Financial product portfolio recommendation method, device, and electronic device

Abstract

The present invention discloses a method for recommending a financial product portfolio, an apparatus thereof, and an electronic device thereof, relating to the field of artificial intelligence. The method comprises: obtaining asset information of a target user and pushing the asset information to a data center; then, using a preset Hall effect three-dimensional structure, establishing a user behavior model. The user behavior model comprises: a first sub-model for calculating the target user's investment scale stability; a second sub-model for determining a first set of financial products to be pushed to the target user; and a third sub-model for determining a second set of financial products to be pushed to the target user. Based on the investment scale stability, a target financial product portfolio is determined from the first set of financial products and / or the second set of financial products, and the target financial product portfolio is recommended to the target user. The present invention solves the technical problem in related arts of being unable to recommend reasonable financial product portfolios to users, resulting in a reduced user experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method for recommending a combination of financial products, a device thereof, and an electronic device. Background Art

[0002] In related technologies, financial institutions divide financial product businesses into monetary financial products, bond-type financial products, etc. Users can only select the financial products they want to purchase individually through various interface option buttons (such as "Selected for You" and "All Financial Products"). However, the current "Selected for You" financial product push only provides two or three financial products, with relatively few options, and cannot provide personalized push notifications to users. Moreover, when users select financial products through the "All Financial Products" push notification, there is no reasonable model for users to refer to regarding the purchase proportion of various financial products. Users cannot be sure whether the financial products they purchase are required for their own financial management plans, nor can they make reasonable allocations of the purchased financial products. The purchase is highly blind, which reduces the customer experience.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present invention provide a method for recommending a financial product combination, an apparatus thereof, and an electronic device, to at least solve the technical problem in related technologies that a reasonable financial product combination cannot be recommended to users, resulting in a decline in user experience.

[0005] According to one aspect of an embodiment of the present invention, a method for recommending a financial product portfolio is provided, comprising: obtaining asset information of a target user and pushing the asset information to a data middle platform; establishing a user behavior model based on the data middle platform using a preset Hall three-dimensional structure, wherein the user behavior model comprises: a first sub-model, a second sub-model, and a third sub-model, the first sub-model being used to calculate the investment scale stability of the target user, the second sub-model being used to determine a first set of financial products to be pushed to the target user, and the third sub-model being used to determine a second set of financial products to be pushed to the target user; determining a target financial product portfolio from the first set of financial products and / or the second set of financial products based on the investment scale stability; and recommending the target financial product portfolio to the target user.

[0006] Optionally, the step of obtaining the target user's asset information includes: generating an information collection instruction when the target user triggers a product purchase operation and / or triggers a product interface browsing operation; and obtaining the target user's asset information based on the information collection instruction.

[0007] Optionally, after pushing the asset information to the data middle platform, it also includes: extracting keywords of the asset information based on the preset data lake technology; classifying the asset information based on the keywords to obtain classification results, wherein the data types in the classification results include at least: transaction data, first-category financial product data, and second-category financial product data.

[0008] Optionally, based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model, including: based on the data middle platform, obtaining the transaction data, the first category financial product data and the second category financial product data; characterizing the investment scale stability as the time dimension standard of the preset Hall three-dimensional structure; characterizing the first financial product set within the first preset time period as the logic dimension standard of the preset Hall three-dimensional structure; characterizing the second financial product set within the second preset time period as the knowledge dimension standard of the preset Hall three-dimensional structure; based on the time dimension standard, the logic dimension standard and the knowledge dimension standard, using the transaction data, the first category financial product data and the second category financial product data, to establish the user behavior model.

[0009] Optionally, the step of calculating the investment scale stability of the target user includes: setting a preset cycle length; based on the preset cycle length, analyzing the transaction data to obtain the transaction data value within each cycle; based on the transaction data value, using a preset logistic regression strategy to calculate the investment scale stability.

[0010] Optionally, the step of determining a first set of financial products to be pushed to the target user includes: analyzing the first category of financial product data to obtain the first product categories of financial products purchased by the target user within the first preset time period and the purchase quantity of each first product category; calculating the target user's preference for each first product category based on the purchase quantity of each first product category; determining the target product category indicated by a preference greater than a first preset threshold, and obtaining the first financial product set.

[0011] Optionally, the step of determining a second set of financial products to be pushed to the target user includes: analyzing the second category of financial product data to obtain a first category set of financial products searched by the target user within the second preset time period, a second product category of financial products purchased, and the purchase quantity of each second product category; based on the purchase quantity of each second product category, calculating the target user's preference for each second product category; determining the target product category indicated by a preference greater than a second preset threshold to obtain a second category set; and obtaining the second financial product set based on the first category set and the second category set.

