Business data analysis method and device, equipment, medium and program product

Abstract

The embodiment of the invention provides a business data analysis method and device, equipment, a medium and a program product. The method comprises the following steps: acquiring original business data, and generating a data chart corresponding to the original business data according to a set chart style; generating a sub-data table of the original business data according to field data of a target field in the original business data; and determining a first analysis result of the original business data according to a comparison detection result of the data chart and the sub-data table. By utilizing the method, a certain number of data charts can be generated through the chart style generation dimension based on the original business data, and the analysis dimension is performed on the analysis item of the specific field of the original business data to generate some sub-data tables; and the analysis information contained in the data chart and the analysis information contained in the sub-data table are compared and detected to obtain the analysis result of the original business data, so that the accuracy and the reliability of the business data analysis result are improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a business data analysis method, device, equipment, medium, and program product. Background Art

[0002] At present, traditional data analysis tools can be used to perform statistical analysis of business data. However, as the business scale continues to expand, the amount of data that needs to be analyzed is also increasing in magnitude, and traditional data analysis tools are unable to cope with the analysis of large-scale data.

[0003] For the analysis of massive data, various business parties try to use machine learning models to achieve it in the hope of reducing data analysis costs. However, in actual applications, it is found that the existing machine learning models for data analysis cannot be actually applied to real business scenarios. The analysis results given by them are greatly deviated from the analysis requirements of real business scenarios, and the reliability is very poor. Summary of the invention

[0004] The present invention provides a business data analysis method, device, equipment, medium and program product, which improve the accuracy and reliability of business data analysis results.

[0005] In a first aspect, an embodiment of the present disclosure provides a business data analysis method, the business data analysis method comprising:

[0006] Obtaining original business data, and generating a data chart corresponding to the original business data according to a set chart style;

[0007] Generate a sub-data table of the original business data according to the field data of the target field in the original business data;

[0008] According to the comparison test results of the data chart and the sub-data table, a first analysis result of the original business data is determined.

[0009] In a second aspect, an embodiment of the present disclosure further provides a business data analysis device, the business data analysis device comprising:

[0010] A data chart generation module, used to obtain original business data and generate a data chart corresponding to the original business data according to a set chart style;

[0011] A sub-data table generating module, used for generating a sub-data table of the original business data according to the field data of the target field in the original business data;

[0012] The analysis result determination module is used to determine the first analysis result of the original business data according to the comparison test results of the data chart and the sub-data table.

[0013] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the business data analysis method as described in any embodiment of the present disclosure.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the business data analysis method as described in any embodiment of the present disclosure.

[0018] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the business data analysis method as described in any embodiment of the present disclosure.

[0019] The technical solution of the disclosed embodiment, through the business data analysis method provided, first obtains the original business data, and generates a data chart corresponding to the original business data according to the set chart style; then generates a sub-data table of the original business data according to the field data of the target field in the original business data; finally, determines the first analysis result of the original business data according to the comparison test result of the data chart and the sub-data table. The above technical solution of this embodiment can obtain the corresponding analysis result by performing graphic comparison analysis on the data chart and the sub-data package determined based on the original business data, thereby improving the accuracy and reliability of the business data analysis result. Compared with the prior art that directly performs data analysis on the original business, there is a problem that it cannot be actually applied to real business scenarios, and the analysis results given therefrom are greatly deviated from the analysis requirements of the real business scenarios. By adopting the technical solution, the original business data can be pre-analyzed before being input into the machine learning model, that is, a certain number of data charts are generated by generating dimensions based on the chart style of the original business data, and some sub-data tables are generated by analyzing the dimensions of the analysis items of specific fields of the original business data, and then the analysis information of the data charts obtained by the pre-analysis and processing is compared with the analysis information of the sub-data tables to obtain the analysis results of the original business data, and the analysis conclusion with higher confidence is selected as the final analysis result of the original business data based on the comparison test results, which not only avoids the unreliability of counting ability and the instability of performance caused by directly adopting the machine learning model, but also prevents the occurrence of data missing based on the pre-analysis operation, so as to obtain true, reliable and more comprehensive data analysis results that are closer to the real business scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 A flow chart of a business data analysis method provided by an embodiment of the present disclosure is given;

[0022] Figure 2 A schematic diagram of the structure of a business data analysis device provided by an embodiment of the present disclosure is given;

[0023] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is given. DETAILED DESCRIPTION

[0024] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0025] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0026] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least two embodiments"; the term "another embodiment" means "at least two additional embodiments"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0027] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0028] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0029] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0030] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0031] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0034] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0035] It should be noted that in actual applications, especially in various businesses serving the enterprise side, there is analysis of massive amounts of data. Each business attempts to use machine learning models to perform low-cost data analysis operations. Specifically, the business data in the business data table to be analyzed can be directly used as input information for the machine learning model, and then combined with the encoded business analysis description information, the business data can be analyzed through the machine learning model, and the output results can be directly used as data analysis results.

[0036] However, the existing analysis methods use machine learning models with weak counting capabilities, and have low reliability and stability for calculation problems such as summation and maximum value. Moreover, when the input data remains unchanged, the analysis results formed by the machine learning model for analysis and processing are still different. Even when the amount of business data is large, the machine learning model will only select the first part of the data for analysis during data analysis. For example, if there are 6 business data that need to be analyzed, it may get 4 corresponding analysis conclusions. However, if the input business data volume is thousands or even more, the model outputs only the analysis conclusions corresponding to a dozen business data. The analysis of business data is not thorough enough, and there is data laziness. The analysis results deviate too much from the expected analysis results in the real scenario, so the business analysis processing cannot be implemented in the real business scenario. In addition, the inaccurate and unreliable business data analysis results make it impossible for business users to trust the analysis conclusions of the machine learning model.

[0037] Based on this, the present disclosure provides a method for analyzing business data. Figure 1A flow chart of a business data analysis method provided by an embodiment of the present disclosure is given. The embodiment of the present disclosure is applicable to situations where various business data are analyzed and processed. The method can be executed by a business data analysis device, which can be implemented in the form of software and / or hardware, and optionally, by an electronic device.

