Data analysis method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a data analysis method and device, electronic equipment, a storage medium and a program product, and can be applied to the field of big data. The method comprises the steps of extracting required to-be-analyzed data from user service data and performing representation processing, projecting a representation result of the to-be-analyzed data into a data point of a two-dimensional plane, displaying the data point in a visual mode, and further analyzing the user service data according to a display result. By means of data extraction and characterization processing, the data size needing to be processed in data analysis can be reduced, characterization results are projected to a plane and visually displayed, and analysts can be assisted to more visually observe distribution characteristics of data of different users. The method is used for achieving the effects of improving the data analysis efficiency and reducing the data analysis difficulty.

Description

Technical Field

[0001] The present application relates to the field of big data, and in particular to a data analysis method, device, electronic device, storage medium and program product. Background Art

[0002] Data analysis can include the process of organizing, processing, analyzing and interpreting the collected data, and has a wide range of applications in various fields. Especially in the financial field, data analysis can help financial institutions improve efficiency, reduce risks, optimize investment decisions and enhance customer experience.

[0003] At present, banks and other financial institutions often conduct manual analysis of data such as user behavior, divide user groups into different groups, and evaluate user credit levels based on certain rules in order to reduce risks.

[0004] However, with the development of user scale, the amount of user data of financial institutions has increased rapidly. Traditional analysis methods are inefficient in processing large-scale data, and the dimensions of user data are becoming more complex, making data analysis more difficult. Summary of the invention

[0005] The embodiments of the present application provide a data analysis method, device, electronic device, storage medium and program product to reduce the difficulty of data analysis and improve the efficiency of data analysis.

[0006] In a first aspect, an embodiment of the present application provides a data analysis method, comprising:

[0007] Obtain user business data;

[0008] Extracting first data to be analyzed from the user service data;

[0009] Characterizing the first data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane;

[0010] The data points are displayed in a visual manner, and the user business data is analyzed based on the display results.

[0011] In a possible implementation manner, characterizing the first data to be analyzed and projecting the characterization results into data points on a two-dimensional plane includes:

[0012] Dividing the first data to be analyzed into a plurality of data subsets belonging to different dimensions, each data subset containing at least two items of the first data to be analyzed;

[0013] Processing the data in the data subset by using a representation model to obtain low-dimensional features of the data subset;

[0014] The feature values ​​of the low-dimensional features are mapped to coordinate points of a two-dimensional plane, and the low-dimensional features are projected onto the two-dimensional plane according to the coordinate points.

[0015] In a possible implementation, presenting the data points in a visual manner includes:

[0016] Obtaining data points obtained by projecting data subsets corresponding to multiple users;

[0017] The data points are integrated into a plurality of visualization interfaces according to the dimensions to which the data subsets belong, and each visualization interface contains data points after the data subsets of different users are projected under the same dimension.

[0018] In a possible implementation, the representation model is obtained by:

[0019] Get sample business data;

[0020] Inputting the sample business data into an autoencoder model, and adjusting model parameters of the autoencoder model based on an output result of the autoencoder model, wherein the autoencoder model includes an encoder and a decoder;

[0021] After the model parameters are adjusted, a representation model is generated according to the encoder of the autoencoder model.

[0022] In a possible implementation manner, analyzing the user service data according to the display result further includes:

[0023] Extracting second data to be analyzed from the user service data according to the display result;

[0024] Characterizing the second data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane;

[0025] The data points obtained by characterizing and projecting the second data to be analyzed are displayed in a visual manner, and the user service data is analyzed again according to the display results.

[0026] In a possible implementation, the data points are displayed in a visual manner, and the target user is analyzed according to the display result, including:

[0027] Performing clustering processing on the data points to obtain multiple clusters;

[0028] The credit level of the user in the user service data is determined according to the service data corresponding to the data points in the cluster.

[0029] In a second aspect, an embodiment of the present application provides a data analysis device, including:

[0030] Acquisition module, used to obtain user business data;

[0031] A data extraction module, used to extract first data to be analyzed from the user service data;

[0032] A characterization processing module, used for characterizing the first data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane;

[0033] The display and analysis module is used to display the data points in a visual manner and analyze the user business data according to the display results.

[0034] In a possible implementation, the characterization processing module is also used to: divide the first data to be analyzed into multiple data subsets belonging to different dimensions, each data subset containing at least two items of the first data to be analyzed; process the data in the data subsets through a characterization model to obtain low-dimensional features of the data subsets; map the feature values ​​of the low-dimensional features to coordinate points on a two-dimensional plane, and project the low-dimensional features onto the two-dimensional plane according to the coordinate points.