[0012] Optionally, the step of determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability includes: when the investment scale stability is a first stability, determining the target financial product portfolio from the first financial product set; when the investment scale stability is a second stability, determining the target financial product portfolio from the second financial product set, wherein the second stability is greater than the first stability; when the investment scale stability is a third stability, determining the target financial product portfolio from the first financial product set and the second financial product set, wherein the third stability is greater than the first stability and less than the second stability.

[0013] According to another aspect of an embodiment of the present invention, a device for recommending a financial product combination is also provided, including: an acquisition unit for acquiring asset information of a target user and pushing the asset information to a data middle platform; an establishment unit for establishing a user behavior model based on the data middle platform and using a preset Hall three-dimensional structure, wherein the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model, the first sub-model being used to calculate the investment scale stability of the target user, the second sub-model being used to determine a first financial product set to be pushed to the target user, and the third sub-model being used to determine a second financial product set to be pushed to the target user; a determination unit being used to determine a target financial product combination from the first financial product set and / or the second financial product set based on the investment scale stability; and a recommendation unit being used to recommend the target financial product combination to the target user.

[0014] Optionally, the acquisition unit includes: a first generation module, used to generate an information collection instruction when the target user triggers a product purchase operation and / or triggers a product interface browsing operation; a first acquisition module, used to acquire the asset information of the target user based on the information collection instruction.

[0015] Optionally, the recommendation device also includes: a first extraction module, used to extract keywords of the asset information based on a preset data lake technology after pushing the asset information to the data middle platform; a first classification module, used to classify the asset information based on the keywords to obtain classification results, wherein the data types in the classification results include at least: transaction data, first-category financial product data, and second-category financial product data.

[0016] Optionally, the establishment unit includes: a second acquisition module, used to acquire the transaction data, the first category financial product data and the second category financial product data based on the data middle platform; a first characterization module, used to characterize the investment scale stability as the time dimension standard of the preset Hall three-dimensional structure; a second characterization module, used to characterize the first financial product set within the first preset time period as the logical dimension standard of the preset Hall three-dimensional structure; a third characterization module, used to characterize the second financial product set within the second preset time period as the knowledge dimension standard of the preset Hall three-dimensional structure; a first establishment module, used to establish the user behavior model based on the time dimension standard, the logical dimension standard and the knowledge dimension standard, using the transaction data, the first category financial product data and the second category financial product data.

[0017] Optionally, the first calculation module includes: a first setting submodule, used to set a preset cycle length; a first analysis submodule, used to analyze the transaction data based on the preset cycle length to obtain the transaction data value within each cycle; and a first calculation submodule, used to calculate the stability of the investment scale based on the transaction data value using a preset logistic regression strategy.

[0018] Optionally, the first determination module includes: a second analysis submodule, used to analyze the first category of financial product data to obtain the first product categories of financial products purchased by the target user within the first preset time period and the purchase quantity of each first product category; a second calculation submodule, used to calculate the target user's preference for each first product category based on the purchase quantity of each first product category; and the first determination submodule, used to determine the target product category indicated by a preference greater than a first preset threshold to obtain the first financial product set.

[0019] Optionally, the second determination module includes: a third analysis submodule, used to analyze the second category of financial product data to obtain a first category set of financial products searched by the target user within the second preset time period, a second product category of financial products purchased, and the purchase quantity of each second product category; a third calculation submodule, used to calculate the target user's preference for each second product category based on the purchase quantity of each second product category; a second determination submodule, used to determine the target product category indicated by a preference greater than a second preset threshold, to obtain a second category set; and a first output submodule, used to obtain the second financial product set based on the first category set and the second category set.

[0020] Optionally, the determination unit includes: a third determination module, used to determine the target financial product portfolio from the first financial product set when the investment scale stability is a first stability; a fourth determination module, used to determine the target financial product portfolio from the second financial product set when the investment scale stability is a second stability, wherein the second stability is greater than the first stability; and a fifth determination module, used to determine the target financial product portfolio from the first financial product set and the second financial product set when the investment scale stability is a third stability, wherein the third stability is greater than the first stability and less than the second stability.

[0021] According to another aspect of an embodiment of the present invention, an electronic device is also provided, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for recommending a combination of financial products.

[0022] In the present disclosure, the asset information of the target user is obtained and pushed to the data middle platform. Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model. The user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first financial product set to be pushed to the target user, and the third sub-model is used to determine the second financial product set to be pushed to the target user. Based on the investment scale stability, the target financial product combination is determined from the first financial product set and / or the second financial product set, and the target financial product combination is recommended to the target user. In this application, based on the asset information on the data platform, a preset Hall three-dimensional structure can be used to establish a user behavior model, thereby obtaining the user's investment scale stability, the first financial product set and the second financial product set, and based on the investment scale stability, a reasonable target financial product combination can be selected from the first financial product set and the second financial product set to recommend to the user, thereby realizing personalized push of financial product combinations, saving users' shopping time, improving the accuracy of financial product selection, and improving user experience, thereby solving the technical problem in related technologies that cannot recommend reasonable financial product combinations to users, resulting in a decline in user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1is a flowchart of an optional method for recommending a financial product combination according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of an optional fund recommendation setting method according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of an optional smart fund portfolio push according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of an optional financial product combination recommendation device according to an embodiment of the present invention;

