Data analysis method, computer equipment and computer storage medium

Abstract

The embodiment of the invention discloses a data analysis method, computer equipment and a computer storage medium. The computer equipment determines index data of a plurality of indexes corresponding to the target data set, determines index data of a target index used for algorithm processing from the index data of the plurality of indexes, and determines an algorithm model corresponding to a target algorithm to be executed, and processing the index data of the target index by using the algorithm model of the target algorithm, outputting an algorithm processing result, and displaying the index data of the target index and the algorithm processing result. Therefore, a user can directly start various algorithm functions pre-configured by the big data platform and the data analysis product to automatically process specific index data by using a specific algorithm function without asking for help of an algorithm engineer to execute an algorithm process and without repeated intervention of the algorithm engineer, the algorithm processing speed can be increased, and the user experience is improved. The data processing cost is reduced, the processing time is shortened, and popularization and use of a big data platform and a data analysis product are facilitated.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data analysis, and specifically to a data analysis method, a computer device, and a computer storage medium. Background Art

[0002] On the big data platform, by building machine learning, deep learning and other algorithm systems, accurate design of data processing for various business scenarios can be achieved. The algorithm system obtains data through the big data platform and performs data preprocessing, model parameter adjustment, testing and ABtest verification before going online, and the algorithm results can be presented in the form of BI visualization. Among them, BI visualization is business intelligence (Business Intelligence) visualization, which is a data management and data analysis tool that can display data in the form of charts, dashboards, tables, etc. ABtest is a comparative test used to compare the effects of two or more plans (usually called plans A and B) to determine the better plan.

[0003] However, the algorithm system of the big data platform has a high threshold for use. When algorithms are needed to support business analysis, algorithm engineers are required to go through the algorithm construction process again, which is costly and time-consuming, and is not conducive to the promotion and use of big data platforms and data analysis products. Summary of the invention

[0004] The embodiments of the present application provide a data analysis method, a computer device, and a computer storage medium for improving the processing speed of an algorithm, reducing the cost of data processing, and shortening the processing time, which is conducive to the promotion and use of big data platforms and data analysis products.

[0005] A first aspect of an embodiment of the present application provides a data analysis method, the method comprising:

[0006] Acquire a target data set to be analyzed, and determine indicator data of multiple indicators corresponding to the target data set;

[0007] Determining the indicator data of the target indicator for algorithm processing from the indicator data of the plurality of indicators;

[0008] Determine an algorithm model corresponding to the target algorithm to be executed, and input the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs the algorithm processing result;

[0009] Display the indicator data of the target indicator and the algorithm processing results.

[0010] A second aspect of an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0011] A third aspect of an embodiment of the present application provides a computer storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the method of the first aspect.

[0012] A fourth aspect of the embodiments of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device executes the method of the first aspect.

[0013] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0014] The computer device obtains the target data set to be analyzed, determines the indicator data of multiple indicators corresponding to the target data set, determines the indicator data of the target indicator used for algorithm processing from the indicator data of multiple indicators, determines the algorithm model corresponding to the target algorithm to be executed, and inputs the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs the algorithm processing result, and displays the indicator data of the target indicator and the algorithm processing result. Therefore, users can directly enable multiple algorithm functions pre-configured in the big data platform and data analysis products to use specific algorithm functions to automatically process specific indicator data, without the need to seek help from algorithm engineers to execute the algorithm process, and without the need for algorithm engineers to repeatedly intervene, which can improve the processing speed of the algorithm, reduce the cost of data processing and shorten the processing time, and is conducive to the promotion and use of big data platforms and data analysis products. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the network framework in the embodiment of the present application;

[0016] Figure 2 A schematic diagram of a flow chart of a data analysis method in an embodiment of the present application;

[0017] Figure 3 This is another flow chart of the data analysis method in the embodiment of the present application;

[0018] Figure 4 This is an exemplary flow chart of an application scenario of the data analysis method in an embodiment of the present application;

[0019] Figure 5 It is a structural schematic diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide a data analysis method, a computer device, and a computer storage medium for improving the processing speed of an algorithm, reducing the cost of data processing, and shortening the processing time, which is conducive to the promotion and use of big data platforms and data analysis products.

[0021] See also Figure 1 In the embodiment of the present application, the network framework includes:

[0022] The service server 100 and the terminal cluster; the terminal cluster may include: terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n and other terminal devices.

