target matching degrees, and sending the product to be recommended to the user terminal.

[0008] Optionally, determining the target user's target behavior information within a historical time period based on the associated time series information includes: obtaining feature values ​​under each user characteristic of the target user from the associated time series information to obtain N feature value sequences, where N is a positive integer; obtaining P behavioral indicator features, and determining the behavioral feature data under each behavioral indicator feature according to the N feature value sequences to obtain P behavioral feature data, and determining the P behavioral feature data as the target behavior information, where P is a positive integer.

[0009] Optionally, determining the matching degree between the target behavior information and each product information to obtain M target matching degrees includes: obtaining a preset user set and determining the user cluster to which the target user belongs in the preset user set to obtain a target user cluster, wherein the preset user set includes H user clusters, where H is a positive integer; determining the matching degree between the target behavior information and each product information to obtain M first matching degrees; obtaining the product purchase records of each preset user in the target user cluster, and determining the matching degree between the target user cluster and each product information based on the product purchase records to obtain M second matching degrees; and determining the target matching degree of each product information based on the first matching degree and the second matching degree to obtain M target matching degrees.

[0010] Optionally, determining the user cluster to which the target user belongs in the preset user set, and obtaining the target user cluster includes: determining the central user located at the cluster center in each user cluster, obtaining H central users, and obtaining the preset behavior information of each central user; calculating the cosine similarity between the target user's target behavior information and the preset behavior information of each central user, respectively, to obtain H first similarities; obtaining the maximum similarity among the H first similarities, and determining the user cluster to which the maximum similarity belongs as the target user cluster.

[0011] Optionally, determining the matching degree between the target behavior information and each product information to obtain M first matching degrees includes: for any product information, inputting the product information into the product recognition model to obtain the standard behavior information corresponding to the product information; determining the similarity between the standard behavior information and the target behavior information to obtain a second similarity, and determining the second similarity as the first matching degree between the product information and the target behavior information.

[0012] Optionally, determining the matching degree between the target user cluster and each product information based on product purchase records to obtain M second matching degrees includes: determining the purchase information of each preset product based on the product purchase records of each preset user to obtain M purchase information, wherein the purchase information includes at least one of the following: purchase quantity, purchase frequency; determining the popularity value of each preset product based on the M purchase information to obtain M popularity values, and determining the popularity value of each preset product as the second matching degree to obtain M second matching degrees.

[0013] Optionally, determining the product to be recommended from M preset products based on M target matching degrees includes: obtaining historical evaluation information for each preset product and determining recommendation parameters for each preset product based on the historical evaluation information; determining a recommendation score for each preset product based on its recommendation parameters and target matching degree, resulting in M ​​recommendation scores; obtaining the number of products in the product demand information and selecting preset products that meet the required number of products from the M preset products according to the order of recommendation scores from largest to smallest, thus obtaining the product to be recommended.

[0014] To achieve the above objectives, according to another aspect of this application, an apparatus for determining a product to be recommended is provided. The apparatus includes: a receiving unit, configured to receive product demand information sent by a target user through a user terminal, and obtain a product type from the product demand information; a first obtaining unit, configured to obtain historical user time-series information of the target user within a historical time period, and obtain associated time-series information related to the product type from the historical user time-series information, and determine the target user's target behavior information within the historical time period based on the associated time-series information; a second obtaining unit, configured to obtain M preset products under the product type, and obtain product information for each preset product, resulting in M ​​product information, where M is a positive integer; and a determining unit, configured to determine the matching degree between the target behavior information and each product information, obtaining M target matching degrees, and determine the product to be recommended from the M preset products based on the M target matching degrees, and send the product to be recommended to the user terminal.

[0015] To achieve the above objectives, according to another aspect of this application, an electronic device is provided, the electronic device including a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described method for determining the recommended product during runtime.

[0016] To achieve the above objectives, according to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the method for determining the recommended product described above.

[0017] In this embodiment, the method involves receiving product demand information sent by a target user through a user terminal and obtaining the product type from the product demand information; obtaining historical user time sequence information of the target user within a historical time period and obtaining associated time sequence information related to the product type from the historical user time sequence information, and determining the target user's target behavior information within the historical time period based on the associated time sequence information; obtaining M preset products under the product type and obtaining product information for each preset product, resulting in M ​​product information, where M is a positive integer; determining the matching degree between the target behavior information and each product information, obtaining M target matching degrees, and determining the product to be recommended from the M preset products based on the M target matching degrees, and sending the product to be recommended to the user terminal. By analyzing the user's behavior information and determining the product to be recommended with the highest matching degree between the behavior information and the product information, the method recommends the product to the user, thereby assisting the user in selecting products and achieving the technical effect of improving the accuracy of product recommendation operations. This solves the technical problem of low accuracy in product recommendation for users in related technologies. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining products to be recommended is shown.

