Financial product recommendation method and device

Abstract

The present application provides a method and device for recommending financial products, the method comprising: obtaining user information of a target user, the target user being a user to whom a financial product is to be recommended, determining the population category to which the target user belongs based on the user information, determining a pre-constructed product library corresponding to the population category to which the target user belongs as a target product library, the target product library including at least one financial product of interest to users belonging to the same population category as the target user, determining the financial product to be recommended from the target product library, and recommending the determined financial product to be recommended to the target user. In the present technical solution, a product library corresponding to different population categories is pre-constructed, and by determining the population category to which the target user belongs, the financial product to be recommended is determined from the product library corresponding to the population category to which the target user belongs, and the financial product to be recommended is recommended to the user, thereby increasing the sales volume of financial products.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for recommending financial products. Background Art

[0002] With the development of the economy and the growth of residents' disposable wealth, residents have become more and more enthusiastic about financial products and the demand for them is also increasing. More and more people like to buy financial products through online mobile banking.

[0003] However, there are too many financial products on mobile banking, and the types are complicated. This brings great inconvenience to users' own choices. It is difficult for users to find financial products that meet their psychological expectations, which makes them lose the enthusiasm to continue purchasing, resulting in the inability to increase the sales of financial products rapidly.

[0004] Therefore, how to provide a technical solution that can increase the sales volume of financial products is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] Based on the above-mentioned deficiencies in the prior art, the present application provides a financial product recommendation method to increase the sales volume of financial products.

[0006] The present application also provides a financial product recommendation device to ensure the implementation and application of the above method in practice.

[0007] A financial product recommendation method, comprising:

[0008] Obtaining user information of a target user; the target user is a user to whom a financial product is to be recommended;

[0009] Based on the user information, determining the population category to which the target user belongs;

[0010] Determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user;

[0011] Determining a financial product to be recommended from the target product library;

[0012] The determined financial products to be recommended are recommended to the target users.

[0013] In the above method, optionally, determining the population category to which the target user belongs based on the user information includes:

[0014] Based on the user information, construct a user profile of the target user;

[0015] Based on the user portrait of the target user, calculating the similarity between the target user and the user set corresponding to each preset population category;

[0016] The crowd category corresponding to the user set corresponding to the highest similarity is used to determine the crowd category to which the target user belongs.

[0017] The above method may, optionally, after recommending the determined financial product to be recommended to the target user, further comprises:

[0018] Obtain the behavior logs generated by the target user purchasing financial products through the application;

[0019] Based on the behavior log, determine the financial products purchased by the target user, and determine each financial product purchased by the target user as a purchased financial product;

[0020] For each purchased financial product, calculate the similarity between the purchased financial product and each other financial product included in the application, and determine the other financial products corresponding to the similarity greater than a preset similarity threshold as the first financial product; wherein the other financial products are financial products in all financial products included in the application except for each purchased financial product;

[0021] For each first financial product, judging whether the target user meets the purchase conditions of the first financial product based on the user profile of the target user, and if so, determining the first financial product as the second financial product;

[0022] Recommend each second financial product to the target user.

[0023] In the above method, optionally, the calculating the similarity between the purchased financial product and each other financial product included in the application comprises:

[0024] The similarity between the purchased financial product and each other financial product included in the application is calculated by using a collaborative filtering algorithm.

[0025] In the above method, optionally, determining the financial product to be recommended from the target product library includes:

[0026] Determine the number of users who have purchased each financial product in the target product library;

[0027] Based on the number of users who have purchased each financial product in the target product library, sorting the financial products included in the target product library in descending order according to the number of users who have purchased the products;

[0028] The first N financial products are selected from the target product library in which the financial products have been ranked as the financial products to be recommended; wherein N is a natural number.

[0029] A financial product recommendation device, comprising:

[0030] A first acquisition unit is used to acquire user information of a target user; the target user is a user to whom a financial product is to be recommended;

[0031] A first determining unit, configured to determine the group category to which the target user belongs based on the user information;

[0032] A second determining unit is used to determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user;

[0033] A third determining unit, configured to determine the financial product to be recommended from the target product library;

[0034] The first recommendation unit is used to recommend the determined financial product to be recommended to the target user.