[0023] The business server 100 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud database, cloud service, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The terminal device (including terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n) may be a smart phone, tablet computer, laptop computer, desktop computer, PDA, mobile internet device (MID), wearable device (such as smart watch, smart bracelet, etc.), smart computer, smart car and other smart terminals.

[0024] Among them, the business server 100 can establish a communication connection with each terminal device in the terminal cluster, and a communication connection can also be established between each terminal device in the terminal cluster. In other words, the business server 100 can establish a communication connection with each terminal device in the terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n. For example, a communication connection can be established between the terminal device 200a and the business server 100. A communication connection can be established between the terminal device 200a and the terminal device 200b, and a communication connection can also be established between the terminal device 200a and the terminal device 200c. Among them, the above-mentioned communication connection does not limit the connection method, and can be directly or indirectly connected through a wired communication method, or can be directly or indirectly connected through a wireless communication method, etc., which can be determined according to the actual application scenario, and this application is not limited here.

[0025] It should be understood that Figure 1Each terminal device in the terminal cluster shown can be installed with an application client. When the application client runs in each terminal device, it can interact with the business server 100 respectively, so that the business server 100 can receive business data from each terminal device (such as financial management data uploaded by the user through the terminal device). Among them, the application client can be an application client with the function of displaying text, images, audio and video, such as a financial management application, an enterprise affairs management application, a browser application, a social application, an instant messaging application, a live broadcast application, a game application, a short video application, a video application, a music application, a shopping application, a novel application, a payment application, etc., which can be determined according to the actual application scenario requirements and is not limited here. Among them, the application client can be an independent client or an embedded sub-client integrated in a client (such as a financial management client, an enterprise affairs management client, etc.), which can be determined according to the actual application scenario and is not limited here.

[0026] On the big data platform, by building machine learning, deep learning and other algorithm systems, accurate design of data processing for various business scenarios can be achieved. The algorithm system obtains data through the big data platform and performs data preprocessing, model parameter adjustment, testing and AB test verification before going online, and the algorithm results can be presented in the form of BI visualization.

[0027] However, the algorithm system of the big data platform has a high threshold for use. When algorithms are needed to support business analysis, algorithm engineers are required to go through the algorithm construction process again, which is costly and time-consuming, and is not conducive to the promotion and use of big data platforms and data analysis products.

[0028] Moreover, the premise of visualization is to output the corresponding algorithm processing results through the algorithm system. However, the existing visualization does not have integrated algorithm functions, and the interface does not have data processing functions. For example, it does not support predictive processing of data, resulting in the inability to directly use agile analysis involving algorithm functions in visualization, and the response to business is not timely enough.

[0029] In order to solve the above technical problems, a data analysis method of the embodiment of the present application is proposed. Figure 1 The data analysis method in the embodiment of the present application is described in the network framework:

[0030] See also Figure 2 In the embodiments of the present application, one embodiment of the data analysis method includes:

[0031] 201. Acquire a target data set to be analyzed, and determine indicator data of multiple indicators corresponding to the target data set;

[0032] The method of this embodiment can be applied to a computer device, which can be Figure 1 The business server 100 or each terminal device in the network framework shown. The computer device can obtain the target data set to be analyzed and determine the indicator data of multiple indicators corresponding to the target data set. The target data set can be business data generated by various business systems, for example, it can be business data generated by business systems such as financial data generated by a financial system and industrial economic data generated by an industrial economic business system. The target data set can correspond to multiple indicators, such as financial data corresponding to multiple financial indicators, business economic data corresponding to multiple industrial economic indicators, then the multiple indicators contained in the target data set can be determined, and the indicator data of each indicator can be determined. The indicator data may include data related to the indicator, such as the indicator name and the specific indicator value corresponding to the indicator name.

[0033] 202. Determine the indicator data of the target indicator for algorithm processing from the indicator data of the plurality of indicators;

[0034] After determining the indicator data of multiple indicators, the indicator data of the target indicator used for algorithm processing can be determined from the indicator data of the multiple indicators, that is, the indicator data of the target indicator is suitable for the processing of the algorithm and can be used for the processing of the algorithm to obtain the corresponding algorithm result.