[0035] In a possible implementation, the display analysis module is also used to: obtain data points obtained by projecting data subsets corresponding to multiple users; integrate the data points into multiple visualization interfaces according to the dimensions to which the data subsets belong, each visualization interface containing data points after projecting data subsets of different users under the same dimension.

[0036] In one possible implementation, the characterization processing module is also used to: obtain sample business data; input the sample business data into an autoencoder model, and adjust the model parameters of the autoencoder model based on the output results of the autoencoder model, wherein the autoencoder model includes an encoder and a decoder; after the model parameter adjustment is completed, generate a characterization model according to the encoder of the autoencoder model.

[0037] In a possible implementation, the display and analysis module is also used to: extract second data to be analyzed from the user business data based on the display result; characterize the second data to be analyzed, and project the characterization result as data points on a two-dimensional plane; display the data points obtained by characterizing and projecting the second data to be analyzed in a visual manner, and analyze the user business data again based on the display result.

[0038] In a possible implementation, the display analysis module is further used to: cluster the data points to obtain a plurality of clusters; and determine the credit level of the user in the user business data according to the business data corresponding to the data points in the clusters.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0040] The memory stores computer-executable instructions;

[0041] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0043] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0044] The data analysis method, device, electronic device, storage medium, and program product provided in the embodiments of the present application can project the characterization results of the data to be analyzed into data points on a two-dimensional plane by extracting the required data to be analyzed from the user business data and performing characterization processing, and then further analyze the user business data based on the display results after displaying the data points in a visual manner. Through data extraction and characterization processing, the amount of data to be processed for data analysis can be reduced, and projecting the characterization results onto a plane and performing visual display can assist analysts in more intuitively observing the distribution characteristics between the data of different users, thereby achieving the effect of improving data analysis efficiency and reducing the difficulty of data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] Figure 1 A schematic diagram of a data analysis method provided in this application Figure 1 ;

[0047] Figure 2 A schematic diagram of a data analysis method provided in this application Figure 2 ;

[0048] Figure 3 A schematic diagram of a data analysis method provided in this application Figure 3 ;

[0049] Figure 4 A schematic diagram of a data analysis method provided in this application Figure 4 ;

[0050] Figure 5 A schematic diagram of the structure of a data analysis device provided in this application;

[0051] Figure 6 A schematic diagram of the structure of an electronic device provided in this application.

[0052] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0054] It should be noted that the data analysis method, device, electronic device, storage medium and program product of the present application can be used in the field of big data, and can also be used in any field except the field of big data. The application field of the refund processing method and device of the present application is not limited.

[0055] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0056] Figure 1 A schematic diagram of a data analysis method provided in this application Figure 1 .like Figure 1 As shown, the method includes:

[0057] Step S101, obtaining user service data.

[0058] Among them, user business data may include the user's age, gender, education, occupation, income, deposit amount, loan record and financial product purchase record, etc.

[0059] Step S102: extracting first data to be analyzed from user service data.

[0060] Specifically, some data for analysis can be initially selected from the user's business data according to the data analysis requirements. For example, if it is necessary to analyze the repayment risk of a user's loan application, basic data such as the user's age, occupation, and income, as well as behavioral data such as historical loan records, can be selected as the first data to be analyzed. For another example, if it is necessary to analyze and predict the financial products that the user may purchase, basic data such as the user's age, occupation, and income, as well as behavioral data such as financial purchase records, can be selected as the first data to be analyzed.

[0061] Step S103: characterize the first data to be analyzed, and project the characterization results into data points on a two-dimensional plane.

[0062] Specifically, the extracted first data to be analyzed can be processed by a representation learning algorithm, the first data to be analyzed can be mapped to a low-dimensional space, the dimension of the first data to be analyzed can be reduced, and the vector representation of the first data to be analyzed in the low-dimensional space can be projected onto a two-dimensional plane, so that the first data to be analyzed is represented as a data point on the two-dimensional plane.

[0063] It should be noted that the characterization of data in this embodiment includes dimensionality reduction processing of data, which is intended to use lower-dimensional data to represent the original data to be analyzed. For example, the first data to be analyzed extracted from the user business data may include 20 dimensions such as user age, gender, occupation, education and income. After the first data to be analyzed is characterized, the characterization result may be 2 dimensions.

[0064] Step S104: display the data points in a visual manner, and analyze the user business data according to the display results.

