Financial analysis visualization method and device based on user portrait and storage medium

Abstract

The invention provides a financial analysis visualization method and device based on a user portrait and a storage medium, and belongs to the technical field of computers. The method comprises the steps of inputting financial index data of a user into a constructed user portrait prediction model in response to a display request of a client, and generating a user portrait; obtaining an initial financial analysis habit of the industry to which the user belongs from the user portrait, and taking the financial analysis habit as a financial analysis habit of the user; and sending the financial index data of the user to the client, so that the client performs componentization processing on the financial index data of the user according to the financial analysis habit of the user and displays the financial index data after componentization processing. Through combination of visualization and artificial intelligence-based user portrait generation, different visualization requirements of different users for financial index analysis are met differently, the financial analysis efficiency and the user experience are improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and specifically to a financial analysis visualization method based on user portraits, a financial analysis visualization device based on user portraits, a computer device, a machine-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of the modern business environment, more and more companies hope to demonstrate their financial status and operating capabilities through financial statement data, and thereby gain the trust and support of financial institutions and investors. Therefore, within the prescribed time period each year, a large number of companies' financial statement data will be presented to financial institutions, which has brought certain pressure and challenges to the credit approval departments of financial institutions. Traditional credit approval mainly relies on a large number of manual and professional personnel to analyze and warn various financial indicators in financial statements, which not only consumes a lot of manpower and material resources, but also has a large amount of repetitive work and lacks user experience. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a financial analysis visualization method based on user portraits, a financial analysis visualization device based on user portraits, a computer device, a machine-readable storage medium and a computer program product, so as to overcome the technical problems of low efficiency, high labor cost and poor user experience existing in the prior art financial analysis methods relying on manual labor.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a financial analysis visualization method based on user portraits, which is applied to a server, and the method includes:

[0005] In response to a display request from a client, the user's financial indicator data is input into a constructed user portrait prediction model to generate a user portrait, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier;

[0006] Obtaining the initial financial analysis habits of the industry to which the user belongs from the user portrait, and using the initial financial analysis habits as the financial analysis habits of the user;

[0007] The user's financial indicator data is sent to the client, so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data.

[0008] In a specific embodiment of the present application, the method further includes:

[0009] Record the user's operating behaviors on the interface and identify changes in financial analysis habits in the operating behaviors;

[0010] The financial analysis habit change is used to update the user's financial analysis habit, so that when responding to the next display request of the client, the client can componentize the user's financial indicator data based on the updated financial analysis habit; and / or; the number of occurrences of the same financial analysis habit change of users in the same industry is accumulated, and if the accumulated number reaches a first threshold, the financial analysis habit change is used to update the initial financial analysis habit of the industry to which the user belongs, so that when responding to the next display request of the client, the updated financial analysis habit of the industry to which the user belongs is used as the user's financial analysis habit.

[0011] In a specific embodiment of the present application, the sending of the user's financial indicator data to the client so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data includes:

[0012] The user's financial indicator data is sent to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits, and load the financial indicator data in the initial interface view, and monitor the user's operation behavior in the interface to determine whether the interface view has changed. If the interface view has changed, the financial indicator data newly entering the interface view will be loaded into the interface view.

[0013] In a specific embodiment of the present application, the user portrait prediction model is obtained after training and optimizing the parameters of the initial classifier, including:

[0014] Collect financial statement data from users in different industries;

[0015] Extract financial indicator data from financial statement data and use the financial indicator data to construct training samples;

[0016] Use the training samples to train the initial classifier and optimize its parameters to obtain a user portrait prediction model;

[0017] Among them, the classifier includes a feature extraction network and a classification network. The feature extraction network is used to extract financial analysis habit features in financial indicator data, and the classification network is used to classify the extracted financial analysis habit features and then output a user portrait corresponding to the financial indicator data. The user portrait includes the financial analysis habits of the industry to which the user belongs.

[0018] In a specific embodiment of the present application, the financial analysis habits include the display status, display position and chart type of financial indicators.

[0019] In a specific embodiment of the present application, the financial analysis habit characteristics include display status characteristics of financial indicators, display position characteristics of financial indicators, and chart type characteristics of financial indicators.

