Financial product recommendation method and device based on big data analysis, equipment and medium

Abstract

The invention belongs to the field of big data and the field of financial science and technology, and relates to a financial product recommendation method and device based on big data analysis, computer equipment and a storage medium. Constructing a user portrait based on the user data; screening financial management product data in a financial management product library based on first label information in the user portrait to obtain a first financial management product; screening the first financial products based on second label information in the user portrait to obtain second financial products; acquiring a preset weight corresponding to the second label information; generating a product score of the second financial product based on the second label information and a preset weight; and screening out a target number of target financial products with the highest product score from all the second financial products, and pushing the target financial products to the user. In addition, the target financial product can be stored in the block chain. According to the method, the financing product recommendation accuracy is improved in a manner of carrying out financing product recommendation based on user portrait analysis.

Description

Technical Field

[0001] The present application relates to the fields of big data technology and financial technology, and in particular to methods, devices, computer equipment and storage media for recommending financial products based on big data analysis. Background Art

[0002] With the development of economy and technology, the financial industry has also launched more and more financial products. As customer income increases and they are more inclined to increase asset value, most users begin to conduct financial management operations. The existing method of recommending financial products usually directly recommends fund managers to users, and guides users to recommend one or two fixed financial products through the effect of fund managers. However, this recommendation method pays limited attention to the data side and does not pay much attention to and analyze financial products. The data support is weak, resulting in some uncertainty in the financial products recommended to users, and it is impossible to achieve accurate recommendations for financial products. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose a financial product recommendation method, device, computer equipment and storage medium based on big data analysis, so as to solve the technical problems that the existing financial product recommendation methods pay limited attention to the data side, do not pay much attention to and analyze financial products, and cannot achieve accurate recommendations for financial products.

[0004] In order to solve the above technical problems, the present application embodiment provides a financial product recommendation method based on big data analysis, which adopts the following technical solutions:

[0005] Acquire user data of the user based on a preset data collection channel;

[0006] Building a user profile corresponding to the user based on the user data;

[0007] Based on the first tag information in the user portrait, all financial product data contained in a preset financial product library is screened and processed to obtain a first financial product corresponding to the first tag information;

[0008] Screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information;

[0009] Obtaining a preset weight corresponding to the second tag information;

[0010] generating a product score corresponding to the second financial product based on the second tag information and the preset weight;

[0011] A target number of target financial products with the highest product scores are screened out from all the second financial products, and the target financial products are pushed to the user.

[0012] Furthermore, the step of constructing a user portrait corresponding to the user based on the user data specifically includes:

[0013] Performing data cleaning processing on the user data to obtain corresponding first user data;

[0014] Performing data integration processing on the first user data to obtain corresponding second user data;

[0015] Performing feature extraction processing on the second user data to obtain corresponding feature data;

[0016] Converting the feature data into corresponding label information;

[0017] Performing weight distribution processing on the label information to obtain a weight corresponding to the label information;

[0018] A user profile of the user is generated based on the tag information and the weight.

[0019] Furthermore, the step of screening all financial product data contained in a preset financial product library based on the first tag information in the user portrait to obtain a first financial product corresponding to the first tag information specifically includes:

[0020] Constructing a database query statement corresponding to the first tag information;

[0021] Performing fuzzy matching processing on the database query statement to obtain a corresponding first query statement;

[0022] Adding synonyms to the first query statement to obtain a corresponding second query statement;

[0023] Calling the financial product library;

[0024] Performing a search process on the financial product database based on the second query statement to obtain a search result corresponding to the second query statement;

[0025] The first financial product is generated based on the search result.

[0026] Furthermore, the second tag information at least includes a point of interest, a minimum purchase amount, an expected return, and a risk level; the step of screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information specifically includes:

[0027] Obtaining a screening order corresponding to the second tag information;

[0028] Based on the screening order, screening out a first product that meets the interest point from the first financial products;

[0029] Filter out a second product that meets the minimum purchase amount from the first product;

[0030] Selecting a third product that meets the expected return from the second product;

[0031] Selecting a fourth product that meets the risk level from the third product;

[0032] The fourth product is used as the second financial product.

[0033] Furthermore, the step of generating a product score corresponding to the second wealth management product based on the second tag information and the preset weight specifically includes:

[0034] Based on a preset scoring rule, determine a first satisfaction score, a second satisfaction score, a third satisfaction score, and a fourth satisfaction score respectively corresponding to the interest point, the minimum purchase amount, the expected return, and the risk level from designated financial products; wherein the designated financial product is any one of all the second financial products;

[0035] Obtaining a first preset weight, a second preset weight, a third preset weight, and a fourth preset weight corresponding to the point of interest, the minimum purchase amount, the expected return, and the risk level, respectively;

[0036] Call the preset score generation algorithm;

[0037] Based on the score generation algorithm, the first satisfaction score, the second satisfaction score, the third satisfaction score, the fourth satisfaction score, the first preset weight, the second preset weight, the third preset weight, and the fourth preset weight are calculated to obtain corresponding calculation results;

[0038] The calculation result is used as the product score of the designated financial product.

