A financial data visualization management system and method based on big data analysis

Abstract

The present invention discloses a financial data visualization management system and method based on big data analysis, belonging to the field of data visualization management technology. The system of the present invention comprises: a data acquisition and classification module, an operation data analysis module, a related path and network diagram construction module, a real-time user judgment module and an intelligent navigation service module; the data acquisition and classification module acquires user information and corresponding historical operation data, divides users into template users and target users, and constructs a template user operation data set; the operation data analysis module analyzes the template user operation data set to obtain operation targets, extracts the characteristics of the operation targets, and divides the operation targets into related and irrelevant operation targets; the related path and network diagram construction module constructs related paths and related network diagrams of related operation targets; the real-time user judgment module judges whether the real-time user is a target user; the intelligent navigation service module provides intelligent navigation services for the target user.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a financial data visualization management system and method based on big data analysis. Background Art

[0002] In recent years, with the continuous maturity and popularization of big data technology, big data analysis has become a key technology for solving the problem of massive data processing and analysis. Big data technology can help quickly process various types of data, explore the potential value behind the data, and provide important support for business decisions. With the development of the financial industry and the advancement of technology, the amount of financial data has shown an explosive growth trend, and data visualization is to present abstract data in a graphical and visual way, which helps users understand the data more intuitively and discover the relationship and rules between the data; therefore, in the financial field, data visualization is of great significance for monitoring market trends, analyzing investment portfolios, identifying risks, etc.

[0003] Traditional financial data visualization platforms often only provide simple data reports or charts for data statistics and analysis. Complex financial data relationships and trends require further in-depth analysis by professionals. However, some existing financial data visualization platforms have complex interfaces and numerous functions, so they may be more suitable for professional users. For non-professional users, the lack of friendly navigation and guidance makes it difficult for them to correctly understand and use the information provided by the platform. Summary of the invention

[0004] The purpose of the present invention is to provide a financial data visualization management system and method based on big data analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A financial data visualization management method based on big data analysis, characterized in that the method comprises the following steps:

[0007] Step S100. Obtain all user information and corresponding historical operation data from the financial data visualization platform, classify users on the financial data visualization platform into template users and target users by analyzing the user information and the corresponding historical operation data, and form a template user operation data set with the historical operation data corresponding to the template users;

[0008] Step S200. For each element in the template user operation data set, analyze according to each function of the financial data visualization platform, and extract features of the operation target to form an operation target feature vector; analyze based on the operation target feature vector, and divide the operation target into relevant operation targets and irrelevant operation targets according to the analysis results;

[0009] Step S300. Obtaining an operation target feature vector of a related operation target, and obtaining a related path of the related operation target by analyzing the operation target feature vector of the related operation target, thereby forming a related network diagram of the related operation target;

[0010] Step S400. Acquire the real-time user information and corresponding real-time operation data of the financial data visualization platform, and determine whether the real-time user is the target user by combining the real-time user information and the corresponding real-time operation data; when the determination result is the target user, provide intelligent navigation service for the real-time user.

[0011] Furthermore, step S100 includes the following contents:

[0012] S101. The user information includes registration information, user's access frequency, length of stay and common functions; the historical operation data includes the user's operation interface and operation path; combining the user information and the corresponding historical operation data, calculate each user's familiarity with the financial visualization platform, the specific calculation formula is:

[0013] ,

[0014] Among them, UD represents user familiarity, UF represents the number of commonly used functions, AP represents the average path length, ID represents the interface diversity index, C represents the commonly used function coefficient, P represents the operation path coefficient, and F represents the professional index, and the professional index is evaluated based on the registration information in the user information, such as the industry to which they belong, the financial certificates they have, work experience, etc.;

[0015] Among them, the interface diversity index represents the number of different operation interfaces on the financial visualization platform and the degree of difference between them. Therefore, the interface diversity index can reflect the functional distribution of the platform and the user's operation experience on the platform. The specific calculation formula of the interface diversity index is:

[0016] ,

[0017] Among them, N i represents the number of different operation interfaces on the financial visualization platform, f i represents the usage frequency of the i-th interface, a i represents the importance weight of the i-th interface;