[0038] For example, the execution subject of the business data analysis method provided in this embodiment can be considered as a business analysis platform, or an electronic device that integrates the business analysis function service. The electronic device is preferably a mobile terminal, a desktop computer, a laptop computer, a server, etc. In different application scenarios, the business party can use the business analysis function service through the application interface of the platform.

[0039] like Figure 1 As shown, the business data analysis method provided by the embodiment of the present disclosure may specifically include:

[0040] S101, obtaining original business data, and generating a data chart corresponding to the original business data according to a set chart style.

[0041] In this embodiment, the original business data can be considered as business data stored in a database, or business data that the business party needs to analyze and process. The chart style set in this embodiment can be implemented by existing statistical tools to obtain different chart styles. The set chart style can be a chart style pre-set by a technician, which can be set according to actual needs. The chart style set in this embodiment may include but is not limited to bar charts, pie charts, and line charts. The data chart can be considered to be statistical processing of the original business data in multiple dimensions to obtain statistical information under the corresponding dimensions, and to characterize the statistical information under the corresponding dimensions in the form of a chart.

[0042] In this embodiment, the data chart may be represented in the form of a picture; the data chart may include charts corresponding to different chart styles, and different chart styles may correspond to different statistical chart dimensions. In this embodiment, at least one data chart corresponding to the original business data may be generated. It is understandable that in this embodiment, corresponding data charts may be generated according to different set chart styles, and different data charts may use different chart styles, so the data information contained in the generated corresponding data charts may be different. In this embodiment, data charts representing different statistical dimensions of business data may be generated for the acquired original business data according to different chart styles.

[0043] S102: Generate a sub-data table of the original business data according to the field data of the target field in the original business data.

[0044] In this embodiment, the original business data can be "compressed" through the above steps, and the corresponding target fields can be determined through pre-configured analysis items to extract field data in different specific fields and generate corresponding sub-data tables based on the analysis results of the specific fields. The original business data can be considered to record the business data in the form of a data table.

[0045] Exemplarily, the original business data in this embodiment can be a business data record in the style of an Excel table. In this embodiment, when the business data is recorded in the style of a data table, different cells can be included in the data chart, and different cells can be considered as fields, and different fields contain different metadata content. The target field can be understood as the different fields contained in the original business data table. The target field in this embodiment can be determined based on pre-configured analysis items. Field data can be understood as the data content corresponding to the target field in the original business data table. The target field in this embodiment can include multiple fields, which can be set according to actual business needs. The sub-data table can be considered as each sub-data table obtained by performing a sub-table operation on the total data table of the original business data.

[0046] In this embodiment, it can be considered that the target field for dividing the original business data is first determined, and then the field data corresponding to the target field in the original business data table is extracted, and then the sub-data table of the original business data is generated according to the field data. The generation of the sub-data table in this embodiment can be considered to have pre-configured analysis items. In this embodiment, the business analysis items to be analyzed can be pre-configured according to actual business needs. Exemplarily, the business analysis items may include counting, sorting, year-on-year, maximum value, minimum value, or average value analysis of the target field.

[0047] Continuing with the above description, in this embodiment, the corresponding target field determined in the original business data table can be analyzed according to the pre-configured analysis items, and then the corresponding field data corresponding to the target field is extracted, and the field analysis results are combined to form a corresponding sub-data table. For example, an analysis item in this embodiment is the analysis, statistics and sorting of the quantity level of the target field, and can also include the analysis of the maximum and minimum values. All the analysis contents about the target field can be stored in a sub-data table.

[0048] It can be understood that in this embodiment, all analysis results obtained by analyzing a target field based on different analysis items can be recorded in a sub-data table. A sub-data table can include multiple field contents, wherein the multiple field contents may include one of the fields in the original business data table, and the other fields may be field contents obtained by analyzing based on the business analysis items.

[0049] Exemplarily, in this embodiment, the original business data table may include target fields such as "business object name", "business risk classification" and "business implementation feedback channel", and different analysis items may be configured for different target fields. Specifically, the analysis item pre-configured for the "business object name" field in the original business data table may be count, so the "business object name" field may be analyzed for counting and stored in the sub-data table corresponding to the business object name field; the analysis item pre-configured for the "business risk classification" field in the original business data table may be sorting, so the "business risk classification" field may be analyzed and processed for sorting, and the corresponding analysis data such as the maximum value or minimum value may be obtained, and stored in the sub-data table corresponding to the business risk classification field. By analogy, different analysis items may be set for different target fields according to actual business needs, so as to obtain corresponding analysis results, which are stored in the sub-data tables corresponding to the target fields respectively.

[0050] In this embodiment, different target fields in the original business data table are analyzed and processed based on pre-configured analysis items, and each sub-data table is formed by combining the corresponding analysis and processing results and the field data corresponding to the target data. In this way, the massive amount of original business data table information can be fully and effectively compressed.

[0051] S103: Determine a first analysis result of the original business data according to the comparison test results of the data chart and the sub-data table.

[0052] The comparison test result can be a test result obtained by comparing the information in the data chart with the information contained in the sub-data table. The first analysis result can be considered as an analysis result that matches the business analysis requirements, or it can be considered as a matching result obtained by comparing the data chart and the sub-data table.

[0053] In this embodiment, the process of generating a data chart corresponding to the original business data can be considered as some data statistical processing or analysis processing, which includes statistical information corresponding to the business data, which can be some textual information or some information combined with pictures and texts. The different field contents included in the sub-data table can be information obtained by analyzing and processing the target field according to different analysis items.

[0054] In this embodiment, by comparing the information contained in the data chart with the information contained in the data table, it can be determined whether the information in the data chart has corresponding information in the sub-data table, so as to obtain the same data information in the data chart and in the sub-data table as the analysis result of the original business data.

[0055] Specifically, in this embodiment, when analyzing the original business data, a corresponding analysis direction can be set based on business needs. For example, if the business needs to determine the business with the highest complaint rate, then it is necessary to perform a statistical calculation of the proportion of business data based on the original business data, generate a corresponding data chart according to the set chart style, and extract the field data of the target field in the corresponding business data according to the business needs for analysis to obtain the corresponding sub-data table, and then match and compare the information contained in the data chart and the sub-data table. If the business with the highest complaint rate determined by the business need is obtained through matching and comparison, the first analysis result of the original business data is determined.