[0020] Figure 2 This is a flowchart of the method for determining the product to be recommended according to Embodiment 1 of this application;

[0021] Figure 3 This is a schematic diagram of the device for determining the product to be recommended according to Embodiment 2 of this application;

[0022] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] It should be noted that the methods, apparatus, and electronic devices for determining the products to be recommended as disclosed herein can be used in the fintech field, or in any field other than fintech. The application fields of the methods, apparatus, and electronic devices for determining the products to be recommended as disclosed herein are not limited.

[0027] It should be noted that all information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) used in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse use. If the user chooses to refuse, the process will proceed to the expert decision-making process. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface. After receiving consent from the aforementioned user or organization, the relevant information is obtained. Users can view the purpose of data use in real time through the authorization interface and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0028] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0029] Example 1

[0030] According to an embodiment of this application, an embodiment of a method for determining a product to be recommended is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining products to be recommended is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, processing devices such as microprocessors or programmable logic devices), 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, a universal serial bus port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0033] 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 method for determining the recommended product in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for determining the recommended product. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0035] The display may be, for example, a touchscreen LCD display that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0036] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for determining the products to be recommended is shown. Figure 2 This is a flowchart of the method for determining the product to be recommended according to Embodiment 1 of this application, such as... Figure 2 As shown, the method includes:

[0037] Step S201: Receive product requirement information sent by the target user through the user terminal, and obtain the product type from the product requirement information.

[0038] It should be noted that the execution entity in this embodiment can be a product recommendation system. This system can determine the product with the highest matching degree with the user's recent behavior information based on the user's product demand information, and recommend it to the user as a product to be recommended.

[0039] It should be noted that product demand information can be a detailed description of the financial products needed, proactively provided by the user, which may include product category, risk tolerance, etc. Product type can be a specific financial service category determined based on the user's demand information, such as short-term liquidity investment products, long-term investment funds, insurance services, etc.

[0040] For example, after a financial institution receives product demand information sent by a target user through a user terminal, it needs to parse the descriptive information contained in the product demand information in order to determine the type of financial product that the user needs to purchase.

[0041] For example, the product demand information could be: "I need to purchase a financial product with stable returns and high liquidity for short-term fund management." In this case, after analyzing the text content, the system can determine the product type as: short-term liquidity financial product.

[0042] Step S202: Obtain historical user time sequence information of the target user within a historical time period, obtain associated time sequence information related to the product type from the historical user time sequence information, and determine the target behavior information of the target user within the historical time period based on the associated time sequence information.

[0043] It should be noted that historical user time-series information refers to time-series data recording all financial activities of the target user over a past period (such as the most recent quarter), which may include account activity, transaction records, product query history, and other information. Related time-series information is user behavior data directly related to a specific product type, filtered from the historical user time-series information. Target behavior information consists of key behavioral characteristics of the target user within a historical time period, derived by the system based on the analysis of related time-series information.

[0044] For example, after determining the product type, the system needs to access all historical user time-series information for the target user within a historical time period, such as the target user's deposit curve and transaction information with financial institutions in the past quarter. Furthermore, the system can identify related time-series information closely associated with the previously identified product type from the historical user time-series information. For example, for "short-term liquidity wealth management products," the system will focus on the user's frequent small-amount deposit and withdrawal records, the frequency of wealth management product inquiries, and other relevant information.

[0045] Furthermore, after obtaining the associated time-series information related to the product type, in order to improve the security of user information when making product recommendations, the user's behavioral information can be determined based on the associated time-series information. This behavioral information can then indirectly reflect the user's economic status. While improving the security of the user's financial information, it is possible to accurately determine financial products with a high degree of matching with the target user based on the behavioral information.

[0046] Step S203: Obtain M preset products under the product type, and obtain product information for each preset product to obtain M product information, where M is a positive integer.

[0047] It should be noted that the preset products can be financial products from financial institutions, and the product information can be detailed attributes of each preset product, including but not limited to yield, risk level, minimum investment amount, redemption conditions, and additional services.

[0048] For example, after determining the user's behavioral information, it is necessary to obtain the financial products contained in the financial institution and the product information of each financial product in order to determine the matching degree between the user and the product. This enables the system to perform matching operations based on the product information and user behavioral information and obtain a more accurate matching result.

[0049] Step S204: Determine the matching degree between the target behavior information and each product information to obtain M target matching degrees, and determine the product to be recommended from the M preset products based on the M target matching degrees, and send the product to be recommended to the user terminal.

