Financial product recommendation method and device, equipment, medium and program product

Abstract

The embodiment of the invention provides a financial product recommendation method and device, equipment, a medium and a program product, and relates to the field of financial science and technology. The method comprises the following steps: acquiring identity information of a target user and an interested financial product; obtaining a first candidate recommended financial product based on the identity information of the target user, the interested financial product and a database; determining a target financial product based on the first candidate recommended financial product and the interested financial product; based on the historical purchase product data of the target user and the purchase description information of the target financial product, obtaining the interestingness of the target user in the target financial product; based on the interestingness and description information of the target financial product, determining a recommendation strategy of the target financial product; and based on the recommendation strategy, outputting recommendation information of the target financial product. According to the method, the accuracy of recommending the financial product to the user is improved.

Description

Technical Field

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

[0002] With the rapid development of the Internet, the types and number of financial products have also grown rapidly. From traditional savings accounts and loan services to emerging Internet insurance and financial products, smart investment advisors and other Internet financial products, the variety of financial products provides users with a wealth of choices.

[0003] Among the current methods for recommending financial products to users, some rely only on basic information of users, such as age, occupation, income, etc., to make simple matching recommendations; some focus on mining historical user purchase records and recommending financial products to users based on historical user purchase records; some focus on financial products, such as recommending financial products to users based on their interest rates, risk levels, etc. These methods ignore the complexity and diversity of user needs due to their single considerations, resulting in low accuracy in the recommended financial products.

[0004] Therefore, how to improve the accuracy of recommending financial products to users is an urgent problem that needs to be solved. Summary of the invention

[0005] The present application provides a financial product recommendation method, apparatus, device, storage medium and program product to improve the accuracy of recommending financial products to users.

[0006] In a first aspect, the present application provides a financial product recommendation method, comprising:

[0007] Obtaining identity information of a target user and financial products of interest to the target user;

[0008] Based on the identity information of the target user, the financial products of interest to the target user, and a database, a first candidate recommended financial product is obtained; the database at least includes: the identity information and associated financial product sets of historical contracted users and historical recommended users; the associated financial product sets of historical contracted users include the interested financial product sets and purchased financial product sets of historical contracted users; the associated financial product sets of historical recommended users include the interested financial product sets and recommended financial product sets of historical recommended users;

[0009] Determining a target financial product for the target user based on the first candidate recommended financial products and the interested financial product;

[0010] Based on the historical product purchase data of the target user and the description information of the target financial product, obtaining the interest of the target user in the target financial product;

[0011] Determining a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product;

[0012] Based on the recommendation strategy, recommendation information of the target financial product is output.

[0013] In a second aspect, the present application provides a financial product recommendation device, comprising:

[0014] A first acquisition module is used to acquire the identity information of a target user and the financial products of interest to the target user;

[0015] A second acquisition module is configured to acquire a first candidate recommended financial product based on the identity information of the target user, the financial products of interest to the target user, and a database; the database at least includes: the identity information and associated financial product sets of historical contracted users and historical recommended users; the associated financial product sets of historical contracted users include the interested financial product sets and purchased financial product sets of historical contracted users; the associated financial product sets of historical recommended users include the interested financial product sets and recommended financial product sets of historical recommended users;

[0016] A first determination module, configured to determine a target financial product for the target user based on the first candidate recommended financial products and the financial product of interest;

[0017] A third acquisition module is used to acquire the interest of the target user in the target financial product based on the historical product purchase data of the target user and the description information of the target financial product;

[0018] A second determination module, configured to determine a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product;

[0019] An output module is used to output recommendation information of the target financial product based on the recommendation strategy.

[0020] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0021] The memory stores computer-executable instructions;

[0022] The processor executes the computer-executable instructions stored in the memory to implement the method described in any one of the first aspects.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in any one of the first aspects.

[0024] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in any one of the first aspects when executed by a processor.

[0025] The financial product recommendation method, device, equipment, medium and program product provided in this application recommend financial products to target users by combining the target user's identity information and financial products of interest, the identity information and related financial products of historical contracted users and historical recommended users, and the target user's interest in the target financial product. Compared with the technical problems that the recommendation of financial products in the prior art is relatively single in consideration and fails to fully and deeply understand the complexity and diversity of user needs, this application can analyze user needs and preferences in multiple dimensions, thereby providing more accurate financial product recommendations that meet the actual needs of users, and effectively improving user experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0027] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of an interface for recommendation information of a target financial product provided in an embodiment of the present application;

[0029] Figure 3 This is a schematic diagram of a process for obtaining a first candidate recommended financial product provided in an embodiment of the present application;

[0030] Figure 4 This is a schematic diagram of a process for obtaining a target user's interested financial products provided in an embodiment of the present application;

[0031] Figure 5 A schematic diagram of the structure of a financial product recommendation device provided in an embodiment of the present application;

[0032] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0033] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0034] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0035] 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 used for analysis, stored data, displayed data, etc.) involved in this application are all 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 the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0036] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0037] It should be noted that the financial product recommendation method, device, equipment, medium and program product provided in the present application can be used in the field of financial technology, and can also be used in any field other than financial technology. The application field of the method, device, equipment, storage medium and financial product of the financial product recommendation method, device, equipment, medium and program product in the present application is not limited.