[0020] A second aspect of the present application provides a financial analysis visualization device based on user portraits, comprising:

[0021] A user portrait generation module, which is used to respond to a display request from a client, input the user's financial indicator data into a constructed user portrait prediction model, and generate a user portrait, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier;

[0022] A financial analysis habit determination module, used to obtain the initial financial analysis habit of the industry to which the user belongs from the user portrait, and use the financial analysis habit as the financial analysis habit of the user;

[0023] The visualization module is used to send the user's financial indicator data to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits and display the componentized financial indicator data.

[0024] A third aspect of the present application provides a computer device, including:

[0025] a memory configured to store instructions; and

[0026] The processor is configured to call the instructions from the memory and implement the user portrait-based financial analysis visualization method according to the first aspect of the present application when executing the instructions.

[0027] The fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the user portrait-based financial analysis visualization method according to the first aspect of the present application.

[0028] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the financial analysis visualization method based on user portraits according to the first aspect of the present application.

[0029] In the above technical solution, based on the technical concept of combining artificial intelligence with visualization, after receiving the display request initiated by the client, the pre-built user portrait prediction model is used to identify and classify the key features of the current user's financial indicator data to generate a user portrait, and the initial financial analysis habits of the user's industry are obtained from the user portrait, and the financial analysis habits are used as the user's financial analysis habits. Then, the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data in a componentized manner, that is, it differentially meets the different visualization needs of different users for financial indicator analysis, avoids manual analysis of financial indicators, thereby improving the efficiency of financial analysis, reducing labor costs and improving user experience.

[0030] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0032] Figure 1 A schematic diagram of an application environment of a financial analysis visualization method based on user portraits according to an embodiment of the present application is schematically shown;

[0033] Figure 2 A first flow chart of a user portrait-based financial analysis visualization method according to an embodiment of the present application is schematically shown;

[0034] Figure 3 A schematic diagram of the process of constructing a user portrait prediction model according to an embodiment of the present application is schematically shown;

[0035] Figure 4 A schematic diagram of the process of obtaining financial indicator data by network downloading according to an embodiment of the present application is shown;

[0036] Figure 5 A second flow chart of the user portrait-based financial analysis visualization method according to an embodiment of the present application is schematically shown;

[0037] Figure 6 A third flow chart of the user portrait-based financial analysis visualization method according to an embodiment of the present application is schematically shown;

[0038] Figure 7 The flowchart of the user portrait-based financial analysis visualization method in a specific application example is schematically shown;

[0039] Figure 8 The structure block diagram of the financial analysis visualization device based on user portrait according to an embodiment of the present application is schematically shown;

[0040] Fig. 9 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown.

[0041] Description of Reference Numerals

[0042] In the figure: 102, client; 104, server; 400, financial analysis visualization device based on user portrait; 410, user portrait generation module; 420, financial analysis habit determination module; 430, visualization module. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0044] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0045] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0046] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In addition, it should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0047] The technical terms involved in this application are explained as follows:

[0048] Financial indicators: usually refer to a series of quantitative values ​​in financial statements, which objectively reflect the business capabilities and financial status of the enterprise;

[0049] Financial analysis: A more comprehensive and in-depth interpretation of the various financial indicators presented in the financial statements is required to help third parties better evaluate the company's financial health, profitability, and market competitiveness;

[0050] User portrait: The full name of this tool is Credit Finance. It is a market research tool that creates fictitious user roles based on real data and analysis strategies. It helps companies shift from macro data analysis to more specific and personalized market and user understanding, and provides users with more personalized services.

[0051] Visualization: The technology of converting data into graphics or images is widely used in business intelligence, scientific research and other fields. This technology makes data more intuitive and easy to understand.

[0052] The financial analysis visualization method based on user portrait provided in this application can be applied to Figure 1 In the application environment shown, the client 102 communicates with the server 104 through a network. The client 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0053] Figure 2 The first flow chart of the user portrait-based financial analysis visualization method according to the embodiment of the present application is schematically shown. Figure 2 As shown, in one embodiment of the present application, a financial analysis visualization method based on user portrait is provided. This embodiment mainly applies this method to the above Figure 1 Taking the server 104 in FIG. 1 as an example, the following steps may be included:

[0054] Step 202: In response to the display request of the client, the user's financial indicator data is input into the constructed user portrait prediction model to generate a user portrait. The user portrait prediction model is obtained by training and optimizing the parameters of the initial classifier.

