Financial product recommendation method and device

Abstract

The present invention provides a method and device for recommending financial products, which relates to the fields of big data analysis and artificial intelligence technology. The recommendation method includes: obtaining financial data of family customers; wherein the financial data includes: investment type; labeling the investment type in the financial data to obtain the customer label of the family customer, clustering and dividing the financial types of the family customers according to the customer label; determining the customer portrait of each family customer and the preference for different financial products; determining the financial product recommendation list corresponding to the family customer based on the customer portrait, the preference and the preset classification model. The present invention can quickly and accurately recommend financial products to users from a large number of financial products.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis and artificial intelligence technology, and in particular to a financial product recommendation method and device. Background Art

[0002] With the development of the industrial revolution and the establishment of cities, the profit-seeking mentality has driven people to engage in financial management. For a large number of non-financial professionals, their income cannot be very well allocated for financial management. They have missed the opportunity to make money through directionless investment or consumption. They all hope that there will be a high-security solution that requires less brainpower and direct execution of financial management.

[0003] In the field of financing services for small and medium-sized enterprises, a wide variety of financial products have been launched for different user types. These financial products have different requirements for applicants, and the difficulty of application and loan time are also different. As a result, users cannot quickly and accurately find financial products that suit them. Enterprises need to spend a lot of time looking for financial products that suit them, which not only affects the user experience, but also increases the cost of financial institutions' products reaching users. Now more intelligent recommended financial solutions are only designed based on big data, and big data information collection is only for the information of the financial products themselves. The financial products recommended in the end do not meet the needs of customers, that is, the accuracy is not high.

[0004] Therefore, how to quickly and accurately recommend financial products to users from a large number of financial products has become a technical problem that needs to be urgently solved in this field. Summary of the invention

[0005] In view of the problems in the prior art, the present invention provides a financial product recommendation method and device, which can quickly and accurately recommend financial products to users from a large number of financial products.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a financial product recommendation method, comprising:

[0008] Acquire financial management data of household customers; wherein the financial management data includes: investment type;

[0009] Labeling the investment types in the financial management data to obtain customer labels of household customers, and clustering and dividing the financial management types of household customers according to the customer labels;

[0010] Determine the customer profile of each category of household customers and their preferences for different financial products;

[0011] A recommendation list of financial products corresponding to household customers is determined based on the customer portrait, the preference and a preset classification model.

[0012] Furthermore, after obtaining the financial management data of the household customers, it also includes:

[0013] Cleaning and cross-validating the financial management data to obtain valid financial management data;

[0014] Correspondingly, the investment types in the financial management data are labeled to obtain customer labels of household customers, including:

[0015] The investment types in the valid financial management data are labeled to obtain the customer labels of household customers.

[0016] The step of determining the customer profile of each type of household customer includes:

[0017] Analyze the correlation between the customer label of the household customer and the financial product to obtain a user label that is strongly correlated with the financial product;

[0018] According to the preset label structure of family customers, user labels that are strongly related to the family customers and financial products are divided into multiple levels to generate user portraits of the family customers.

[0019] Wherein, determining a recommendation list of financial products corresponding to household customers based on the customer portrait, the preference and a preset classification model includes:

[0020] Based on the customer profile and the preference, calculate the product recommendation weight of each financial product relative to the household customer;

[0021] The product recommendation weights and classification model generate a list of recommended financial products corresponding to household customers.

[0022] Furthermore, it also includes:

[0023] Obtain historical data of household customers, and train a classification model based on the historical data and the Wide & Deep Learning algorithm, specifically including:

[0024] The historical data is divided into training samples and verification samples; the classification model based on Wide & Deep Learning is trained by the training samples, and the trained classification model is verified by the verification samples.

[0025] The historical data is split into training samples and verification samples, specifically including: taking the historical data before a set time as the training samples, and taking the historical data after the set time as the verification samples.

[0026] In a second aspect, the present invention provides a financial product recommendation device, comprising:

[0027] The acquisition module is used to acquire the financial management data of the family customer; wherein the financial management data includes: investment type;

[0028] A label module, used to label the investment types in the financial management data to obtain customer labels of family customers, and to cluster and divide the financial management types of family customers according to the customer labels;

[0029] The preference module is used to determine the customer profile of each type of household customer and their preference for different financial products;

[0030] A recommendation module is used to determine a recommendation list of financial products corresponding to household customers based on the customer portrait, the preference and a preset classification model.

[0031] Furthermore, it also includes:

[0032] A cleaning module, used for cleaning and cross-validating the financial management data to obtain valid financial management data;

[0033] Correspondingly, the label module includes:

[0034] The label unit is used to label the investment types in the valid financial management data to obtain the customer labels of the household customers.