[0039] Furthermore, the step of pushing the target financial product to the user specifically includes:

[0040] Generate product explanation information related to the target financial product;

[0041] Determine a target push method corresponding to the target financial product;

[0042] Obtaining communication information of the user;

[0043] Based on the communication information, the target financial product and the product explanation information are pushed to the user using the target push method.

[0044] Furthermore, after the step of pushing the target financial product to the user, the method further includes:

[0045] Determining whether product confirmation information returned by the user is received; wherein the product confirmation information includes confirmation of the financial product;

[0046] If yes, obtaining the authorization status information of the user;

[0047] If the authorization status information indicates that automated operation is allowed, obtaining the confirmed financial product from all the target financial products;

[0048] Obtaining an execution strategy corresponding to the confirmed financial product;

[0049] The confirmed financial product is processed accordingly based on the execution strategy.

[0050] In order to solve the above technical problems, the present application also provides a financial product recommendation device based on big data analysis, which adopts the following technical solution:

[0051] A first acquisition module, used to acquire user data of a user based on a preset data collection channel;

[0052] A construction module, used to construct a user portrait corresponding to the user based on the user data;

[0053] A first screening module, configured to screen all financial product data contained in a preset financial product library based on the first tag information in the user portrait, and obtain a first financial product corresponding to the first tag information;

[0054] A second screening module, configured to screen the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information;

[0055] A second acquisition module, used to acquire a preset weight corresponding to the second tag information;

[0056] A generating module, configured to generate a product score corresponding to the second financial product based on the second tag information and the preset weight;

[0057] A push module is used to screen out a target number of target financial products with the highest product scores from all the second financial products, and push the target financial products to the user.

[0058] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0059] Acquire user data of the user based on a preset data collection channel;

[0060] Building a user profile corresponding to the user based on the user data;

[0061] Based on the first tag information in the user portrait, all financial product data contained in a preset financial product library is screened and processed to obtain a first financial product corresponding to the first tag information;

[0062] Screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information;

[0063] Obtaining a preset weight corresponding to the second tag information;

[0064] generating a product score corresponding to the second financial product based on the second tag information and the preset weight;

[0065] A target number of target financial products with the highest product scores are screened out from all the second financial products, and the target financial products are pushed to the user.

[0066] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0067] Acquire user data of the user based on a preset data collection channel;

[0068] Building a user profile corresponding to the user based on the user data;

[0069] Based on the first tag information in the user portrait, all financial product data contained in a preset financial product library is screened and processed to obtain a first financial product corresponding to the first tag information;

[0070] Screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information;

[0071] Obtaining a preset weight corresponding to the second tag information;

[0072] generating a product score corresponding to the second financial product based on the second tag information and the preset weight;

[0073] A target number of target financial products with the highest product scores are screened out from all the second financial products, and the target financial products are pushed to the user.

[0074] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0075] This application first obtains user data of the user based on a preset data collection channel; and constructs a user portrait corresponding to the user based on the user data; then, based on the first tag information in the user portrait, all wealth management product data contained in a preset wealth management product library are screened and processed to obtain a first wealth management product corresponding to the first tag information; then, based on the second tag information in the user portrait, the first wealth management product is screened and processed to obtain a second wealth management product corresponding to the second tag information; subsequently, a preset weight corresponding to the second tag information is obtained; further, a product score corresponding to the second wealth management product is generated based on the second tag information and the preset weight; finally, a target number of target wealth management products with the highest product scores are screened from all the second wealth management products, and the target wealth management products are pushed to the user. The present application constructs a user portrait based on user data, then filters the wealth management product data based on the first label information and the second label information in the user portrait to obtain a second wealth management product, and then generates a product score corresponding to the second wealth management product based on the second label information and the corresponding preset weight, and finally filters out a target number of target wealth management products with the highest product scores from all the second wealth management products, and pushes the target wealth management products to the user, so as to accurately recommend target wealth management products that meet the user's personalized needs to the user based on the analysis of the user portrait, effectively improving the recommendation accuracy of the target wealth management products, and helping to improve user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0077] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0078] Figure 2 A flowchart of an embodiment of a financial product recommendation method based on big data analysis according to the present application;

[0079] Figure 3It is a structural schematic diagram of an embodiment of a financial product recommendation device based on big data analysis according to the present application;

[0080] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0081] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0082] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0083] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0084] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0085] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0086] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0087] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0088] It should be noted that the financial product recommendation method based on big data analysis provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the financial product recommendation device based on big data analysis is generally set in the server / terminal device.

[0089] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0090] Continue to refer Figure 2 , showing a flowchart of an embodiment of a financial product recommendation method based on big data analysis according to the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The financial product recommendation method based on big data analysis provided in the embodiment of the present application can be applied to any scenario where financial product recommendations are required, and the financial product recommendation method based on big data analysis can be applied to products in these scenarios, for example, financial product recommendations in the financial insurance field. The financial product recommendation method based on big data analysis includes the following steps:

[0091] Step S201: acquiring user data of a user based on a preset data collection channel.