[0050] It should be noted that target matching degree refers to the assessment of the degree of consistency between target behavioral information and each preset product information, which is used to quantify the fit between the product and user needs.

[0051] For example, after obtaining target behavior information and product information, the system defines a set of quantitative indicators to evaluate the similarity between user behavior information and product information. These indicators may include the degree of direct overlap between user behavior and product characteristics, the correlation between user preferences and product market performance, etc. The system will use these indicators to compare and analyze the target user's behavior data with each preset product, and calculate M matching scores, thereby realizing intelligent and personalized product recommendations, ensuring that each matching score is a precise match based on specific user needs and product attributes.

[0052] After obtaining M target matching scores, the system will sort them according to the matching score from highest to lowest, and select the product with the highest score as the product to be recommended. This improves the matching score between users and products, thereby improving the accuracy of product recommendations and indirectly reducing the complexity of users selecting products, thus improving the efficiency of users purchasing financial products.

[0053] It should be noted that when determining the products to be recommended, the system can also select the same number of products as indicated in the product demand information, in descending order of matching degree, allowing users to further select the products they need to purchase from multiple recommended products.

[0054] It's worth noting that when determining which products to recommend, additional constraints can be considered, such as product inventory and compliance requirements. This ensures that the recommended products not only best meet the user's needs but are also the current priority. Through this comprehensive approach, the system can find the optimal balance between personalization and practical feasibility, improving the feasibility and appeal of the recommendations.

[0055] The method for determining the product to be recommended provided in this application embodiment involves receiving product demand information sent by a target user through a user terminal and obtaining the product type from the product demand information; obtaining historical user time sequence information of the target user within a historical time period and obtaining associated time sequence information related to the product type from the historical user time sequence information, and determining the target user's target behavior information within the historical time period based on the associated time sequence information; obtaining M preset products under the product type and obtaining product information for each preset product, resulting in M ​​product information, where M is a positive integer; determining the matching degree between the target behavior information and each product information, obtaining M target matching degrees, and determining the product to be recommended from the M preset products based on the M target matching degrees, and sending the product to be recommended to the user terminal. By analyzing the user's behavior information and determining the product to be recommended with the highest matching degree between the behavior information and the product information, the method recommends the product to the user, thereby assisting the user in selecting products and achieving the technical effect of improving the accuracy of product recommendation operations. This solves the technical problem of low accuracy in product recommendation for users in related technologies.

[0056] To accurately determine target behavior information, optionally, in the method for determining the product to be recommended provided in this application embodiment, determining the target user's target behavior information within a historical time period based on associated time series information includes: obtaining feature values ​​under each user characteristic of the target user from the associated time series information to obtain N feature value sequences, where N is a positive integer; obtaining P behavioral indicator features, and determining behavioral feature data under each behavioral indicator feature according to the N feature value sequences to obtain P behavioral feature data, and determining the P behavioral feature data as target behavior information, where P is a positive integer.

[0057] It should be noted that user characteristics refer to multiple dimensions describing user attributes, such as age, occupation, financial status, and historical transaction preferences. The feature value sequence represents the user's specific quantitative performance over a historical period under each user characteristic, forming a series of values ​​used to construct the user's behavioral model. Behavioral indicator characteristics are specific behavioral metrics related to product recommendations, such as the frequency of user inquiries about financial products, average daily assets, and transfer frequency. Behavioral feature data is a quantitative description of user behavior calculated based on the feature value sequence for each behavioral indicator characteristic. P behavioral feature data collectively depict the user's historical behavioral patterns regarding product needs.

[0058] For example, the system first extracts feature values ​​for each user characteristic of the target user from the associated time-series information. For instance, for the product type "short-term liquidity financial products," the system might focus on N features such as age, occupation, investment experience, average daily assets, and trading activity. For each feature, the system collects the user's specific performance over a historical period, such as determining the "average daily assets" of the past quarter, thus constructing a "daily average asset feature value sequence." By quantifying user characteristics and forming N feature value sequences, a multi-dimensional behavioral profile can be built for the user, enabling financial institutions to gain a more comprehensive understanding of the user and laying the foundation for subsequent accurate recommendations.

[0059] Next, the system acquires P behavioral indicator features related to a specific product type, such as transfer frequency and number of times financial product queries are made. Based on N feature value sequences, behavioral feature data matching each behavioral indicator feature is calculated, such as the average number of times a user queries high-liquidity products per day and the number of times they transfer funds per month during a historical period. Finally, P behavioral feature data are obtained, and the target behavioral information is obtained.

[0060] For example, if the system identifies user characteristics including "frequent small-amount financial product inquiries" and "high liquidity needs," it can further analyze the frequency of user inquiries about financial products, the time of each inquiry, and the actual operation data after the inquiry in the past year, forming a series of behavioral characteristic data, such as inquiry frequency sequences and operation conversion rate sequences.