[0035] 203. Determine an algorithm model corresponding to the target algorithm to be executed, and input the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs an algorithm processing result;

[0036] After determining the indicator data of the target indicator used for algorithm processing, the algorithm model corresponding to the target algorithm to be executed can be determined, and the indicator data of the target indicator can be input into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator based on the data processing knowledge obtained through pre-training and outputs the algorithm processing results.

[0037] For example, the target algorithm can be a classification algorithm, a regression algorithm, a clustering algorithm, a time series algorithm, or the like. An algorithm model can be constructed based on the corresponding algorithm, and the algorithm model can be trained using training sample data so that the algorithm model can learn the corresponding algorithm processing knowledge during the model training process. The algorithm model that has completed the model training can be used to process the corresponding indicator data and output the algorithm processing results.

[0038] 204. Display the indicator data of the target indicator and the algorithm processing result;

[0039] After obtaining the indicator data and algorithm processing results of the target indicator, the indicator data and algorithm processing results of the target indicator can be output and displayed to the user, so that the user can obtain the indicator data of the target data set on the corresponding indicator and the processing results obtained by performing algorithm processing on the indicator data.

[0040] In this embodiment, the computer device obtains the target data set to be analyzed, determines the indicator data of multiple indicators corresponding to the target data set, determines the indicator data of the target indicator used for algorithm processing from the indicator data of multiple indicators, determines the algorithm model corresponding to the target algorithm to be executed, and inputs the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs the algorithm processing result, and displays the indicator data of the target indicator and the algorithm processing result. Therefore, users can directly enable a variety of algorithm functions pre-configured by the big data platform and data analysis products to use specific algorithm functions to automatically process specific indicator data, without the need to seek help from algorithm engineers to execute the algorithm process, and without the need for algorithm engineers to repeatedly intervene, which can improve the processing speed of the algorithm, reduce the cost of data processing and shorten the processing time, and is conducive to the promotion and use of big data platforms and data analysis products.

[0041] The following will be Figure 2 Based on the embodiment shown, the embodiment of the present application is further described in detail. Figure 3 Another embodiment of the data analysis method in the embodiment of the present application includes:

[0042] 301. Acquire a target data set to be analyzed, and determine indicator data of multiple indicators corresponding to the target data set;

[0043] In this embodiment, when obtaining the target data set, an optional implementation method is to obtain the initial data set to be analyzed, perform data cleansing on the initial data set, obtain the target data set, and store the target data set in layers. Among them, the layered storage can be a basic data warehouse layer to standardize data governance, such as using the common dimension layer, standard detail layer, data summary layer and data application layer as layered standard storage. Among them, the common dimension layer standardizes common dimension attributes, such as time, location, and category; the standard detail layer retains the finest granularity of the original business data after cleaning; the data summary layer performs calculations and summaries based on the standard detail layer data to achieve fast query; the data application layer customizes the corresponding model or view according to specific business needs.

[0044] Figure 4 An exemplary process of an application scenario of the data analysis method of this embodiment is shown as follows: Figure 4As shown in the figure, the big data platform can be used to integrate various industrial economic business systems and collect the initial business data of each business system, and the initial business data can be cleaned and processed by ETL through the data development module to obtain the target business data. Among them, ETL cleaning (ExtractTransformLoad) is an important part of data processing, which is mainly used for data cleaning, transformation and loading.

[0045] The target business data obtained after cleaning is stored in a hierarchical and standardized manner in the data warehouse at multiple levels, including the common dimension layer, standard detail layer, data summary layer, and data application layer. As the infrastructure for storing and managing data, the data warehouse can well solve the problem of balancing storage cost and performance in data storage through hierarchical storage technology.

[0046] After obtaining the target data set, the indicator data of multiple indicators corresponding to the target data set can be determined. Specifically, an optional implementation method is to determine the indicator data of multiple standard indicators corresponding to the target data set, determine the derived indicators corresponding to the standard indicators, and determine the composite indicators corresponding to the standard indicators, determine the indicator data of the derived indicators from the target data set, and then calculate the indicator data of the standard indicators according to the indicator data algorithm corresponding to the composite indicators to obtain the indicator data of the composite indicators.