[0035] In the above method, optionally, the first determining unit is used to determine the group category to which the target user belongs based on the user information, including the first determining unit being specifically used to:

[0036] Based on the user information, construct a user profile of the target user;

[0037] Based on the user portrait of the target user, calculating the similarity between the target user and the user set corresponding to each preset population category;

[0038] The crowd category corresponding to the user set corresponding to the highest similarity is used to determine the crowd category to which the target user belongs.

[0039] The above method may optionally further include:

[0040] The second acquisition unit is used to acquire the behavior log generated by the target user purchasing the financial product through the application;

[0041] a fourth determining unit, configured to determine the financial products purchased by the target user based on the behavior log, and determine each financial product purchased by the target user as a purchased financial product;

[0042] a calculation unit, configured to calculate, for each purchased financial product, a similarity between the purchased financial product and each other financial product included in the application, and determine other financial products corresponding to similarities greater than a preset similarity threshold as first financial products; wherein other financial products are financial products other than each purchased financial product among all financial products included in the application;

[0043] a judgment unit, configured to judge, for each first financial product, whether the target user meets the purchase conditions of the first financial product based on the user profile of the target user, and if so, determine the first financial product as a second financial product;

[0044] The second recommendation unit is used to recommend each second financial management product to the target user.

[0045] In the above method, optionally, the calculation unit is used to calculate the similarity between the purchased financial product and each other financial product included in the application, including the calculation unit being specifically used to:

[0046] The similarity between the purchased financial product and each other financial product included in the application is calculated by using a collaborative filtering algorithm.

[0047] In the above method, optionally, the third determining unit is used to determine the financial product to be recommended from the target product library, including the third determining unit being specifically used to:

[0048] Determine the number of users who have purchased each financial product in the target product library;

[0049] Based on the number of users who have purchased each financial product in the target product library, sorting the financial products included in the target product library in descending order of the number of users who have purchased the products;

[0050] The first N financial products are selected from the target product library in which the financial products have been ranked as the financial products to be recommended; wherein N is a natural number.

[0051] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned financial product recommendation method.

[0052] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the above-mentioned financial product recommendation method.

[0053] Compared with the prior art, this application has the following advantages:

[0054] The present application provides a method and device for recommending financial products, the method comprising: obtaining user information of a target user, the target user being a user to whom a financial product is to be recommended, determining the population category to which the target user belongs based on the user information, determining a pre-constructed product library corresponding to the population category to which the target user belongs as a target product library, the target product library including at least one financial product of interest to users belonging to the same population category as the target user, determining the financial product to be recommended from the target product library, and recommending the determined financial product to be recommended to the target user. In the present technical solution, a product library corresponding to different population categories is pre-constructed, and by determining the population category to which the target user belongs, the financial product to be recommended is determined from the product library corresponding to the population category to which the target user belongs, and the financial product to be recommended is recommended to the user, thereby increasing the sales volume of financial products. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0056] Figure 1 A method flow chart of a financial product recommendation method provided for this application;

[0057] Figure 2 Another method flow chart of a financial product recommendation method provided in this application;

[0058] Figure 3 Another method flow chart of a financial product recommendation method provided in this application;

[0059] Figure 4 A flowchart of another method for recommending a financial product provided in this application;

[0060] Figure 5 A schematic diagram of the structure of a financial product recommendation device provided in this application;

[0061] Figure 6 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0064] The embodiment of the present invention provides a method for recommending financial products. The method can be applied to a variety of system platforms. The execution subject can be a processor of a computer terminal or various mobile devices. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0065] S101. Obtain user information of a target user; the target user is a user to whom a financial product is to be recommended.

[0066] In this embodiment, user information of a target user is obtained, wherein the target user is a user to whom a financial product is to be recommended, and the user information includes but is not limited to the user's basic information, risk tolerance, and property status.