[0035] Wherein, the preference module includes:

[0036] A label unit, used to analyze the correlation between the customer label of the household customer and the financial product, and obtain a user label that is strongly correlated with the financial product;

[0037] A portrait unit is used to divide the user tags of the family customers that are strongly related to the financial products into multiple levels according to the preset label structure of the family customers, and generate user portraits of the family customers.

[0038] Wherein, the recommendation module includes:

[0039] A weighting unit, used for calculating a product recommendation weight of each financial product relative to household customers based on the customer profile and the preference;

[0040] List unit, used for product recommendation weights and classification models to generate a list of financial product recommendations corresponding to household customers.

[0041] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the financial product recommendation method when executing the program.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the financial product recommendation method.

[0043] It can be seen from the above technical scheme that the present invention provides a method and device for recommending financial products, by obtaining the financial data of family customers; wherein the financial data includes: investment type; labeling the investment type in the financial data to obtain the customer label of the family customer, clustering the financial types of the family customers according to the customer label; determining the customer portrait of each family customer and the preference for different financial products; determining the financial product recommendation list corresponding to the family customer based on the customer portrait, the preference and the preset classification model. The present invention can quickly and accurately recommend financial products to users from a large number of financial products. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 Schematic diagram of the first process of the financial product recommendation method in an embodiment of the present invention.

[0046] Figure 2 Schematic diagram of a second process of the financial product recommendation method in an embodiment of the present invention.

[0047] Figure 3 The figure is a flowchart of the entire process of the financial product recommendation method in an embodiment of the present invention.

[0048] Figure 4 Schematic diagram of the structure of the financial product recommendation device in an embodiment of the present invention.

[0049] Figure 5 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 described embodiments are 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 creative work are within the scope of protection of the present invention.

[0051] Before fully describing the technical solution in this embodiment, the technical field involved in the technical solution in this embodiment is explained. The technical solution in this embodiment can analyze and process a large amount of data, so the technical solution in the embodiment involves the field of big data technology. The technical solution in this embodiment uses artificial intelligence algorithms in the process of analyzing and processing a large amount of data. Therefore, the technical solution in the embodiment also involves the field of artificial intelligence technology. The technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the present invention.

[0052] The present invention provides an embodiment of a method for recommending financial products. Figure 1 The financial product recommendation method specifically includes the following contents:

[0053] S101: Acquire financial management data of a household customer; wherein the financial management data includes: investment type;

[0054] In this step, the financial management data of suitable household customers are collected. Through a carefully designed questionnaire, household customers are asked to fill out the questionnaire to collect various types of data such as household customers' funds, consumption, and investment behavior, so as to solve the "cold start" problem when household customers have no user data when using the product for the first time, and realize data collection. After the product has been used for a period of time, household customer data will also be collected through online real-time collection.

[0055] S102: labeling the investment types in the financial management data to obtain customer labels of household customers, and clustering and dividing the financial management types of household customers according to the customer labels;

[0056] S103: Determine the customer profile of each category of household customers and their preferences for different financial products;

[0057] In this step, determining the customer portrait of each category of family customers specifically includes: analyzing the correlation between the customer tags of the family customers and the financial products to obtain user tags that are strongly correlated with the financial products; dividing the user tags that are strongly correlated with the family customers and the financial products into multiple levels according to the preset family customer tag structure to generate the user portrait of the family customers.

[0058] S104: Determine a recommendation list of financial products corresponding to the household customer based on the customer portrait, the preference and a preset classification model.

[0059] This step specifically includes: calculating the product recommendation weight of each financial product relative to household customers based on the customer portrait and the preference; and generating a financial product recommendation list corresponding to household customers using the product recommendation weight and classification model.

[0060] In this embodiment, customers are clustered into three types of family customers: conservative family customers, safe family customers, and aggressive family customers. After the product has been in use for a period of time, customers with similar characteristics are clustered into the same cluster based on the data of other customers using the unsupervised cluster analysis method combined with multi-dimensional data calculation and analysis such as customer age, family asset financial management style, and family asset risk tolerance in the data.

[0061] Based on the clustering results of new customers, we conduct in-depth analysis on the category to which the new customers belong, explore their potential characteristics and preferences, and use Wide & Deep Learning to implement intelligent financial management recommendations for new family customers based on the financial plans of other customers in the category.

[0062] This embodiment provides a specific embodiment of obtaining a classification model based on the Wide & Deep Learning algorithm, including:

[0063] Obtain historical data of household customers, and train a classification model based on the historical data and the Wide & Deep Learning algorithm, specifically including:

[0064] The historical data is divided into training samples and verification samples; the classification model based on Wide & Deep Learning is trained by the training samples, and the trained classification model is verified by the verification samples.