[0047] Among them, the standard indicators are as follows Figure 4 Atomic metrics are shown in Figure 1. Atomic metrics refer to the smallest measurable unit in data analysis, usually a value or a count. Atomic metrics are the basis of data analysis, and they can be used to describe a specific event, behavior, or state, such as sales, visits, conversion rate, etc.

[0048] Atomic indicators are usually the basis of other indicators. Higher-level indicators can be derived by analyzing atomic indicators. For example, derived indicators can be obtained by combining atomic indicators with other dimensions or elements. Derived indicators are composed of three major elements: atomic indicators, time periods, and dimensions within the scope of business. They are used to count the numerical performance of atomic indicators under specific time, dimensions, and business conditions, reflecting the business status of a certain business activity.

[0049] A composite indicator refers to a set of calculated indicators that are based on atomic indicators or derived indicators and formed through certain calculation rules, such as average user transaction amount, debt-to-asset ratio, etc.

[0050] For example, when the atomic indicator is turnover, the derived indicator can be the atomic indicator with a time period and modifiers added, such as turnover of a certain branch in the past six months; and the composite indicator is the indicator calculated from the atomic indicator or derived indicator, such as profit margin and other indicators calculated from the atomic indicator or derived indicator.

[0051] Therefore, through the indicator analysis of the target data set, multiple analysis dimensions of the target data set can be provided to users, making it convenient for users to select specific algorithms for processing and analysis of indicator data, which is conducive to realizing the analytical value of the target data set.

[0052] 302. Determine the indicator data of the target indicator for algorithm processing from the indicator data of the multiple indicators;

[0053] When determining the indicator data for algorithm processing, an optional implementation is that the user can configure multiple indicator combinations, that is, the computer device receives the indicator configuration instruction input by the user, determines multiple indicator combinations from multiple indicators according to the indicator configuration instruction, and determines the correlation coefficient between multiple indicators in each indicator combination. Afterwards, the indicator data of multiple indicators in the indicator combination whose correlation coefficient is greater than a preset threshold can be used as the indicator data of the target indicator for algorithm processing.

[0054] For example, Figure 4 As shown in the figure, after determining the indicator data of multiple indicators in the target data set, the correlation indicators can be explored. When analyzing and exploring business data, the combination of indicators (such as single indicator, two-by-two combination, etc.) can be selected through configuration, and the quantitative relationship between indicators can be explored through the correlation coefficient method. Among them, the quantitative relationship between indicators can be expressed by three major correlation coefficients, namely Pearson, Spearman and Kendall, which reflect the direction and degree of the trend between two variables. The value range is -1 to +1, 0 means that the two variables are unrelated, positive values ​​indicate positive correlation, negative values ​​indicate negative correlation, and the larger the value, the stronger the correlation.

[0055] Therefore, through the exploration and analysis of the correlation between indicators, the correlation between multiple indicators can be determined, and the indicator data of multiple indicators with correlation greater than the preset threshold can be applied to the processing of the corresponding algorithm, so that the algorithm processing results can reflect the correlation between multiple indicators, thereby making the algorithm processing results more in line with actual business analysis needs and making them more valuable for business applications.

[0056] 303. Determine an algorithm model corresponding to the target algorithm to be executed, and input the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs an algorithm processing result;

[0057] In this embodiment, the visualization interface of the big data platform can integrate multiple data processing algorithms, such as configuring automatic classification, automatic regression, automatic clustering, automatic time series and other self-learning function algorithms, so that users can choose the algorithms required to process actual business, meet users' diverse business processing needs, and improve business processing efficiency.

[0058] During the use of the algorithm model, the algorithm model can update model parameters as the training sample data is updated. Specifically, based on the random search method, the updated data of the training sample data can be used to update the model parameters of the algorithm model corresponding to the training sample data. For example, the updated data of the training sample data corresponding to the target algorithm can be used to update the model parameters of the algorithm model of the target algorithm. Among them, the random search method is a model hyperparameter optimization, which can find the best parameter combination of the algorithm model through random sampling.

[0059] Therefore, through the self-update of the algorithm model, the processing results of the algorithm model on the indicator data can be made more accurate, making the processed algorithm results more in line with the actual business situation.

[0060] 304. Display the indicator data of the target indicator and the algorithm processing result;

[0061] After obtaining the algorithm processing results, the computer device can display the indicator data of the target indicator and the algorithm processing results obtained by processing the indicator data of the target indicator by the algorithm model of the target algorithm on a visualization interface to achieve data visualization.