[0061] This embodiment accurately obtains users' target behavior information through in-depth mining and multi-dimensional analysis of user behavior information. Then, without reflecting the user's real data, it determines the user profile through behavior data, and then determines the products to be recommended to the user, thereby improving the accuracy of determining the products to be recommended and the security of information.

[0062] To accurately determine the matching degree, optionally, in the method for determining the product to be recommended provided in this application embodiment, determining the matching degree between the target behavior information and each product information to obtain M target matching degrees includes: obtaining a preset user set and determining the user cluster to which the target user belongs in the preset user set to obtain a target user cluster, wherein the preset user set includes H user clusters, where H is a positive integer; determining the matching degree between the target behavior information and each product information to obtain M first matching degrees; obtaining the product purchase records of each preset user in the target user cluster, and determining the matching degree between the target user cluster and each product information based on the product purchase records to obtain M second matching degrees; and determining the target matching degree of each product information based on the first matching degree and the second matching degree to obtain M target matching degrees.

[0063] It should be noted that the preset user set is a set of user categories composed of multiple preset users, and the user cluster is a group of preset users derived from cluster analysis based on user characteristics and behavioral patterns.

[0064] For example, when calculating the matching degree between a target user and various preset products, a clustering algorithm is first used to determine the user cluster to which the target user belongs in the preset user set. For instance, suppose the system constructs five user clusters through cluster analysis, each representing a different user type, such as "high-net-worth investors," "young professionals," and "conservative savers." If the target user is someone who frequently queries and purchases short-term financial products and has a high average daily asset value, the system will classify them into the "high-net-worth investors" user cluster.

[0065] Furthermore, after determining the user cluster to which the target user belongs, the system calculates the first matching degree between the target behavioral information and M preset products. Calculating the first matching degree involves comprehensive consideration of multiple dimensions, including but not limited to the matching of user risk preference with product risk level, the matching of user investment period with product term, and the matching of user financial situation with product minimum investment amount. Through quantitative analysis, the system can determine the degree of direct matching between each product and the user's behavioral information.

[0066] Furthermore, the system also needs to collect product purchase records of all preset users from the target user cluster, including purchase frequency, purchase volume, satisfaction feedback, etc., in order to determine the characteristic data of the target user cluster. Based on the characteristic data of the target user cluster, statistical analysis methods are applied to determine the second matching degree between the target user cluster and each preset product, thereby determining the degree of matching between the target user group and the preset product.

[0067] Finally, the system comprehensively considers the first and second matching degrees to calculate the target matching degree for each preset product. This allows the system to comprehensively determine the matching degree between users and products from two dimensions: individual user needs and user group preferences, thereby improving the accuracy of the calculated matching degree.

[0068] This embodiment calculates the matching degree between the user and the product, and the matching degree between the user's group and the product. Then, it comprehensively determines the matching degree between the user and each preset product based on the values ​​of the two matching degrees, thereby achieving the technical effect of improving the accuracy of the calculated matching degree.

[0069] Optionally, in the method for determining the product to be recommended provided in the embodiments of this application, determining the user cluster to which the target user belongs in the preset user set and obtaining the target user cluster includes: determining the central user located at the cluster center in each user cluster to obtain H central users, and obtaining the preset behavior information of each central user; calculating the cosine similarity between the target user's target behavior information and the preset behavior information of each central user to obtain H first similarities; obtaining the maximum similarity among the H first similarities, and determining the user cluster to which the maximum similarity belongs as the target user cluster.

[0070] It should be noted that the central user is a representative user within each user cluster, located at the cluster center, and is used to represent the characteristics and behavioral patterns of the entire user cluster. The preset behavioral information consists of the central user's behavioral characteristic data, including user operation frequency, product preferences, asset allocation, etc., used for comparison with the behavioral information of the target users.

[0071] For example, when determining the target user cluster, a clustering algorithm is first used to classify the preset user set into H user clusters, and then the central user of each cluster is determined. Each central user represents the core characteristics and behavioral patterns of a user cluster. Further, the system extracts preset behavioral information of each central user from historical user time-series information, including but not limited to the frequency of user queries for specific types of products, purchase records, transaction habits, and fund flows, forming a comprehensive behavioral information database that accurately reflects the characteristics of the user group.

[0072] Furthermore, the system converts the acquired target user behavior feature data into vector form, and simultaneously represents the preset behavior information of the central user of each user cluster as a corresponding vector. By calculating the cosine similarity between the target user behavior vector and the behavior vectors of H central users, the system can obtain H first similarity scores, which represent the degree of similarity between the target user and each user cluster in terms of behavioral patterns. Subsequently, the system selects the highest similarity score from the H first similarity scores and determines the corresponding user cluster as the target user cluster, that is, the user group that best represents the target user's behavioral characteristics and needs preferences.