[0055] It should be understood that the classifier can be an artificial intelligence model based on a machine learning classification algorithm. The machine learning classification algorithm can be logistic regression, support vector machine, decision tree, random forest, naive Bayes and neural network, etc. This application does not specifically limit the machine learning classification algorithm used.

[0056] Step 204, obtaining the initial financial analysis habits of the industry to which the user belongs from the user portrait generated by the user portrait prediction model, and using the financial analysis habits as the financial analysis habits of the user.

[0057] In this application, financial analysis habits refer to the user's habits of analyzing financial indicators. Financial analysis habits include which financial indicators need to be displayed in the financial analysis results, which financial indicators do not need to be displayed in the financial analysis results, the display positions of each financial indicator that needs to be displayed in the financial analysis results, and the specific chart types used to display each financial indicator that needs to be displayed in the financial analysis results. Chart types include but are not limited to bar charts, line charts, pie charts, scatter plots, radar charts, maps, etc.

[0058] It is important to understand that the user portrait includes the initial financial analysis habits of the industry to which the user belongs.

[0059] Step 206 : sending the user's financial indicator data to the client, so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data.

[0060] In this application, the componentization described in step 206 refers to the componentization processing for realizing data visualization. In a common embodiment, the componentization processing of data generally includes the following steps: determining the type of data, data volume, data dimension, etc. to be displayed; obtaining the data to be visualized; cleaning, preprocessing and converting the data to ensure the quality and consistency of the data; selecting the appropriate data structure and storage method to store the data according to the requirements; determining the type and style of visualization according to the requirements and data characteristics; selecting the appropriate visualization component, such as charts, etc.; formulating the layout and interaction method of the component; and writing code to bind and interact the data with the component.

[0061] In this application, the user's financial analysis habits are defined as the requirements for componentized processing, and the user's financial indicator data is componentized by referring to the processing process in the above-mentioned ordinary embodiment. This embodiment does not describe this part in detail.

[0062] As in the above embodiment, in order to meet the different personalized needs of users in different industries for financial analysis results, a user portrait prediction model is first constructed, persisted and loaded onto the server. The user portrait prediction model is obtained by training the initial classifier and optimizing the parameters. It can be seen that the classifier based on the machine learning classification algorithm can extract features and classify the input data. The user portrait prediction model uses the user's financial indicator data as input data and the user portrait as output data, and the user portrait includes the initial financial analysis habits of the industry to which the user belongs. It can be seen that the features extracted by the feature extraction network in the user portrait prediction model are features that can characterize the financial analysis habits of the industry to which the user belongs. User portraits of different categories correspond to different industry types or one category of user portraits corresponds to multiple industry types. Then, when responding to the display request of the client, the constructed user portrait prediction model is used to predict the user portrait of the current user. Finally, the client performs component processing on the user's financial indicator data based on the financial analysis habits in the user portrait and displays the componentized financial indicator data, so that the financial indicator analysis results displayed on the client interface meet the financial indicator analysis needs of the industry to which the user belongs. In a comparative embodiment, in order to visualize the results of financial analysis on the client side, the financial indicators are first analyzed one by one, and then the user selects and judges according to his or her own experience. After selecting and judging the financial indicators, a default template is used for visualization. This method cannot perform macro analysis of financial indicators, does not support the construction of user portraits, lacks diversified user experience and interactivity, and has low financial analysis efficiency. Based on this, the above embodiment of the present application abandons the traditional manual analysis of financial indicators, thereby improving the efficiency of financial analysis, reducing labor costs, and improving user experience.

[0063] In a specific embodiment of the present application, the user portrait prediction model is obtained after training and optimizing the parameters of the initial classifier, which may include the following steps:

[0064] Collect financial statement data from users in different industries;

[0065] Extract financial indicator data from financial statement data, and use the extracted financial indicator data to construct training samples;

[0066] Use the training samples to train the initial classifier and optimize its parameters to obtain a user portrait prediction model;

[0067] Among them, the classifier includes a feature extraction network and a classification network. The feature extraction network is used to extract the financial analysis habit features in the financial indicator data, and the classification network is used to classify the extracted financial analysis habit features and then output the user portrait corresponding to the financial indicator data. The user portrait includes the financial analysis habits of the industry to which the user belongs.