[0018] The specific calculation formula of commonly used functional coefficients is: , where N c Represents the number of common functions of the financial visualization platform, N t It indicates the total number of functions, and the more commonly used functions there are, the more familiar users are with the financial visualization platform;

[0019] The specific calculation formula of the operation path coefficient is: , where L a represents the average path length of the financial visualization platform, L m It represents the maximum path length, and the shorter the average path length is, the more familiar the user may be with the operation process of the financial visualization platform;

[0020] S102. Obtain the familiarity UD of all users with the financial visualization platform, mark the users whose familiarity UD is greater than or equal to the familiarity threshold Q as template users, and mark the users whose familiarity UD is less than the familiarity threshold Q as target users; and obtain the historical operation data corresponding to all template users to form a template user operation data set B, and B={b1,b2,...,bk}, where b1 represents the historical operation data corresponding to the first template user, b2 represents the historical operation data corresponding to the second template user, and so on, bk represents the historical operation data corresponding to the kth template user, and each element in the template user operation data set B corresponds to unique user information.

[0021] Furthermore, step S200 includes the following contents:

[0022] S201. For each element in the template user operation data set, the operation path corresponding to each function of the financial data visualization platform is analyzed; the starting point and the end point of the operation path corresponding to each function are marked, and the end point of the operation path corresponding to a function is named as the operation target, and the starting point of the operation path corresponding to a function is named as the operation target starting point; the operation target of each element and the corresponding operation target information are obtained; the operation target information includes the operation target starting point and the operation target time period, and the starting point of the operation target time period is the timestamp of the operation target starting point, and the end point of the operation target time period is the timestamp of the operation target;

[0023] S202. Perform feature extraction and normalization processing on the operation target and the corresponding operation target information to form an operation target feature vector V t , and V t =[v1,v2,v3,v4] t, where v1 represents the starting point of the operation target, v2 represents the timestamp of the starting point of the operation target, v3 represents the operation target, and v4 represents the timestamp of the operation target; t represents the operation target number of an element in the template user operation data set, and each element in the template user operation data set includes several operation targets;

[0024] S203. Obtain the operation target feature vector of each element in the template user operation data set, and perform similarity calculation on the operation target feature vectors of an element, with the specific calculation formula being:

[0025] ,

[0026] Among them, V x represents the xth operation target feature vector, V y Represents the tth operation target feature vector; classifies the operation targets corresponding to the operation target feature vectors whose similarity is greater than or equal to the similarity threshold S0 as related operation targets, classifies the operation targets corresponding to the operation target feature vectors whose similarity is less than the similarity threshold S0 as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

[0027] Furthermore, step S300 includes the following contents:

[0028] S301. Obtain the operation target feature vectors of all relevant operation targets, obtain the operation target starting points of all operation targets, and extract the initial starting point corresponding to the initial operation interface of the financial visualization platform in combination with the operation interface in the historical operation data; the initial starting point refers to the operation target starting point of the first operation target that the user of the financial visualization platform starts to operate;

[0029] S302. Find the operation target directly related to the initial starting point according to the initial starting point, connect the initial starting point with the operation target directly related to the initial starting point, and obtain the relevant path of the relevant operation target, and the length of the relevant path is equal to the average similarity of the same operation target of different elements; traverse the operation target feature vector of the relevant operation target of each element in the template user operation data set to obtain the relevant paths of all relevant operation targets, thereby forming a relevant network diagram of the relevant operation targets.

[0030] Furthermore, step S400 includes the following contents:

[0031] S401. Acquire the real-time user information and corresponding real-time operation data of the financial data visualization platform, as well as the time interval T between the timestamp of the most recent operation of the operation interface of the current financial data visualization platform and the current time. When the time interval T is greater than the longest operation time interval T0, calculate the real-time user familiarity UD' according to the calculation formula of S101; compare the real-time user familiarity UD' with the familiarity threshold Q. If UD'≥Q, the current user is a template user and no intelligent navigation service is provided; if UD'<Q, the current user is a target user and go to S402;

[0032] S402. Obtain the operation target of the most recent operation as the pending operation target, and search in the relevant network diagram; if there is a pending operation target, output the relevant path of the pending operation target in the relevant network diagram, and arrange them in descending order according to the length of the relevant path;

[0033] If there is no pending operation target, the operation target starting points of the pending operation target and the irrelevant operation target will be searched. If there is no pending operation target at the operation target starting points of the irrelevant operation target, the current user will be reminded to perform the operation; if there is a pending operation target at the operation target starting points of the irrelevant operation target, the operation path corresponding to the irrelevant operation target will be output.