[0092] In this embodiment, the financial product recommendation method based on big data analysis is run on an electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain user data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi DeBand) connection, and other wireless connection methods currently known or to be developed in the future. The above data collection channels may at least include questionnaires, user behavior analysis, social media, etc., and user data such as basic information, investment habits, risk preferences, return expectations, and focus sectors of users can be collected based on the data collection channels. Specifically, 1) the process of obtaining user data through questionnaires includes: according to the needs of financial services, designing a questionnaire containing basic user information (such as age, gender, occupation, income level), investment habits (such as investment experience, investment cycle), risk preferences (assessed in the form of multiple-choice questions or scales), return expectations, focus sectors, etc. Questionnaires are then published through online platforms (such as websites, APPs, social media) or offline channels (such as stores, event sites), and data filled out by users are collected. 2) The process of obtaining user data through user behavior analysis includes: using the log system to record the user's browsing history, click behavior, search keywords, dwell time, etc. Then the user behavior data is associated with the user account information to ensure the accuracy of the data. After that, the user behavior is deeply analyzed through data analysis tools (such as Google Analytics, Mixpanel) to identify the user's interests, purchasing habits, etc. 3) The process of obtaining user data through social media includes: obtaining the user's public information on social media through the API interface or third-party data providers, such as topics of interest, groups participated in, and content posted. Then use natural language processing technology to perform sentiment analysis on the content posted by the user to understand the user's attitude towards specific sections or products. Subsequently, the user's social behavior and content analysis are combined to explore the user's potential interests and preferences.

[0093] Step S202: construct a user portrait corresponding to the user based on the user data.

[0094] In this embodiment, the specific implementation process of constructing the user portrait corresponding to the user based on the user data will be described in further detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0095] Step S203: Screening and processing all financial product data contained in a preset financial product library based on the first tag information in the user portrait to obtain a first financial product corresponding to the first tag information.

[0096] In this embodiment, the first tag information may specifically include the type of income and the section of interest. The specific implementation process of filtering all the financial product data contained in the preset financial product library based on the first tag information in the user portrait to obtain the first financial product corresponding to the first tag information will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0097] Step S204: Screen the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information.

[0098] In this embodiment, the above-mentioned specific implementation process of screening and processing the first wealth management product based on the second label information in the user portrait to obtain the second wealth management product corresponding to the second label information will be further described in detail in the subsequent specific embodiments of this application and will not be elaborated here.

[0099] Step S205: Obtain a preset weight corresponding to the second tag information.

[0100] In this embodiment, the above-mentioned preset weights can be determined based on the preference intensity in the user portrait and the actual market situation.

[0101] Step S206: Generate a product score corresponding to the second financial product based on the second tag information and the preset weight.

[0102] In this embodiment, the specific implementation process of generating the product score corresponding to the second wealth management product based on the second tag information and the preset weight will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0103] Step S207, selecting a target number of target financial products with the highest product scores from all the second financial products, and pushing the target financial products to the user.

[0104] In this embodiment, the product scores of all second financial products can be numerically compared to select the target number of target financial products with the highest product scores from all the second financial products. The specific implementation process of pushing the target financial products to the user will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0105] The present application constructs a user portrait based on user data, then filters the wealth management product data based on the first label information and the second label information in the user portrait to obtain a second wealth management product, and then generates a product score corresponding to the second wealth management product based on the second label information and the corresponding preset weight, and finally filters out a target number of target wealth management products with the highest product scores from all the second wealth management products, and pushes the target wealth management products to the user, so as to accurately recommend target wealth management products that meet the user's personalized needs to the user based on the analysis of the user portrait, effectively improving the recommendation accuracy of the target wealth management products, and helping to improve user satisfaction.

[0106] In some optional implementations, step S202 includes the following steps:

[0107] The user data is cleansed to obtain corresponding first user data.

[0108] In this embodiment, the data cleaning process includes removing duplicate, erroneous or invalid data to ensure the accuracy and consistency of user data.

[0109] Perform data integration processing on the first user data to obtain corresponding second user data.

[0110] In this embodiment, the data integration process refers to integrating user information from different channels, such as questionnaires, user behaviors, and social media data, to form a complete user data set to obtain the above-mentioned second user data.

[0111] Perform feature extraction processing on the second user data to obtain corresponding feature data.

[0112] In this embodiment, the feature extraction process includes: Extracting basic features: extracting basic information of users, such as age, occupation, income level, etc., as the basis of user portraits. Extracting investment features: extracting investment-related features such as investment experience, risk tolerance, return preference, investment term preference, etc. based on the user's investment habits, risk preferences, return expectations, etc. Extracting preference features: extracting features such as the user's specific industry or sector preferences based on the user's behavior data and social media data.

[0113] The feature data is converted into corresponding label information.

[0114] In this embodiment, the extracted feature data is converted into a label form to obtain corresponding label information, such as "middle-aged male", "high-income group", "conservative investor", "technology sector preference", etc.