[0056] In this embodiment, since the data chart is represented in the form of a picture, before comparing the data chart with the sub-data table, the data chart can be analyzed by image analysis to obtain multiple analysis conclusions contained in the data chart; or the data chart can be identified by graphic recognition to obtain multiple analysis conclusions, which is not limited in this embodiment.

[0057] In this embodiment, after obtaining multiple analysis conclusions from the data chart, the multiple analysis conclusions obtained from the analysis of the data chart are matched in the sub-data table to see whether there are identical analysis conclusions; if any analysis conclusion obtained from the analysis in the data chart exists in the sub-data table, it is considered that the data chart and the sub-data table can be matched, and the analysis conclusion corresponding to the match can be used as the first analysis result of the original business data; if any analysis conclusion obtained from the analysis in the data chart does not exist in the sub-data table, it can be considered that the data chart and the sub-data table do not match.

[0058] It can be understood that in this embodiment, multiple data charts can be obtained based on the original business data according to different set chart styles, and when multiple data charts are analyzed to obtain analysis conclusions, each data chart can obtain multiple analysis conclusions through analysis, and multiple analysis conclusions can participate in the comparison and detection process with multiple sub-data tables. In this embodiment, if multiple analysis conclusions need to be matched with multiple sub-data tables, the matching process can be carried out in the form of traversal, and the analysis conclusions obtained by analyzing each data chart are compared with multiple sub-data tables to obtain the comparison results of each conclusion, which can be used as the first analysis result of the original business data.

[0059] The above technical solution of this embodiment can obtain corresponding analysis results by performing graphic comparison analysis on data charts and sub-data packages determined based on the original business data, thereby improving the accuracy and reliability of the business data analysis results. Compared with the prior art that directly performs data analysis on the original business, there is a problem that it cannot be actually applied to real business scenarios, and the analysis results given by it are greatly deviated from the analysis requirements of the real business scenarios. By adopting this technical solution, the original business data can be pre-analyzed before being input into the machine learning model, that is, a certain number of data charts are generated by generating dimensions based on the chart style of the original business data, and some sub-data tables are generated by analyzing the dimensions of the analysis items of the specific fields of the original business data, and then the analysis information of the data chart obtained by the pre-analysis process is compared with the analysis information of the sub-data table to obtain the analysis results of the original business data, and the analysis conclusion with higher confidence is selected as the final analysis result of the original business data based on the comparison test results, which not only avoids the unreliability of counting ability and the instability of performance caused by directly adopting the machine learning model, but also prevents the occurrence of data missing according to the pre-analysis operation, and can obtain true, reliable, and more comprehensive data analysis results that are closer to the real business scenario.

[0060] As a second optional embodiment of this embodiment, based on the above embodiment, the sub-data table of the original business data can be generated according to the field data of the target field in the original business data, which is specifically optimized as follows:

[0061] a1) Obtain a pre-configured target analysis item, and determine a target field associated with the target analysis item.

[0062] Among them, the target analysis items can be pre-configured business analysis items. In this embodiment, some common business analysis items can be pre-integrated and pre-configured as target analysis items. The target analysis items may include counting, sorting, average, maximum and minimum values, etc. The target field can be considered as a business-related field analyzed from the original business data according to business needs; illustratively, fields such as "business risk classification", "business object name", "complaint channel" or some codes can be analyzed from the original business data as the target field of the analysis item.

[0063] In this embodiment, a pre-configured target analysis item can be obtained first, and then according to the business analysis requirement information of the original business data, the fields in the original business data that are suitable as analysis items for data analysis can be determined based on the business analysis requirements, and then the target field associated with the target analysis item can be determined.

[0064] Exemplarily, if the original business data is complaint-type business data, when the pre-configured target analysis item is count, maximum, minimum, or sorting analysis item, the target field associated with the target analysis item can be determined to be different business party names or business party identifiers, and any field that can uniquely correspond to a business object can be used as a target field associated with the target analysis item. In this embodiment, different fields that can characterize the business object can be determined from the original business data based on the target analysis item corresponding to the target analysis item as the associated target field.

[0065] b1) extracting target field data of the target field from the original business data, and analyzing and processing the target field data according to the target analysis item to obtain field analysis content corresponding to the target analysis item.

[0066] Among them, the field analysis content can be the corresponding analysis content obtained by analyzing and processing multiple field data corresponding to each target field based on different target analysis items. In this embodiment, after determining the target field associated with the target analysis item, the target field data of the target field can be extracted from the original business data, and then the extracted target fields can be analyzed and processed according to these analysis items. For example, if the target analysis item is a statistical analysis of the counting type, and the target field associated with the target analysis item is extracted as "business object name", the statistical analysis of each business object name in the original business data table can be determined, which can include the number of times the business object name A appears and the number of times the business object name B appears. After counting, the maximum value analysis item or the minimum value analysis item can be analyzed, and the analysis processing of the business object name A with the most occurrences or the business object name A with the least occurrences can be obtained, so that the field analysis content corresponding to each target analysis item can be obtained.

[0067] c1) Based on the target field, target field data, target analysis items and field analysis content, a sub-data table of the original business data is constructed.

[0068] Among them, the target field data can be considered as the specific content of the corresponding target field; for example, when the target field is "business object name", then the target field data can be considered as each specific business object name, such as business object name A, business object name B, and business object name C and other field data.

[0069] In this embodiment, in the process of constructing the sub-data table of the original business data, the target field can be displayed as a field content of the sub-data table, and then the specific field data corresponding to the target field and each target analysis item can be considered as some sorted fields in the sub-data table and the specific analysis content obtained by analyzing and processing based on the target analysis items. These data together constitute the sub-data table of the original business data.

[0070] In this embodiment, through the data focusing sub-table operation, each sub-data packet of the original business data is obtained, which realizes the "compression" processing of massive business data, improves the information density, and determines that the number of data tokens can be effectively reduced. The core data information is calculated externally, avoiding the shortcomings of the model in computing power, and solving the problem of data laziness of the model.