[0065] It should be noted that the historical data is split into training samples and verification samples, specifically including: taking the historical data before the set time as the training sample, and taking the historical data after the set time as the verification sample. The classification model includes two parts: the Wide model and the Deep model. Using the Wide model, by analyzing the historical allocation plan of old family customers, the purchase record of financial products and other feature data, the influence weight of each type of feature on the current new family customers is calculated. The Wide model mainly analyzes and calculates the historical data of customers' purchases, browsing, consultations, etc., and generates a rough financial plan recommendation. Using the Deep model, analyze and mine various features such as age, investment style, risk tolerance and historical data filled in by customers in the questionnaire, and transform the feature data into a 1200-dimensional high-order vector for training, so as to combine various types of data to mine more refined new feature combinations and improve the diversity of recommended combinations. After the Wide and Deep parts are weighted and summed by a common model, the financial products intelligently recommended to family customers are output.

[0066] Recommend household purchase items for household customers, including shopping, travel, entertainment, etc. Based on the characteristics and categories of similar items and the historical browsing relationship of customers in the same cluster, a multi-way recall strategy is adopted. First, the items are represented by vectors, and some items that meet the target are selected from all items. The selected items are sorted by similarity, and finally the display items recommended to customers are determined and recommended for consumption.

[0067] From the above description, it can be seen that the financial product recommendation method provided by the embodiment of the present invention obtains the financial data of the family customer; wherein the financial data includes: investment type; the investment type in the financial data is labeled to obtain the customer label of the family customer, and the financial types of the family customer are clustered according to the customer label; the customer portrait of each family customer and the preference for different financial products are determined; based on the customer portrait, the preference and the preset classification model, the financial product recommendation list corresponding to the family customer is determined. The present invention can quickly and accurately recommend financial products to users from a large number of financial products.

[0068] In one embodiment of the present invention, see Figure 2 After step S101 of the financial product recommendation method, the following contents are specifically included:

[0069] S105: Cleaning and cross-validating the financial management data to obtain valid financial management data;

[0070] Correspondingly, step S102 labels the investment types in the financial management data to obtain customer labels for household customers, including:

[0071] S1021: Label the investment types in the valid financial management data to obtain customer labels for household customers.

[0072] In this embodiment, by eliminating abnormal data and noise data in the questionnaire collection, correcting inconsistent data, removing noise in the data, and then performing standardized processing, the accuracy of the financial management data can be improved.

[0073] To further illustrate this solution, the present invention provides a full-process embodiment of a financial product recommendation method, such as Figure 3 As shown, the financial product recommendation method specifically includes the following contents:

[0074] Step 1: Preprocessing of household customer data collection.

[0075] Collect user behavior data of new household customers, remove noise and inconsistent data in the data by eliminating abnormal data and smoothing noise data, and then convert the data into a data set suitable for model training through normalization or standardization;

[0076] Step 2: Clustering profile of new household users.

[0077] Based on the data in step 1, cluster analysis is performed on new household customers, and they are divided into user clusters with the same characteristics to achieve user clustering profiling.

[0078] Step 3: Intelligently recommend financial products based on the family behavior data characteristics of the same cluster of family users.

[0079] We conduct in-depth analysis of the cluster to which the new customer belongs, explore potential characteristics and preferences, and use the Wide & Deep Learning algorithm to train and analyze multi-dimensional data such as historical asset allocation plans, financial product purchase records, and consultation records of other family customers in the same cluster, so as to intelligently recommend suitable financial products to family users.

[0080] Step 4: Recommend daily necessities based on the family life goals of the family user cluster.

[0081] Based on the family goals of other users in the cluster to which the new family customer belongs, their common life consumption habits, historical browsing and purchasing information of users in the same cluster, etc., after screening and sorting the items, we can accurately recommend life goal items to the family customers.

[0082] Step 5: The recommended results are displayed on the front-end page.

[0083] Smart financial products and family life target items are recommended and displayed on the front page to complete the product display.

[0084] The embodiment of the present invention provides a specific implementation of a financial product recommendation device that can implement all the contents of the financial product recommendation method, see Figure 4 The financial product recommendation device specifically includes the following contents:

[0085] The acquisition module 10 is used to acquire the financial management data of the family customer; wherein the financial management data includes: investment type;

[0086] The label module 20 is used to label the investment types in the financial management data to obtain customer labels of family customers, and to cluster and divide the financial management types of family customers according to the customer labels;

[0087] A preference module 30, for determining the customer profile of each type of household customer and their preference for different financial products;

[0088] The recommendation module 40 is used to determine a recommendation list of financial products corresponding to household customers based on the customer portrait, the preference and a preset classification model.