[0073] For example, for the user groups targeted by commercial banks, cluster analysis can identify user clusters such as "high-frequency traders," "conservative investors," and "risk-seeking investors," and then identify the central user of each cluster. Assuming that a target user has a high frequency of inquiries and purchases of short-term liquid financial products, the system calculates and finds that the cosine similarity between the target user's behavior vector and the behavior vector of the central user of the "conservative investor" cluster is the highest. Therefore, the system will determine that the user belongs to the "conservative investor" cluster.

[0074] This embodiment achieves accurate user cluster positioning of the target user in the preset user set by determining the central user, calculating the cosine similarity, and filtering the maximum similarity, laying a data foundation for subsequently determining the matching degree between users and products.

[0075] To accurately calculate the first matching degree, optionally, in the method for determining the product to be recommended provided in the embodiments of this application, determining the matching degree between the target behavior information and each product information to obtain M first matching degrees includes: for any product information, inputting the product information into the product recognition model to obtain the standard behavior information corresponding to the product information; determining the similarity between the standard behavior information and the target behavior information to obtain the second similarity, and determining the second similarity as the first matching degree between the product information and the target behavior information.

[0076] It should be noted that the product identification model can be any type of machine learning model, trained to identify and classify different product types, and to infer the standard behavioral information of users corresponding to those products. Standard behavioral information refers to the model's predicted behavioral patterns representing the expected behavior patterns of users under a specific product type, used to compare with the behavioral information of the target user to assess the product's suitability.

[0077] For example, the system first selects product information as input and feeds it into a pre-trained product recognition model. Based on historical user data and product usage, the model learns and predicts standard behavioral information that matches the product type. For instance, for a short-term liquid financial product, the model might predict standard behavioral information including: frequent user inquiries about financial product information, frequent small deposits and withdrawals, and a preference for highly liquid products.

[0078] Furthermore, after obtaining the standard behavioral information, the system uses data comparison and similarity calculation methods to evaluate the degree of similarity between the target user's behavioral information and the standard behavioral information, thus obtaining a second similarity. The similarity calculation can employ various methods, such as cosine similarity and Pearson correlation coefficient, to quantify the fit between the product and user behavior. Finally, the calculated second similarity is used as the first matching degree between the product information and the target behavioral information, thereby directly reflecting the degree of matching between the product and the target user's needs.

[0079] It should be noted that the product recognition model can be any type of neural network model. The model structure can include an input layer, multiple hidden layers, and an output layer. The input layer receives sample feature information, the hidden layers are responsible for feature learning and transformation, and the output layer generates standard behavioral information that matches the product type. The training set can consist of multiple sample data, and each sample data can include a certain product type and user behavior information of users who purchase products under that product type.

[0080] This embodiment uses a product recognition model to determine standard behavioral information, and compares the standard behavioral information with the target behavioral information to obtain a first matching degree, thereby accurately obtaining the matching degree value between the product and the user at the user dimension.

[0081] To accurately calculate the second matching degree, optionally, in the method for determining the product to be recommended provided in the embodiments of this application, determining the matching degree between the target user cluster and each product information based on the product purchase records to obtain M second matching degrees includes: determining the purchase information of each preset product based on the product purchase records of each preset user to obtain M purchase information, wherein the purchase information includes at least one of the following: purchase quantity, purchase frequency; determining the popularity value of each preset product based on the M purchase information to obtain M popularity values, and determining the popularity value of each preset product as the second matching degree to obtain M second matching degrees.

[0082] It should be noted that product purchase records refer to the historical purchase behavior data of each user in the user cluster for a specific product, including purchase volume and purchase frequency. Purchase volume is the cumulative number of times users in the user cluster have purchased a specific product within a historical time period. Purchase frequency is the average time interval between user purchases of a specific product, used to measure product usage frequency and user stickiness. Popularity value is an indicator of the popularity of each product within the user cluster, derived from the analysis and calculation of M purchase information. The higher the popularity value, the more popular the product is among the user group.

[0083] For example, the system first extracts purchase data related to M preset products from the product purchase records of all preset users in the target user cluster. This process involves data cleaning, classification, and organization to improve the accuracy and completeness of purchase information. For each product, the system analyzes its purchase volume and frequency within the user cluster, forming a dataset of M purchase information. For instance, for product X, the system might find that the average monthly purchase volume in the user cluster is 200 times, with an average purchase interval of 3 days; this data will be recorded as purchase information for product X.