[0065] Specifically, a visualization interface can be generated based on the two-dimensional plane in the projection process. Each characterization result can be represented as a data point in the two-dimensional plane. The data points corresponding to the characterization results of different users are represented in the same visualization interface, and the user business data can be further analyzed based on the distribution of the data points.

[0066] After characterizing the first data to be analyzed, each characterization result can characterize the first data to be analyzed extracted from the user business data of a user. The positions of the data points formed by projecting the characterization results onto the two-dimensional plane can reflect some characteristics of the user's data. By displaying the data points after characterization of different users in a visualization interface, it is convenient for analysts to obtain some group characteristics of the user data.

[0067] In some possible implementations, a variety of interactive methods can be designed in a visualization interface generated based on a two-dimensional plane for analysts to use. For example, the visualization interface can provide a variety of functional interfaces, through which analysts can perform operations such as box selection and highlighting on data points in the visualization interface, or select data through the functional interface for display in other forms (such as histograms, bar charts, or line charts, etc.), or select some clustering methods through the functional interface to process the data. Based on the visualization interface, the first analysis data corresponding to the data point can be further displayed in the visualization interface by selecting the data point.

[0068] In some possible implementations, data points are displayed in a visual manner, and target users are analyzed based on the displayed results, including:

[0069] The data points are clustered to obtain a plurality of clusters; and the credit level of the user in the user business data is determined according to the business data corresponding to the data points in the clusters.

[0070] The data analysis method provided in the embodiment of the present application can project the characterization results of the data to be analyzed into data points on a two-dimensional plane by extracting the required data to be analyzed from the user business data and performing characterization processing, and then further analyze the user business data based on the display results after displaying the data points in a visual manner. Through data extraction and characterization processing, the amount of data to be processed for data analysis can be reduced, and projecting the characterization results onto a plane and performing visual display can assist analysts in more intuitively observing the distribution characteristics of data between different users, thereby achieving the effect of improving data analysis efficiency and reducing data analysis difficulty.

[0071] Figure 2 A schematic diagram of a data analysis method provided in this application Figure 2 .like Figure 2 As shown, the first data to be analyzed is characterized, and the characterization result is projected as data points on a two-dimensional plane, including:

[0072] Step S201: divide the first data to be analyzed into multiple data subsets belonging to different dimensions.

[0073] Each data subset contains at least two items of the first data to be analyzed.

[0074] Specifically, the first data to be analyzed extracted from the user service data can be divided into multiple groups, each group of data is a data subset. The data subset can be obtained by dividing according to a preset rule, or the data subset can be divided manually.

[0075] For example, the first data to be analyzed includes multiple data such as the user's age, gender, education level, income, consumption category, consumption time, loan amount, loan type, loan overdue record, financial investment amount and financial product purchase record. Age, gender, education level and income can be divided into a data subset, consumption category and consumption time can be divided into a data subset, loan amount, loan type, loan overdue record can be divided into a data subset, and financial investment amount and financial product purchase record can be divided into a data subset. These data subsets can reflect the user's data in different dimensions, and each data subset contains at least two data.

[0076] Step S202: Process the data in the data subset by using the representation model to obtain low-dimensional features of the data subset.

[0077] Among them, the representation model can reduce the dimension of the input data and output the low-dimensional features of the data.

[0078] Specifically, a pre-trained representation model can be obtained, and for any data subset, the data subset can be input into the representation model to obtain low-dimensional features corresponding to the data subset output by the representation model.

[0079] In some possible implementations, the low-dimensional features output by the representation model may be two-dimensional coordinates. For example, the data subset includes the user's age, gender, education level, and income. Inputting these data into the representation model may result in the output of the representation model having two-dimensional coordinates (0.3, 0.7).

[0080] Step S203 , mapping the feature values ​​of the low-dimensional features into coordinate points of a two-dimensional plane, and projecting the low-dimensional features onto the two-dimensional plane according to the coordinate points.

[0081] Exemplarily, the eigenvalue of the low-dimensional feature is (5, 10), and the eigenvalue can be mapped to coordinates in the plane at a certain ratio. For example, the eigenvalue can be mapped to coordinates (0.5, 1) at a ratio of 10:1. According to the mapped coordinates, a data point corresponding to the low-dimensional feature can be formed on the two-dimensional plane.

[0082] In some possible implementations, data points are displayed in a visual manner, including:

[0083] Acquire data points obtained by projecting data subsets corresponding to multiple users; and integrate the data points into multiple visualization interfaces according to the dimensions to which the data subsets belong.

[0084] Each visualization interface contains data points after projection of data subsets of different users in the same dimension.