[0034] The above-mentioned intelligent navigation service specifically refers to outputting the operation path of the corresponding operation target to the target user.

[0035] A financial data visualization management system based on big data analysis, the system includes: a data acquisition and classification module, an operation data analysis module, a related path and network diagram construction module, a real-time user judgment module and an intelligent navigation service module;

[0036] The data acquisition and classification module obtains all user information and historical operation data from the financial data visualization platform, classifies users into template users and target users by analyzing the user information and historical operation data, and constructs a template user operation data set;

[0037] The operation data analysis module analyzes each function of the financial data visualization platform for each element in the template user operation data set, extracts the characteristics of the operation target, forms an operation target feature vector, and divides the operation target into relevant operation targets and irrelevant operation targets according to the analysis results;

[0038] The relevant path and network diagram construction module obtains the operation target feature vector of the relevant operation target, obtains the relevant path of the relevant operation target through analysis, and constructs the relevant network diagram of the relevant operation target;

[0039] The real-time user judgment module obtains the real-time user information and real-time operation data of the financial data visualization platform, combines the template user information and the operation target feature vector, and judges whether the real-time user is the target user;

[0040] The intelligent navigation service module provides intelligent navigation services for target users based on the real-time operation data and characteristics of target users.

[0041] Further, the data acquisition and classification module includes a data acquisition unit, a familiarity calculation unit, and a classification unit;

[0042] The data acquisition unit is responsible for collecting user information and historical operation data from the financial visualization platform; the familiarity calculation unit combines user information and historical operation data to calculate each user's familiarity with the financial visualization platform; the classification unit divides users into two categories: template users and target users according to the calculated familiarity, and also constructs the template user's historical operation data set into a template user operation data set.

[0043] Further, the operation data analysis module includes an operation target division unit, an operation target feature vector generation unit, and an operation target classification unit;

[0044] The operation target division unit analyzes each element in the template user operation data set, marks the starting point and end point of the operation path for each function of the financial data visualization platform, and names them as the operation target starting point and the operation target;

[0045] The operation target feature vector generating unit performs feature extraction and normalization processing on the operation target and its information to form an operation target feature vector;

[0046] The operation target classification unit obtains the operation target feature vector of each element in the template user operation data set, and performs pairwise similarity calculation on the operation target feature vectors of each element; classifies the operation targets with similarity greater than or equal to a threshold as related operation targets, classifies the operation targets with similarity less than the threshold as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

[0047] Further, the relevant path and network graph construction module includes an initial starting point extraction unit, a relevant path construction unit and a relevant network graph construction unit;

[0048] The initial starting point extraction unit extracts the initial starting point corresponding to the initial operation interface of the financial visualization platform in combination with the operation interface in the historical operation data; the related path construction unit finds the operation target directly related to it according to the initial starting point, connects the initial starting point with the directly related operation target, and forms a related path; the related network diagram construction unit traverses the operation target feature vector of the related operation target of each element in the template user operation data set, thereby forming a related network diagram of the related operation target.