[0071] As a third optional embodiment of this embodiment, based on the above embodiment, the business data analysis method provided by this embodiment can determine the first analysis result of the original business data according to the comparison test results of the data chart and the sub-data table, and further optimization includes:

[0072] a2) using the data chart and the sub-data table saved in a picture format as input data, and inputting the input data into a picture-text comparison detection model in combination with pre-configured analysis requirement description information.

[0073] Among them, the analysis requirement description information can be considered as a pre-configured description text of the analysis requirement. In this embodiment, different analysis requirement description texts can be pre-configured according to different businesses to form different analysis requirement description information. The analysis requirement description information can be understood as an analysis guidance information of the image-text comparison detection model, so that the image-text comparison detection model performs corresponding comparison analysis detection on the input data charts and sub-data tables according to the analysis guidance of the analysis requirement description information. The image-text comparison detection model can be considered as a large language model that can be used to compare and detect image objects and text objects.

[0074] In this embodiment, the image-text comparison detection model can be pre-trained, and the machine learning model can be pre-trained using the proper nouns or probability information involved in the original business data to form a business knowledge base of the machine learning model, so that the machine learning model can recognize the relevant business description information involved in the input data.

[0075] In this embodiment, the determined data charts in picture format and each sub-data table, as well as different analysis requirement description information corresponding to different business data, can be input into the image-text comparison detection model so that the image-text comparison detection model performs detection processing.

[0076] b2) performing a comparison test on the data chart and the sub-data table according to the analysis requirement description information through the graphic comparison test model to obtain a comparison test result, and determining a first analysis result of the original business data according to the comparison test result.

[0077] Among them, the machine learning model adopted in this embodiment can be specifically a graphic object detection model. The comparison detection result can be considered as the analysis and processing of the graphic comparison detection model on the input data for comparison detection to obtain multiple analysis conclusions. It can be understood that in this embodiment, the data chart and the sub-data table are compared and detected based on the analysis requirement description information, and the corresponding comparison detection result can be the result that the analysis conclusion in the data chart can match the field content in the sub-data table or the result that the analysis conclusion in the data chart does not match the field content in the sub-data table. The first analysis result can be considered as the result that the analysis conclusion in the data chart can match the field content in the sub-data table.

[0078] In this embodiment, during the comparison and detection process of the image-text comparison detection model on the input data, the image-text comparison detection model will first perform an image-text recognition operation on the data chart, and use the content obtained by the image-text recognition that meets the analysis requirement description information as the image-text comparison detection model to analyze and process to obtain output information, and then match the output information obtained in the data chart with all the field contents in the sub-data table to obtain a matching or non-matching conclusion, that is, a comparison detection result, and then the matching conclusion in the comparison detection result can be used as the first analysis result of the original business data.

[0079] In this embodiment, each conclusion obtained from the image and text recognition in the data chart can be traversed and searched from the field data content included in the sub-data table. If any conclusion included in the target image and text content can be found with corresponding field data content in the sub-data table, it can be considered that there is a matching conclusion. If any conclusion included in the target image and text content cannot be found with corresponding field data content in the sub-data table, it can be considered that there is no matching conclusion.

[0080] The above technical solution of this embodiment can match and compare the input data chart and sub-data table through the image-text comparison detection model, so as to obtain the corresponding data analysis results. By pre-analyzing the original business data in different dimensions, the accuracy of the data analysis conclusion is effectively improved.

[0081] As a fourth optional embodiment of this embodiment, based on the above embodiment, the image-text comparison detection model can be optimized to perform comparison detection on the data chart and the sub-data table according to the analysis requirement description information, obtain comparison detection results, and determine the first analysis result of the original business data according to the comparison detection results:

[0082] a3) performing image and text recognition on the data chart by using the image comparison detection model to obtain the image and text recognition content of the data chart;

[0083] The image and text recognition content can be considered as multiple text conclusion contents obtained by performing image and text recognition on the data chart. In this embodiment, image and text recognition can be performed on each of the multiple data charts through the image comparison detection model, and each data chart can obtain at least one corresponding text recognition content. Multiple data charts can be recognized to obtain multiple text recognition contents to obtain all the image and text recognition contents of the data charts.

[0084] b3) Filtering target graphic content that matches the information described according to the analysis requirement from the graphic and text recognition content.

[0085] Among them, the target graphic content can be considered as the graphic content that meets the analysis requirement description information in the graphic content recognition content. In this embodiment, there can be multiple target graphic content. In this embodiment, multiple graphic content recognition results obtained from the data chart can be screened, and the graphic content that matches the analysis requirement description information can be determined as the target graphic content.

[0086] c3) performing a content comparison between the target graphic content and the field analysis content included in the sub-data table to obtain a content comparison result.

[0087] The content comparison result can be considered as the result of matching the target graphic content with the various field analysis contents contained in the sub-data table. In this embodiment, the content comparison result can include field analysis contents that are consistent with the target graphic content, and can also include field analysis contents that are inconsistent with the target graphic content.

[0088] In this embodiment, each target graphic content among multiple target graphic content and the field data content included in the sub-data table can be traversed and searched to determine whether there is any consistency between the target graphic content and the field data content included in the sub-data table. It can be obtained that the field analysis content included in the sub-data package contains field analysis content that is consistent with the target graphic content, and / or the field analysis content included in the sub-data package contains field analysis content that is inconsistent with the target graphic content, as the content comparison result.

[0089] d3) If the content comparison result is that the field analysis content contains target field analysis content that is consistent with the target graphic content, then determining a first analysis result of the original business data according to the target field analysis content.

[0090] The target field analysis content can be considered as the field analysis content included in the sub-data table that is consistent with the target graphic content. In this embodiment, there can be multiple target field analysis contents in the sub-data table. In this embodiment, if there is a target field analysis content that is consistent with the target graphic content in the field analysis content in the content comparison result, all corresponding target field analysis contents can be determined as the first analysis result of the original business data.

[0091] It can be understood that in the present embodiment, there are multiple data charts, and at least one piece of image and text recognition content can be obtained by performing image and text recognition on each data chart. Therefore, multiple pieces of image and text recognition content can be obtained by performing image and text recognition on multiple data charts. There may be a situation where the analysis content of the same field in the sub-data table is consistent with the target analysis content in the sub-data table. The target analysis content in the sub-data table has been recorded, or has been used as the first analysis result of the original business data. At this time, the same target analysis content does not need to be recorded repeatedly when it appears again.

