Data report generation method, electronic device, storage medium and computer program product

Abstract

The present application discloses a data report generation method, electronic device, storage medium and computer program product, which relate to the fields of large model technology and data analysis technology. The method includes: obtaining a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; calling the target language model to analyze the data file and the brief description information to generate an analysis plan; based on the analysis plan, calling the target language model to perform mathematical statistics on the data file to obtain the target statistical results; generating a target data report based on the target statistical results. The present application solves the technical problems in the related art that the data report generation plan has a complex process, low efficiency, and a high degree of reliance on manual operation of technicians.

Description

Technical Field

[0001] The present application relates to the fields of large model technology and data analysis technology, and in particular to a data report generating method, electronic device, storage medium and computer program product. Background Art

[0002] When processing large amounts of data, enterprises and individual users need to be able to quickly and accurately obtain valuable information, and need to present this information in an easy-to-understand form. However, the automated data mining methods provided in the prior art pay more attention to the process of exploration based on data features, and only present the data mining results in a simple text form, which is difficult to meet the user's needs for information presentation. In addition, users can also manually draw charts or make reports based on the data features obtained by mining to meet the above-mentioned information presentation needs, but the whole process is relatively complicated and time-consuming. It is difficult to ensure the accuracy of the correlation between the searched or mined data and the final generated data report, and users are required to have a variety of professional skills, and the technical threshold is high.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a data report generation method, an electronic device, a storage medium, and a computer program product to at least solve the technical problems in the related art that the data report generation solution has a complex process, low efficiency, and a high reliance on manual operation of technicians.

[0005] According to one aspect of an embodiment of the present application, a data report generation method is provided, including: obtaining a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; calling a target language model to analyze the data file and the brief description information to generate an analysis plan, wherein the analysis plan is used to perform data extraction and value assessment on the data content in the data file based on the brief description information; based on the analysis plan, calling the target language model to perform mathematical statistics on the data file to obtain target statistical results, wherein the target statistical results are used to record insights that match the content to be reported; and generating a target data report based on the target statistical results.

[0006] According to another aspect of an embodiment of the present application, a data report generation method is also provided, including: obtaining a commodity sales data file and commodity sales summary information, wherein the commodity sales data file is used to provide commodity sales data content prepared for generating a data report that meets commodity sales requirements, and the commodity sales summary information is used to briefly describe the commodity sales content to be reported; calling a target language model to analyze the commodity sales data file and the commodity sales summary information to generate a commodity sales analysis plan, wherein the commodity sales analysis plan is used to extract commodity sales data and evaluate commodity sales value from the commodity sales data file based on the commodity sales summary information; based on the commodity sales analysis plan, calling the target language model to perform mathematical statistics on the commodity sales data file to obtain commodity sales statistical results, wherein the commodity sales statistical results are used to record commodity sales insights that match the commodity sales content to be reported; and generating a commodity sales data report based on the commodity sales statistical results.

[0007] According to another aspect of an embodiment of the present application, a data report generation method is also provided, including: obtaining a data report generation request through a first application programming interface, wherein the request data carried in the data report generation request includes: a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; returning a data report generation response through a second application programming interface, wherein the response data carried in the data report generation response includes: a target data report, the target data report is generated based on a target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief description information and then generates it, and the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief description information.

[0008] According to another aspect of an embodiment of the present application, a data report generation method is also provided, which provides a graphical user interface through a terminal device, and the data report generation method includes: in response to a first control operation performed on the graphical user interface, uploading a data file and entering brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; in response to a second control operation performed on the graphical user interface, a target data report is generated, the target data report is generated based on target statistical results, the target statistical results are obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical results are used to record insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief description information and then generates it, and the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief description information; and the target data report is displayed in the graphical user interface.

[0009] According to another aspect of an embodiment of the present application, an electronic device is further provided, including: a memory storing an executable program; and a processor for running the program, wherein any one of the above-mentioned data report generation methods is executed when the program is running.

[0010] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned data report generation methods.

[0011] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, it implements any one of the above-mentioned data report generation methods.

[0012] In an embodiment of the present application, a data file and a brief description information are obtained, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; the target language model is called to analyze the data file and the brief description information to generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file according to the brief description information; based on the analysis plan, the target language model is called to perform mathematical statistics on the data file to obtain the target statistical results, wherein the target statistical results are used to record the insights that match the content to be reported; and the target data report is generated based on the target statistical results. Thus, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief description information, and the analysis and mathematical statistics involved in this process are all automated, ensuring that the target data report is closely related to the data content and the content to be reported, and achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the efficiency of data report generation and user-friendliness, and thus solving the technical problems of the data report generation scheme in the related technology that the process is complex, the efficiency is low, and the dependence on manual operation of technicians is strong.

[0013] It is easy to notice that the above general description and the following detailed description are only for the purpose of exemplifying and explaining the present application, and do not constitute a limitation of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1 It is a schematic diagram of an application scenario of a data report generation method according to an embodiment of the present application;

[0016] Figure 2 is a flow chart of a data report generating method according to an embodiment of the present application;

[0017] Figure 3 is a schematic diagram of an optional data report generation process according to an embodiment of the present application;

[0018] Figure 4 is a flow chart of another data report generating method according to an embodiment of the present application;

[0019] Figure 5 is a flow chart of another data report generating method according to an embodiment of the present application;

[0020] Figure 6is a flow chart of another data report generating method according to an embodiment of the present application;

[0021] Figure 7 is a structural schematic diagram of a data report generating device according to an embodiment of the present application;

[0022] Figure 8 is a structural schematic diagram of another data report generating device according to an embodiment of the present application;

[0023] Fig. 9 is a structural schematic diagram of another data report generating device according to an embodiment of the present application;

[0024] Fig.10 is a structural schematic diagram of another data report generating device according to an embodiment of the present application;

[0025] Fig.11 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] The technical solution provided in this application is mainly implemented using large-scale model technology. The large model here refers to a deep learning model with large-scale model parameters, which can usually contain hundreds of millions, tens of billions, hundreds of billions, trillions or even more than 10 trillion model parameters. The large model can also be called a foundation model / foundation model. The large model is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as large-scale language model (Large Language Model, LLM for short), multi-modal pre-training model, etc.