[0049] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0050] By calculating the user's familiarity with the financial visualization platform, the users are divided into template users and target users. The historical operation data set of the template users constitutes the template user operation data set. The operation behavior and habits of the template users are deeply analyzed to provide a more effective reference for the subsequent intelligent navigation service. By marking the operation target and starting point, recording the operation target information in detail, feature extraction and normalization processing, similarity calculation and dividing the relevant and irrelevant operation targets, it helps to identify the user's key operation targets, thereby optimizing the user experience and improving the effect of data visualization. The feature vectors of the relevant operation targets are obtained, and the relevant paths are obtained through analysis to form a network diagram of the relevant operation targets. In this way, the correlation and path between user behaviors can be presented more intuitively, providing users with clearer data navigation and decision support. Using real-time user information and operation data, it is determined whether the user is a target user, and intelligent navigation services are provided for the target user. This real-time personalized service can help non-professional users find the required information and functions more quickly, improving user satisfaction and platform value. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 It is a schematic diagram of a module of a financial data visualization management system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1, the present invention provides a technical solution:

[0055] A financial data visualization management system based on big data analysis, the system includes: a data acquisition and classification module, an operation data analysis module, a related path and network diagram construction module, a real-time user judgment module and an intelligent navigation service module;

[0056] The data acquisition and classification module obtains all user information and historical operation data from the financial data visualization platform, classifies users into template users and target users by analyzing the user information and historical operation data, and constructs a template user operation data set;

[0057] The operation data analysis module analyzes each function of the financial data visualization platform for each element in the template user operation data set, extracts the characteristics of the operation target, forms an operation target feature vector, and divides the operation target into relevant operation targets and irrelevant operation targets according to the analysis results;

[0058] The relevant path and network diagram construction module obtains the operation target feature vector of the relevant operation target, obtains the relevant path of the relevant operation target through analysis, and constructs the relevant network diagram of the relevant operation target;

[0059] The real-time user judgment module obtains the real-time user information and real-time operation data of the financial data visualization platform, combines the template user information and the operation target feature vector, and judges whether the real-time user is the target user;

[0060] The intelligent navigation service module provides intelligent navigation services for target users based on the real-time operation data and characteristics of target users.

[0061] The data acquisition and classification module includes a data acquisition unit, a familiarity calculation unit and a classification unit;

[0062] The data acquisition unit is responsible for collecting user information and historical operation data from the financial visualization platform; the familiarity calculation unit combines user information and historical operation data to calculate each user's familiarity with the financial visualization platform; the classification unit divides users into two categories: template users and target users according to the calculated familiarity, and also constructs the template user's historical operation data set into a template user operation data set.

[0063] The operation data analysis module includes an operation target division unit, an operation target feature vector generation unit and an operation target classification unit;

[0064] The operation target division unit analyzes each element in the template user operation data set, marks the starting point and end point of the operation path for each function of the financial data visualization platform, and names them as the operation target starting point and the operation target;

[0065] The operation target feature vector generating unit performs feature extraction and normalization processing on the operation target and its information to form an operation target feature vector;

[0066] The operation target classification unit obtains the operation target feature vector of each element in the template user operation data set, and performs pairwise similarity calculation on the operation target feature vectors of each element; classifies the operation targets with similarity greater than or equal to a threshold as related operation targets, classifies the operation targets with similarity less than the threshold as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

[0067] The related path and network graph construction module includes an initial starting point extraction unit, a related path construction unit and a related network graph construction unit;

[0068] The initial starting point extraction unit extracts the initial starting point corresponding to the initial operation interface of the financial visualization platform in combination with the operation interface in the historical operation data; the related path construction unit finds the operation target directly related to it according to the initial starting point, connects the initial starting point with the directly related operation target, and forms a related path; the related network diagram construction unit traverses the operation target feature vector of the related operation target of each element in the template user operation data set, thereby forming a related network diagram of the related operation target.

[0069] A financial data visualization management method based on big data analysis, characterized in that the method comprises the following steps:

[0070] Step S100. Obtain all user information and corresponding historical operation data from the financial data visualization platform, classify users on the financial data visualization platform into template users and target users by analyzing the user information and the corresponding historical operation data, and form a template user operation data set with the historical operation data corresponding to the template users;

[0071] Step S200. For each element in the template user operation data set, analyze according to each function of the financial data visualization platform, and extract features of the operation target to form an operation target feature vector; analyze based on the operation target feature vector, and divide the operation target into relevant operation targets and irrelevant operation targets according to the analysis results;

[0072] Step S300. Obtaining an operation target feature vector of a related operation target, and obtaining a related path of the related operation target by analyzing the operation target feature vector of the related operation target, thereby forming a related network diagram of the related operation target;

[0073] Step S400. Acquire the real-time user information and corresponding real-time operation data of the financial data visualization platform, and determine whether the real-time user is the target user by combining the real-time user information and the corresponding real-time operation data; when the determination result is the target user, provide intelligent navigation service for the real-time user.