[0115] A weight distribution process is performed on the label information to obtain a weight corresponding to the label information.

[0116] In this embodiment, weights may be assigned to different tag information according to the importance and relevance of the features to reflect the feature strength of the user in various dimensions.

[0117] A user profile of the user is generated based on the tag information and the weight.

[0118] In this embodiment, a comprehensive user portrait, i.e., the above-mentioned user portrait, is generated by integrating all tag information and weights. The generated user portrait can comprehensively and accurately reflect the user's personal information, investment habits, risk preferences, and return expectations. In addition, the accuracy and effectiveness of the user portrait can also be verified through actual application scenarios (such as financial recommendations and marketing activities). And based on user feedback and actual results, the construction method of the user portrait is continuously adjusted and optimized to improve the accuracy and practicality of the portrait.

[0119] This application performs data cleaning on the user data to obtain the corresponding first user data; then performs data integration on the first user data to obtain the corresponding second user data; then performs feature extraction on the second user data to obtain the corresponding feature data; subsequently converts the feature data into corresponding label information; further performs weight assignment on the label information to obtain the weight corresponding to the label information; and finally generates a user portrait of the user based on the label information and the weight. This application performs data cleaning, data integration, feature extraction, label conversion, and weight assignment on the user data obtained based on the data collection channel to quickly and accurately construct a user portrait that matches the user data, thereby improving the efficiency and intelligence of constructing the user portrait and ensuring the accuracy of the obtained user portrait.

[0120] In some optional implementations of this embodiment, step S203 includes the following steps:

[0121] Construct a database query statement corresponding to the first tag information.

[0122] In this embodiment, the first tag information may specifically include the type of income and the sector of interest. According to the first tag information, a corresponding database query statement is constructed using an SQL statement.

[0123] Perform fuzzy matching processing on the database query statement to obtain a corresponding first query statement.

[0124] In this embodiment, the fuzzy matching process refers to adding wildcards or regular expressions to the database query statement to support fuzzy matching of tags. For example, the LI KE operator is used to implement fuzzy matching.

[0125] The first query statement is processed by adding synonyms to obtain a corresponding second query statement.

[0126] In this embodiment, a preset synonym library may be called, and a target synonym matching the first tag information may be found from the synonym library, and then the target synonym may be dynamically added to the first query statement to obtain the second query statement.

[0127] The financial product library is called.

[0128] In this embodiment, the construction process of the above-mentioned financial product library includes: using crawler technology to capture detailed information of financial products in real time from websites of major financial institutions, financial platforms, exchanges, etc., including but not limited to: product name, rate of return, minimum purchase amount, rate, investment period, product type (such as money fund, bond fund, stock fund, etc.), risk level, etc. Then the captured data is stored in the HDFS of the Hadoop platform to obtain the above-mentioned financial product library. Among them, Hi ve tools can be further used to clean and preprocess the data to remove duplicate, erroneous or invalid data to ensure the accuracy and completeness of the data. In addition, the data is formatted, and the data structure and field naming are unified to facilitate subsequent analysis and processing.

[0129] The financial product database is searched based on the second query statement to obtain a search result corresponding to the second query statement.

[0130] In this embodiment, the constructed second query statement is sent to the financial product database for execution, and the search results returned by the financial product database are received.

[0131] The first financial product is generated based on the search result.

[0132] In this embodiment, the first financial product is obtained by performing deduplication, sorting, etc. on the search results. In addition, the search results may be paginated or the number of results returned may be limited as needed.

[0133] The present application constructs a database query statement corresponding to the first tag information; then performs fuzzy matching processing on the database query statement to obtain the corresponding first query statement; then performs synonym addition processing on the first query statement to obtain the corresponding second query statement; subsequently calls the financial product library; and performs search processing on the financial product library based on the second query statement to obtain the search result corresponding to the second query statement; and finally generates the first financial product based on the search result. The present application constructs a database query statement corresponding to the first tag information, and intelligently performs fuzzy matching processing and synonym addition processing on the database query statement to obtain the second query statement, and then uses the second query statement to search the financial product library to quickly and accurately obtain the first financial product corresponding to the first tag information, thereby improving the screening intelligence of the initial screening of financial product data based on the first tag information, and improving the data richness and accuracy of the generated first financial product.

[0134] In some optional implementations, the second tag information includes at least points of interest, a minimum purchase amount, an expected return, and a risk level; step S204 includes the following steps:

[0135] A filtering order corresponding to the second tag information is obtained.

[0136] In this embodiment, the above screening order is a priority order for various second tag information that is predefined according to actual business needs. Preferably, the above priority order includes: point of interest (focused section) > minimum purchase amount > expected return > risk level.

[0137] Based on the screening order, a first product meeting the interest point is screened out from the first financial products.

[0138] In this embodiment, from the first financial product, the related products are screened out according to the labels of the user's concerned section corresponding to the above interest points to obtain the first product. In the process of screening related products, fuzzy matching and synonym processing of labels can be further used to improve the accuracy of screening.

[0139] Filter out a second product that meets the minimum purchase amount from the first product.