[0089] Furthermore, it also includes:

[0090] A cleaning module, used for cleaning and cross-validating the financial management data to obtain valid financial management data;

[0091] Correspondingly, they include:

[0092] The cleaning unit is used to label the investment types in the valid financial management data to obtain the customer labels of the household customers.

[0093] Wherein, the preference module includes:

[0094] A label unit, used to analyze the correlation between the customer label of the household customer and the financial product, and obtain a user label that is strongly correlated with the financial product;

[0095] The investment types in the valid financial management data are labeled to obtain the customer labels of household customers.

[0096] Wherein, the preference module includes:

[0097] A label unit, used to analyze the correlation between the customer label of the household customer and the financial product, and obtain a user label that is strongly correlated with the financial product;

[0098] A portrait unit is used to divide the user tags of the family customers that are strongly related to the financial products into multiple levels according to the preset label structure of the family customers, and generate user portraits of the family customers.

[0099] Wherein, the recommendation module includes:

[0100] A weighting unit, used for calculating a product recommendation weight of each financial product relative to household customers based on the customer profile and the preference;

[0101] List unit, used for product recommendation weights and classification models to generate a list of financial product recommendations corresponding to household customers.

[0102] The embodiment of the financial product recommendation device provided by the present invention can be specifically used to execute the processing flow of the embodiment of the financial product recommendation method in the above embodiment. Its functions are not repeated here, and reference can be made to the detailed description of the above method embodiment.

[0103] From the above description, it can be seen that the financial product recommendation device provided by the embodiment of the present invention obtains the financial data of the family customer; wherein the financial data includes: investment type; the investment type in the financial data is labeled to obtain the customer label of the family customer, and the financial types of the family customer are clustered according to the customer label; the customer portrait of each family customer and the preference for different financial products are determined; based on the customer portrait, the preference and the preset classification model, the financial product recommendation list corresponding to the family customer is determined. The present invention can quickly and accurately recommend financial products to users from a large number of financial products.

[0104] The present application provides an embodiment of an electronic device for implementing all or part of the content of the financial product recommendation method. The electronic device specifically includes the following content:

[0105] A processor, a memory, a communications interface and a bus; wherein the processor, the memory and the communications interface communicate with each other through the bus; the communications interface is used to realize information transmission between related devices; the electronic device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the electronic device can be implemented with reference to the embodiment for realizing the financial product recommendation method and the embodiment for realizing the financial product recommendation device, and the contents thereof are incorporated herein and the repeated parts are not repeated.

[0106] Figure 5 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 5 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Figure 5 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0107] In one embodiment, the financial product recommendation function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0108] Acquire the financial management data of household customers; wherein the financial management data includes: investment type; label the investment type in the financial management data to obtain the customer label of the household customer, and cluster the financial management types of the household customer according to the customer label; determine the customer profile of each type of household customer and the preference for different financial products; determine a recommended list of financial products corresponding to the household customer based on the customer profile, the preference and a preset classification model.

[0109] From the above description, it can be seen that the electronic device provided by the embodiment of the present application obtains the financial management data of the family customer; wherein the financial management data includes: investment type; the investment type in the financial management data is labeled to obtain the customer label of the family customer, and the financial management type of the family customer is clustered according to the customer label; the customer portrait of each family customer and the preference for different financial products are determined; based on the customer portrait, the preference and the preset classification model, the financial product recommendation list corresponding to the family customer is determined. The present invention can quickly and accurately recommend financial products to users from a large number of financial products.

[0110] In another embodiment, the financial product recommendation device may be configured separately from the central processor 9100. For example, the financial product recommendation device may be configured as a chip connected to the central processor 9100, and the financial product recommendation function may be implemented under the control of the central processor.

[0111] like Figure 5 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 5 In addition, the electronic device 9600 may also include Figure 5 For components not shown, reference may be made to the prior art.

[0112] like Figure 5 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0113] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0114] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0115] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0116] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0117] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0118] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0119] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps of the financial product recommendation method in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps of the financial product recommendation method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0120] Acquire the financial management data of household customers; wherein the financial management data includes: investment type; label the investment type in the financial management data to obtain the customer label of the household customer, and cluster the financial management types of the household customer according to the customer label; determine the customer profile of each type of household customer and the preference for different financial products; determine a recommended list of financial products corresponding to the household customer based on the customer profile, the preference and a preset classification model.