[0028] Figure 5 This is a hardware structure block diagram of an electronic device (or mobile device) for a method for recommending a financial product combination according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] To facilitate those skilled in the art to understand the present invention, some of the terms or nouns involved in the embodiments of the present invention are explained below:

[0032] The Data Center Platform collects, processes, stores, and computes massive, multi-source, and diverse data, unifying standards and calibers. Once unified, the data is stored in a standardized format, forming a big data asset layer to meet the needs of front-end data analysis and applications. The Data Center Platform places greater emphasis on applications, is closer to the business, and emphasizes its ability to serve the front-end. It enables the accumulation and reuse of logic, algorithms, labels, models, and data assets, enabling faster adaptation to business and application development needs. It also offers traceability and greater accuracy.

[0033] Financial risk quantification: This approach uses risks and their interactions to estimate the range of possible outcomes for a financial project. Common risk quantification methods include expected value, statistical aggregation, simulation, and decision trees.

[0034] User portrait: also known as user role, is an effective tool for outlining target users and linking user demands with design direction. It can combine user behavior, attributes and expected data conversion.

[0035] Hall three-dimensional structure: a three-dimensional spatial structure model composed of "time dimension", "logic dimension" and "knowledge dimension".

[0036] Logistic regression algorithm: also known as regression analysis, is a generalized linear regression analysis model, often used in data mining.

[0037] Smart financial product portfolio push: Personalized push based on the customer's financial goals, customer assets, transaction data and other information.

[0038] It should be noted that the method for recommending a financial product combination and the device thereof in the present disclosure can be used in the field of artificial intelligence when recommending a financial product combination, and can also be used in any field other than the field of artificial intelligence when recommending a financial product combination. The present disclosure does not limit the application field of the method for recommending a financial product combination and the device thereof.

[0039] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display and analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0040] The following embodiments of the present invention can be applied to various systems / applications / devices for recommending financial product combinations. The present invention can use the data middle platform to provide personalized financial product combination push to users (including corporate users). When users purchase financial products, they can be evaluated based on user behavior models (including corporate operating models), user profile preferences, financial management risks, and other aspects, and multiple financial product combinations that meet the requirements can be pushed to them. The financial product combination can include a variety of different types of financial products, and provide a suitable financial product purchase ratio and purchase cycle for user reference. This not only saves customers' shopping time, but also improves the accuracy of financial product selection, thereby enhancing the user experience.

[0041] The present invention will be described in detail below with reference to various embodiments.

[0042] Example 1

[0043] According to an embodiment of the present invention, an embodiment of a method for recommending a combination of financial products is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] Figure 1 is a flow chart of an optional method for recommending a financial product combination according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0045] Step S101: Obtain the asset information of the target user and push the asset information to the data center.

[0046] Step S102: Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model, wherein the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first set of financial products to be pushed to the target user, and the third sub-model is used to determine the second set of financial products to be pushed to the target user.

[0047] Step S103: determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability.

[0048] Step S104: recommend the target financial product portfolio to the target user.

[0049] Through the above steps, the asset information of the target user can be obtained and pushed to the data middle platform. Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model. The user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first financial product set to be pushed to the target user, and the third sub-model is used to determine the second financial product set to be pushed to the target user. Based on the investment scale stability, the target financial product combination is determined from the first financial product set and / or the second financial product set, and the target financial product combination is recommended to the target user. In an embodiment of the present invention, a user behavior model can be established based on the asset information on the data platform using a preset Hall three-dimensional structure, thereby obtaining the user's investment scale stability, the first financial product set, and the second financial product set. Based on the investment scale stability, a reasonable target financial product combination can be selected from the first financial product set and the second financial product set and recommended to the user, thereby realizing personalized push of financial product combinations, saving the user's shopping time, improving the accuracy of financial product selection, and improving user experience, thereby solving the technical problem in related technologies that a reasonable financial product combination cannot be recommended to the user, resulting in a decline in user experience.

[0050] The embodiment of the present invention is described in detail below in conjunction with the above steps.

[0051] Step S101: Obtain the asset information of the target user and push the asset information to the data center.

[0052] Optionally, the step of obtaining the target user's asset information includes: generating an information collection instruction when the target user triggers a product purchase operation and / or triggers a product interface browsing operation; and obtaining the target user's asset information based on the information collection instruction.

[0053] In an embodiment of the present invention, when a user purchases a financial product and / or views the financial product process, an information collection operation can be entered (i.e., when the target user triggers a product purchase operation and / or triggers a product interface browsing operation, an information collection instruction is generated) to obtain the user's asset information (i.e., based on the information collection instruction, the target user's asset information is obtained), and then the obtained asset information is pushed to the data middle platform in a centralized manner.