[0038] Financial products are the objects of buying and selling in the financial market, and refer to various carriers in the process of financing. Financial products are the core components of the financial market, with characteristics such as profitability, risk, and liquidity. With the continuous development and innovation of the financial market, the types and number of financial products are also increasing. From traditional financial services such as savings accounts and loan services to a series of innovative Internet financial products that have emerged in recent years, such as Internet insurance finance, smart investment advisors and other emerging financial products, financial products are becoming increasingly diversified, providing users with a wide range of choices.

[0039] At present, although there are various methods to recommend financial products to users, most of them have limitations. Some methods only rely on basic information of users, such as age, occupation, income level, marital status, etc., to make simple matching recommendations. Although this method is easy to implement, due to the lack of understanding and mining of users' deep needs, the accuracy of recommendations is often not high. Other methods focus on mining the purchase records of all historical users and recommend financial products by analyzing the purchase behavior and preferences of all users. Although this method can analyze user behavior from a wide range of perspectives, it is difficult to accurately capture the unique needs and preference changes of each user. In addition, some methods focus on the financial products themselves, and recommend financial products based on the attributes of financial products such as interest rate level, risk level, investment period, and combined with factors such as user's risk tolerance and investment goals. Although this method is more scientific in theory, its recommendation effect is often unsatisfactory because it ignores the personalized needs of users and changes in the market environment. In summary, the current methods of recommending financial products to users fail to fully and deeply understand the complexity and diversity of user needs due to relatively single considerations.

[0040] In view of this, the embodiments of the present application provide a financial product recommendation method that can be applied in scenarios where banks recommend financial products to users. The executor of the present application may be a banking system. The embodiments of the present application may recommend financial products to target users based on the target user's identity information and financial products of interest, the identity information and associated financial products of historical contracted users and historical recommended users, and the target user's interest in the target financial product. Compared with the technical problems in the prior art that the recommendation of financial products has relatively single considerations and fails to fully and deeply understand the complexity and diversity of user needs, the present application can analyze user needs and preferences in multiple dimensions, thereby providing more accurate financial product recommendations that meet the actual needs of users, and effectively improving user experience and satisfaction.

[0041] The method of the embodiments of the present application can be applied to any scenario of financial product recommendation, for example, a scenario in which a user browses financial products through a banking system client, or a scenario in which a banking system regularly or proactively pushes recommended financial products to a user, or a scenario in which a bank staff obtains financial products that can be recommended to a user through a banking system.

[0042] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0043] Figure 1 A flow chart of a data processing method provided in an embodiment of the present application. Figure 1 As shown, the method includes:

[0044] S101. Obtain identity information of a target user and financial products of interest to the target user.

[0045] The target user may be a user belonging to any account in the banking system.

[0046] Optionally, the identity information of the target user may include any one or more information that can represent the identity information of the target user, such as name information, ID number, age, occupation, etc. The target user's financial products of interest can be analyzed based on the target user's browsing history, click behavior and other data on the financial products.

[0047] Optionally, the user's interest in each financial product may be determined based on the user's browsing time and / or the number of clicks on each financial product, or based on the user's browsing cycle for each financial product. For example, if the current user has a long browsing time and / or a high number of clicks on a certain financial product, it is determined that the current user has a high interest in the financial product. For another example, if the current user has a short browsing cycle for a certain financial product, that is, browses the financial product multiple times within a fixed time period, it can be determined that the current user has a high interest in the financial product.

[0048] S102: Based on the identity information of the target user, the financial products of interest to the target user, and the database, a first candidate recommended financial product is obtained. The database includes at least the identity information and associated financial product sets of the historical contracted users and the historical recommended users. The associated financial product sets of the historical contracted users include the interested financial product sets and the purchased financial product sets of the historical contracted users. The associated financial product sets of the historical recommended users include the interested financial product sets and the recommended financial product sets of the historical recommended users.

[0049] Optionally, the historical contracted users may be users who have purchased financial products in the banking system, and the historical recommended users may be users to whom financial products have been recommended in the banking system.

[0050] The identity information of the historical subscriber may include name information, ID number, age, occupation, etc. The associated financial product set of the historical subscriber includes the set of financial products of interest and the set of purchased financial products of the historical subscriber. The set of financial products of interest to the historical subscriber is consistent with the acquisition rules of the above-mentioned target user's financial products of interest, and the set of purchased financial products includes some or all of the financial products that the historical subscriber has purchased.