[0140] In this embodiment, on the basis of the screening of interest points, products whose minimum purchase amount is within the user's acceptable range are further screened from the above-mentioned first products to obtain second products.

[0141] A third product that meets the expected return is selected from the second products.

[0142] In this embodiment, the second products are sorted or further screened according to the expected revenue range of the user to obtain the corresponding third products. A revenue threshold can be set to retain only products with expected revenue higher than the revenue threshold as the third products.

[0143] A fourth product that meets the risk level is selected from the third products.

[0144] In this embodiment, the risk level of the screened third product is evaluated to ensure that the risk levels of all selected products are within the user-acceptable range corresponding to the above risk levels, thereby obtaining the above fourth product.

[0145] The fourth product is used as the second financial product.

[0146] This application obtains a screening order corresponding to the second tag information; and based on the screening order, screens out a first product that meets the interest point from the first financial product; then screens out a second product that meets the minimum purchase amount from the first product; then screens out a third product that meets the expected return from the second product; subsequently screens out a fourth product that meets the risk level from the third product; and finally uses the fourth product as the second financial product. This application improves the screening efficiency of the second financial product and ensures the accuracy of the obtained second financial product by screening out products that meet the interest point, minimum purchase amount, expected return and risk level of the user corresponding to the user portrait from the above-mentioned first financial product according to the screening order corresponding to the second tag information and uses them as the corresponding second financial product.

[0147] In some optional implementations, step S206 includes the following steps:

[0148] Based on the preset scoring rules, a first satisfaction score, a second satisfaction score, a third satisfaction score and a fourth satisfaction score respectively corresponding to the interest point, the minimum purchase amount, the expected return and the risk level are determined from the designated financial products; wherein the designated financial product is any one of all the second financial products.

[0149] In this embodiment, for a designated financial product, after screening according to the conditions (second label information) such as interest points, minimum purchase amount, expected return, risk level, etc., a satisfaction score will be assigned to each condition. Among them, the above-mentioned scoring rule can determine the corresponding satisfaction score based on the degree of compliance with the condition, such as the closer the minimum purchase amount is to the value set by the user, the higher the score.

[0150] Obtain a first preset weight, a second preset weight, a third preset weight, and a fourth preset weight corresponding to the point of interest, the minimum purchase amount, the expected return, and the risk level, respectively.

[0151] In this embodiment, the subjective weighting method or the objective weighting method can be used to set the weight. Among them, the subjective weighting method can adopt the expert scoring method or the hierarchical analysis method. The objective weighting method can adopt the entropy weight method or the coefficient of variation method. Specifically, the expert scoring method: invite industry experts or senior users to score the importance of each screening condition (second label information) based on experience, and then normalize the weight. The hierarchical analysis method (AHP): decompose the screening conditions into different components, and group the factors according to the dominant relationship to form a recursive hierarchical structure, and determine the relative importance of the factors in the hierarchy by comparing them two by two. Finally, calculate the order weight reflecting the importance of a certain factor relative to the overall goal, and calculate the relative weights of all factors through the total ranking between all levels and sort them. Entropy weight method: determine the weight according to the amount of information provided by each screening condition. The larger the amount of information, the smaller the uncertainty, the smaller the entropy, and the condition should be given a larger weight; conversely, the smaller the amount of information, the greater the uncertainty, the greater the entropy, and the condition should be given a smaller weight. Coefficient of variation method: directly use the information contained in the index values ​​of each screening condition, calculate the coefficient of variation of the index, and then find the weight of each index after normalization.

[0152] Call the preset score generation algorithm.

[0153] In this embodiment, the score generation algorithm specifically includes: S = a*U+b*V+c*W+d*X. Among them, S is the product score, U is the first satisfaction score, a is the first preset weight, V is the second satisfaction score, b is the second preset weight, W is the third satisfaction score, c is the third preset weight, X is the fourth satisfaction score, and d is the fourth preset weight.

[0154] Based on the score generation algorithm, the first satisfaction score, the second satisfaction score, the third satisfaction score, the fourth satisfaction score, the first preset weight, the second preset weight, the third preset weight and the fourth preset weight are calculated and processed to obtain corresponding calculation results.

[0155] In this embodiment, the first satisfaction score, the second satisfaction score, the third satisfaction score, the fourth satisfaction score, the first preset weight, the second preset weight, the third preset weight and the fourth preset weight can be substituted into the corresponding positions in the above-mentioned score generation algorithm for calculation, thereby obtaining the corresponding calculation result.

[0156] The calculation result is used as the product score of the designated financial product.

[0157] The present application determines, from the designated financial products, a first satisfaction score, a second satisfaction score, a third satisfaction score and a fourth satisfaction score respectively corresponding to the interest point, the minimum purchase amount, the expected return and the risk level based on the use of a scoring rule, and then calculates and processes the first preset weight, the second preset weight, the third preset weight and the fourth preset weight respectively corresponding to the interest point, the minimum purchase amount, the expected return and the risk level based on the use of a score generation algorithm, thereby achieving rapid and accurate generation of product scores for designated financial products, thereby ensuring the data accuracy of the obtained product scores.