[0054] Optionally, after pushing the asset information to the data middle platform, it also includes: extracting keywords of the asset information based on the preset data lake technology; classifying the asset information based on the keywords to obtain classification results, wherein the data types in the classification results include at least: transaction data, first-category financial product data, and second-category financial product data.

[0055] In an embodiment of the present invention, keywords of asset information can be extracted by using preset data lake technology. Afterwards, the asset information can be labeled according to the keywords and statistically classified to obtain classification results (the data types in the classification results include at least: transaction data, first-category financial product data, second-category financial product data, etc.).

[0056] Figure 2 is a schematic diagram of an optional fund recommendation setting method according to an embodiment of the present invention, such as Figure 2 As shown, the customer's data sources include: customer information, product information, embedded data, transaction monitoring logs, transaction data and other sources. The purchase process can be entered into information collection and my fund-investor information collection (that is, users purchase financial products and users view financial products) as trigger conditions for data collection. The recommendation factors are set as: customers (customer groups) (including: user behavior data, user preference data, user transaction data), time (including: cycle, time, timing, real-time), labels (including: fact labels, model labels, prediction labels), strategies (including: frequency strategies, blacklist filtering, risk control filtering), etc. The recommendation types that can be used are: statistical analysis recommendation (including: data lake, big data analysis), intelligent recommendation (including: knowledge graph, recommendation model), etc. The Hall three-dimensional structure used in this embodiment belongs to the statistical analysis recommendation type.

[0057] Step S102: Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model, wherein the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first set of financial products to be pushed to the target user, and the third sub-model is used to determine the second set of financial products to be pushed to the target user.

[0058] Optionally, based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model, including: based on the data middle platform, obtaining transaction data, first-category financial product data, and second-category financial product data; characterizing the stability of the investment scale as the time dimension standard of the preset Hall three-dimensional structure; characterizing the first set of financial products within the first preset time period as the logic dimension standard of the preset Hall three-dimensional structure; characterizing the second set of financial products within the second preset time period as the knowledge dimension standard of the preset Hall three-dimensional structure; based on the time dimension standard, the logic dimension standard, and the knowledge dimension standard, using transaction data, first-category financial product data, and second-category financial product data, to establish a user behavior model.

[0059] In an embodiment of the present invention, transaction data (including: transaction volume in each cycle, etc.), first-category financial product data (including: types of financial products purchased by users over a long period of time (e.g., within a year) and the number of different types of financial products purchased, etc.) and second-category financial product data (including: types of financial products searched and purchased by users over a short period of time (e.g., within a month) and the number of different types of financial products purchased, etc.) can be obtained based on the data middle platform. Moreover, since the Hall three-dimensional structure is a three-dimensional spatial structure model composed of "time dimension", "logic dimension" and "knowledge dimension", this embodiment can use "user investment scale stability" as the "time dimension" standard, "user preference data in a long period of time" as the "logic dimension" standard, and "user sensitivity to a certain type of product in the short term" as the "knowledge dimension" standard (that is, the investment scale stability is characterized as the time dimension standard of the preset Hall three-dimensional structure, and the first preset The first set of financial products within a time period (i.e., a longer period, such as within one year) is characterized as the logical dimension standard of a preset Hall three-dimensional structure, and the second set of financial products within a second preset time period (i.e., a short period, such as within one month) is characterized as the knowledge dimension standard of a preset Hall three-dimensional structure) for analysis. Based on the time dimension standard, the logical dimension standard, and the knowledge dimension standard, transaction data, first-category financial product data, and second-category financial product data are used to establish a user behavior model. The user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first financial product set to be pushed to the target user (i.e., the user preference financial product set in a long period), and the third sub-model is used to determine the second financial product set to be pushed to the target user (i.e., the user sensitivity financial product set in a short period).

[0060] Optionally, the step of calculating the investment scale stability of the target user includes: setting a preset cycle length; based on the preset cycle length, analyzing transaction data to obtain transaction data values ​​within each cycle; based on the transaction data values, using a preset logistic regression strategy to calculate the investment scale stability.

[0061] In an embodiment of the present invention, a preset cycle length T can be set first (for example, if a cycle is three months, then T1 is from January to March, T2 is from February to April, and so on). Then, through the transaction data, the transaction data value X in each cycle can be analyzed. For example, the transaction data value of the user in the first cycle T is X1, the transaction data value in the second cycle T is X2, ..., and the transaction data value in the nth cycle T is X. n , then, a preset logistic regression strategy (e.g., logistic regression algorithm) can be used to calculate the investment scale stability P using the following formula (1):

[0062]

[0063] Where e is a preset base constant, and z is a multivariate linear function with X as the variable: n means there are n cycles.

[0064] Finally, the "time dimension" standard in the Hall three-dimensional structure can be obtained: the "user investment scale stability" value.