[0051] The identity information of the historical recommendation user may include name information, ID number, age, occupation, etc. The associated financial product set of the historical recommendation user includes the set of financial products of interest and the set of recommended financial products of the historical recommendation user. The set of financial products of interest to the historical recommendation user is consistent with the acquisition rules of the above-mentioned target user's financial products of interest. The recommended financial product set of the historical recommendation user includes the financial products recommended by the salesperson to the recommendation user based on the user's needs or actively through the bank system and / or the bank system history.

[0052] The identity information of historical contracted users and the method for obtaining the associated financial product set, the identity information of historical recommended users and the method for obtaining the associated financial product set are the same as the above-mentioned target user's identity information and the method for obtaining the interested financial product set, and will not be repeated here.

[0053] The first candidate recommended financial products may include one or more financial products determined from a set of associated financial products of historical contracted users and a set of associated financial products of historical recommending users.

[0054] For example, the banking system can search for a set of related financial products of users with similar identity information to the target user from the database based on the identity information of the target user, and use the financial products in these sets as the first candidate recommended financial products. The banking system can also search for a set of financial products similar to the financial product of interest to the target user from the database based on the financial product of interest to the target user, and use these financial products or all products in the set that includes the financial product as the first candidate recommended financial products. The banking system can also construct feature vectors for these three types of data respectively, so as to obtain financial products related to the target user based on these feature vectors, etc.

[0055] S103: Determine a target financial product for the target user based on the first candidate recommended financial product and the interested financial product.

[0056] For example, the first candidate recommended financial products and the interested financial products may be used as the target financial products of the target user, or a financial product with a recommendation degree or purchase degree higher than a preset recommendation degree may be selected from the first candidate recommended financial products and the interested financial products as the target financial products of the target user, or the target financial product of the target user may be determined based on the first candidate recommended financial products and the interested financial products, and further combined with financial products determined from other dimensions, etc. The other dimensions mentioned here may be, for example, currently hot financial products, or main recommended financial products, etc.

[0057] For example, the banking system may determine the second candidate recommended financial product to be recommended to the target user from the hot financial products based on the popularity of the financial product, the trend of the financial product, and the historical purchase data of the target user. The historical purchase data at least includes the historical purchase data of the financial product. Then, the banking system may determine the target financial product based on the first candidate financial product, the second candidate financial product, and the financial product of interest.

[0058] Optionally, the popularity of a financial product can be measured by any one or more indicators such as the search volume and transaction volume of the financial product. For example, a financial product with a large search volume can indicate that the financial product is popular. The trend of a financial product can be the fluctuation of the value of the financial product within a fixed time period. For example, if the value of a financial product continues to rise in the past week, it can indicate that the trend of the financial product is good.

[0059] For example, the first candidate financial product, the second candidate financial product, and the financial product of interest may be used as the target financial product of the target user, or a financial product with a recommendation degree or purchase degree higher than a preset recommendation degree may be selected from the first candidate financial product, the second candidate financial product, and the financial product of interest as the target financial product of the target user, or the target financial product of the target user may be determined based on the first candidate financial product, the second candidate financial product, the financial product of interest, and the financial product determined from other dimensions, etc. The other dimensions mentioned here may be, for example, currently hot financial products, or main recommended financial products, etc.

[0060] The embodiment of the present application can determine the target financial product based on the popularity of the financial product, the trend of the financial product, and the historical purchase data of the target user, combined with the first candidate financial product mentioned above and the financial product of interest. Compared with the method of recommending financial products to target users by only considering a single factor in the prior art, the present application also considers the characteristics of the financial product itself, provides a more comprehensive reference for recommending financial products, and improves the accuracy of recommending financial products to target users.

[0061] S104: Based on the historical product purchase data of the target user and the description information of the target financial product, obtain the interest of the target user in the target financial product.

[0062] Optionally, the target user's historical product purchase data may include any one or more of the target user's historical financial product purchase type, purchase time, purchase amount, etc. The target financial product description information may include any one or more of the financial product's product type, risk level, investment period, etc.

[0063] Optionally, the banking system may use an interest recognition model to obtain the interest of the target user in the target financial product. The interest model may be pre-trained based on previous financial product recommendation information and may be updated in real time in actual applications, thereby ensuring that the interest of the target user in the target financial product obtained each time is highly accurate.

[0064] The interest level can reflect the degree of interest of the target user in the target financial product. The higher the interest level, the higher the interest level, and the lower the interest level, the lower the interest level. Generally speaking, the value range of the interest level is usually 0-1.

[0065] S105: Determine a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product.

[0066] Optionally, the recommendation strategy may include a recommendation order and / or layout style adopted when displaying the target financial product on the user interface of the client. The layout style may include, for example, the position, size, color, style, etc. on the page.