[0158] In some optional implementations of this embodiment, the pushing of the target financial product to the user in step S207 includes the following steps:

[0159] Generate product explanation information related to the target financial product.

[0160] In this embodiment, the product explanation information refers to explaining to the user the reasons for recommending the target financial product, and the product explanation information may at least include information such as the product's features, expected returns, advantages, potential risks, etc. In addition, charts, data comparisons, historical performance, etc. may be used to enhance the persuasiveness and intuitiveness of the product explanation information, and emphasize how the target financial product is selected based on the user's personalized needs (such as return preferences, risk tolerance, etc.).

[0161] Determine a target push method corresponding to the target financial product.

[0162] In this embodiment, the selection of the above-mentioned target push mode is not specifically limited and can be set according to actual business needs. Specifically, the target push mode can be any one of application notification, SMS, email or direct display on the user interface.

[0163] Acquire the communication information of the user.

[0164] In this embodiment, the communication information may include a mobile phone number or an email address.

[0165] Based on the communication information, the target financial product and the product explanation information are pushed to the user using the target push method.

[0166] In this embodiment, the target financial product and the product explanation information can be sent to the communication terminal of the user corresponding to the communication information according to the communication information. For example, if the target push mode is page display, a user interaction interface can be provided to allow the user to view, compare and ask questions about the recommended target financial products. The user can deeply understand the specific information of each target financial product through operations such as clicking, sliding, zooming in and out, etc. A question-and-answer or chat robot can be set to answer the user's questions to improve user participation and satisfaction.

[0167] This application generates product explanation information for the target financial product; then determines the target push method corresponding to the target financial product; then obtains the user's communication information; and subsequently pushes the target financial product and the product explanation information to the user based on the communication information using the target push method. This application intelligently generates product explanation information for the target financial product, and then based on the user's communication information, pushes the target financial product and the product explanation information to the user using the target push method corresponding to the target financial product, so as to accurately recommend target financial products that meet the user's personalized needs to the user based on the user portrait, thereby effectively improving the accuracy of the recommendation of the target financial product. In addition, product explanation information will be intelligently pushed to the user so that the user can understand the reasons for recommending the target financial product, thereby improving the user experience.

[0168] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0169] Determine whether product confirmation information returned by the user is received; wherein the product confirmation information includes confirmation of the financial product.

[0170] In this embodiment, after the user fully understands and compares the recommended target financial products, the user can also filter out the confirmed financial products that need to be invested from all target financial products according to the actual financial needs, and perform the corresponding confirmation operation. Among them, the confirmation operation can be clicking buttons such as "Agree" and "Buy", or filling in a confirmation form and submitting it. Before the user confirms, the system should remind the user again to pay attention to the investment risks and confirm that the user has fully understood and accepted the relevant risks.

[0171] If yes, obtain the authorization status information of the user.

[0172] In this embodiment, the authorization status information of the user can be obtained by reading the user configuration or account authority management corresponding to the user to confirm whether the user is allowed to perform fully automated operations. The authorization status information may include whether automated operations are allowed or not.

[0173] If the authorization status information indicates that automated operation is allowed, the confirmed financial product is obtained from all the target financial products.

[0174] In this embodiment, the confirmed financial product may be a product among all the target financial products corresponding to the confirmation operation triggered by the user.

[0175] Obtain an execution strategy corresponding to the confirmed financial product.

[0176] In this embodiment, the above-mentioned execution strategy may include performing subsequent processing according to the user's instructions, such as executing processing of fund transfer, product purchase, etc.

[0177] The confirmed financial product is processed accordingly based on the execution strategy.

[0178] In this embodiment, the confirmed financial product can be processed for corresponding investment according to the policy content of the above-mentioned execution policy. The user's confirmation operation and timestamp can be recorded for subsequent tracking and auditing. In addition, if the user chooses not to purchase or cancels the operation, the system should also provide corresponding processing procedures and feedback.

[0179] This application determines whether the product confirmation information returned by the user is received; wherein the product confirmation information includes the confirmed financial product; if so, obtain the authorization status information of the user; if the authorization status information allows automated operations, obtain the confirmed financial product from all the target financial products; then obtain the execution policy corresponding to the confirmed financial product; and subsequently perform corresponding processing on the confirmed financial product based on the execution policy. After the target financial product is pushed to the user, if the product confirmation information returned by the user is received and it is detected that the user's authorization status information allows automated operations, the application will automatically and intelligently perform corresponding processing on the confirmed financial product corresponding to the product confirmation information according to the execution policy corresponding to the confirmed financial product, so as to complete the automated execution processing of the confirmed financial product, effectively improving the execution intelligence of the confirmed financial product and improving the user experience.

[0180] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0181] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target financial products, the above-mentioned target financial products can also be stored in a node of a blockchain.