[0067] It should be noted that the target users mentioned in step S101 are users who have no record of purchasing financial products.

[0068] S102: Determine the population category to which the target user belongs based on the user information.

[0069] Based on the user information of the target user, determine the population category to which the target user belongs.

[0070] For details, see Figure 2 , based on user information, the process of determining the population category to which the target user belongs includes:

[0071] S201. Build a user profile of the target user based on the user information.

[0072] Based on user information, construct user portraits for target users.

[0073] In this embodiment, the process of constructing the user portrait can refer to the existing process of constructing the user portrait, which will not be described in detail here.

[0074] S202: Based on the user portrait of the target user, calculate the similarity between the target user and the user set corresponding to each preset population category.

[0075] In this embodiment, each user who purchases financial products through the application is classified in advance to obtain multiple population categories, each population category corresponds to a user set, and the user set includes multiple users. Among them, the application can be mobile banking.

[0076] Based on the user portrait of the target user, the similarity between the target user and each user set is calculated. Optionally, an existing similarity calculation formula can be used to calculate the similarity between the target user and each user set. The similarity calculation formula can be a cosine similarity calculation formula or a Pearson correlation coefficient calculation formula.

[0077] It should be noted that this embodiment does not limit the similarity calculation formula.

[0078] S203: Determine the population category to which the target user belongs by using the population category corresponding to the user set corresponding to the highest similarity.

[0079] Based on the calculated similarities, the similarities are sorted to determine the similarity with the largest value, that is, the highest similarity.

[0080] The crowd category corresponding to the user set corresponding to the highest similarity is determined as the crowd category of the target user.

[0081] It should be noted that users belonging to the same population category have similar user characteristics.

[0082] S103: Determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library.

[0083] In this embodiment, a product library corresponding to different population categories is pre-constructed, and the product library includes at least one financial product that each user in the user set corresponding to the product library is interested in. That is to say, each financial product included in the product library is a financial product that each user in the user set corresponding to the product library is interested in.

[0084] The process of building a product library corresponding to different population categories specifically includes: building a product profile for each financial product based on the product information of each financial product, obtaining the financial products that each user in the user set is interested in for the user set corresponding to each population category, and organizing the financial products that each user is interested in into the product library corresponding to the population category.

[0085] S104: Determine the financial product to be recommended from the target product library.

[0086] In this embodiment, the financial products to be recommended are determined from various financial products included in the target product library.

[0087] For details, see Figure 3 , the process of determining the financial products to be recommended from the target product library includes:

[0088] S301: Determine the number of users who have purchased each financial product in the target product library.

[0089] In this embodiment, the number of users who have purchased each financial product included in the target product library is determined. Specifically, the number of users who have purchased each financial product included in the target product library in the target user set is counted, wherein the target user set is the user set corresponding to the target product library.

[0090] S302: Based on the number of users who have purchased each financial product in the target product library, sort the financial products included in the target product library in descending order according to the number of users who have purchased each financial product.

[0091] In this embodiment, based on the number of users who have purchased each financial product in the target product library, the financial products included in the target product library are sorted in descending order according to the number of users who have purchased. That is to say, the larger the number of users who have purchased, the higher the sorting number of the corresponding financial product.

[0092] S303. Select the first N financial products from the target product library that has been ranked as financial products to be recommended; N is a natural number.

[0093] The first N financial products are selected from the target product library that has been ranked for financial products, where N is a natural number.

[0094] The first N selected financial products are all used as financial products to be recommended.

[0095] S105: Recommend the determined financial products to be recommended to the target users.

[0096] In this embodiment, the determined financial products to be recommended are recommended to the target users.