[0067] For example, the target financial product with a higher interest level is ranked higher in the recommendation order. Its description information occupies a larger area in the user interface. Alternatively, the target financial products in the same interest level range are recommended using the same recommendation strategy.

[0068] S106. Based on the recommendation strategy, output recommendation information of the target financial product.

[0069] Figure 2 This is a schematic diagram of the interface for recommendation information of target financial products provided in the embodiment of the present application. Figure 2 As shown, taking the recommendation strategy that may include the recommendation order as an example, assuming that the interest level of target financial product A is higher than the interest level of target financial product B, in this scenario, when the user interface side of the client displays target financial product A and target financial product B, target financial product A is located before target financial product B.

[0070] Optionally, after outputting the recommendation information of the target financial product, the present application may also adjust the recommendation information of the target financial product according to the browsing preference of the target user when browsing the recommendation information of the target financial product, so as to dynamically update and adjust the recommendation information according to the real-time preference of the user.

[0071] For example, the banking system may obtain the focus and / or facial expression of the target user when the target user browses the recommended information of the target financial product, and obtain the browsing preference of the target user based on the focus and / or facial expression.

[0072] Optionally, the focus of the target user when browsing the recommended information of the target financial product can be inferred based on any one or more of the number of clicks, browsing time, etc. of the recommended information of the financial product by the target user. For example, if the number of clicks of the recommended information of the financial product by the target user is large, it can be represented that the target user has a high focus on the target financial product, thereby obtaining the browsing preference of the target user.

[0073] Optionally, the banking system may use existing face recognition technology and / or emotion recognition technology to obtain the facial expression of the target user when browsing the recommended information of the target financial product. By obtaining the facial expression of the target user when browsing the recommended information of the target financial product, it is possible to infer whether the recommended information of the target financial product matches the target user's demand for financial products, thereby obtaining the browsing preference of the target user.

[0074] The banking system may adjust the order and / or layout style of the target financial product recommendation information based on the target user's browsing preferences. For example, the banking system may adjust the order of the target financial product recommendation information that the target user has not browsed based on the target user's browsing preferences, and arrange the target financial product recommendation information preferred by the target user at the front. For another example, the banking system may adjust the layout style of the target financial product recommendation information that the target user has not browsed based on the target user's browsing preferences, and highlight the description information in the target financial product recommendation information preferred by the target user on the page.

[0075] The embodiment of the present application can recommend financial products to the target user by combining the target user's identity information and the financial products of interest, the identity information and related financial products of the historical contracted users and the historical recommended users, and the target user's interest in the target financial products. Compared with the technical problems that the recommendation of financial products in the prior art is relatively single in consideration and fails to fully and deeply understand the complexity and diversity of user needs, the present application can analyze user needs and preferences in multiple dimensions, thereby providing more accurate financial product recommendations that meet the actual needs of users, and effectively improving user experience and satisfaction.

[0076] The following further describes how to obtain the first candidate recommended financial product based on the identity information of the target user, the financial products of interest to the target user, and the database. Figure 3 : is a schematic diagram of the process of obtaining the first candidate recommended financial product provided in the embodiment of the present application. Figure 3 As shown, the above step S102 may include the following steps:

[0077] S201. Construct a feature vector to be searched of the target user based on the identity information of the target user and the financial products of interest to the target user.

[0078] Optionally, the target user's identity information may include any one or more of the target user's identity (name or ID number), age, occupation, etc. For example, the target user's identity information may be expressed as identity (name or ID number)-age-occupation, such as Zhang-38 years old-teacher.

[0079] The target user's financial products of interest may include any one or more of the type, name, and page views of the financial products of interest. For example, the target user's financial products of interest may be represented as the type-name-page views of the financial products of interest, such as fund products-product A-1899, stock products-product B-1355, etc.

[0080] The target user's to-be-searched feature vector is constructed based on the representation of the target user's identity information and the representation of the target user's interested financial products. For example, the to-be-searched feature vector may be Zhang-38 years old-teacher-fund product-product A-1899.

[0081] S202: Construct a first search feature vector of the historical contracting user based on the identity information of the historical contracting user and the set of associated financial products.

[0082] Optionally, the representation of the identity information of the historical contracted user is consistent with the representation of the identity information of the target user, which will not be described in detail here.

[0083] The associated financial product set of the historical contracting user may include the set of financial products of interest to the historical contracting user and the set of financial products purchased by the historical contracting user. The representation of the set of financial products of interest to the historical contracting user is consistent with the representation of the financial products of interest to the target user, and will not be repeated here. The set of financial products purchased by the historical contracting user may include any one or more items such as the type, name, and number of purchases of the purchased financial products. For example, the set of financial products purchased by the historical contracting user may be represented as the type-name-number of purchases of the purchased financial products, such as stock product-product B-853.