[0062] In an optional implementation, the big data platform may have an AI chart analysis function. The data visualization module of the big data platform supports the output of chart analysis through dialogue. The platform may have a built-in natural language processing (NLP) algorithm, which can parse the key indicators and analysis dimensions input by the user based on the NLP algorithm, and generate chart analysis based on this. The computer device can receive the user's input, and parse the target indicator and / or analysis dimension indicated by the user based on the NLP algorithm, and display the indicator data of the target indicator indicated by the user and the processing result of the algorithm in the style of a chart according to the analysis dimension indicated by the user.

[0063] For example, if the user inputs "sales trend analysis in the past six months", the data visualization module of the big data platform can query the absolute value of sales and year-on-year growth rate in the past six months, and display it to the user through a bar chart, thereby identifying user needs based on user input and displaying the charts required by the user, thereby improving the intelligence of the big data platform.

[0064] 305. Verify the indicator data of the target indicator and / or the algorithm processing result according to a preset verification rule; when the indicator data of the target indicator fails to be verified or the algorithm processing result fails to be verified, display a warning prompt message;

[0065] In an optional implementation of this embodiment, after obtaining the indicator data of the target indicator and the algorithm processing result obtained by processing the indicator data of the target indicator, the indicator data of the target indicator and / or the algorithm processing result can be verified according to a preset verification rule. When the indicator data of the target indicator fails to be verified or the algorithm processing result fails to be verified, a warning prompt message is displayed to prompt the user that the indicator data of the target indicator is incorrect or the algorithm processing result is incorrect.

[0066] Specifically, when the indicator data verification of the target indicator fails, a first warning prompt message is displayed, and the first warning prompt message is used to prompt that the indicator data verification of the target indicator fails; when the algorithm processing result verification fails, a second warning prompt message is displayed, and the second warning prompt message is used to prompt that the algorithm processing result verification fails.

[0067] The indicator data of the target indicator or the result of the algorithm processing can be verified by setting a threshold or a confidence interval of the summarized data. For example, if the indicator data of the target indicator exceeds the preset threshold, it is determined that the indicator data of the target indicator does not meet the verification rule, and the indicator data of the target indicator fails the verification; or, if the indicator data of the target indicator exceeds the corresponding confidence interval, the indicator data of the target indicator is considered to be an abnormal value, and the verification fails.

[0068] Therefore, by verifying the indicator data of the target indicator or the algorithm processing results, data that does not meet the data specifications can be identified, so that users can process the data that does not meet the data specifications and improve the accuracy of the data.

[0069] In an optional implementation of this embodiment, the user may also be supported to configure a visual warning style. Specifically, when displaying the first warning prompt information, the first warning style pre-configured for the first warning prompt information may be obtained, and the first warning prompt information may be displayed according to the pre-configured first warning style. When displaying the second warning prompt information, the second warning style pre-configured for the second warning prompt information may be obtained, and the second warning prompt information may be displayed according to the pre-configured second warning style.

[0070] For example, when displaying the above-mentioned warning prompt information, a special color can be displayed in the visual chart to highlight the indicator data or algorithm processing results with data anomalies; or flashing text or flashing patterns can be used to remind users to pay attention to the indicator data or algorithm processing results with data anomalies; or, a warning prompt message box can be displayed to display the warning prompt information of the indicator data or algorithm processing results in the message box, so that users can quickly notice the abnormal data.

[0071] Therefore, through the early warning prompts of abnormal data, users can quickly obtain abnormal data in the visualization interface, quickly discover abnormal indicator data or algorithm processing results, and facilitate users to take corresponding processing measures for abnormal data, such as eliminating abnormal indicator data, or restarting algorithm processing, so as to improve data accuracy and help ensure business accuracy and effectiveness.

[0072] The data analysis method of this embodiment comprehensively covers all aspects of the data analysis process, including data collection, cleaning, storage, calculation, modeling, training and display, etc., so that business personnel and technical personnel can share a data analysis system to complete the whole process of data analysis, which greatly reduces costs and improves data analysis efficiency.

[0073] The computer device in the embodiment of the present application is described below. Figure 5 In the embodiment of the present application, one embodiment of the computer device includes:

[0074] The computer device 500 may include one or more central processing units (CPU) 501 and a memory 505 , wherein the memory 505 stores one or more application programs or data.