[0097] The financial product recommendation method provided in the embodiment of the present application obtains user information of a target user, where the target user is a user to whom a financial product is to be recommended. Based on the user information, the population category to which the target user belongs is determined, and a pre-constructed product library corresponding to the population category to which the target user belongs is determined as a target product library, where the target product library includes at least one financial product of interest to users belonging to the same population category as the target user, and the financial product to be recommended is determined from the target product library, and the determined financial product to be recommended is recommended to the target user. The financial product recommendation method provided in the embodiment of the present application is applied to pre-construct product libraries corresponding to different population categories, and by determining the population category to which the target user belongs, the financial product to be recommended is determined from the product library corresponding to the population category to which the target user belongs, and the financial product to be recommended is recommended to the user, thereby increasing the sales of financial products.

[0098] In the method provided in the embodiment of the present application, after the determined financial product to be recommended is recommended to the target user in step S105, Figure 4 As shown, the following steps may also be included:

[0099] S401: Obtaining a behavior log of a target user purchasing a financial product through an application.

[0100] In this embodiment, after the target user purchases a financial product through an application, a behavior log generated by the target user purchasing the financial product through the application is obtained. The behavior log includes the product identifier of the financial product purchased by the target user. The product identifier is used to uniquely identify the financial product, that is, different financial products correspond to different product identifiers.

[0101] S402: Based on the behavior log, determine the financial products purchased by the target user, and determine each financial product purchased by the target user as a purchased financial product.

[0102] In this embodiment, the financial product purchased by the target user is determined based on the behavior log. Specifically, based on the product identifier included in the behavior log, the financial product corresponding to the product identifier is determined, and the financial product corresponding to the product identifier is determined as the financial product purchased by the target user.

[0103] The financial products purchased by the target users are determined as purchased financial products.

[0104] S403: For each purchased financial product, calculate the similarity between the purchased financial product and each other financial product included in the application, and determine the other financial product corresponding to the similarity greater than a preset similarity threshold as the first financial product.

[0105] In this embodiment, for each purchased financial product, the similarity between the purchased financial product and each other financial product included in the application is calculated, wherein the other financial products are all financial products included in the application except for each purchased financial product.

[0106] In this implementation, the process of calculating the similarity between the purchased financial product and each other financial product included in the application specifically includes:

[0107] The similarity between the purchased financial product and each other financial product included in the application is calculated using a collaborative filtering algorithm.

[0108] In this embodiment, optionally, a collaborative filtering algorithm may be used to calculate the similarity between the purchased financial product and each other financial product included in the application, or a cosine similarity calculation formula may be used to calculate the similarity between the purchased financial product and each other financial product included in the application.

[0109] In this embodiment, for each purchased financial product, the similarity between the purchased financial product and each other financial product included in the application is compared with a preset similarity threshold, and the other financial product corresponding to the similarity greater than the similarity threshold is determined as the first financial product.

[0110] S404. For each first financial product, based on the user portrait of the target user, determine whether the target user meets the purchase conditions of the first financial product. If yes, determine the first financial product as the second financial product.

[0111] In this embodiment, for each first financial product, based on the user portrait of the target user, it is determined whether the target user meets the purchase conditions of the first financial product. If it is determined that the target user meets the purchase conditions of the first financial product, the first financial product is determined as the second financial product. If it is determined that the target user does not meet the purchase conditions of the first financial product, the first financial product is not determined as the second financial product.

[0112] S405: Recommend each second financial product to the target user.

[0113] In this embodiment, each determined second financial management product is recommended to the target user.

[0114] In the financial product recommendation method provided in the embodiment of the present application, after the target user purchases a financial product through an application, financial products that are highly similar to the financial products purchased by the target user and that the target user meets the purchase conditions can be selected from the various financial products included in the application and recommended to the target user.

[0115] and Figure 1 Corresponding to the method described above, the embodiment of the present application also provides a financial product recommendation device for Figure 1 The specific implementation of the method is shown in the following diagram: Figure 5 As shown, specifically including:

[0116] The first acquisition unit 501 is used to acquire user information of a target user; the target user is a user to whom a financial product is to be recommended;

[0117] A first determining unit 502 is used to determine the group category to which the target user belongs based on the user information;

[0118] The second determining unit 503 is used to determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user;

[0119] A third determining unit 504 is used to determine the financial product to be recommended from the target product library;

[0120] The first recommendation unit 505 is used to recommend the determined financial product to be recommended to the target user.