[0074] Step S100 includes the following contents:

[0075] S101. The user information includes registration information, user's access frequency, length of stay and common functions; the historical operation data includes the user's operation interface and operation path; combining the user information and the corresponding historical operation data, calculate each user's familiarity with the financial visualization platform, the specific calculation formula is:

[0076] ,

[0077] Among them, UD represents user familiarity, UF represents the number of commonly used functions, AP represents the average path length, ID represents the interface diversity index, C represents the commonly used function coefficient, P represents the operation path coefficient, and F represents the professional index, and the professional index is evaluated based on the registration information in the user information, such as the industry to which they belong, the financial certificates they have, and their work experience;

[0078] Among them, the interface diversity index represents the number of different operation interfaces on the financial visualization platform and the degree of difference between them. Therefore, the interface diversity index can reflect the functional distribution of the platform and the user's operation experience on the platform. The specific calculation formula of the interface diversity index is:

[0079] ,

[0080] Among them, N i represents the number of different operation interfaces on the financial visualization platform, f i represents the usage frequency of the i-th interface, a i represents the importance weight of the i-th interface;

[0081] The specific calculation formula of commonly used functional coefficients is: , where N c Represents the number of common functions of the financial visualization platform, N t It indicates the total number of functions, and the more commonly used functions there are, the more familiar users are with the financial visualization platform;

[0082] The specific calculation formula of the operation path coefficient is: , where L a represents the average path length of the financial visualization platform, L mIt represents the maximum path length, and the shorter the average path length is, the more familiar the user may be with the operation process of the financial visualization platform;

[0083] S102. Obtain the familiarity UD of all users with the financial visualization platform, mark the users whose familiarity UD is greater than or equal to the familiarity threshold Q as template users, and mark the users whose familiarity UD is less than the familiarity threshold Q as target users; and obtain the historical operation data corresponding to all template users to form a template user operation data set B, and B={b1,b2,...,bk}, where b1 represents the historical operation data corresponding to the first template user, b2 represents the historical operation data corresponding to the second template user, and so on, bk represents the historical operation data corresponding to the kth template user, and each element in the template user operation data set B corresponds to unique user information.

[0084] Step S200 includes the following contents:

[0085] S201. For each element in the template user operation data set, the operation path corresponding to each function of the financial data visualization platform is analyzed; the starting point and the end point of the operation path corresponding to each function are marked, and the end point of the operation path corresponding to a function is named as the operation target, and the starting point of the operation path corresponding to a function is named as the operation target starting point; the operation target of each element and the corresponding operation target information are obtained; the operation target information includes the operation target starting point and the operation target time period, and the starting point of the operation target time period is the timestamp of the operation target starting point, and the end point of the operation target time period is the timestamp of the operation target;

[0086] In this embodiment, it is assumed that a template user performs the following operations on the financial data visualization platform, as shown in Table 1:

[0087] User ID Operation target starting point Operation Target Operation target starting point timestamp 1 Log in Create a chart 2024-04-18，08:00:00 1 Create a chart View Chart 2024-04-18，08:10:00 1 View Chart Edit a chart 2024-04-18，08:15:00 1 Edit a chart Save the chart 2024-04-18，08:20:00

[0088] Table 1

[0089] Therefore, the user 1 has four operation goals. For example, if the operation goal is to create a chart, the operation target time period corresponding to the chart creation is: from 2024-04-18, 08:00:00 to 2024-04-18, 08:10:00;

[0090] S202. Perform feature extraction and normalization processing on the operation target and the corresponding operation target information to form an operation target feature vector V t , and V t =[v1,v2,v3,v4] t, where v1 represents the starting point of the operation target, v2 represents the timestamp of the starting point of the operation target, v3 represents the operation target, and v4 represents the timestamp of the operation target; t represents the operation target number of an element in the template user operation data set, and each element in the template user operation data set includes several operation targets;