[0085] It should be noted that, through the method in the above embodiment, data related to multiple users can be characterized and projected, the data of each user can be divided into multiple data subsets, each data subset can be projected into a data point, and then based on the data of each user, multiple data points can be obtained on a two-dimensional plane. When performing a visual display, the data points projected by different users corresponding to the same type of data subsets can be displayed in the same visualization interface, and the data points projected by different types of data subsets can be displayed in different visualization interfaces.

[0086] In one embodiment, Figure 3 As shown, the representation model is obtained by:

[0087] Step S301, obtaining sample business data.

[0088] The sample business data may be selected from user-related business data.

[0089] Step S302: input the sample business data into the autoencoder model, and adjust the model parameters of the autoencoder model based on the output result of the autoencoder model.

[0090] Among them, the autoencoder model includes an encoder and a decoder. Autoencoder is a neural network model that can be used for data dimensionality reduction and feature extraction. Autoencoder can include an encoder and a decoder. The encoder can map the input data to a lower-dimensional latent space, and the decoder can reconstruct the input data from the latent space.

[0091] Specifically, the structure of the autoencoder can be pre-defined, including the number of layers of the encoder and decoder, the number of neurons in each layer, and the activation function, etc., and then the sample business data can be input into the encoder after preprocessing. The encoder can represent the input data in a low-dimensional space, and the decoder can reconstruct the representation result of the encoder to output data that is similar to the sample data. The difference between the input sample business data and the decoder output result can be calculated through loss functions such as MSE (mean square error) to adjust the model parameters.

[0092] Step S303, after the model parameters are adjusted, a representation model is generated according to the encoder of the autoencoder model.

[0093] Specifically, after adjusting the parameters of the autoencoder model, the encoder in the autoencoder model can be separated out as a representation model. In some possible implementations, the encoder can be separated out and some neural network structures can be added to the encoder to obtain a representation model. The added neural network structure can make the dimension of the output result of the representation model two-dimensional.

[0094] In the above embodiment, the autoencoder model can be trained and a representation model can be obtained based on the encoder in the autoencoder model. The representation model obtained in this way can retain the characteristics of the user business data to a greater extent and improve the credibility of the data analysis results.

[0095] In one embodiment, Figure 4 As shown, the analysis of user business data based on the display results includes:

[0096] Step S401: extracting second data to be analyzed from user service data according to the display result.

[0097] Step S402: characterize the second data to be analyzed, and project the characterization results into data points on a two-dimensional plane.

[0098] Step S403: Display the data points obtained by the characterization projection of the second data to be analyzed in a visual manner, and analyze the user service data again according to the display result.

[0099] Specifically, after characterizing and projecting the data to be analyzed based on the first extraction, analysts can conduct manual analysis of users based on the first display results. If analysts discover new points of interest based on the data distribution characteristics of the first display, they can extract new data to be analyzed from the user's business data again, and re-characterize and project based on the new data to be analyzed for further analysis.

[0100] For example, based on the results of the first display, analysts find that users who live in a certain city apply for credit cards more frequently. In the second extraction, the data of users related to the city can be extracted as the data to be analyzed, and the user data of the city can be grouped to obtain a data subset, which can be further characterized and projected, so as to perform visual analysis again and observe the data patterns of users in the city.

[0101] In the above embodiment, after manual analysis is performed based on the display results obtained based on the first data to be analyzed, the analysis direction of interest can be determined based on the preliminary results of the manual analysis, and data can be extracted from the user business data for a second time based on the analysis direction for characterization and projection, thereby performing in-depth analysis of the user data, exploring the potential value of the data, and improving data utilization.

[0102] Figure 5 This is a schematic diagram of the structure of a data analysis device provided in this application. Figure 5 As shown, the data analysis device 500 provided in this embodiment includes:

[0103] The acquisition module 501 is used to acquire user service data.

[0104] The data extraction module 502 is used to extract the first data to be analyzed from the user service data.

[0105] The characterization processing module 503 is used to characterize the first data to be analyzed and project the characterization results into data points on a two-dimensional plane.

[0106] The display and analysis module 504 is used to display the data points in a visual manner and analyze the user service data according to the display results.

[0107] In one embodiment, the characterization processing module 503 is also used to: divide the first data to be analyzed into multiple data subsets belonging to different dimensions, each data subset containing at least two items of the first data to be analyzed; process the data in the data subsets through a characterization model to obtain low-dimensional features of the data subsets; map the feature values ​​of the low-dimensional features to coordinate points on a two-dimensional plane, and project the low-dimensional features onto the two-dimensional plane according to the coordinate points.