[0092] The above technical scheme of this embodiment can match the multiple graphic recognition results obtained by data chart recognition with the multiple field analysis contents contained in the sub-data packet, and determine the field analysis contents with consistent matches as the first analysis result of the original business data, thereby improving the accuracy and reliability of the business data analysis results.

[0093] As a fifth optional embodiment of this embodiment, based on the above embodiment, the method provided in this embodiment can be further optimized to include:

[0094] a4) Accumulate the set number of data analysis times.

[0095] Among them, when the original business data is initially analyzed and processed, the number of data analysis of the original business data can be initialized to 0, and then each time the analysis process of the original business data is executed, the number of data analysis is accumulated by 1. In this embodiment, the analysis and processing process of the original business data can be executed multiple times in a loop. After obtaining the first analysis result of the original business data, it can be considered that a data analysis process has been performed, and the number of data analysis can be accumulated by 1. The data analysis process of the original business data can be repeatedly analyzed multiple times according to actual needs. Therefore, in this embodiment, the number of cycles of data analysis of the original business data can be accumulated to obtain the accumulated number of data analysis.

[0096] b4) If the accumulated number of data analysis times is less than the set threshold, the process returns to the set chart style and generates a data chart corresponding to the original business data and executes the process again.

[0097] The set threshold value may be a pre-set threshold value for the number of analyses, and may be set according to actual needs. In this embodiment, if the accumulated number of data analyses is less than the set threshold value, it can be considered that the conditions for continuing data analysis of the original business data are met, and the data analysis process can be re-executed by returning to generate a data chart corresponding to the original business data according to the set chart style.

[0098] In this embodiment, the first analysis result obtained by cyclically executing the data analysis process on the original business data may be the same or different. In each data analysis process, the selected chart style can be a different chart style, which can generate different data charts corresponding to the original business data for data analysis processing, or the same chart style can be selected. The target fields associated with the analysis may be different, which can be based on the actual analysis situation of each data analysis process. This embodiment does not limit this.

[0099] c4) if the accumulated number of data analysis times is greater than or equal to the set threshold, determining a second analysis result of the original business data according to each first analysis result of the original business data.

[0100] The second analysis result may be considered as a combined processing of the first analysis result of the original business data, or may be considered as a screening processing of the first analysis result of the original business data.

[0101] In this embodiment, after performing multiple data analysis processes on the original business data, if the accumulated number of data analysis times is greater than or equal to a set threshold, the first analysis results obtained based on the accumulated number of data analysis processes on the original business data can be merged, or the first analysis results can be screened to use the analysis results obtained after the merging or screening process as the second analysis results of the original business data.

[0102] It can be understood that in this embodiment, the first analysis results obtained after multiple data analyses of the original business data may have the same or different analysis results. The same and different analysis results in the first analysis results can be merged to obtain a wider and more comprehensive second analysis result. Alternatively, only the same analysis results in each first analysis result can be screened, and the same analysis conclusions in each first analysis result can be recorded as the second analysis result of the original business data.

[0103] In this embodiment, the second analysis result is obtained by merging or screening the first analysis results obtained by performing multiple cycles of data analysis on the original business data, which can make the obtained analysis results more comprehensive and wider in scope, thereby improving the confidence of the analysis results.

[0104] On the basis of the above optional embodiment, the second analysis result of the original business data may be further optimized according to each first analysis result of the original business data. Specifically, the optimization may be as follows:

[0105] a41) merging the first analysis results of the original business data to obtain an analysis merging result.

[0106] Among them, the analysis merging result can be considered as the result data obtained by merging and processing each first analysis result. In this embodiment, when the same data analysis logic is executed multiple times on the same original business data, different chart styles or different analysis methods can be used for data analysis, so as to obtain different first analysis results corresponding to the original business data. Correspondingly, these different first analysis results may have the same analysis conclusions or different analysis conclusions. These same analysis conclusions or different analysis conclusions can be merged to obtain the result of the total data analysis conclusion of the original business data.

[0107] b42) Inputting the analysis merging result into a set result screening model to obtain an output analysis calibration result, and determining the analysis calibration result as the second analysis result of the original business data.

[0108] Among them, the result screening model can be considered as a large language model, which can be used to screen the analysis conclusions obtained by specifying information. The analysis calibration result can be considered as the analysis conclusion obtained after the analysis merging result is screened by the screening limiting information in the result screening model. In this embodiment, the analysis calibration result obtained by the result screening model can be considered as a more accurate analysis result.

[0109] In this embodiment, some descriptive limiting information for screening can be pre-set for the result screening model, and then the result screening model can perform screening and calibration operations on multiple analysis conclusions contained in the input analysis merging results based on the pre-set descriptive information for screening, so as to obtain a more accurate analysis calibration result, and determine the analysis calibration result as the second analysis result of the original business data.

[0110] For example, if the analysis merging result contains 20 analysis conclusions, these 20 analysis conclusions are input into the set result screening model, and these 20 analysis conclusions are screened and optimized according to the screening description information in the result screening model, so that 16 more accurate analysis conclusions can be obtained. These 16 analysis conclusions can be used as the output analysis calibration results and stored as the second analysis result of the original business data, and the remaining 4 inaccurate analysis conclusions can be deleted.

[0111] In this embodiment, the analysis merging results are screened and calibrated through the set result screening model, so that the analysis results can be re-analyzed and updated, thereby improving the accuracy of the analysis conclusions and the confidence level of the analysis results of the business data.

[0112] As the sixth optional embodiment of this embodiment, based on the above embodiments, the method provided by this embodiment can be further optimized to include: performing a result sampling check on the first analysis result according to the set result sampling conditions, and adding a sampling failure mark to the data analysis results that failed the result sampling check.