[0065] Optionally, the step of determining a first set of financial products to be pushed to the target user includes: analyzing the first category of financial product data to obtain the first product categories of financial products purchased by the target user within a first preset time period and the purchase quantity of each first product category; based on the purchase quantity of each first product category, calculating the target user's preference for each first product category; determining the target product category indicated by a preference greater than a first preset threshold, and obtaining the first financial product set.

[0066] In the embodiment of the present invention, the first category of financial product data can be used to analyze the types of financial products X purchased by the user over a long period of time and the number of different types of financial products purchased a (i.e., the first product types of financial products purchased by the target user within the first preset time period and the purchase quantity of each first product type). Then, the user's preference for different types of financial products can be calculated using the following formula (2) (i.e., the target user's preference for each first product type is calculated based on the purchase quantity of each first product type):

[0067]

[0068] Among them, there are X types of financial products, a1 is the number of financial products of category 1 purchased, a2 is the number of financial products of category 2 purchased, ..., a x Q is the quantity of the corresponding x-th type of financial product purchased. x Indicates the user's preference for different types of financial products.

[0069] This embodiment can determine the preference greater than the first preset threshold (eg, ) indicates the target product type, and obtains the first financial product set Q, which is the "logical dimension" standard in the Hall three-dimensional structure: "user preference data in the long period".

[0070] Optionally, the step of determining a second set of financial products to be pushed to the target user includes: analyzing the second category of financial product data to obtain a first category set of financial products searched by the target user within a second preset time period, a second product category of financial products purchased, and the purchase quantity of each second product category; based on the purchase quantity of each second product category, calculating the target user's preference for each second product category; determining the target product category indicated by a preference greater than a second preset threshold to obtain a second category set; and obtaining a second financial product set based on the first category set and the second category set.

[0071] In the embodiment of the present invention, the second category of financial product data can be analyzed to obtain the set R1 of financial product categories searched by users in a short period of time (i.e., the set of first categories of financial products searched by the target user in the second preset time period), the second product categories of financial products purchased by the target user in the second preset time period, and the purchase quantity of each second product category. Then, the set R2 of financial product categories preferred by users in a short period of time can be calculated using the following formula (3):

[0072]

[0073] Here, it is defined that there are X types of financial products purchased in the short term, a1 is the number of financial products of category 1 purchased, a2 is the number of financial products of category 2 purchased, ..., a x is the quantity of financial products corresponding to category X purchased, r x Indicates the user's preference for different types of financial products.

[0074] This embodiment can determine the preference greater than the second preset threshold (eg, ) is used to obtain the target product category indicated by the first category set (i.e., the user preference financial product category set R2 in the short term). Then, based on the first category set and the second category set, the second financial product set R is obtained, which is the "knowledge dimension" standard in the Hall three-dimensional structure: the "short-term user sensitivity to a certain type of product" set is: R=R1∪R2.

[0075] Step S103: determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability.

[0076] Optionally, the step of determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability includes: when the investment scale stability is a first stability, determining the target financial product portfolio from the first financial product set; when the investment scale stability is a second stability, determining the target financial product portfolio from the second financial product set, wherein the second stability is greater than the first stability; when the investment scale stability is a third stability, determining the target financial product portfolio from the first financial product set and the second financial product set, wherein the third stability is greater than the first stability and less than the second stability.

[0077] In an embodiment of the present invention, based on the "user investment scale stability", and guided by the "user preference data in the long term" and the "user sensitivity to a certain type of product in the short term", a financial product portfolio recommendation can be made to the target user. Specifically, the user group whose "user investment scale stability" is the first stability (e.g., in the range of [0, 0.6)) can be set as low-stability users, the user group whose "user investment scale stability" is the third stability (e.g., in the range of [0.6, 0.8)) can be set as medium-stability users, and the user group whose "user investment scale stability" is the second stability (e.g., in the range of [0.8, 1]) can be set as high-stability users.

[0078] For users with low stability, we can recommend a financial product portfolio for "stock maintenance", that is, push the financial product portfolio in the "long-term user preference data" set Q to the user (that is, when the investment scale stability is the first stability, determine the target financial product portfolio from the first financial product set) to achieve the goal of stably maintaining target users.

[0079] For highly stable users, we can recommend "innovative push" financial product portfolios, that is, push to users the financial product portfolios in the financial product set R that represents "user sensitivity to a certain type of product in the short term" (that is, when the investment scale stability is the second stability, determine the target financial product portfolio from the second financial product set) to achieve innovative recommendations and incremental maintenance of customer base.

[0080] For users with medium stability, we can recommend financial product portfolios with "innovation push" as the main focus and "stock maintenance" as the supplement. That is, we can push financial product portfolios of the "long-term user preference data" set Q and the "short-term user sensitivity to a certain type of product" set R to users (that is, when the investment scale stability is the third stability, the target financial product portfolio is determined from the first financial product set and the second financial product set). This can provide incremental services while ensuring stable user purchases.