[0068] For example, the data source required for building a user profile prediction model can be collected by collecting business data and downloading financial statement data from the network. Accordingly, in a specific application, such as Figure 3 As shown, the process of building a user portrait prediction model may include the following steps:

[0069] Step A1, data collection: Collect financial statement data of users in different industries through internal channels, web crawlers, etc.

[0070] The data sources required for building the user portrait prediction model mainly come from business data and network downloads. Among them, business data is mainly obtained through internal channels, has the characteristics of wide distribution, and has a very deep relationship with users. Network downloads refer to downloading open source data sets from public websites on the Internet, or writing crawler codes to crawl data from target addresses, thereby quickly obtaining a large amount of financial statement data, saving a lot of time and energy spent on manual data collection. Figure 4 As shown, the process of obtaining financial indicator data through network downloading may include the following steps:

[0071] Step S1, defining a target website with an open source data set and a target URL for crawling financial statement data;

[0072] Step S2, using the Get network request library to obtain web page content;

[0073] Step S3, if the request is successful, store the response content into the webpage variable and execute S4, otherwise record the error information and jump to S7;

[0074] Step S4, creating a parser instance, and using the HTML parsing library to parse the web page;

[0075] Step S5, locating the data and extracting the required financial indicator data according to the structure of the financial statement data;

[0076] Step S6, storing the extracted financial indicator data into a CSV file, and closing the CSV file after completion;

[0077] Step S7, end the program.

[0078] Step A2, data preprocessing: Use the collected financial indicator data to construct training samples and test samples, clean the training samples and test samples, and process missing values ​​and outliers.

[0079] Step A3, initializing the classifier: split the training sample into a feature set and a label set, and initialize the classifier. The classifier is used to extract the key features of the user's financial indicator data as input data, classify the key features, and then generate a user profile containing the initial financial analysis habits of the industry to which the user belongs. It can be seen that the key features are features that can characterize financial analysis habits, that is, the financial analysis habit features described in the above embodiment.

[0080] Step A4, model training and parameter optimization: Use training samples to train the initial classifier, and use test samples to evaluate the performance of the classifier. According to the performance evaluation results, optimize the hyperparameters in the classifier until the performance of the classifier meets the preset requirements, and obtain the final user profile prediction model.

[0081] In a specific embodiment of the present application, the financial analysis habit includes the display status, display position and chart type of the financial indicator. The display status of the financial indicator refers to whether the financial indicator is displayed, the display position of the financial indicator refers to the display position of the financial indicator on the display interface, and involves the display layout and interaction mode between other financial indicators. The chart types of financial indicators include but are not limited to bar charts, line charts, pie charts, scatter plots, radar charts, maps, etc.

[0082] In a specific embodiment of the present application, the financial analysis habit features include display status features of financial indicators, display position features of financial indicators, and chart type features of financial indicators.

[0083] Figure 5 The second flow chart of the user portrait-based financial analysis visualization method according to an embodiment of the present application is schematically shown. Figure 5 As shown, in an embodiment of the present application, a financial analysis visualization method based on user portrait is provided. Different from the above embodiments, after step 206, the following steps are further included:

[0084] Step 208 , when the user is editing, the user's operation behavior on the interface is recorded, and changes in the financial analysis habits in the user's operation behavior are identified.

[0085] Step 210, using the identified change in the user's operating behavior, the user's financial analysis habit is updated, so that when responding to the next display request from the client, the client performs component processing on the user's financial indicator data according to the updated financial analysis habit;

[0086] and / or;

[0087] The number of occurrences of the same financial analysis habit changes of users in the same industry is accumulated. If the accumulated number reaches a first threshold, the financial analysis habit changes are used to update the initial financial analysis habits of the industry to which the user belongs, so that when responding to the next display request from the client, the updated financial analysis habits of the industry to which the user belongs are used as the user's financial analysis habits.

[0088] It should be understood that the user portraits generated by the user portrait prediction model for users in the same industry are the same. Based on this, the financial indicator data of each user can be used to identify whether these users are from the same industry.