[0084] After acquiring M purchase information entries, the system will calculate a popularity score for each preset product based on purchase volume and frequency. The calculation method for the popularity score can be varied, including but not limited to calculating a weighted average of purchase volume, the median of purchase frequency, or a comprehensive index combining user feedback and satisfaction ratings, ensuring that the popularity score fully reflects the product's actual performance within the user group. For product X, the system calculates a popularity score of 75 (out of 100), reflecting product X's high popularity and frequent use within the user group.

[0085] Finally, the popularity value can be directly used as a quantitative indicator of the degree of matching between product information and user groups to obtain the second degree of matching between user groups and preset products. Thus, the second degree of matching reflects the degree of matching between the product and the needs of target users from the perspective of user groups.

[0086] This embodiment determines the popularity value of each preset product in the user cluster by using the product purchase records of each user in the user cluster, and uses the popularity value as the second matching degree, thereby accurately obtaining the matching degree value between the product and the user in the user group.

[0087] Optionally, in the method for determining the product to be recommended provided in the embodiments of this application, determining the product to be recommended from M preset products based on M target matching degrees includes: obtaining historical evaluation information of each preset product and determining recommendation parameters of each preset product based on the historical evaluation information; determining a recommendation score for each preset product based on the recommendation parameters and target matching degree of each preset product, thereby obtaining M recommendation scores; obtaining the number of products in the product demand information, and selecting preset products that meet the required number of products from the M preset products according to the order of recommendation scores from largest to smallest, thereby obtaining the product to be recommended.

[0088] It should be noted that historical evaluation information refers to user feedback data on preset products, including but not limited to user satisfaction, product complaint rate, and product conversion rate, used to assess the long-term stability and market acceptance of the products. Recommendation parameters are composite indicators calculated based on historical evaluation information, describing the product's recommendation value. The recommendation score is the final score used for product recommendation ranking, calculated by combining target matching degree and recommendation parameters.

[0089] For example, when determining which products to recommend, the system first retrieves historical user reviews of M preset products from the database. This may include user satisfaction ratings, product complaint records, conversion rate statistics, etc. Based on this information, the system uses data analysis and statistical models to calculate the recommendation parameters for each product. For instance, for product C, the system can consider factors such as user satisfaction and conversion rate to calculate a recommendation parameter of 8.5 (out of 10).

[0090] Furthermore, after obtaining the recommendation parameters and target matching degree of M preset products, the system performs a weighted calculation of these two indicators to obtain a recommendation score for each product. Finally, based on the product quantity requirement in the product demand information and the ranking of the M recommendation scores, the system selects the preset product that best meets the recommendation quantity requirement from the M preset products as the product to be recommended.

[0091] For example, if the system receives product demand information requesting recommendations for 5 products, the system will select the top 5 preset products with the highest ratings based on the ranking of M recommendation ratings as the products to be recommended. For example, if the recommendation ratings for products 1-5 are 9.5, 9.2, 8.9, 8.8, and 8.7 respectively, the system will mark these 5 products as products to be recommended.

[0092] This embodiment analyzes historical evaluation information of products, determines recommendation parameters based on the analysis results, and determines a recommendation score based on the matching degree and recommendation parameters. Then, it determines the products to be recommended based on the recommendation score, thus achieving the technical effect of accurately determining the products to be recommended.

[0093] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0094] Example 2

[0095] This application also provides a device for determining a product to be recommended. It should be noted that this device can be used to execute the product determination method provided in the above embodiments. The following describes the device for determining a product to be recommended provided in this application.

[0096] According to an embodiment of this application, an apparatus for implementing the above-described method for determining the product to be recommended is also provided. Figure 3 This is a schematic diagram of the device for determining the product to be recommended according to Embodiment 2 of this application, as shown below. Figure 3 As shown, the device includes:

[0097] The receiving unit 31 is used to receive product demand information sent by the target user through the user terminal, and to obtain the product type from the product demand information.

[0098] The first acquisition unit 32 is used to acquire the historical user time sequence information of the target user within a historical time period, and to acquire the associated time sequence information related to the product type from the historical user time sequence information, and to determine the target behavior information of the target user within the historical time period based on the associated time sequence information.

[0099] The second acquisition unit 33 is used to acquire M preset products under the product type, and acquire product information for each preset product to obtain M product information, where M is a positive integer.

[0100] The determining unit 34 is used to determine the matching degree between the target behavior information and each product information, obtain M target matching degrees, determine the product to be recommended from M preset products based on the M target matching degrees, and send the product to be recommended to the user terminal.