[0075] The memory 505 may be a volatile storage or a persistent storage. The program stored in the memory 505 may include one or more modules, each of which may include a series of instruction operations in the computer device. Furthermore, the central processing unit 501 may be configured to communicate with the memory 505 and execute a series of instruction operations in the memory 505 on the computer device 500.

[0076] The computer device 500 may also include one or more power supplies 502, one or more wired or wireless network interfaces 503, one or more input and output interfaces 504, and / or one or more operating systems, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0077] The CPU 501 can execute the aforementioned Figures 2 to 3 The operations performed by the computer device in the illustrated embodiment will not be described in detail here.

[0078] The present application also provides a computer storage medium, wherein one embodiment includes: the computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the aforementioned Figures 2 to 3 The operations performed by the computer device in the illustrated embodiment.

[0079] The present application also provides a computer program product, wherein one embodiment includes: when the computer program product is run on a computer device, the computer device executes the aforementioned Figures 2 to 3 The operations performed by the computer device in the illustrated embodiment.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit 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 is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable 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 method described in each embodiment 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 code.

Claims

1. A data analysis method, characterized in that: The method comprises: Acquire a target data set to be analyzed, and determine indicator data of multiple indicators corresponding to the target data set; Determining the indicator data of the target indicator for algorithm processing from the indicator data of the plurality of indicators; Determine an algorithm model corresponding to the target algorithm to be executed, and input the indicator data of the target indicator into the algorithm model of the target algorithm, so that the algorithm model of the target algorithm processes the indicator data of the target indicator and outputs the algorithm processing result; Display the indicator data of the target indicator and the algorithm processing results.

2. The method according to claim 1, characterized in that The step of determining the indicator data of the target indicator for algorithm processing from the indicator data of the plurality of indicators includes: receiving an indicator configuration instruction input by a user, and determining a plurality of indicator combinations from the plurality of indicators according to the indicator configuration instruction; Determine the correlation coefficient between the multiple indicators in each of the indicator combinations; The indicator data of multiple indicators in the indicator combination whose correlation coefficient is greater than a preset threshold is used as the indicator data of the target indicator.

3. The method according to claim 1, characterized in that The step of obtaining a target data set to be analyzed includes: An initial data set to be analyzed is obtained, data cleaning is performed on the initial data set to obtain the target data set, and the target data set is stored in layers.

4. The method according to claim 1, characterized in that The determining of the indicator data of the multiple indicators corresponding to the target data set includes: Determining indicator data of a plurality of standard indicators corresponding to the target data set; Determine a derived indicator corresponding to the standard indicator and determine a composite indicator corresponding to the standard indicator, and determine indicator data of the derived indicator from the target data set; The indicator data of the standard indicator is calculated according to the indicator data algorithm corresponding to the composite indicator to obtain the indicator data of the composite indicator.

5. The method according to claim 1, characterized in that The method further comprises: Based on the random search method, the model parameters of the algorithm model of the target algorithm are updated using the updated data of the training sample data.

6. The method according to any one of claims 1 to 5, characterized in that: After displaying the indicator data of the target indicator and the algorithm processing result, the method further includes: Verifying the indicator data of the target indicator and / or the algorithm processing result according to a preset verification rule; When the indicator data verification of the target indicator fails, displaying a first warning prompt information, wherein the first warning prompt information is used to prompt that the indicator data verification of the target indicator fails; When the algorithm processing result verification fails, a second warning prompt message is displayed, and the second warning prompt message is used to prompt that the algorithm processing result verification fails.

7. The method according to claim 6, characterized in that The displaying of the first warning prompt information includes: Acquire a first warning style preconfigured for the first warning prompt information, and display the first warning prompt information according to the preconfigured first warning style; The displaying of the second warning prompt information includes: A second warning style preconfigured for the second warning prompt information is obtained, and the second warning prompt information is displayed according to the preconfigured second warning style.

8. The method according to claim 1, characterized in that: The display of the indicator data of the target indicator and the algorithm processing result includes: Receive the target indicator and / or analysis dimension indicated by the user, and display the indicator data of the target indicator indicated by the user and the algorithm processing result in the form of a chart according to the analysis dimension.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 8.

Images