[0033] In order to enable those skilled in the art to better understand the solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.
[0034] A best embodiment is given below:
[0035] Such as figure 1 As shown, the personalized recommendation method for financial service platform products in this embodiment is divided into the following steps:
[0036] S1. Create a user portrait, including the following three parts:
[0037] S101. Collect data,
[0038] S102. Analyze the data,
[0039] S103. Form a portrait;
[0040] S2. Financial product recommendation, including the following two parts:
[0041] S201. The user submits requirements,
[0042] S202. Financial product recommendation function.
[0043] In step S101 collecting data, use web crawler technology to crawl or cooperate with government departments to obtain financial-related government data. These data mainly come from the public security department, the industry and commerce department, and the taxation department. There are certain differences in the data standards of the above three government departments. After the data is obtained, preliminary processing and screening should be carried out. The processing and screening include data association of various departments and statistics of data missing rates.
[0044] In step S102, the data is analyzed, through trend analysis, comparative analysis, quadrant analysis or cross-analysis, the existing data is preliminarily analyzed, and the data analysis standards are based on the various indicators set by the user ,
[0045] Income ability and fixed assets can be divided into strong, strong, general, poor and poor according to specific indicators. Through the analysis of various user data, the processed data is converted into various indicators. The process of data analysis is also At the same time, count the missing data of each particular user.
[0046] In step S103, the portrait is formed. After the data analysis step, the user’s various indicators and the missing rate of data are obtained. When the non-key data missing rate is less than 12%, the user portrait has higher accuracy. Analyze the debt repayment ability, annual income level and personal asset volume, and combine the characteristics of financial products for user groups, credit or mortgage methods, and the level of loan finance to profile users.
[0047] In step S201, the user-oriented financial platform of the financial institution will provide users with a demand submission function. When it is difficult for the user to select the financial product they want in a short time, the user can submit their demand to the system, the submitted demand and the financial product When relevant information is relevant, combine user needs with user portraits and recommend products that are more likely to satisfy users and choose.
[0048] In step S202, the user has a user portrait, and the existing financial products are screened. According to the user's various indicators and the importance of the indicators, as well as the used products, the products that are more likely to meet the actual needs of the user are screened out, and Recommend to users based on likelihood.
[0049] The above operating method is based on a financial service platform product personalized recommendation system, which includes a user profile creation module and a financial product recommendation module connected in sequence.
[0050] The user profile creation module includes successively connected data collection sub-modules, data analysis sub-modules, and profile formation sub-modules. The data collection sub-module is used to crawl through web crawler technology or cooperate with government departments to obtain government data related to finance. Mainly from the public security department, the industry and commerce department and the taxation department. There are certain differences in the data standards of the above three government departments. After the data is obtained, preliminary processing and screening should be carried out. The processing and screening include data association and data missing rate statistics of various departments.
[0051] The data analysis sub-module is used to conduct preliminary analysis of existing data through trend analysis, comparative analysis, quadrant analysis or cross-analysis. The data analysis standards are based on the various indicators set by the user.
[0052] Income ability and fixed assets can be divided into strong, strong, general, poor and poor according to specific indicators. Through the analysis of various user data, the processed data is converted into various indicators. The process of data analysis is also At the same time, count the missing data of each particular user.
[0053] The portrait sub-module is formed to obtain the user’s various indicators and the missing data rate. When the non-key data missing rate is less than 12%, the user portrait has a higher accuracy. The debt repayment ability and annual Income level and personal asset volume, combined with the characteristics of financial products for user groups, credit or mortgage methods, and the level of loan finance, portray users;
[0054] The financial product recommendation module includes a user-submitted demand sub-module and a financial product recommendation function sub-module that are connected in turn. The user-submitted demand sub-module is used in the user-oriented financial platform of financial institutions to provide users with a demand submission function. When choosing the financial products they want in a short time, users can submit their needs to the system. When the submitted needs are related to financial product-related information, combine the needs of users with user portraits, and recommendations to users are more likely to satisfy users. And selected products;
[0055] The financial product recommendation function sub-module is used to filter existing financial products after having a user portrait, and filter out the indicators that are more likely to meet the actual needs of the user according to the user’s various indicators and the importance of the indicators, and the conditions of the products used Products, and recommend them to users according to their likelihood.
[0056] The above-mentioned specific implementations are only specific cases of the present invention. The scope of patent protection of the present invention includes but is not limited to the above-mentioned specific implementations, any personal recommendation methods and system claims that comply with the financial service platform products of the present invention and any Appropriate changes or substitutions made by those of ordinary skill in the technical field shall fall within the scope of patent protection of the present invention.
[0057] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, and substitutions can be made to these embodiments without departing from the principle and spirit of the present invention. And variations, the scope of the present invention is defined by the appended claims and their equivalents.