[0101] The device for determining the product to be recommended provided in this application embodiment receives product demand information sent by a target user through a user terminal via a receiving unit 31, and obtains the product type from the product demand information; a first obtaining unit 32 obtains historical user time sequence information of the target user within a historical time period, and obtains associated time sequence information related to the product type from the historical user time sequence information, and determines the target behavior information of the target user within the historical time period based on the associated time sequence information; a second obtaining unit 33 obtains M preset products under the product type, and obtains product information for each preset product, resulting in M ​​product information, where M is a positive integer; a determining unit 34 determines the matching degree between the target behavior information and each product information, obtaining M target matching degrees, and determines the product to be recommended from the M preset products based on the M target matching degrees, and sends the product to be recommended to the user terminal. By analyzing user behavior information and determining the matching degree between behavior information and product information, the system identifies the product with the highest matching degree to recommend to the user, and then recommends the product to the user. This achieves the goal of assisting the user in selecting products, thereby improving the technical effect of improving the accuracy of product recommendation operations and solving the technical problem of low accuracy in product recommendation for users in related technologies.

[0102] Optionally, in the device for determining the product to be recommended provided in the embodiments of this application, the first acquisition unit 32 includes: a first acquisition module, used to acquire feature values ​​under each user feature of the target user from the associated time series information to obtain N feature value sequences, where N is a positive integer; and a second acquisition module, used to acquire P behavioral indicator features, and determine behavioral feature data under each behavioral indicator feature according to the N feature value sequences to obtain P behavioral feature data, and determine the P behavioral feature data as target behavioral information, where P is a positive integer.

[0103] Optionally, in the device for determining the product to be recommended provided in the embodiments of this application, the determining unit 34 includes: a third acquisition module, used to acquire a preset user set and determine the user cluster to which the target user belongs in the preset user set, thereby obtaining a target user cluster, wherein the preset user set includes H user clusters, where H is a positive integer; a first determining module, used to determine the matching degree between the target behavior information and each product information, thereby obtaining M first matching degrees; a fourth acquisition module, used to acquire the product purchase records of each preset user in the target user cluster, and determine the matching degree between the target user cluster and each product information based on the product purchase records, thereby obtaining M second matching degrees; and a second determining module, used to determine the target matching degree of each product information based on the first matching degree and the second matching degree, thereby obtaining M target matching degrees.

[0104] Optionally, in the device for determining the product to be recommended provided in the embodiments of this application, the third acquisition module includes: a first determination submodule, used to determine the central users located at the cluster center in each user cluster, obtain H central users, and acquire the preset behavior information of each central user; a calculation submodule, used to calculate the cosine similarity between the target behavior information of the target user and the preset behavior information of each central user, respectively, to obtain H first similarities; and a second determination submodule, used to obtain the maximum similarity among the H first similarities, and determine the user cluster to which the maximum similarity belongs as the target user cluster.

[0105] Optionally, in the device for determining the product to be recommended provided in the embodiments of this application, the first determining module includes: a prediction submodule, used to input the product information into the product recognition model for any product information to obtain the standard behavior information corresponding to the product information; and a third determining submodule, used to determine the similarity between the standard behavior information and the target behavior information to obtain a second similarity, and to determine the second similarity as the first matching degree between the product information and the target behavior information.

[0106] Optionally, in the device for determining the product to be recommended provided in the embodiments of this application, the fourth acquisition module includes: a fourth determination submodule, used to determine the purchase information of each preset product based on the product purchase records of each preset user, to obtain M purchase information, wherein the purchase information includes at least one of the following: purchase quantity, purchase frequency; and a fifth determination submodule, used to determine the popularity value of each preset product based on the M purchase information, to obtain M popularity values, and to determine the popularity value of each preset product as a second matching degree, to obtain M second matching degrees.

[0107] Optionally, in the device for determining the product to be recommended provided in this application embodiment, the determining unit 34 includes: a fifth acquisition module, used to acquire historical evaluation information of each preset product and determine the recommendation parameters of each preset product based on the historical evaluation information; a third determining module, used to determine the recommendation score of each preset product based on the recommendation parameters and target matching degree of each preset product, to obtain M recommendation scores; and a selection module, used to acquire the number of products in the product demand information and select preset products that meet the number of products from the M preset products according to the order of recommendation scores from largest to smallest, to obtain the product to be recommended.

[0108] It should be noted that the receiving unit 31, the first acquiring unit 32, the second acquiring unit 33, and the determining unit 34 mentioned above correspond to steps S201 to S204 in Embodiment 1. The instances and application scenarios implemented by each of the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0109] Example 3

[0110] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) processor 1002, memory 1004, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0111] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0113] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0114] Example 4

[0115] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the recommended product provided in Embodiment 1.

[0116] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0117] Embodiments of this application also provide a computer program product, which, when executed on a data processing device, is adapted to perform the steps of a method for determining a product to be recommended.