[0089] In the present application, the user's operation behavior on the interface may be mouse click behavior, keyboard input behavior, modification behavior of interface elements, etc. These operation behaviors may involve changes in financial analysis habits. Changes in financial analysis habits refer to operation behaviors that cause changes in financial analysis habits. For example: the user adds a new financial indicator to the interface, the user moves the position of the financial indicator on the interface, the user changes the chart type of the financial indicator on the interface from a line chart to a bar chart, the user changes the statistical analysis period of the financial indicator on the interface from 10 years to 5 years, etc. In addition, when accumulating the number of occurrences of the same financial analysis habit changes of users in the same industry, the number of occurrences of the same financial analysis habit changes of a single user can be accumulated, or the number of occurrences of the same financial analysis habit changes of multiple users in the same industry can be accumulated.

[0090] If it is identified that there is a financial analysis habit change A in the current user's operation behavior, and the cumulative number of occurrences of the financial analysis habit change B of each user in the industry to which the user belongs reaches a first threshold, then when the current user initiates the next display request through the client, the new financial analysis habit obtained by updating the financial analysis habit of the industry to which the current user belongs using the financial analysis habit change B is first used as the financial analysis habit of the current user. Then, the new financial analysis habit obtained by updating the financial analysis habit of the current user using the financial analysis habit change A is used as the requirement definition for componentized processing, and the financial indicator data of the current user is componentized, so that the financial analysis results displayed by the client are adjusted according to the financial analysis habit changes A and B compared to the previous display request, that is, the user portrait presented on the interface is the iteratively updated user portrait.

[0091] As in the above embodiment, the user's financial analysis habits and / or the industry's financial analysis habits are iteratively updated by recording the user's operating behavior in the interface, thereby realizing iterative updates of user portraits. In a comparative embodiment, by pre-customizing the financial analysis visualization templates required by different users in the server, the user then selects different financial analysis visualization templates on the client according to personal needs. This method is not very adaptable, and it is difficult to implement visualization styles outside the template. In addition, if the existing financial analysis visualization template needs to be updated, the server technicians are required to optimize the algorithm. The algorithm optimization process often requires a long wait time, and the process is also more complicated. It can be seen that by recording the user's operating behavior, the automatic iterative update of the user portrait is realized, the efficiency of financial analysis visualization is higher, the personalized needs of users are quickly matched, and the user experience is improved.

[0092] In a specific embodiment of the present application, step 206, sending the user's financial indicator data to the client, so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data, specifically includes the following steps:

[0093] The user's financial indicator data is sent to the client so that the client can componentize the user's financial indicator data according to the user's financial analysis habits, and load the financial indicator data in the initial interface view, and monitor the user's operation behavior in the interface to determine whether the interface view has changed. If the interface view has changed, the financial indicator data newly entering the interface view will be loaded into the interface view.

[0094] As shown in the above embodiment, lazy loading technology is introduced. First, only the financial indicator data in the initial interface view is loaded, and then new financial indicators are loaded into the interface view as needed according to the user's operation behavior in the interface. While supporting the visualization of multiple financial indicator data or all financial indicator data in the same view, it avoids the client from freezing or crashing due to loading too much componentized financial indicator data at one time, takes into account the user experience, and saves the performance loss of the client.

[0095] In a specific embodiment of the present application, the client displays the componentized financial indicator data on a browser page, the componentized financial indicator data is Json data, and the client displays the componentized financial indicator data, specifically including the following steps:

[0096] Configure the componentized financial indicator data to the option object of the client's Echarts instance, render it to the Echarts chart, and complete the data loading and display.

[0097] Figure 6 The third flow chart of the financial analysis visualization method based on user images according to an embodiment of the present application is schematically shown. Figure 6 As shown, in one embodiment of the present application, a financial analysis visualization method based on user portrait is provided, which is applied to Figure 1 The system composed of the server 104 and the client 102 shown may include the following steps:

[0098] Step 302: In response to the display request of the client 102, the server 104 inputs the user's financial indicator data into the constructed user portrait prediction model to generate a user portrait. The user portrait prediction model is obtained by training and optimizing the parameters of the initial classifier.