[0121] The financial product recommendation device provided in the embodiment of the present application obtains user information of a target user, where the target user is a user to whom a financial product is to be recommended, determines the population category to which the target user belongs based on the user information, determines a pre-constructed product library corresponding to the population category to which the target user belongs as a target product library, and includes at least one financial product of interest to users belonging to the same population category as the target user in the target product library, determines the financial product to be recommended from the target product library, and recommends the determined financial product to be recommended to the target user. The financial product recommendation device provided in the embodiment of the present application is applied to pre-construct product libraries corresponding to different population categories, determines the population category to which the target user belongs, determines the financial product to be recommended from the product library corresponding to the population category to which the target user belongs, and recommends the financial product to be recommended to the user, thereby increasing the sales of financial products.

[0122] In one embodiment of the present application, based on the above solution, the first determination unit 502 is used to determine the group category to which the target user belongs based on the user information, including the first determination unit 502 being specifically used to:

[0123] Based on the user information, construct a user profile of the target user;

[0124] Based on the user portrait of the target user, calculating the similarity between the target user and the user set corresponding to each preset population category;

[0125] The crowd category corresponding to the user set corresponding to the highest similarity is used to determine the crowd category to which the target user belongs.

[0126] In one embodiment of the present application, based on the above solution, it can also be configured as follows:

[0127] Also includes:

[0128] The second acquisition unit is used to acquire the behavior log generated by the target user purchasing the financial product through the application;

[0129] a fourth determining unit, configured to determine the financial products purchased by the target user based on the behavior log, and determine each financial product purchased by the target user as a purchased financial product;

[0130] a calculation unit, configured to calculate, for each purchased financial product, a similarity between the purchased financial product and each other financial product included in the application, and determine other financial products corresponding to similarities greater than a preset similarity threshold as first financial products; wherein other financial products are financial products other than each purchased financial product among all financial products included in the application;

[0131] a judgment unit, configured to judge, for each first financial product, whether the target user meets the purchase conditions of the first financial product based on the user profile of the target user, and if so, determine the first financial product as a second financial product;

[0132] The second recommendation unit is used to recommend each second financial management product to the target user.

[0133] In one embodiment of the present application, based on the above solution, the calculation unit is used to calculate the similarity between the purchased financial product and each other financial product included in the application, including the calculation unit specifically used to:

[0134] The similarity between the purchased financial product and each other financial product included in the application is calculated by using a collaborative filtering algorithm.

[0135] In one embodiment of the present application, based on the above solution, the third determining unit 504 is used to determine the financial product to be recommended from the target product library, including the third determining unit 504 being specifically used to:

[0136] Determine the number of users who have purchased each financial product in the target product library;

[0137] Based on the number of users who have purchased each financial product in the target product library, sorting the financial products included in the target product library in descending order of the number of users who have purchased the products;

[0138] The first N financial products are selected from the target product library in which the financial products have been ranked as the financial products to be recommended; wherein N is a natural number.

[0139] The embodiment of the present application further provides a storage medium, wherein the storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to perform the following operations:

[0140] Obtaining user information of a target user; the target user is a user to whom a financial product is to be recommended;

[0141] Based on the user information, determining the population category to which the target user belongs;

[0142] Determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user;

[0143] Determining a financial product to be recommended from the target product library;

[0144] The determined financial products to be recommended are recommended to the target users.

[0145] The present application also provides an electronic device, whose structural diagram is as follows: Figure 6 As shown, it specifically includes a memory 601 and one or more instructions 602, wherein the one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to perform the following operations:

[0146] Obtaining user information of a target user; the target user is a user to whom a financial product is to be recommended;

[0147] Based on the user information, determining the population category to which the target user belongs;

[0148] Determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user;

[0149] Determining a financial product to be recommended from the target product library;

[0150] The determined financial products to be recommended are recommended to the target users.