[0113] Among them, the result sampling condition can be considered as the setting condition for random sampling operation of the analysis results, which can be set according to actual needs, and this embodiment does not limit this. In this embodiment, the set result sampling condition may include the setting of the sampling time or the setting of the sampling method. Exemplarily, the analysis results of the original business data can be sampled in the form of daily or weekly reports, or the analysis results can be sampled in the form of regular inspections. The sampling failure mark can be considered as a highlight display or a special mark display, which can reflect a display mark that is significantly different from other conclusion data, and can be set according to actual conditions.

[0114] In this embodiment, the analysis results obtained by performing data analysis on the original business data may not only include the corresponding analysis conclusions, but also be associated with the analysis conclusion data chart and data sub-table, and even index the location data of the target field of the original business data, etc. Specifically, each analysis conclusion contained in the first analysis result may also correspond to the image identification of the data chart of its analysis source, such as the image ID, the corresponding sub-data table representation of its analysis source, such as the sub-data table ID, and the detailed information of which row and column in the data table corresponds to the analysis conclusion, which can be set and reflected based on actual needs. After the result sampling operation, the result display of the result sampling can also be added to the analysis result, such as the result of the result sampling is correct or failed.

[0115] In this embodiment, one or two analysis conclusions of the first analysis result can be sampled according to the set result sampling conditions to verify whether the sampled analysis conclusions are correct. Specifically, the specific business data corresponding to the data chart identifier and the sub-data table identifier based on the sampled analysis conclusion can be determined from the sampled analysis conclusion to verify whether the obtained analysis conclusion is correct, and then it can be determined whether the result sampling is correct or not.

[0116] Continuing with the above description, if the sampled data obtained can correspond to the information in the corresponding data chart and sub-data table, and the analysis conclusion obtained is consistent with the information in the data chart and sub-data package, then the analysis conclusion can be considered correct. If the sampled data obtained does not correspond to the information in the corresponding data chart and sub-data table, that is, the analysis conclusion is not established, then the conclusion data of the analysis conclusion that is not established can be considered as the data analysis result of the failed sampled data, and it can be highlighted or displayed in the form of special marks to facilitate the technicians to perform manual review operations or other processing operations.

[0117] It can be understood that in this embodiment, performing a result sampling operation on the first analysis result according to the set result sampling conditions can be a way to implement the sampling operation on the first analysis result; similarly, when the second analysis result of the original business data is determined according to the first analysis result in this embodiment, the same implementation method can also be used for the second analysis result to perform a result sampling operation on the second analysis result, and add a sampling identification mark to the data analysis result identified by the result sampling operation, which is not elaborated in this embodiment.

[0118] In this embodiment, the analysis results of the original business data are extracted through the set result sampling conditions, and the corresponding analysis data are checked again to verify the accuracy of the analysis conclusions, thereby further ensuring the accuracy and credibility of the data analysis conclusions; and by adding a sampling failure mark to the data analysis results that fail the sampling inspection, it is convenient for relevant technical personnel to perform manual review operations again, so as to better proofread and review the data that failed the sampling inspection.

[0119] As the seventh optional embodiment of this embodiment, based on the above embodiment, the method provided by this embodiment can be further optimized to include: in response to the triggered analysis result display request, generating and displaying the analysis display content of the original business data according to the first analysis result.

[0120] Among them, the analysis result display request can be a request initiated by the user to display the analysis results corresponding to the original business data. The analysis display content can be considered as visual display information of the first analysis result. In this embodiment, the analysis display content of the analysis result may include the analysis conclusion and the source information on which the analysis conclusion is based, such as associated data charts, sub-data tables, sampling information, and corresponding configuration information, etc., which can be provided to the user in a visual display manner, so that the user can intuitively understand the entire analysis process, making the analysis process traceable.

[0121] In this embodiment, the data analysis and processing of the original business data can be considered as a data analysis function provided by the business analysis platform for the user. The user may have an access link to the business analysis platform. When the user provides the original business data to be analyzed and processed through the access link, the first analysis result obtained by the business analysis platform through the corresponding business analysis logic can be displayed to the user. It can be understood that the user can trigger the corresponding analysis result display request, and the business analysis platform in this embodiment can respond to the analysis result display request triggered by the user, generate visual analysis display content for the first analysis result corresponding to the original business data provided by the user and display it.

[0122] It should be noted that, in this embodiment, the analysis display content may not only include the display presentation effect of each analysis conclusion, but also the data chart or sub-data table associated with the analysis conclusion may be presented as a display content, so that each analysis conclusion has a corresponding source of analysis basis, so that the user can trace back the analysis conclusion.

[0123] It can be understood that in this embodiment, in response to the triggered analysis result display request, the analysis display content of the original business data can be generated and displayed based on the first analysis result, which is an implementation method of the first analysis result; similarly, if the second analysis result of the original business data is determined based on the first analysis result in this embodiment, the same analysis result display implementation method can also be used for the second analysis result, so as to generate and display the analysis display content of the original business data based on the second analysis result, and the effect is presented, which is not elaborated in this embodiment.

[0124] In this embodiment, corresponding analysis display information is generated in response to the user's analysis result display request, so that the user can clearly and intuitively understand the multiple conclusion data obtained after data analysis of the business data, thereby improving the user experience.

[0125] Figure 2 A schematic diagram of the structure of a business data analysis device provided by an embodiment of the present disclosure is given. Figure 2 As shown, the device includes: a data chart generating module 21, a sub-data table generating module 22 and an analysis result determining module 23, wherein:

[0126] The data chart generation module 21 is used to obtain the original business data and generate a data chart corresponding to the original business data according to a set chart style;

[0127] A sub-data table generating module 22, configured to generate a sub-data table of the original business data according to the field data of the target field in the original business data;

[0128] The analysis result determination module 23 is used to determine the first analysis result of the original business data according to the comparison test result of the data chart and the sub-data table.