[0084] Based on the identity information representation of the historical contracted user and the associated financial product set representation, a first search feature vector of the historical contracted user is constructed. For example, the first search feature vector may be Zhang-38 years old-teacher-stock product-product B-853.

[0085] S203: Construct a second search feature vector of the historically recommended user based on the identity information and the associated financial product set of the historically recommended user.

[0086] Optionally, the representation of the identity information of the historically recommended user is consistent with the representation of the identity information of the target user described above, which will not be described in detail here.

[0087] The associated financial product set of the historically recommended user may include the interested financial product set of the historically recommended user and the recommended financial product set of the historically recommended user. The representation of the associated financial product set of the historically recommended user is consistent with the representation of the associated financial product set of the historically contracted user, and will not be repeated here.

[0088] Based on the representation of the identity information of the historically recommended user and the representation of the associated financial product set, a second search feature vector of the historically recommended user is constructed. For example, the second search feature vector may be Zhang-38 years old-teacher-stock product-product B-1355.

[0089] S204: Determine a first candidate recommended financial product from a set of associated financial products of historical contracted users and a set of associated financial products of historical recommended users based on the feature vector to be searched, the first search feature vector, and the second search feature vector.

[0090] Optionally, the banking system may calculate the similarity between the feature vector to be searched and the first search feature vector, calculate the similarity between the feature vector to be searched and the second search feature vector, and select the financial products in the associated financial product set corresponding to the feature vectors with high similarity as the first candidate recommended financial products.

[0091] The similarity can be calculated by calculating the Euclidean distance between the feature vector to be searched and the first search feature vector and the second search feature vector, respectively. The closer the distance, the higher the similarity, and the farther the distance, the lower the similarity. Optionally, the similarity can also be obtained by pre-trained models, which is not limited to this.

[0092] In some embodiments, the number of financial products included in the above-mentioned financial products of interest, the associated financial product set of historical contracted users, and the associated financial product set of historical recommended users is consistent. That is, when acquiring data, these three financial products are acquired based on a preset number, or a preset number of financial products are selected from the acquired three financial products to construct feature vectors. In this implementation, the lengths of the feature vectors constructed based on the above three are consistent.

[0093] Optionally, the number of the above three financial products may also have a certain deviation, so the lengths of the feature vectors constructed based on the above three may be inconsistent. Therefore, in this scenario, before determining the first candidate recommended financial product based on the feature vector to be searched, the first search feature vector, and the second search feature vector, the bank system can also process the three feature vectors to make the feature vectors consistent in length.

[0094] For example, the longest target search feature vector can be determined from the feature vector to be searched, the first search feature vector, and the second search feature vector. Secondly, based on the length of the target search feature vector, other search feature vectors are padded to make the feature vector to be searched, the first search feature vector, and the second search feature vector have the same length.

[0095] Optionally, zero filling, average value filling, fixed value filling or other filling methods may be used for the padding operation, and this application does not limit this.

[0096] The embodiment of the present application further processes the length of the search feature vector, which can facilitate the search feature vector while maintaining the integrity of key information, reducing redundancy and noise, thereby improving computing efficiency and matching accuracy.

[0097] Exemplarily, a method for calculating the similarity of a search feature vector is taken as an example for further explanation.

[0098] First, the similarity between the feature vector to be searched and the first search feature vector, and the similarity between the feature vector to be searched and the second search feature vector are calculated respectively.

[0099] Optionally, the cosine similarities of the feature vector to be searched and the first search feature vector and the second search feature vector may be calculated respectively, thereby obtaining a similarity calculation result.

[0100] Secondly, the financial products in the associated financial product set corresponding to the first search feature vector and the second search feature vector whose similarity is higher than a preset threshold are taken as first candidate recommended financial products.

[0101] Optionally, the financial product sets are sorted in descending order based on similarity, and the required first candidate recommended financial products are determined from the sorting according to the required number of first candidate recommended financial products.

[0102] The embodiment of the present application can vectorize the target user, historical contracted users and historical recommended users, as well as the corresponding associated financial product sets, and calculate the similarity based on the vectors, so as to more accurately obtain the first candidate recommended financial product for the target user and improve the accuracy of recommending financial products to the target user.

[0103] In the embodiment of the present application, the target user's financial products of interest can be obtained based on the target user's historical browsing data on the bank system, or can be combined with the target user's browsing data from other channels or ways to obtain multiple dimensions to improve the accuracy of the obtained financial products of interest. The following example takes the acquisition of the target user's financial products of interest from multiple dimensions as an example for explanation:

[0104] Figure 4 Schematic diagram of the process of obtaining the target user's interested financial products provided in the embodiment of the present application. Figure 4 As shown, the above step S101 may include:

[0105] S301. Obtain a first candidate financial product of interest to the target user based on the financial product browsing data of the target user within a first historical period of time.