[0091] S203. Obtain the operation target feature vector of each element in the template user operation data set, and perform similarity calculation on the operation target feature vectors of an element, with the specific calculation formula being:

[0092] ,

[0093] Among them, V x represents the xth operation target feature vector, V y Represents the tth operation target feature vector; classifies the operation targets corresponding to the operation target feature vectors whose similarity is greater than or equal to the similarity threshold S0 as related operation targets, classifies the operation targets corresponding to the operation target feature vectors whose similarity is less than the similarity threshold S0 as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

[0094] Step S300 includes the following contents:

[0095] S301. Obtain the operation target feature vectors of all relevant operation targets, obtain the operation target starting points of all operation targets, and extract the initial starting point corresponding to the initial operation interface of the financial visualization platform in combination with the operation interface in the historical operation data; the initial starting point refers to the operation target starting point of the first operation target that the user of the financial visualization platform starts to operate;

[0096] S302. Find the operation target directly related to the initial starting point according to the initial starting point, connect the initial starting point with the operation target directly related to the initial starting point, and obtain the relevant path of the relevant operation target, and the length of the relevant path is equal to the average similarity of the same operation target of different elements; traverse the operation target feature vector of the relevant operation target of each element in the template user operation data set to obtain the relevant paths of all relevant operation targets, thereby forming a relevant network diagram of the relevant operation targets.

[0097] Step S400 includes the following contents:

[0098] S401. Acquire the real-time user information and corresponding real-time operation data of the financial data visualization platform, as well as the time interval T between the timestamp of the most recent operation of the operation interface of the current financial data visualization platform and the current time. When the time interval T is greater than the longest operation time interval T0, calculate the real-time user familiarity UD' according to the calculation formula of S101; compare the real-time user familiarity UD' with the familiarity threshold Q. If UD'≥Q, the current user is a template user and no intelligent navigation service is provided; if UD'<Q, the current user is a target user and go to S402;

[0099] S402. Obtain the operation target of the most recent operation as the pending operation target, and search in the relevant network diagram; if there is a pending operation target, output the relevant path of the pending operation target in the relevant network diagram, and arrange them in descending order according to the length of the relevant path;

[0100] If there is no pending operation target, the operation target starting points of the pending operation target and the irrelevant operation target will be searched. If there is no pending operation target at the operation target starting points of the irrelevant operation target, the current user will be reminded to perform the operation; if there is a pending operation target at the operation target starting points of the irrelevant operation target, the operation path corresponding to the irrelevant operation target will be output.

[0101] The above-mentioned intelligent navigation service specifically refers to outputting the operation path of the corresponding operation target to the target user.