[0081] Step S104: recommend the target financial product portfolio to the target user.

[0082] In the embodiments of the present invention, the problems that users have in the past when purchasing financial products are too limited in the content they can choose from, the proportion of investment content may not necessarily meet their own development needs, and the independent choices are often blind can be overcome. Through "personalized financial product portfolio push", users can be accurately provided with financial product portfolios that meet their financial management goals, so that users can reasonably allocate resources, and a good reference guidance plan is provided for users' investments, which can increase users' financial management returns and greatly improve user experience, making users more sticky and beneficial to the development of financial institutions.

[0083] The following describes in detail another optional specific implementation method. This implementation method is described by taking a fund portfolio as an example, and the application scenario can be fund portfolio push.

[0084] Figure 3 FIG. 1 is a schematic diagram of an optional smart fund portfolio push according to an embodiment of the present invention. Figure 3 As shown in the figure, the smart fund portfolio push includes: channel client (such as mobile client, computer client, etc.), user interface, channel server (such as mobile server, computer server, etc.), and data middle platform. The specific push process is as follows:

[0085] A personalized fund portfolio purchase interface can be set up on the user interface. After entering the personalized fund portfolio purchase interface, the customer first determines whether a personalized assessment has been conducted. If so, the fund portfolio can be directly provided to the customer. Otherwise, the customer's asset information is obtained through the channel client to evaluate the customer's financial risk tolerance. Afterwards, the information is saved through the channel server, and the centralized data is sent to the data middle platform. The data middle platform processes, stores, and calculates the acquired data, unifies the standards, forms a data asset layer, and provides the data assets to the channel server. The channel server screens out fund portfolios that meet the requirements based on the conclusions of the data asset layer. Afterwards, the fund portfolio is provided to the customer through the user interface.

[0086] In this embodiment, if the customer wants to change the fund purchase preference information, the data needs to be acquired again and personalized push is performed.

[0087] In an embodiment of the present invention, the data center can calculate and process various data, including asset information, user profiles, and financial risk quantification, to ultimately determine the financial product portfolio recommended to the user. For example, it can determine whether a corporate user requires stable mid- to long-term financing, whether they need rapid capital turnover, and whether they can afford short-term asset depreciation. By comparing the proportion of past investment financial product choices and the purchase content of similar corporate users, comprehensive personalized recommendations can be made.

[0088] Example 2

[0089] The financial product combination recommendation device provided in this embodiment includes multiple implementation units, each implementation unit corresponding to each implementation step in the above-mentioned embodiment 1.

[0090] Figure 4 is a schematic diagram of an optional financial product combination recommendation device according to an embodiment of the present invention, such as Figure 4 As shown, the recommendation device may include: an acquisition unit 40, an establishment unit 41, a determination unit 42, and a recommendation unit 43, wherein:

[0091] The acquisition unit 40 is used to obtain the asset information of the target user and push the asset information to the data center;

[0092] Establishing unit 41 is configured to establish a user behavior model based on the data middle platform using a preset Hall three-dimensional structure, wherein the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is configured to calculate the investment scale stability of the target user. The second sub-model is configured to determine a first set of financial products to be pushed to the target user. The third sub-model is configured to determine a second set of financial products to be pushed to the target user.

[0093] a determination unit 42, configured to determine a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability;

[0094] The recommendation unit 43 is configured to recommend the target financial product combination to the target user.

[0095] The above-mentioned recommendation device can obtain the asset information of the target user and push the asset information to the data middle platform. Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model. The user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The first sub-model is used to calculate the investment scale stability of the target user, the second sub-model is used to determine the first financial product set to be pushed to the target user, and the third sub-model is used to determine the second financial product set to be pushed to the target user. Based on the investment scale stability, the target financial product combination is determined from the first financial product set and / or the second financial product set, and the target financial product combination is recommended to the target user. In an embodiment of the present invention, a user behavior model can be established based on the asset information on the data platform using a preset Hall three-dimensional structure, thereby obtaining the user's investment scale stability, the first financial product set, and the second financial product set. Based on the investment scale stability, a reasonable target financial product combination can be selected from the first financial product set and the second financial product set and recommended to the user, thereby realizing personalized push of financial product combinations, saving the user's shopping time, improving the accuracy of financial product selection, and improving user experience, thereby solving the technical problem in related technologies that a reasonable financial product combination cannot be recommended to the user, resulting in a decline in user experience.

[0096] Optionally, the acquisition unit includes: a first generation module, used to generate an information collection instruction when the target user triggers a product purchase operation and / or triggers a product interface browsing operation; a first acquisition module, used to acquire the target user's asset information based on the information collection instruction.