[0106] Optionally, the first historical duration may be the duration of the user's browsing in the banking system, which may be any one of 1 hour, 1 week, 1 month, etc., and this application does not limit this. The target user's financial product browsing data may include any one or more items such as the product name and product type of the financial product, and may also include any one or more items such as the target user's browsing time, browsing duration, browsing frequency, click behavior, etc. for each financial product, and may also include the target user's search history.

[0107] The banking system may obtain the first candidate financial product of interest to the target user based on the financial product browsing data of the target user in the first historical time period. For example, the financial product whose browsing time by the target user exceeds a preset threshold in the first historical time period is taken as the first candidate financial product of interest to the target user.

[0108] S302: Based on the financial event attention data of the target user within the second historical period, obtain the financial events that the target user is interested in.

[0109] Optionally, the second historical duration is similar to the first historical duration, and will not be described in detail here. The event attention data of the target user may include any one or more of the target user's click records, browsing records, search records, etc. for the event, and also include any one or more of the target user's collection records, sharing records, comment records, etc. for the event page or article.

[0110] The banking system may obtain the financial events that the target user is interested in based on the event attention data of the target user in the second historical time period. For example, the financial events that the target user clicked on and recorded exceeding a preset threshold in the second historical time period are regarded as the financial events that the target user is interested in.

[0111] S303: Based on the financial event, obtain a second candidate financial product of interest to the target user.

[0112] Optionally, the banking system may obtain associated information and / or keywords of financial products from financial events of interest to the target user, and based on the extracted associated information and / or keywords, search a financial product database for a financial product that matches the associated information and / or keywords, and use the financial product as a second candidate financial product of interest to the target user; or the banking system may obtain similar financial products based on the extracted description information of the financial products, and use the similar financial products as the second candidate financial product of interest to the target user.

[0113] That is, based on the financial event, a first financial product associated with the financial event is obtained; based on the description information of the first financial product, a second financial product similar to the first financial product is obtained from financial products; based on the first financial product and the second financial product, a second candidate financial product of interest to the target user is determined.

[0114] Optionally, the description information of the first financial product is consistent with the description information of the target financial product, which is not described in detail here. For example, a financial product that is consistent and / or partially consistent with the description information of the first financial product can be used as the second financial product.

[0115] Secondly, based on the first financial product and the second financial product, a second candidate financial product of interest to the target user is determined.

[0116] For example, the first and second candidate financial products of interest may be determined from the first financial product and the second financial product based on the set screening dimensions. The screening dimensions may include, for example, at least one of the following: investment cycle, investment income, and number of purchasers. The above-set screening dimensions may be determined based on the target user's historical purchase behavior of financial products, or may be preset dimensions.

[0117] Optionally, both the first financial product and the second financial product may be used as second candidate financial products of interest to the target user.

[0118] The embodiment of the present application can obtain a second financial product similar to the first financial product based on the first financial product associated with the financial event, and determine the second candidate financial product of interest to the target user, which can better meet the user's potential needs and improve the accuracy of recommending financial products to the target user.

[0119] S304: Determine the target user's financial product of interest based on the first candidate financial product of interest and the second candidate financial product of interest.

[0120] For example, the target user's financial product of interest may be determined from the first candidate financial product of interest and the second candidate financial product of interest based on the set screening dimension. The screening dimension may include, for example, at least one of the following: investment cycle, investment income, and number of purchasers. The above-set screening dimension may be determined based on the target user's historical purchase behavior of financial products, or may be a preset dimension.

[0121] The embodiment of the present application integrates the target user's browsing data on financial products and data on their attention to financial events, and analyzes user needs and preferences from multiple aspects. Compared with the single recommendation method in the prior art, the present application can improve the accuracy of recommending financial products to target users.

[0122] The above is an embodiment of the method provided by the present application. The following is a description of the device provided by the present application.

[0123] Figure 5 This is a schematic diagram of the structure of a financial product recommendation device provided in an embodiment of the present application. Figure 5 As shown, the financial product recommendation device 400 may include, for example: a first acquisition module 401, a second acquisition module 402, a first determination module 403, a third acquisition module 404, a second determination module 405, and an output module 406. Optionally, the device 400 may further include, for example, a processing module 407.

[0124] The first acquisition module 401 is used to acquire the identity information of the target user and the financial products of interest to the target user.

[0125] The second acquisition module 402 is used to acquire a first candidate recommended financial product based on the identity information of the target user, the financial products of interest to the target user, and a database; the database at least includes: the identity information and associated financial product sets of historical contracted users and historical recommended users; the associated financial product sets of historical contracted users include the interested financial product sets and purchased financial product sets of historical contracted users; the associated financial product sets of historical recommended users include the interested financial product sets and recommended financial product sets of historical recommended users.