[0099] In step 304, the server 104 obtains the initial financial analysis habits of the industry to which the user belongs from the user portrait generated by the user portrait prediction model, and uses the financial analysis habits as the financial analysis habits of the user.

[0100] Step 306 : the server 104 sends the user's financial indicator data to the client 102 .

[0101] Step 308 , the client 102 performs component processing on the user's financial indicator data according to the user's financial analysis habits.

[0102] In step 310, the client 102 displays the componentized financial indicator data.

[0103] Step 312: When the user edits on the client 102, the server 104 records the user's operation behavior and iteratively updates the user portrait.

[0104] The following content is a specific application of the above embodiment. Figure 7 As shown, in this specific application, the financial analysis visualization method based on user images includes the following steps:

[0105] Step B1, the server 104 inputs the user's financial indicator data into the constructed user portrait prediction model to generate a user portrait;

[0106] Step B2, the server 104 obtains the initial financial analysis habit of the industry to which the user belongs from the user portrait generated by the user portrait prediction model, and uses the financial analysis habit as the financial analysis habit of the user;

[0107] Step B3, the client 102 obtains the user's financial indicator data from the server 104 through an Ajax request, and performs component processing on the user's financial indicator data according to the user's financial analysis habits obtained in step B2 to obtain Json format data;

[0108] Step B4, the client 102 determines whether there is an Echarts instance for the DOM element corresponding to the DOM node number. If there is an Echarts instance, execute step B5; otherwise, create an Echarts instance corresponding to the DOM element, and then execute step B5;

[0109] Step B5, construct an Option object, configure the Json format data obtained in step B3 into the Option object, render it to the Ecahrts chart, and perform lazy loading display on the browser page;

[0110] Step B6: When the user edits on the client, the server records the user's operation behavior and iteratively updates the user portrait.

[0111] Figure 1 to Figure 7 All of them are flow charts of the financial analysis visualization method based on user portraits. It should be understood that although Figure 1 to Figure 7 The steps in each flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 to Figure 7 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequentially, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0112] In one embodiment, Figure 8 In the embodiment, a financial analysis visualization device 400 based on user portrait is provided, comprising a user portrait generation module, a financial analysis habit determination module and a visualization module, wherein:

[0113] A user portrait generation module 410 is used to generate a user portrait by inputting the user's financial indicator data into a constructed user portrait prediction model in response to a display request from a client, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier;

[0114] A financial analysis habit determination module 420 is used to obtain the initial financial analysis habit of the industry to which the user belongs from the user portrait, and use the financial analysis habit as the financial analysis habit of the user;

[0115] The visualization module 430 is used to send the user's financial indicator data to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits and display the componentized financial indicator data.

[0116] In a specific embodiment of the present application, the device further includes:

[0117] An operation behavior recording module is used to record the user's operation behavior on the interface and identify changes in financial analysis habits in the operation behavior;

[0118] A financial analysis habit updating module is used to update the financial analysis habits of the user using the changes in the financial analysis habits, so that when responding to the next display request of the client, the client performs componentized processing on the user's financial indicator data based on the updated financial analysis habits; and / or; accumulate the number of occurrences of the same financial analysis habit changes of users in the same industry, and if the accumulated number reaches a first threshold, use the changes in the financial analysis habits to update the initial financial analysis habits of the industry to which the user belongs, so that when responding to the next display request of the client, the updated financial analysis habits of the industry to which the user belongs are used as the user's financial analysis habits.

[0119] In a specific embodiment of the present application, the sending of the user's financial indicator data to the client so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data includes:

[0120] The user's financial indicator data is sent to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits, and load the financial indicator data in the initial interface view, and monitor the user's operation behavior in the interface to determine whether the interface view has changed. If the interface view has changed, the financial indicator data newly entering the interface view will be loaded into the interface view.

[0121] In a specific embodiment of the present application, the user portrait prediction model is obtained after training and optimizing the parameters of the initial classifier, including:

[0122] Collect financial statement data from users in different industries;

[0123] Extract financial indicator data from financial statement data and use the financial indicator data to construct training samples;

[0124] Use the training samples to train the initial classifier and optimize its parameters to obtain a user portrait prediction model;

[0125] Among them, the classifier includes a feature extraction network and a classification network. The feature extraction network is used to extract financial analysis habit features in financial indicator data, and the classification network is used to classify the extracted financial analysis habit features and then output a user portrait corresponding to the financial indicator data. The user portrait includes the financial analysis habits of the industry to which the user belongs.