[0118] Embodiments of this application also provide a computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to execute the above-described method for determining the recommended product.

[0119] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0125] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining products to be recommended, characterized in that, include: Receive product demand information sent by the target user through the user terminal, and obtain the product type from the product demand information; Obtain historical user time sequence information of the target user within a historical time period, and obtain associated time sequence information related to the product type from the historical user time sequence information, and determine the target behavior information of the target user within the historical time period based on the associated time sequence information; Obtain M preset products under the product type, and obtain product information for each preset product to obtain M product information, where M is a positive integer; The matching degree between the target behavior information and each product information is determined to obtain M target matching degrees. Based on the M target matching degrees, a product to be recommended is determined from the M preset products, and the product to be recommended is sent to the user terminal.

2. The method according to claim 1, characterized in that, Determining the target user's target behavior information within the historical time period based on the associated time sequence information includes: The feature values ​​of each user feature of the target user are obtained from the associated time series information, resulting in N feature value sequences, where N is a positive integer; P behavioral indicator features are obtained, and behavioral feature data under each behavioral indicator feature is determined according to the N feature value sequences to obtain P behavioral feature data. The P behavioral feature data are then determined as the target behavioral information, where P is a positive integer.

3. The method according to claim 1, characterized in that, The matching degree between the target behavior information and each product information is determined, resulting in M ​​target matching degrees, including: Obtain a preset user set and determine the user cluster to which the target user belongs in the preset user set to obtain the target user cluster, wherein the preset user set includes H user clusters, where H is a positive integer; Determine the matching degree between the target behavior information and each product information to obtain M first matching degrees; Obtain the product purchase records of each preset user in the target user cluster, and determine the matching degree between the target user cluster and each product information based on the product purchase records to obtain M second matching degrees; The target matching degree of each product information is determined based on the first matching degree and the second matching degree, thus obtaining the M target matching degrees.

4. The method according to claim 3, characterized in that, The target user is determined to belong to a user cluster within the preset user set, resulting in the following target user clusters: Identify the central users located at the cluster centers in each user cluster, obtain H central users, and acquire the preset behavioral information of each central user; Calculate the cosine similarity between the target user's target behavior information and the preset behavior information of each central user to obtain H first similarity scores; Obtain the maximum similarity among the H first similarities, and determine the user cluster to which the maximum similarity belongs as the target user cluster.

5. The method according to claim 3, characterized in that, The matching degree between the target behavior information and each product information is determined, resulting in M ​​first matching degrees, including: For any given product information, the product information is input into the product recognition model to obtain the standard behavioral information corresponding to the product information; The similarity between the standard behavioral information and the target behavioral information is determined to obtain a second similarity, and the second similarity is determined as the first matching degree between the product information and the target behavioral information.

6. The method according to claim 3, characterized in that, Based on the product purchase records, the matching degree between the target user cluster and each product information is determined, resulting in M ​​second matching degrees, including: Based on the product purchase records of each preset user, the purchase information of each preset product is determined, resulting in M ​​purchase information entries, wherein the purchase information includes at least one of the following: purchase quantity and purchase frequency; Based on the M purchase information, the popularity value of each preset product is determined to obtain M popularity values, and the popularity value of each preset product is determined as the second matching degree to obtain the M second matching degrees.

7. The method according to claim 1, characterized in that, The products to be recommended are determined from the M preset products based on the M target matching degrees, including: Obtain historical evaluation information for each preset product, and determine recommended parameters for each preset product based on the historical evaluation information; Based on the recommended parameters and target matching degree of each preset product, a recommendation score is determined for each preset product, resulting in M ​​recommendation scores; Obtain the number of products in the product demand information, and select preset products that meet the required number of products from the M preset products according to the order of the recommendation scores from largest to smallest, to obtain the products to be recommended.

8. A device for determining products to be recommended, characterized in that, include: The receiving unit is used to receive product demand information sent by the target user through the user terminal, and to obtain the product type from the product demand information; The first acquisition unit is used to acquire the historical user time sequence information of the target user within a historical time period, acquire the associated time sequence information related to the product type from the historical user time sequence information, and determine the target behavior information of the target user within the historical time period based on the associated time sequence information. The second acquisition unit is used to acquire M preset products under the product type, and acquire product information for each preset product to obtain M product information, where M is a positive integer; The determining unit is used to determine the matching degree between the target behavior information and each product information to obtain M target matching degrees, and to determine the product to be recommended from the M preset products based on the M target matching degrees, and send the product to be recommended to the user terminal.

9. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method for determining the product to be recommended as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method for determining the product to be recommended as described in any one of claims 1 to 7.

Images