[0182] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0183] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0185] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0186] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a financial product recommendation device based on big data analysis. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0187] like Figure 3 As shown, the financial product recommendation device 300 based on big data analysis described in this embodiment includes: a first acquisition module 301, a construction module 302, a first screening module 303, a second screening module 304, a second acquisition module 305, a generation module 306 and a push module 307. Among them:

[0188] The first acquisition module 301 is used to acquire user data of the user based on a preset data collection channel;

[0189] A construction module 302 is used to construct a user portrait corresponding to the user based on the user data;

[0190] A first screening module 303 is used to screen all financial product data contained in a preset financial product library based on the first tag information in the user portrait to obtain a first financial product corresponding to the first tag information;

[0191] A second screening module 304, configured to screen the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information;

[0192] A second acquisition module 305, used to acquire a preset weight corresponding to the second tag information;

[0193] A generating module 306, configured to generate a product score corresponding to the second financial product based on the second tag information and the preset weight;

[0194] The push module 307 is used to select a target number of target financial products with the highest product scores from all the second financial products, and push the target financial products to the user.

[0195] In some optional implementations of this embodiment, the construction module 302 includes:

[0196] A first processing submodule, configured to perform data cleaning processing on the user data to obtain corresponding first user data;

[0197] A second processing submodule, configured to perform data integration processing on the first user data to obtain corresponding second user data;

[0198] A third processing submodule is used to perform feature extraction processing on the second user data to obtain corresponding feature data;

[0199] A conversion submodule, used to convert the feature data into corresponding label information;

[0200] An allocation submodule, used to perform weight allocation processing on the label information to obtain a weight corresponding to the label information;

[0201] The first determination submodule is used to generate a user portrait of the user based on the tag information and the weight.

[0202] In some optional implementations of this embodiment, the first screening module 303 includes:

[0203] A construction submodule, used to construct a database query statement corresponding to the first tag information;

[0204] A fourth processing submodule, configured to perform fuzzy matching processing on the database query statement to obtain a corresponding first query statement;

[0205] A fifth processing submodule, configured to perform synonym addition processing on the first query statement to obtain a corresponding second query statement;

[0206] A first calling submodule, used for calling the financial product library;

[0207] A search submodule, configured to perform a search process on the financial product library based on the second query statement to obtain a search result corresponding to the second query statement;

[0208] The first generating submodule is used to generate the first financial product based on the search result.

[0209] In some optional implementations of this embodiment, the second tag information includes at least points of interest, a minimum purchase amount, an expected return, and a risk level; the second screening module 304 includes:

[0210] A first acquisition submodule, used to acquire a screening order corresponding to the second tag information;

[0211] A first screening submodule, configured to screen out a first product that meets the interest point from the first financial products based on the screening order;

[0212] A second screening submodule is used to screen out second products that meet the minimum purchase amount from the first products;

[0213] A third screening submodule, used to screen out a third product that meets the expected return from the second product;

[0214] A fourth screening submodule, used for screening out fourth products meeting the risk level from the third products;

[0215] The second determining submodule is used to use the fourth product as the second financial product.

[0216] In some optional implementations of this embodiment, the generating module 306 includes:

[0217] A third determination submodule is used to determine, based on a preset scoring rule, a first satisfaction score, a second satisfaction score, a third satisfaction score, and a fourth satisfaction score corresponding to the interest point, the minimum purchase amount, the expected return, and the risk level, respectively, from designated financial products; wherein the designated financial product is any one of all the second financial products;

[0218] A second acquisition submodule is used to acquire a first preset weight, a second preset weight, a third preset weight, and a fourth preset weight corresponding to the point of interest, the minimum purchase amount, the expected return, and the risk level, respectively;

[0219] The second calling submodule is used to call a preset score generation algorithm;

[0220] a calculation submodule, configured to calculate the first satisfaction score, the second satisfaction score, the third satisfaction score, the fourth satisfaction score, the first preset weight, the second preset weight, the third preset weight, and the fourth preset weight based on the score generation algorithm to obtain a corresponding calculation result;

[0221] The fourth determination submodule is used to use the calculation result as the product score of the designated financial product.

[0222] In some optional implementations of this embodiment, the push module 307 includes:

[0223] The second generation submodule is used to generate product explanation information related to the target financial product;

[0224] A fifth determination submodule is used to determine a target push mode corresponding to the target financial product;

[0225] A third acquisition submodule is used to acquire the communication information of the user;

[0226] The push submodule is used to push the target financial product and the product explanation information to the user based on the communication information using the target push method.

[0227] In some optional implementations of this embodiment, the financial product recommendation device based on big data analysis further includes:

[0228] A judgment module, used to judge whether the product confirmation information returned by the user is received; wherein the product confirmation information includes confirmation of the financial product;

[0229] A third acquisition module is used to obtain the authorization status information of the user;

[0230] A fourth acquisition module, configured to acquire the confirmed financial product from all the target financial products if the authorization status information indicates that the automated operation is allowed;

[0231] A fifth acquisition module, used to acquire an execution strategy corresponding to the confirmed financial product;

[0232] An execution module is used to perform corresponding processing on the confirmed financial product based on the execution strategy.