[0151] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0152] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0153] For the convenience of description, the above system is described by dividing it into various units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0154] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0155] The above is a detailed introduction to a financial product recommendation method and device provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for recommending financial products, characterized in that: include: Get the user information of the target user; The target users are users to whom financial products are to be recommended; The user information at least includes the user's basic information, risk tolerance and property status; Determining the crowd category to which the target user belongs based on the user information includes: constructing a user profile of the target user based on the user information; calculating the similarity between the target user and a user set corresponding to each preset crowd category based on the user profile of the target user; determining the crowd category to which the target user belongs by using the crowd category corresponding to the user set corresponding to the highest similarity; Determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user; Determining the financial products to be recommended from the target product library includes: determining the number of users who have purchased each financial product in the target product library; sorting the financial products included in the target product library in descending order of the number of users who have purchased each financial product in the target product library based on the number of users who have purchased each financial product in the target product library; selecting the first N financial products from the sorted target product library as the financial products to be recommended; N is a natural number; Recommending the determined financial products to be recommended to the target user; Obtain the behavior logs generated by the target user purchasing financial products through the application; Based on the behavior log, determine the financial products purchased by the target user, and determine each financial product purchased by the target user as a purchased financial product; For each purchased financial product, calculate the similarity between the purchased financial product and each other financial product included in the application, and determine the other financial products corresponding to the similarity greater than a preset similarity threshold as the first financial product; wherein the other financial products are financial products in all financial products included in the application except for each purchased financial product; For each first financial product, judging whether the target user meets the purchase conditions of the first financial product based on the user profile of the target user, and if so, determining the first financial product as the second financial product; Each second financial product is recommended to the target user.

2. The method according to claim 1, characterized in that The calculating the similarity between the purchased financial product and each other financial product included in the application comprises: The similarity between the purchased financial product and each other financial product included in the application is calculated by using a collaborative filtering algorithm.

3. A financial product recommendation device, characterized in that: include: A first acquisition unit, used to acquire user information of a target user; The target users are users to whom financial products are to be recommended; A first determination unit is used to determine the crowd category to which the target user belongs based on the user information, including: constructing a user profile of the target user based on the user information; calculating the similarity between the target user and a user set corresponding to each preset crowd category based on the user profile of the target user; determining the crowd category to which the target user belongs by using the crowd category corresponding to the user set corresponding to the highest similarity; A second determining unit is used to determine a pre-built product library corresponding to the population category to which the target user belongs as a target product library; the target product library includes at least one financial product that is of interest to users belonging to the same population category as the target user; The third determining unit is used to determine the financial products to be recommended from the target product library, including: determining the number of users who have purchased each financial product in the target product library; sorting the financial products included in the target product library in descending order of the number of users who have purchased each financial product in the target product library based on the number of users who have purchased each financial product in the target product library; selecting the first N financial products from the sorted target product library as the financial products to be recommended; N is a natural number; A first recommendation unit, configured to recommend the determined financial product to be recommended to the target user; The second acquisition unit is used to acquire the behavior log generated by the target user purchasing the financial product through the application; a fourth determining unit, configured to determine the financial products purchased by the target user based on the behavior log, and determine each financial product purchased by the target user as a purchased financial product; a calculation unit, configured to calculate, for each purchased financial product, a similarity between the purchased financial product and each other financial product included in the application, and determine other financial products corresponding to similarities greater than a preset similarity threshold as first financial products; wherein other financial products are financial products other than each purchased financial product among all financial products included in the application; a judgment unit, configured to judge, for each first financial product, whether the target user meets the purchase conditions of the first financial product based on the user profile of the target user, and if so, determine the first financial product as a second financial product; The second recommendation unit is used to recommend each second financial management product to the target user.

4. The device according to claim 3, characterized in that The calculation unit is used to calculate the similarity between the purchased financial product and each other financial product included in the application, including the calculation unit being specifically used to: The similarity between the purchased financial product and each other financial product included in the application is calculated by using a collaborative filtering algorithm.

Images