[0102] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0103] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A financial data visualization management method based on big data analysis, characterized by: The method comprises the following steps: Step S100. Obtain all user information and corresponding historical operation data from the financial data visualization platform, classify users on the financial data visualization platform into template users and target users by analyzing the user information and the corresponding historical operation data, and form a template user operation data set with the historical operation data corresponding to the template users; Step S200. For each element in the template user operation data set, analyze according to each function of the financial data visualization platform, and extract features of the operation target to form an operation target feature vector; analyze based on the operation target feature vector, and divide the operation target into relevant operation targets and irrelevant operation targets according to the analysis results; Step S300. Obtaining an operation target feature vector of a related operation target, and obtaining a related path of the related operation target by analyzing the operation target feature vector of the related operation target, thereby forming a related network diagram of the related operation target; Step S400. Acquire the real-time user information and the corresponding real-time operation data of the financial data visualization platform, and determine whether the real-time user is a target user by combining the real-time user information and the corresponding real-time operation data; if the determination result is that the real-time user is a target user, provide intelligent navigation services for the real-time user; The step S100 includes the following contents: S101. The user information includes registration information, user's access frequency, length of stay and common functions; the historical operation data includes the user's operation interface and operation path; combining the user information and the corresponding historical operation data, calculate each user's familiarity with the financial visualization platform, the specific calculation formula is: ， Among them, UD represents user familiarity, UF represents the number of commonly used functions, AP represents the average path length, ID represents the interface diversity index, C represents the commonly used function coefficient, P represents the operation path coefficient, and F represents the professional index; Among them, the specific calculation formula of the interface diversity index is: ， Among them, N i represents the number of different operation interfaces on the financial visualization platform, f i represents the usage frequency of the i-th interface, a i represents the importance weight of the i-th interface; The specific calculation formula of commonly used functional coefficients is: , where N c Represents the number of common functions of the financial visualization platform, N t It indicates the total number of functions, and the more commonly used functions there are, the more familiar users are with the financial visualization platform; The specific calculation formula of the operation path coefficient is: , where L a represents the average path length of the financial visualization platform, L m It represents the maximum path length, and the shorter the average path length is, the more familiar the user may be with the operation process of the financial visualization platform; S102. Obtain the familiarity UD of all users with the financial visualization platform, mark the users whose familiarity UD is greater than or equal to the familiarity threshold Q as template users, and mark the users whose familiarity UD is less than the familiarity threshold Q as target users; and obtain the historical operation data corresponding to all template users to form a template user operation data set B, and B={b1,b2,...,bk}, where b1 represents the historical operation data corresponding to the first template user, b2 represents the historical operation data corresponding to the second template user, and so on, bk represents the historical operation data corresponding to the kth template user, and each element in the template user operation data set B corresponds to unique user information.

2. The financial data visualization management method based on big data analysis according to claim 1 is characterized by: The step S200 includes the following contents: S201. For each element in the template user operation data set, the operation path corresponding to each function of the financial data visualization platform is analyzed; the starting point and the end point of the operation path corresponding to each function are marked, and the end point of the operation path corresponding to a function is named as the operation target, and the starting point of the operation path corresponding to a function is named as the operation target starting point; Obtaining the operation target and corresponding operation target information of each element; the operation target information includes the operation target starting point and the operation target time period, and the starting point of the operation target time period is the timestamp of the operation target starting point, and the end point of the operation target time period is the timestamp of the operation target; S202. Perform feature extraction and normalization processing on the operation target and the corresponding operation target information to form an operation target feature vector V t , and V t =[v1,v2,v3,v4] t , where v1 represents the starting point of the operation target, v2 represents the timestamp of the starting point of the operation target, v3 represents the operation target, and v4 represents the timestamp of the operation target; t represents the operation target number of an element in the template user operation data set, and each element in the template user operation data set includes several operation targets; S203. Obtain the operation target feature vector of each element in the template user operation data set, and perform similarity calculation on the operation target feature vectors of an element, with the specific calculation formula being: ， Among them, V x represents the xth operation target feature vector, V y Represents the tth operation target feature vector; classifies the operation targets corresponding to the operation target feature vectors whose similarity is greater than or equal to the similarity threshold S0 as related operation targets, classifies the operation targets corresponding to the operation target feature vectors whose similarity is less than the similarity threshold S0 as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

3. The financial data visualization management method based on big data analysis according to claim 1 is characterized by: The step S300 includes the following contents: S301. Obtaining the operation target feature vectors of all relevant operation targets, obtaining the operation target starting points of all operation targets, combining the operation interface in the historical operation data, and extracting the initial starting point corresponding to the initial operation interface of the financial visualization platform; The initial starting point refers to the operation target starting point of the first operation target that the user of the financial visualization platform starts to operate; S302. Find the operation target directly related to the initial starting point according to the initial starting point, connect the initial starting point with the operation target directly related to the initial starting point, and obtain the relevant path of the relevant operation target, and the length of the relevant path is equal to the average similarity of the same operation target of different elements; traverse the operation target feature vector of the relevant operation target of each element in the template user operation data set to obtain the relevant paths of all relevant operation targets, thereby forming a relevant network diagram of the relevant operation targets.