[0121] From the above description, it can be seen that the computer-readable storage medium provided by the embodiment of the present invention obtains the financial management data of the family customer; wherein the financial management data includes: investment type; the investment type in the financial management data is labeled to obtain the customer label of the family customer, and the financial management type of the family customer is clustered according to the customer label; the customer portrait of each family customer and the preference for different financial products are determined; based on the customer portrait, the preference and the preset classification model, the financial product recommendation list corresponding to the family customer is determined. The present invention can quickly and accurately recommend financial products to users from a large number of financial products.

[0122] Although the present invention provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).

[0123] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, devices (systems) or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict. The present invention is not limited to any single aspect, any single embodiment, or any combination and / or replacement of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for recommending financial products, characterized in that: include: Acquire financial management data of household customers; wherein the financial management data includes: investment type; Labeling the investment types in the financial management data to obtain customer labels of household customers, and clustering and dividing the financial management types of household customers according to the customer labels; Determine the customer profile of each category of household customers and their preferences for different financial products; Determine a recommended list of financial products corresponding to the household customer based on the customer portrait, the preference and a preset classification model; Also includes: Obtain historical data of household customers, and train a classification model based on the historical data and the Wide & Deep Learning algorithm, specifically including: Splitting the historical data into training samples and verification samples; training the classification model based on Wide & Deep Learning by the training samples, and verifying the trained classification model by the verification samples, specifically including: Use the historical data before the set time as training samples, and use the historical data after the set time as verification samples; The classification model includes the Wide model and the Deep model. The Wide model is used to analyze the characteristic data of old household customers and calculate the impact weight of each type of feature on current new household customers. The Deep model is used to analyze and mine various types of characteristic data in the questionnaire, and the characteristic data is processed and converted into high-order vectors for training. After the Wide and Deep parts use a common model to weight the sum of the characteristic weights, the output is the financial products that are intelligently recommended to household customers.

2. The financial product recommendation method according to claim 1, characterized in that: After obtaining the financial management data of household customers, it also includes: Cleaning and cross-validating the financial management data to obtain valid financial management data; Correspondingly, the investment types in the financial management data are labeled to obtain customer labels of household customers, including: The investment types in the valid financial management data are labeled to obtain the customer labels of household customers.

3. The financial product recommendation method according to claim 1, characterized in that: Determining the customer profile of each type of household customer includes: Analyze the correlation between the customer label of the household customer and the financial product to obtain a user label that is strongly correlated with the financial product; According to the preset label structure of family customers, user labels that are strongly related to the family customers and financial products are divided into multiple levels to generate user portraits of the family customers.

4. The financial product recommendation method according to claim 1, characterized in that: The determining of a recommendation list of financial products corresponding to the household customer based on the customer portrait, the preference and a preset classification model includes: Based on the customer profile and the preference, calculate the product recommendation weight of each financial product relative to the household customer; The product recommendation weights and classification model generate a list of recommended financial products corresponding to household customers.

5. A financial product recommendation device, characterized in that: include: The acquisition module is used to acquire the financial management data of the family customer; wherein the financial management data includes: investment type; A label module, used to label the investment types in the financial management data to obtain customer labels of family customers, and to cluster and divide the financial management types of family customers according to the customer labels; The preference module is used to determine the customer profile of each type of household customer and their preference for different financial products; A recommendation module, used to determine a recommendation list of financial products corresponding to household customers based on the customer portrait, the preference and a preset classification model; Also includes: An acquisition module is used to acquire historical data of household customers and obtain a classification model through training based on the historical data and the Wide & Deep Learning algorithm; The acquisition module is specifically used to split the historical data into training samples and verification samples; train the classification model based on Wide & Deep Learning through the training samples, and verify the trained classification model through the verification samples; The acquisition module is specifically used to use historical data before a set time as training samples, and historical data after the set time as verification samples; the classification model includes a Wide model and a Deep model; using the Wide model, by analyzing the feature data of old family customers, the influence weight of each type of feature on the current new family customers is calculated; using the Deep model, various types of feature data in the questionnaire are analyzed and mined, and the feature data are processed and converted into high-order vectors for training; after the Wide and Deep parts use a common model to weighted sum the feature weights, the financial products intelligently recommended to family customers are output.

6. The financial product recommendation device according to claim 5, characterized in that: Also includes: A cleaning module, used for cleaning and cross-validating the financial management data to obtain valid financial management data; Correspondingly, the label module includes: The label unit is used to label the investment types in the valid financial management data to obtain the customer labels of the household customers.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the financial product recommendation method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the financial product recommendation method according to any one of claims 1 to 4 are implemented.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the financial product recommendation method according to any one of claims 1 to 4 are implemented.

Images