[0097] Optionally, the recommendation device also includes: a first extraction module, used to extract keywords of the asset information based on the preset data lake technology after pushing the asset information to the data middle platform; a first classification module, used to classify the asset information based on the keywords to obtain classification results, wherein the data types in the classification results include at least: transaction data, first-category financial product data, and second-category financial product data.

[0098] Optionally, the establishment unit includes: a second acquisition module, used to acquire transaction data, first-category financial product data, and second-category financial product data based on the data middle platform; a first characterization module, used to characterize the stability of the investment scale as a time dimension standard of a preset Hall three-dimensional structure; a second characterization module, used to characterize the first set of financial products within the first preset time period as a logic dimension standard of a preset Hall three-dimensional structure; a third characterization module, used to characterize the second set of financial products within the second preset time period as a knowledge dimension standard of a preset Hall three-dimensional structure; a first establishment module, used to establish a user behavior model based on the time dimension standard, the logic dimension standard, and the knowledge dimension standard, using transaction data, first-category financial product data, and second-category financial product data.

[0099] Optionally, the first calculation module includes: a first setting submodule, used to set a preset cycle length; a first analysis submodule, used to analyze transaction data based on the preset cycle length to obtain transaction data values ​​within each cycle; and a first calculation submodule, used to calculate the stability of the investment scale based on the transaction data values ​​using a preset logistic regression strategy.

[0100] Optionally, the first determination module includes: a second analysis submodule, used to analyze the first category of financial product data to obtain the first product types of financial products purchased by the target user within a first preset time period and the purchase quantity of each first product type; a second calculation submodule, used to calculate the target user's preference for each first product type based on the purchase quantity of each first product type; and a first determination submodule, used to determine the target product type indicated by a preference greater than a first preset threshold to obtain a first financial product set.

[0101] Optionally, the second determination module includes: a third analysis submodule, used to analyze the second category of financial product data to obtain a first category set of financial products searched by the target user within a second preset time period, a second product category of financial products purchased, and the purchase quantity of each second product category; a third calculation submodule, used to calculate the target user's preference for each second product category based on the purchase quantity of each second product category; a second determination submodule, used to determine the target product category indicated by a preference greater than a second preset threshold, to obtain a second category set; and a first output submodule, used to obtain a second financial product set based on the first category set and the second category set.

[0102] Optionally, the determination unit includes: a third determination module, used to determine the target financial product portfolio from the first financial product set when the investment scale stability is a first stability; a fourth determination module, used to determine the target financial product portfolio from the second financial product set when the investment scale stability is a second stability, wherein the second stability is greater than the first stability; and a fifth determination module, used to determine the target financial product portfolio from the first financial product set and the second financial product set when the investment scale stability is a third stability, wherein the third stability is greater than the first stability and less than the second stability.

[0103] The above-mentioned recommendation device may further include a processor and a memory. The above-mentioned acquisition unit 40, establishment unit 41, determination unit 42, recommendation unit 43, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0104] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be configured, and the target financial product portfolio can be recommended to the target user by adjusting the kernel parameters.

[0105] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0106] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialized program having the following method steps: obtaining the asset information of the target user and pushing the asset information to the data middle platform; based on the data middle platform, using a preset Hall three-dimensional structure, establishing a user behavior model; the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model; the first sub-model is used to calculate the investment scale stability of the target user; the second sub-model is used to determine a first financial product set to be pushed to the target user; the third sub-model is used to determine a second financial product set to be pushed to the target user; based on the investment scale stability, a target financial product combination is determined from the first financial product set and / or the second financial product set, and the target financial product combination is recommended to the target user.

[0107] According to another aspect of an embodiment of the present invention, an electronic device is also provided, including one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned method for recommending a combination of financial products.

[0108] Figure 5FIG. 1 is a hardware structure block diagram of an electronic device (or mobile device) for a method for recommending a financial product combination according to an embodiment of the present invention. Figure 5 As shown, the electronic device may include one or more (illustrated as 502a, 502b, ..., 502n in the figure) processors 502 (the processor 502 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 504 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 5 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 5 More or fewer components than shown, or with Figure 5 Different configurations shown.

[0109] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0110] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0112] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0113] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0114] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0115] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for recommending a financial product portfolio, characterized in that: include: Obtain the target user's asset information and push the asset information to the data center; Based on the data middle platform, a preset Hall three-dimensional structure is used to establish a user behavior model, wherein the preset Hall three-dimensional structure includes: a time dimension standard, a logic dimension standard, and a knowledge dimension standard. The user behavior model includes: a first sub-model, a second sub-model, and a third sub-model. The time dimension standard is determined by the first sub-model, the logic dimension standard is determined by the second sub-model, and the knowledge dimension standard is determined by the third sub-model. The first sub-model calculates the target user's investment scale stability based on the transaction data in the asset information using a preset logistic regression algorithm, wherein the investment scale stability refers to a quantitative value of the target user's investment scale fluctuation within a preset time period; the second sub-model calculates the target user's preference for the first category of financial products based on the first category of financial product data in the asset information, and determines a first set of financial products to be pushed to the target user based on the preference for the first category of financial products; the third sub-model calculates the target user's preference for the second category of financial products based on the second category of financial product data in the asset information, and determines a second set of financial products to be pushed to the target user based on the preference for the second category of financial products; determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability; The target financial product portfolio is recommended to the target user.