4. The method for visualizing financial data based on big data analysis according to claim 3 is characterized in that: The step S400 includes the following contents: S401. Acquire the real-time user information and corresponding real-time operation data of the financial data visualization platform, as well as the time interval T between the timestamp of the most recent operation of the operation interface of the current financial data visualization platform and the current time. When the time interval T is greater than the longest operation time interval T0, calculate the real-time user familiarity UD' according to the calculation formula of S101; compare the real-time user familiarity UD' with the familiarity threshold Q. If UD'≥Q, the current user is a template user and no intelligent navigation service is provided. If UD'<Q, the current user is the target user, and go to S402; S402. Obtain the operation target of the most recent operation as the pending operation target, and search in the relevant network diagram; if there is a pending operation target, output the relevant path of the pending operation target in the relevant network diagram, and arrange them in descending order according to the length of the relevant path; If there is no pending operation target, search the pending operation target and the operation target starting point of the irrelevant operation target, and if there is no pending operation target at the operation target starting point of the irrelevant operation target, remind the current user to perform the operation; If there is an operation target to be processed at the operation target starting point of the irrelevant operation target, output is performed according to the operation path corresponding to the irrelevant operation target.

5. A financial data visualization management system based on big data analysis, applied to a financial data visualization management method based on big data analysis as claimed in any one of claims 1 to 4, characterized in that: The system includes: a data acquisition and classification module, an operation data analysis module, a related path and network diagram construction module, a real-time user judgment module and an intelligent navigation service module; The data acquisition and classification module acquires all user information and historical operation data from the financial data visualization platform, classifies users into template users and target users by analyzing the user information and historical operation data, and constructs a template user operation data set; The operation data analysis module analyzes each function of the financial data visualization platform for each element in the template user operation data set, extracts the characteristics of the operation target, forms an operation target characteristic vector, and divides the operation target into relevant operation targets and irrelevant operation targets according to the analysis results; The relevant path and network diagram construction module obtains the operation target feature vector of the relevant operation target, obtains the relevant path of the relevant operation target through analysis, and constructs the relevant network diagram of the relevant operation target; The real-time user judgment module obtains the real-time user information and real-time operation data of the financial data visualization platform, and judges whether the real-time user is the target user by combining the template user information and the operation target feature vector; The intelligent navigation service module provides intelligent navigation services for target users based on real-time operation data and target user characteristics.

6. A financial data visualization management system based on big data analysis according to claim 5, characterized in that: The data acquisition and classification module includes a data acquisition unit, a familiarity calculation unit and a classification unit; The data acquisition unit is responsible for collecting user information and historical operation data from the financial visualization platform; the familiarity calculation unit combines the user information and historical operation data to calculate each user's familiarity with the financial visualization platform; The classification unit classifies users into two categories, template users and target users, according to the calculated familiarity, and also constructs the historical operation data set of the template users into the template user operation data set.

7. The financial data visualization management system based on big data analysis according to claim 5 is characterized by: The operation data analysis module includes an operation target division unit, an operation target feature vector generation unit and an operation target classification unit; The operation target division unit analyzes each element in the template user operation data set, marks the starting point and the end point of the operation path for each function of the financial data visualization platform, and names them as the operation target starting point and the operation target; The operation target feature vector generating unit performs feature extraction and normalization processing on the operation target and its information to form an operation target feature vector; The operation target classification unit obtains the operation target feature vector of each element in the template user operation data set, and performs pairwise similarity calculation on the operation target feature vectors of each element; classifies the operation targets whose similarity is greater than or equal to a threshold as related operation targets, classifies the operation targets whose similarity is less than the threshold as irrelevant operation targets, and records the operation paths corresponding to the irrelevant operation targets.

8. The financial data visualization management system based on big data analysis according to claim 5 is characterized by: The related path and network graph construction module includes an initial starting point extraction unit, a related path construction unit and a related network graph construction unit; The initial starting point extraction unit extracts the initial starting point corresponding to the initial operation interface of the financial visualization platform in combination with the operation interface in the historical operation data; The related path construction unit finds an operation target directly related to the initial starting point according to the initial starting point, connects the initial starting point with the directly related operation target, and forms a related path; The related network graph construction unit traverses the operation target feature vector of the related operation target of each element in the template user operation data set, thereby forming a related network graph of the related operation targets.

Images