[0108] In one embodiment, the display analysis module 504 is also used to: obtain data points obtained by projecting data subsets corresponding to multiple users; integrate the data points into multiple visualization interfaces according to the dimensions to which the data subsets belong, and each visualization interface contains data points after projecting data subsets of different users under the same dimension.

[0109] In one embodiment, the characterization processing module 503 is also used to: obtain sample business data; input the sample business data into the autoencoder model, and adjust the model parameters of the autoencoder model based on the output results of the autoencoder model, wherein the autoencoder model includes an encoder and a decoder; after the model parameter adjustment is completed, generate a characterization model according to the encoder of the autoencoder model.

[0110] In one embodiment, the display analysis module 504 is also used to: extract second data to be analyzed from the user business data according to the display result; characterize the second data to be analyzed, and project the characterization result as data points on a two-dimensional plane; display the data points obtained by characterizing and projecting the second data to be analyzed in a visual manner, and analyze the user business data again according to the display result.

[0111] In one embodiment, the display analysis module 504 is further used to: perform clustering processing on the data points to obtain multiple clusters; and determine the credit level of the user in the user business data according to the business data corresponding to the data points in the clusters.

[0112] The data analysis device 500 provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0113] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 60 may include:

[0114] Processor 61, memory 62, and communication interface 63;

[0115] The memory 62 is used to store executable instructions of the processor 61; the executable instructions may be computer-executable instructions;

[0116] The processor 61 is configured to execute the technical solution in any of the aforementioned method embodiments by executing the executable instructions.

[0117] Optionally, the memory 62 may be independent or integrated with the processor 61 .

[0118] Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include:

[0119] The bus 64 , the memory 62 and the communication interface 63 are connected to the processor 61 via the bus 64 and communicate with each other. The communication interface 63 is used to communicate with other devices.

[0120] Optionally, the communication interface 63 may be implemented by a transceiver. The communication interface is used to implement communication between the database access device and other devices (such as a client, a read-write library, and a read-only library). The memory may include a random access memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0121] The bus 64 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0122] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0123] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0124] An embodiment of the present application also provides a readable storage medium, which may be a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the technical solution provided by any of the aforementioned method embodiments is implemented.

[0125] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when executed by a processor.

[0126] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0129] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0130] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A data analysis method, characterized in that: include: Obtain user business data; Extracting first data to be analyzed from the user service data; Characterizing the first data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane; The data points are displayed in a visual manner, and the user business data is analyzed based on the display results.

2. The method according to claim 1, characterized in that Characterizing the first data to be analyzed and projecting the characterization results into data points on a two-dimensional plane includes: Dividing the first data to be analyzed into a plurality of data subsets belonging to different dimensions, each data subset containing at least two items of the first data to be analyzed; Processing the data in the data subset by using a representation model to obtain low-dimensional features of the data subset; The feature values ​​of the low-dimensional features are mapped to coordinate points of a two-dimensional plane, and the low-dimensional features are projected onto the two-dimensional plane according to the coordinate points.

3. The method according to claim 2, characterized in that The visual display of the data points includes: Obtaining data points obtained by projecting data subsets corresponding to multiple users; The data points are integrated into a plurality of visualization interfaces according to the dimensions to which the data subsets belong, and each visualization interface contains data points after the data subsets of different users are projected under the same dimension.

4. The method according to claim 2 or 3, characterized in that: The characterization model is obtained by: Get sample business data; Inputting the sample business data into an autoencoder model, and adjusting model parameters of the autoencoder model based on an output result of the autoencoder model, wherein the autoencoder model includes an encoder and a decoder; After the model parameters are adjusted, a representation model is generated according to the encoder of the autoencoder model.

5. The method according to any one of claims 1 to 3, characterized in that: The analyzing the user service data according to the display result also includes: Extracting second data to be analyzed from the user service data according to the display result; Characterizing the second data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane; The data points obtained by characterizing and projecting the second data to be analyzed are displayed in a visual manner, and the user service data is analyzed again according to the display results.

6. The method according to any one of claims 1 to 3, characterized in that: The visually displaying the data points and analyzing the target users according to the display results include: Performing clustering processing on the data points to obtain multiple clusters; The credit level of the user in the user service data is determined according to the service data corresponding to the data points in the cluster.

7. A data analysis device, characterized in that: include: Acquisition module, used to obtain user business data; A data extraction module, used to extract first data to be analyzed from the user service data; A characterization processing module, used for characterizing the first data to be analyzed, and projecting the characterization results into data points on a two-dimensional plane; The display and analysis module is used to display the data points in a visual manner and analyze the user business data according to the display results.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images