[0129] The disclosed embodiment provides a business data analysis device, which can perform a graphic comparison analysis on a data chart and a sub-data package determined based on the original business data to obtain a corresponding analysis result, thereby improving the accuracy and reliability of the business data analysis result. Compared with the prior art, which directly performs data analysis on the original business, there is a problem that it cannot be actually applied to the real business scenario, and the analysis result given by it has a large deviation from the analysis requirements of the real business scenario. By adopting the technical solution, the original business data can be pre-analyzed before being input into the machine learning model, that is, a certain number of data charts are generated by generating dimensions based on the chart style of the original business data, and some sub-data tables are generated by analyzing the dimensions of the analysis items of the specific fields of the original business data, and then the analysis information of the data chart obtained by the pre-analysis processing is compared with the analysis information of the sub-data table to obtain the analysis result of the original business data, and the analysis conclusion with higher confidence is selected as the final analysis result of the original business data based on the comparison test result, which not only avoids the unreliability of the counting ability and the instability of the performance caused by directly adopting the machine learning model, but also prevents the occurrence of data missing according to the pre-analysis operation, so that a true, reliable and more comprehensive data analysis result can be obtained, which is closer to the real business scenario.

[0130] Furthermore, the sub-data table generating module 22 can be specifically used for:

[0131] Obtaining a pre-configured target analysis item, and determining a target field associated with the target analysis item;

[0132] Extracting target field data of the target field from the original business data, and analyzing and processing the target field data according to the target analysis item to obtain field analysis content corresponding to the target analysis item;

[0133] Based on the target field, target field data, target analysis items and field analysis content, a sub-data table of the original business data is constructed.

[0134] Furthermore, the analysis result determination module 23 may include:

[0135] A model input unit, used to use the data chart and the sub-data table saved in a picture format as input data, and input the input data into the picture-text comparison detection model in combination with pre-configured analysis requirement description information;

[0136] The model comparison and detection unit is used to compare and detect the data chart and the sub-data table according to the analysis requirement description information through the graphic comparison and detection model, obtain the comparison and detection result, and determine the first analysis result of the original business data according to the comparison and detection result.

[0137] Furthermore, the model comparison detection unit can be specifically used for:

[0138] Performing image and text recognition on the data chart by using the image comparison detection model to obtain image and text recognition content of the data chart;

[0139] Filtering target graphic content that matches the information described according to the analysis requirement from the graphic recognition content,

[0140] Compare the target graphic content with the field analysis content included in the sub-data table to obtain a content comparison result;

[0141] If the content comparison result is that the field analysis content contains target field analysis content that is consistent with the target graphic content, a first analysis result of the original business data is determined according to the target field analysis content.

[0142] Furthermore, the device may also include:

[0143] A times accumulation module, used for accumulating a set number of data analyses after determining the first analysis result of the original business data;

[0144] A re-execution module, for returning to generate a data chart corresponding to the original business data according to a set chart style and re-executing if the accumulated number of data analysis times is less than a set threshold;

[0145] The second analysis result determination module is used to determine the second analysis result of the original business data according to the first analysis results of the original business data if the accumulated number of data analysis times is greater than or equal to the set threshold.

[0146] Furthermore, the second analysis result determination module can be specifically used for:

[0147] Merging the first analysis results of the original business data to obtain an analysis merger result;

[0148] The analysis merging result is input into a set result screening model to obtain an output analysis calibration result, and the analysis calibration result is determined as the second analysis result of the original business data.

[0149] Furthermore, the device may also include: a sampling inspection module, which is used to perform a sampling inspection on the first analysis result according to the set result sampling inspection conditions, and add a sampling inspection failure mark to the data analysis result that fails the result sampling inspection.

[0150] Furthermore, the device may also include: a display module, which is used to generate and display the analysis display content of the original business data according to the first analysis result in response to the triggered analysis result display request. The business data analysis device provided in the embodiment of the present disclosure can execute the business data analysis method provided in any embodiment of the present disclosure, and has the functional modules and beneficial effects corresponding to the execution method.

[0151] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0152] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is given. Figure 3 , which shows an electronic device (eg, Figure 3 The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0153] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An edit / output (I / O) interface 305 is also connected to the bus 304.

[0154] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0155] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0156] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0157] The electronic device provided in the embodiment of the present disclosure and the business data analysis method provided in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0158] The embodiments of the present disclosure provide a computer storage medium on which a computer program is stored. When the program is executed by a processor, the business data analysis method provided by the above embodiments is implemented.

[0159] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0160] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0161] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0162] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: receives a trigger operation for a page editing component in a first interface, and displays a second interface, wherein the second interface includes a page preview area and a page content configuration area, wherein an initial page is presented in the page preview area, and the page content configuration area includes at least one page content configuration entry, wherein the initial page includes a content-to-be-filled position to be filled with content, and the page content configuration entry is associated with the content-to-be-filled position; receives an editing operation for the page content configuration entry, and presents a target page corresponding to the edited page content configuration entry in the page preview area.

[0163] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0164] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0166] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0167] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0168] According to one or more embodiments of the present disclosure, [Example 1] provides a business data analysis method, the method comprising:

[0169] Obtaining original business data, and generating a data chart corresponding to the original business data according to a set chart style;

[0170] Generate a sub-data table of the original business data according to the field data of the target field in the original business data;

[0171] According to the comparison test results of the data chart and the sub-data table, a first analysis result of the original business data is determined.

[0172] According to one or more embodiments of the present disclosure, [Example 2] provides a business data analysis method, wherein the method generates a sub-data table of the original business data according to the field data of the target field in the original business data, including:

[0173] Obtaining a pre-configured target analysis item, and determining a target field associated with the target analysis item;

[0174] Extracting target field data of the target field from the original business data, and analyzing and processing the target field data according to the target analysis item to obtain field analysis content corresponding to the target analysis item;

[0175] Based on the target field, target field data, target analysis items and field analysis content, a sub-data table of the original business data is constructed.

[0176] When it is monitored that the target game meets the progress collection condition during operation, the game operation data of the target game is written into the local storage space as progress archive content through the progress saving interface configured in the container.

[0177] According to one or more embodiments of the present disclosure, [Example 3] provides a business data analysis method, wherein the method determines a first analysis result of the original business data according to the comparison test result of the data chart and the sub-data table, including:

[0178] The data chart and the sub-data table saved in a picture format are used as input data, and the input data is input into a picture-text comparison detection model in combination with pre-configured analysis requirement description information;

[0179] Through the graphic-text comparison detection model, the data chart and the sub-data table are compared and detected according to the analysis requirement description information to obtain a comparison detection result, and the first analysis result of the original business data is determined according to the comparison detection result.