[0126] The first determination module 403 is used to determine the target financial product of the target user based on the first candidate recommended financial product and the interested financial product.

[0127] The third acquisition module 404 is used to acquire the target user's interest in the target financial product based on the target user's historical product purchase data and the description information of the target financial product.

[0128] The second determination module 405 is used to determine a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product.

[0129] The output module 406 is used to output the recommendation information of the target financial product based on the recommendation strategy.

[0130] Optionally, the second acquisition module 402 is specifically configured to construct a to-be-searched feature vector of the target user based on the identity information of the target user and the target user's interested financial products. A first search feature vector of the historical contracted user is constructed based on the identity information of the historical contracted user and the associated financial product set. A second search feature vector of the historical recommended user is constructed based on the identity information of the historical recommended user and the associated financial product set. A first candidate recommended financial product is determined from the associated financial product set of the historical contracted user and the associated financial product set of the historical recommended user based on the to-be-searched feature vector, the first search feature vector, and the second search feature vector.

[0131] For example, the processing module 407 is used for the second acquisition module 402 to determine the first candidate recommended financial product from the associated financial product set of the historical contracted user and the associated financial product set of the historical recommended user based on the feature vector to be searched, the first search feature vector, and the second search feature vector, and to determine the target search feature vector with the longest length from the feature vector to be searched, the first search feature vector, and the second search feature vector. Based on the length of the target search feature vector, the other search feature vectors are padded to make the lengths of the feature vector to be searched, the first search feature vector, and the second search feature vector consistent.

[0132] For example, the second acquisition module 402 is specifically used to calculate the similarity between the feature vector to be searched and the first search feature vector, and the similarity between the feature vector to be searched and the second search feature vector, respectively, and to select the financial products in the associated financial product set corresponding to the first search feature vector and the second search feature vector whose similarity is higher than a preset threshold as the first candidate recommended financial products.

[0133] Optionally, the first acquisition module 401 is specifically configured to acquire a first candidate financial product of interest to the target user based on the financial product browsing data of the target user within a first historical duration. Based on the financial event attention data of the target user within a second historical duration, acquire a financial event of interest to the target user. Based on the financial event, acquire a second candidate financial product of interest to the target user. Based on the first candidate financial product of interest and the second candidate financial product of interest, determine the financial product of interest to the target user.

[0134] For example, the first acquisition module 401 is specifically configured to acquire a first financial product associated with the financial event based on the financial event, acquire a second financial product similar to the first financial product from the financial products based on the description information of the first financial product, and determine a second candidate financial product of interest to the target user based on the first financial product and the second financial product.

[0135] Optionally, the first determination module 403 is specifically configured to determine a second candidate recommended financial product to be recommended to the target user from the hot financial products based on the popularity of the financial product, the trend of the financial product, and the historical purchase data of the target user. The historical purchase data at least includes the historical purchase data of the financial product. The target financial product is determined based on the first candidate financial product and the second candidate financial product.

[0136] Optionally, the processing module 407 is further configured to obtain the focus and / or facial expression of the target user when browsing the recommended information of the target financial product. Based on the focus and / or facial expression, the browsing preference of the target user is obtained. Based on the browsing preference, the order and / or layout style of the recommended information of the target financial product is adjusted.

[0137] The financial product recommendation device 400 provided in the embodiment of the present application can be used to implement the actions performed by the banking system in any of the aforementioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0138] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 500 may include: a memory 501 and a processor 502. Optionally, the electronic device may further include a transceiver 503, wherein the memory 501 and the processor 502 communicate; illustratively, the memory 501, the processor 502 and the transceiver 503 may communicate via a communication bus 504, the memory 501 is used to store a computer program, and the processor 502 executes the computer program to implement the method of the above embodiment.

[0139] Optionally, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps in the method embodiments disclosed in the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0140] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, a method in any of the above method embodiments is implemented.

[0141] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method in any of the above method embodiments when the computer program is executed by a processor.

[0142] All or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions. The above-mentioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the above-mentioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc and any combination thereof.

[0143] The embodiments of the present application are 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 processing unit 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 processing unit 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.

[0144] 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.

[0145] 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.

[0146] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0147] In the present application, the term "include" and its variations may refer to non-restrictive inclusion; the term "or" and its variations may refer to "and / or". The terms "first", "second", etc. in the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. In the present application, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.