2. The recommendation method according to claim 1, characterized in that The steps for obtaining the target user's asset information include: When the target user triggers a product purchase operation and / or a product interface browsing operation, an information collection instruction is generated; Based on the information collection instruction, the asset information of the target user is obtained.

3. The recommendation method according to claim 1, characterized in that: After pushing the asset information to the data center, it also includes: Extracting keywords of the asset information based on the preset data lake technology; Based on the keywords, the asset information is classified to obtain a classification result, wherein the data types in the classification result include at least: transaction data, first-category financial product data, and second-category financial product data.

4. The recommendation method according to claim 3, characterized in that: Based on the data center, the steps of establishing a user behavior model using a preset Hall 3D structure include: Based on the data middle platform, obtain the transaction data, the first category financial product data, and the second category financial product data; Characterizing the investment scale stability as a time dimension standard of the preset Hall three-dimensional structure; Characterizing a first set of financial products within a first preset time period as a logical dimension standard of the preset Hall three-dimensional structure; Characterizing a second set of financial products within a second preset time period as a knowledge dimension standard of the preset Hall three-dimensional structure; Based on the time dimension standard, the logic dimension standard, and the knowledge dimension standard, the user behavior model is established using the transaction data, the first category financial product data, and the second category financial product data.

5. The recommendation method according to claim 4, characterized in that: The step of calculating the investment scale stability of the target user comprises: Set the preset cycle duration; Analyzing the transaction data based on the preset cycle length to obtain transaction data values ​​within each cycle; Based on the transaction data value, a preset logistic regression strategy is adopted to calculate the investment scale stability.

6. The recommendation method according to claim 4, characterized in that: The step of determining a first set of financial products to be pushed to the target user includes: Analyzing the first category of financial product data to obtain first product categories of financial products purchased by the target user within the first preset time period and the purchase quantity of each first product category; Calculating the target user's preference for each of the first product categories based on the purchase quantity of each of the first product categories; Determine the target product categories indicated by the preference degree greater than a first preset threshold to obtain the first financial product set.

7. The recommendation method according to claim 4, characterized in that: The step of determining a second set of financial products to be pushed to the target user includes: Analyze the second category of financial product data to obtain a first category set of financial products searched by the target user within the second preset time period, a second category of financial products purchased by the target user, and a purchase quantity of each second category of financial products; Calculating the target user's preference for each second product category based on the purchase quantity of each second product category; Determining target product categories indicated by preference levels greater than a second preset threshold to obtain a second category set; The second financial product set is obtained based on the first category set and the second category set.

8. The recommendation method according to claim 1, characterized in that: The step of determining a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability includes: When the investment scale stability is a first stability, determining the target financial product portfolio from the first financial product set; determining the target financial product portfolio from the second financial product set when the investment scale stability is a second stability, wherein the second stability is greater than the first stability; When the investment scale stability is a third stability, the target financial product portfolio is determined from the first financial product set and the second financial product set, and the third stability is greater than the first stability and less than the second stability.

9. A device for recommending a combination of financial products, characterized in that: include: An acquisition unit, configured to acquire the asset information of a target user and push the asset information to a data center; An establishing unit, configured to establish a user behavior model based on the data middle platform and using a preset Hall three-dimensional structure, wherein the preset Hall three-dimensional structure includes: a time dimension standard, a logic dimension standard, and a knowledge dimension standard; the user behavior model includes: a first sub-model, a second sub-model, and a third sub-model; the time dimension standard is determined by the first sub-model, the logic dimension standard is determined by the second sub-model, and the knowledge dimension standard is determined by the third sub-model; The first sub-model calculates the target user's investment scale stability based on the transaction data in the asset information using a preset logistic regression algorithm, wherein the investment scale stability refers to a quantitative value of the target user's investment scale fluctuation within a preset time period; the second sub-model calculates the target user's preference for the first category of financial products based on the first category of financial product data in the asset information, and determines a first set of financial products to be pushed to the target user based on the preference for the first category of financial products; the third sub-model calculates the target user's preference for the second category of financial products based on the second category of financial product data in the asset information, and determines a second set of financial products to be pushed to the target user based on the preference for the second category of financial products; a determining unit, configured to determine a target financial product portfolio from the first financial product set and / or the second financial product set based on the investment scale stability; A recommendation unit is used to recommend the target financial product combination to the target user.

10. An electronic device, characterized in that: The invention comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for recommending a combination of financial products as described in any one of claims 1 to 8.

Images