[0180] According to one or more embodiments of the present disclosure, [Example 4] provides a business data analysis method, in which the data chart and the sub-data table are subjected to a comparison test according to the analysis requirement description information through the image-text comparison test model to obtain a comparison test result, and a first analysis result of the original business data is determined according to the comparison test result, including:

[0181] Performing image and text recognition on the data chart by using the image comparison detection model to obtain image and text recognition content of the data chart;

[0182] Filtering target graphic content that matches the information described according to the analysis requirement from the graphic recognition content,

[0183] Compare the target graphic content with the field analysis content included in the sub-data table to obtain a content comparison result;

[0184] If the content comparison result is that the field analysis content contains target field analysis content that is consistent with the target graphic content, a first analysis result of the original business data is determined according to the target field analysis content.

[0185] According to one or more embodiments of the present disclosure, [Example 5] provides a business data analysis method, in which after determining the first analysis result of the original business data, the method may also be optimized to include:

[0186] Accumulate the set number of data analysis times;

[0187] If the accumulated number of data analysis times is less than the set threshold, the process returns to generate a data chart corresponding to the original business data according to the set chart style and executes again;

[0188] If the accumulated number of data analysis times is greater than or equal to the set threshold, a second analysis result of the original business data is determined according to each first analysis result of the original business data.

[0189] According to one or more embodiments of the present disclosure, [Example 6] provides a business data analysis method. Optionally, in the method, determining a second analysis result of the original business data according to each first analysis result of the original business data includes:

[0190] Merging the first analysis results of the original business data to obtain an analysis merger result;

[0191] The analysis merging result is input into a set result screening model to obtain an output analysis calibration result, and the analysis calibration result is determined as the second analysis result of the original business data.

[0192] According to one or more embodiments of the present disclosure, [Example 7] provides a business data analysis method, the method further comprising:

[0193] The first analysis result is subjected to a result sampling check according to the set result sampling check conditions, and a sampling check failure mark is added to the data analysis result that fails the result sampling check.

[0194] According to one or more embodiments of the present disclosure, [Example 8] provides a business data analysis method, the method further comprising:

[0195] In response to the triggered analysis result display request, analysis display content of the original business data is generated and displayed according to the first analysis result.

[0196] According to one or more embodiments of the present disclosure, [Example 9] provides a business data analysis device, the device comprising:

[0197] A data chart generation module, used to obtain original business data and generate a data chart corresponding to the original business data according to a set chart style;

[0198] A sub-data table generating module, used for generating a sub-data table of the original business data according to the field data of the target field in the original business data;

[0199] The analysis result determination module is used to determine the first analysis result of the original business data according to the comparison test results of the data chart and the sub-data table.

[0200] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0201] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0202] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A business data analysis method, characterized in that: include: Obtaining original business data, and generating a data chart corresponding to the original business data according to a set chart style; Generate a sub-data table of the original business data according to the field data of the target field in the original business data; According to the comparison test results of the data chart and the sub-data table, a first analysis result of the original business data is determined.

2. The method according to claim 1, characterized in that The step of generating a sub-data table of the original business data according to the field data of the target field in the original business data comprises: Obtaining a pre-configured target analysis item, and determining a target field associated with the target analysis item; Extracting target field data of the target field from the original business data, and analyzing and processing the target field data according to the target analysis item to obtain field analysis content corresponding to the target analysis item; Based on the target field, target field data, target analysis items and field analysis content, a sub-data table of the original business data is constructed.

3. The method according to claim 1, characterized in that Determining the first analysis result of the original business data according to the comparison test result of the data chart and the sub-data table includes: The data chart and the sub-data table saved in a picture format are used as input data, and the input data is input into a picture-text comparison detection model in combination with pre-configured analysis requirement description information; Through the graphic-text comparison detection model, the data chart and the sub-data table are compared and detected according to the analysis requirement description information to obtain a comparison detection result, and the first analysis result of the original business data is determined according to the comparison detection result.

4. The method according to claim 3, characterized in that The step of performing a comparison test on the data chart and the sub-data table according to the analysis requirement description information through the graphic comparison test model to obtain a comparison test result, and determining a first analysis result of the original business data according to the comparison test result includes: Performing image and text recognition on the data chart by using the image comparison detection model to obtain image and text recognition content of the data chart; Filtering target graphic content that matches the information described according to the analysis requirement from the graphic and text recognition content; Compare the target graphic content with the field analysis content included in the sub-data table to obtain a content comparison result; If the content comparison result is that the field analysis content contains target field analysis content that is consistent with the target graphic content, a first analysis result of the original business data is determined according to the target field analysis content.

5. The method according to claim 1, characterized in that After determining the first analysis result of the original business data, the method further includes: Accumulate the set number of data analysis times; If the accumulated number of data analysis times is less than the set threshold, the process returns to generate a data chart corresponding to the original business data according to the set chart style and executes again; If the accumulated number of data analysis times is greater than or equal to the set threshold, a second analysis result of the original business data is determined according to each first analysis result of the original business data.

6. The method according to claim 5, characterized in that Determining the second analysis result of the original business data according to each first analysis result of the original business data includes: Merging the first analysis results of the original business data to obtain an analysis merger result; The analysis merging result is input into a set result screening model to obtain an output analysis calibration result, and the analysis calibration result is determined as the second analysis result of the original business data.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: The first analysis result is subjected to a result sampling check according to the set result sampling check conditions, and a sampling check failure mark is added to the data analysis result that fails the result sampling check.

8. The method according to any one of claims 1 to 6, characterized in that: Also includes: In response to the triggered analysis result display request, analysis display content of the original business data is generated and displayed according to the first analysis result.

9. A business data analysis device, characterized in that: include: A data chart generation module, used to obtain original business data and generate a data chart corresponding to the original business data according to a set chart style; A sub-data table generating module, used for generating a sub-data table of the original business data according to the field data of the target field in the original business data; The analysis result determination module is used to determine the first analysis result of the original business data according to the comparison test results of the data chart and the sub-data table.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the business data analysis method as described in any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the business data analysis method as described in any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the business data analysis method according to any one of claims 1 to 8.

Images