Claims

1. A financial product recommendation method, characterized in that: Obtaining identity information of a target user and financial products of interest to the target user; Based on the identity information of the target user, the financial products of interest to the target user, and a database, a first candidate recommended financial product is obtained; the database at least includes: the identity information and associated financial product sets of historical contracted users and historical recommended users; the associated financial product sets of historical contracted users include the interested financial product sets and purchased financial product sets of historical contracted users; the associated financial product sets of historical recommended users include the interested financial product sets and recommended financial product sets of historical recommended users; Determining a target financial product for the target user based on the first candidate recommended financial products and the financial product of interest; Based on the historical product purchase data of the target user and the description information of the target financial product, obtaining the interest of the target user in the target financial product; Determining a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product; Based on the recommendation strategy, recommendation information of the target financial product is output.

2. The method according to claim 1, characterized in that The step of acquiring a first candidate recommended financial product based on the identity information of the target user, the financial products of interest to the target user, and a database includes: Based on the identity information of the target user and the financial products of interest to the target user, construct a feature vector to be searched for the target user; Constructing a first search feature vector of the historical contracting user based on the identity information of the historical contracting user and the associated financial product set; Based on the identity information and the associated financial product set of the historically recommended user, construct a second search feature vector of the historically recommended user; Based on the feature vector to be searched, the first search feature vector, and the second search feature vector, the first candidate recommended financial product is determined from the associated financial product set of the historical contracted users and the associated financial product set of the historical recommended users.

3. The method according to claim 2, characterized in that Before determining the first candidate recommended financial product from the associated financial product set of the historical contracted user and the associated financial product set of the historical recommended user based on the feature vector to be searched, the first search feature vector, and the second search feature vector, the method further includes: Determine a target search feature vector with the longest length from the feature vector to be searched, the first search feature vector, and the second search feature vector; Based on the length of the target search feature vector, a padding operation is performed on other search feature vectors to make the lengths of the feature vector to be searched, the first search feature vector, and the second search feature vector consistent.

4. The method according to claim 2, characterized in that: The determining the first candidate recommended financial product from the associated financial product set of the historical contracted user and the associated financial product set of the historical recommended user based on the to-be-searched feature vector, the first search feature vector, and the second search feature vector comprises: respectively calculating the similarity between the feature vector to be searched and the first search feature vector, and the similarity between the feature vector to be searched and the second search feature vector; The financial products in the associated financial product set corresponding to the first search feature vector and the second search feature vector, whose similarity is higher than a preset threshold, are used as the first candidate recommended financial products.

5. The method according to claim 1, characterized in that The obtaining of the target user's interested financial products includes: Acquire a first candidate financial product of interest to the target user based on the financial product browsing data of the target user within a first historical period; Acquire financial events that the target user is interested in based on the financial event attention data of the target user within a second historical period; Based on the financial event, obtaining a second candidate financial product of interest to the target user; The financial product of interest to the target user is determined based on the first candidate financial product of interest and the second candidate financial product of interest.

6. The method according to claim 5, characterized in that The acquiring, based on the financial event, a second candidate financial product of interest to the target user includes: Based on the financial event, obtaining a first financial product associated with the financial event; Based on the description information of the first financial product, acquiring a second financial product similar to the first financial product from financial products; Based on the first financial product and the second financial product, a second candidate financial product of interest to the target user is determined.

7. The method according to claim 1, characterized in that The determining the target financial product of the target user based on the first candidate recommended financial product and the interested financial product includes: Based on the popularity of financial products, the trend of financial products, and the historical purchase data of the target user, determining a second candidate recommended financial product to be recommended to the target user from the hot financial products; the historical purchase data at least includes the historical purchase data of the financial product; The target financial product is determined based on the first candidate financial product, the second candidate financial product, and the financial product of interest.

8. The method according to claim 1, characterized in that The method further comprises: Acquiring the focus and / or facial expression of the target user when browsing the recommendation information of the target financial product; Based on the focus and / or facial expression, obtaining the browsing preference of the target user; Based on the browsing preference, the order and / or layout style of the recommendation information of the target financial product is adjusted.

9. A financial product recommendation device, characterized in that: The device comprises: A first acquisition module is used to acquire the identity information of a target user and the financial products of interest to the target user; A second acquisition module is configured to acquire a first candidate recommended financial product based on the identity information of the target user, the financial products of interest to the target user, and a database; the database at least includes: the identity information and associated financial product sets of historical contracted users and historical recommended users; the associated financial product sets of historical contracted users include the interested financial product sets and purchased financial product sets of historical contracted users; the associated financial product sets of historical recommended users include the interested financial product sets and recommended financial product sets of historical recommended users; A first determination module, configured to determine a target financial product for the target user based on the first candidate recommended financial products and the financial product of interest; A third acquisition module is used to acquire the interest of the target user in the target financial product based on the historical product purchase data of the target user and the description information of the target financial product; A second determination module, configured to determine a recommendation strategy for the target financial product based on the interest level and the description information of the target financial product; An output module is used to output recommendation information of the target financial product based on the recommendation strategy.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program financial product, characterized in that: The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images