[0126] In a specific embodiment of the present application, the financial analysis habits include the display status, display position and chart type of financial indicators.

[0127] In a specific embodiment of the present application, the financial analysis habit characteristics include display status characteristics of financial indicators, display position characteristics of financial indicators, and chart type characteristics of financial indicators.

[0128] The user portrait-based financial analysis visualization device 400 includes a processor and a memory. The user portrait generation module, financial analysis habit determination module, and visualization module are all stored in the memory as program units, and the processor executes the program modules stored in the memory to implement corresponding functions.

[0129] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the financial analysis visualization method based on user portraits can be realized by adjusting kernel parameters.

[0130] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0131] An embodiment of the present application provides a machine-readable storage medium on which a program is stored. When the program is executed by a processor, the above-mentioned financial analysis visualization method based on user portrait is implemented.

[0132] An embodiment of the present application provides a processor, which is used to run a program, wherein the program executes the above-mentioned financial analysis visualization method based on user portrait when running.

[0133] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a financial analysis visualization method based on user portraits is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0134] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] In one embodiment, the user portrait-based financial analysis visualization device provided by the present application can be implemented in the form of a computer program. The computer program can be used in Fig. 9 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules constituting the financial analysis visualization device based on user portraits, for example, Figure 8 The user portrait generation module 410, the financial analysis habit determination module 420 and the visualization module 430 are shown. The computer program composed of various program modules enables the processor to execute the steps of the financial analysis visualization method based on user portraits in various embodiments of the present application described in this specification.

[0136] Fig. 9 The computer device shown can be Figure 8 The user portrait generation module 410 in the user portrait-based financial analysis visualization device shown executes step 202 , the computer device may execute step 204 through the financial analysis habit determination module 420 , and the computer device may execute step 206 through the visualization module 430 .

[0137] The present application also provides a user image-based financial analysis visualization system, comprising the above-mentioned computer device, encapsulation module, introduction module and rendering module, wherein:

[0138] The encapsulation module is used to encapsulate the Vue files of various Echarts instances. By creating an Echarts instance, the financial indicator data is rendered into the Echarts instance;

[0139] Import module, used to install various dependency packages of Echarts instance, and import Echarts chart library and related themes on demand or globally in the entry file;

[0140] The rendering module is used to monitor the Echarts instance. If a new financial indicator is found to be added, the Echarts instance will be recreated and rendered. If only the financial indicator data to be rendered has changed, only the changed financial indicator data needs to be loaded, and there is no need to create the Echarts instance again. For financial indicators that are not in the browser page view, they will not be loaded and rendered.

[0141] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the following method steps:

[0142] In response to a display request from a client, the user's financial indicator data is input into a constructed user portrait prediction model to generate a user portrait, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier;

[0143] Obtaining the initial financial analysis habits of the industry to which the user belongs from the user portrait, and using the initial financial analysis habits as the financial analysis habits of the user;

[0144] The user's financial indicator data is sent to the client, so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data.

[0145] In one embodiment, the program further comprises the following steps:

[0146] Record the user's operating behaviors on the interface and identify changes in financial analysis habits in the operating behaviors;

[0147] The financial analysis habit change is used to update the user's financial analysis habit, so that when responding to the next display request of the client, the client can componentize the user's financial indicator data based on the updated financial analysis habit; and / or; the number of occurrences of the same financial analysis habit change of users in the same industry is accumulated, and if the accumulated number reaches a first threshold, the financial analysis habit change is used to update the initial financial analysis habit of the industry to which the user belongs, so that when responding to the next display request of the client, the updated financial analysis habit of the industry to which the user belongs is used as the user's financial analysis habit.

[0148] In one embodiment, the sending of the user's financial indicator data to the client so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data includes:

[0149] The user's financial indicator data is sent to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits, and load the financial indicator data in the initial interface view, and monitor the user's operation behavior in the interface to determine whether the interface view has changed. If the interface view has changed, the financial indicator data newly entering the interface view will be loaded into the interface view.