[0233] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0234] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0235] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0236] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a financial product recommendation method based on big data analysis, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0237] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the financial product recommendation method based on big data analysis.

[0238] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0239] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the financial product recommendation method based on big data analysis as described above.

[0240] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0241] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A financial product recommendation method based on big data analysis, characterized in that: The steps include: Acquire user data of the user based on a preset data collection channel; Building a user profile corresponding to the user based on the user data; Based on the first tag information in the user portrait, all financial product data contained in a preset financial product library is screened and processed to obtain a first financial product corresponding to the first tag information; Screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information; Obtaining a preset weight corresponding to the second tag information; generating a product score corresponding to the second financial product based on the second tag information and the preset weight; A target number of target financial products with the highest product scores are screened out from all the second financial products, and the target financial products are pushed to the user.

2. The financial product recommendation method based on big data analysis according to claim 1, characterized in that: The step of constructing a user portrait corresponding to the user based on the user data specifically includes: Performing data cleaning processing on the user data to obtain corresponding first user data; Performing data integration processing on the first user data to obtain corresponding second user data; Performing feature extraction processing on the second user data to obtain corresponding feature data; Converting the feature data into corresponding label information; Performing weight distribution processing on the label information to obtain a weight corresponding to the label information; A user profile of the user is generated based on the tag information and the weight.

3. The financial product recommendation method based on big data analysis according to claim 1, characterized in that: The step of screening all financial product data contained in a preset financial product library based on the first tag information in the user portrait to obtain a first financial product corresponding to the first tag information specifically includes: Constructing a database query statement corresponding to the first tag information; Performing fuzzy matching processing on the database query statement to obtain a corresponding first query statement; Adding synonyms to the first query statement to obtain a corresponding second query statement; Calling the financial product library; Performing a search process on the financial product database based on the second query statement to obtain a search result corresponding to the second query statement; The first financial product is generated based on the search result.

4. The financial product recommendation method based on big data analysis according to claim 1, characterized in that: The second tag information at least includes a point of interest, a minimum purchase amount, an expected return, and a risk level; the step of screening the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information specifically includes: Obtaining a screening order corresponding to the second tag information; Based on the screening order, screening out a first product that meets the interest point from the first financial products; Filter out a second product that meets the minimum purchase amount from the first product; Selecting a third product that meets the expected return from the second product; Selecting a fourth product that meets the risk level from the third product; The fourth product is used as the second financial product.

5. The financial product recommendation method based on big data analysis according to claim 4 is characterized in that: The step of generating a product score corresponding to the second financial product based on the second tag information and the preset weight specifically includes: Based on a preset scoring rule, determine a first satisfaction score, a second satisfaction score, a third satisfaction score, and a fourth satisfaction score respectively corresponding to the interest point, the minimum purchase amount, the expected return, and the risk level from designated financial products; wherein the designated financial product is any one of all the second financial products; Obtaining a first preset weight, a second preset weight, a third preset weight, and a fourth preset weight corresponding to the point of interest, the minimum purchase amount, the expected return, and the risk level, respectively; Call the preset score generation algorithm; Based on the score generation algorithm, the first satisfaction score, the second satisfaction score, the third satisfaction score, the fourth satisfaction score, the first preset weight, the second preset weight, the third preset weight, and the fourth preset weight are calculated to obtain corresponding calculation results; The calculation result is used as the product score of the designated financial product.

6. The financial product recommendation method based on big data analysis according to claim 1, characterized in that: The step of pushing the target financial product to the user specifically includes: Generate product explanation information related to the target financial product; Determine a target push method corresponding to the target financial product; Obtaining communication information of the user; Based on the communication information, the target financial product and the product explanation information are pushed to the user using the target push method.

7. The financial product recommendation method based on big data analysis according to claim 1, characterized in that: After the step of pushing the target financial product to the user, the method further includes: Determining whether product confirmation information returned by the user is received; wherein the product confirmation information includes confirmation of the financial product; If yes, obtaining the authorization status information of the user; If the authorization status information indicates that automated operation is allowed, obtaining the confirmed financial product from all the target financial products; Obtaining an execution strategy corresponding to the confirmed financial product; The confirmed financial product is processed accordingly based on the execution strategy.

8. A financial product recommendation device based on big data analysis, characterized in that: include: A first acquisition module, used to acquire user data of a user based on a preset data collection channel; A construction module, used to construct a user portrait corresponding to the user based on the user data; A first screening module, configured to screen all financial product data contained in a preset financial product library based on the first tag information in the user portrait, and obtain a first financial product corresponding to the first tag information; A second screening module, configured to screen the first financial product based on the second tag information in the user portrait to obtain a second financial product corresponding to the second tag information; A second acquisition module, used to acquire a preset weight corresponding to the second tag information; A generating module, configured to generate a product score corresponding to the second financial product based on the second tag information and the preset weight; A push module is used to screen out a target number of target financial products with the highest product scores from all the second financial products, and push the target financial products to the user.

9. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the financial product recommendation method based on big data analysis as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the financial product recommendation method based on big data analysis as described in any one of claims 1 to 7.

Images