[0150] In one embodiment, the user portrait prediction model is obtained after training and optimizing the parameters of the initial classifier, including:

[0151] Collect financial statement data from users in different industries;

[0152] Extract financial indicator data from financial statement data and use the financial indicator data to construct training samples;

[0153] Use the training samples to train the initial classifier and optimize its parameters to obtain a user portrait prediction model;

[0154] Among them, the classifier includes a feature extraction network and a classification network. The feature extraction network is used to extract financial analysis habit features in financial indicator data, and the classification network is used to classify the extracted financial analysis habit features and then output a user portrait corresponding to the financial indicator data. The user portrait includes the financial analysis habits of the industry to which the user belongs.

[0155] In one embodiment, the financial analysis habits include display status, display position and chart type of financial indicators.

[0156] In one embodiment, the financial analysis habit features include display status features of financial indicators, display position features of financial indicators, and chart type features of financial indicators.

[0157] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0158] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0161] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0162] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0163] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0165] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A financial analysis visualization method based on user portrait, characterized in that: Applied to a server, the method comprises: In response to a display request from a client, the user's financial indicator data is input into a constructed user portrait prediction model to generate a user portrait, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier; Obtaining the initial financial analysis habits of the industry to which the user belongs from the user portrait, and using the initial financial analysis habits as the financial analysis habits of the user; The user's financial indicator data is sent to the client, so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data.

2. The method according to claim 1, characterized in that Also includes: Record the user's operating behaviors on the interface and identify changes in financial analysis habits in the operating behaviors; The financial analysis habit change is used to update the user's financial analysis habit, so that when responding to the next display request of the client, the client can componentize the user's financial indicator data based on the updated financial analysis habit; and / or; the number of occurrences of the same financial analysis habit change of users in the same industry is accumulated, and if the accumulated number reaches a first threshold, the financial analysis habit change is used to update the initial financial analysis habit of the industry to which the user belongs, so that when responding to the next display request of the client, the updated financial analysis habit of the industry to which the user belongs is used as the user's financial analysis habit.

3. The method according to claim 1, characterized in that The sending of the user's financial indicator data to the client so that the client performs component processing on the user's financial indicator data according to the user's financial analysis habits and displays the componentized financial indicator data includes: The user's financial indicator data is sent to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits, and load the financial indicator data in the initial interface view, and monitor the user's operation behavior in the interface to determine whether the interface view has changed. If the interface view has changed, the financial indicator data newly entering the interface view will be loaded into the interface view.

4. The method according to claim 1, characterized in that After training and optimizing the parameters of the initial classifier, the user portrait prediction model is obtained, including: Collect financial statement data from users in different industries; Extract financial indicator data from financial statement data and use the financial indicator data to construct training samples; Use the training samples to train the initial classifier and optimize its parameters to obtain a user portrait prediction model; Among them, the classifier includes a feature extraction network and a classification network. The feature extraction network is used to extract financial analysis habit features in financial indicator data, and the classification network is used to classify the extracted financial analysis habit features and then output a user portrait corresponding to the financial indicator data. The user portrait includes the financial analysis habits of the industry to which the user belongs.

5. The method according to claim 1, characterized in that The financial analysis habits include the display status, display position and chart type of financial indicators.

6. The method according to claim 4, characterized in that The financial analysis habit characteristics include display status characteristics of financial indicators, display position characteristics of financial indicators, and chart type characteristics of financial indicators.

7. A financial analysis visualization device based on user portrait, characterized in that: include: A user portrait generation module, which is used to respond to a display request from a client, input the user's financial indicator data into a constructed user portrait prediction model, and generate a user portrait, wherein the user portrait prediction model is obtained by training and optimizing parameters of an initial classifier; A financial analysis habit determination module, used to obtain the initial financial analysis habit of the industry to which the user belongs from the user portrait, and use the financial analysis habit as the financial analysis habit of the user; The visualization module is used to send the user's financial indicator data to the client, so that the client can componentize the user's financial indicator data according to the user's financial analysis habits and display the componentized financial indicator data.

8. A computer device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and to implement the user portrait-based financial analysis visualization method according to any one of claims 1 to 6 when executing the instructions.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the financial analysis visualization method based on user portrait according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the financial analysis visualization method based on user portrait according to any one of claims 1 to 6.

Images