[0029] It should be noted that when the large model is actually applied, the pre-trained model can be fine-tuned through a small number of samples so that the large model can be applied to different tasks. For example, the large model can be widely used in natural language processing (NLP), computer vision, speech processing and other fields, and can be specifically applied to computer vision tasks such as visual question answering (VQA), image caption (IC), image generation, etc. It can also be widely used in text-based sentiment classification, text summary generation, machine translation and other natural language processing tasks. Therefore, the main application scenarios of the large model include but are not limited to digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc. In the embodiment of the present application, the generation of data reports through a large language model in an e-commerce scenario is used as an example for explanation.

[0030] First, some nouns or terms that appear in the process of describing the embodiments of the present application are subject to the following explanations.

[0031] Large Language Model (LLM): refers to an advanced deep learning architecture that can master the complex ability to understand and generate natural language through training on large amounts of text data. Large language models can not only deeply analyze text content, but also use logical reasoning skills to generate coherent and insightful text, thus demonstrating excellent performance in understanding and creating complex language structures.

[0032] Mathematical statistics: Mathematical statistics is a mathematical discipline based on probability theory, focusing on analyzing and explaining the statistical laws behind random phenomena. Commonly used mathematical statistics methods include hypothesis testing (used to verify whether the data pattern is significant) and regression analysis (used to explore the correlation between variables).

[0033] According to an embodiment of the present application, a data report generating method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Considering the huge number of model parameters of the large model and the limited computing resources of the mobile terminal, the above data report generation method provided in the embodiment of the present application can be applied to Figure 1 The application scenarios shown are not limited to these. Figure 1 In the application scenario shown, the large model is deployed in the server 10, and the server 10 can be connected to one or more client devices 20 through a local area network connection, a wide area network connection, an Internet connection, or other types of data networks. The client device 20 here may include but is not limited to: a smart phone, a tablet computer, a laptop computer, a PDA, a personal computer, a smart home device, a vehicle-mounted device, etc. The client device 20 can interact with the user through a graphical user interface to implement the call of the large model, thereby implementing the method provided in the embodiment of the present application.

[0035] In an embodiment of the present application, a system composed of a client device and a server can perform the following steps: the client device uploads a data file and brief description information to the server, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; the server executes a call to the target language model to analyze the data file and the brief description information, generates an analysis plan, and based on the analysis plan, calls the target language model to perform mathematical statistics on the data file to obtain the target statistical results, and generates a target data report based on the target statistical results, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information, and the target statistical results are used to record insights that match the content to be reported. Further, the server returns the target data report to the client. It should be noted that when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiment of the present application can be performed in the client device.

[0036] Under the above operating environment, this application provides Figure 2 The data report generation method shown. Figure 2 is a flow chart of a data report generation method according to an embodiment of the present application, such as Figure 2 As shown, the data report generating method includes the following steps S21 to S24.

[0037] Step S21, obtaining data files and brief description information, wherein the data files are used to provide data content prepared for generating data reports that meet field requirements, and the brief description information is used to briefly describe the content to be reported.

[0038] The above data files may contain raw data and / or pre-processed data, such as table files, database query results, etc. The data content in the above data files may include structured data, such as table data; the above data content may also include semi-structured data, such as Extensible Markup Language (XML) data, (JavaScript Object Notation, JSON) data, etc.; the above data content may also include unstructured data, such as text, images, etc.

[0039] The above brief information can be a description of the user's requirements for the target data report to be generated. The brief information includes but is not limited to: analysis objectives, analysis dimensions, expected report results, and problem background. Obtaining the above brief information can help the target language model understand and focus on the user's requirements for generating data reports.

[0040] The above method steps provided in the embodiment of the present application can provide data analysis and data report generation services for preset application scenarios. The technical fields to which the above preset application scenarios belong may include but are not limited to: financial field, medical field, education field, e-commerce sales field, etc. Data files in different fields may correspond to unique data report generation requirements. Users can enter brief information while uploading data files to reflect the field requirements corresponding to the data files.

[0041] Taking the e-commerce sales application scenario as an example, the above data file may include e-commerce sales data, such as order quantity, sales, geographical distribution, time series, etc. The user uploads the above e-commerce sales data and briefly describes the information he wants to know (i.e. enters a brief description), such as "analyze the sales trend of a certain product in 2023".

[0042] Step S22, calling the target language model to analyze the data file and the brief information, and generating an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief information.

[0043] The target language model can be a large model for understanding and generating natural language. In the embodiment of the present application, the target language model can understand the user's needs and design an analysis plan based on the data file and brief information input by the user.

[0044] The above target language model can also be a data asset evaluation model, a machine learning algorithm (such as support vector machine, random forest, etc.), a document topic generation model (Latent Dirichlet Allocation, LDA for short), a data regression analysis model (such as Bayesian regression model, outlier robust regressor, etc.) and a data dimension evaluation model, etc. For example, the above analysis plan can be generated by preprocessing, feature extraction, data extraction, data integration, value evaluation, result verification, etc. of the data file and brief information through the above target language model.

[0045] Still taking the e-commerce sales application scenario as an example, the system calls the target language model to perform preliminary analysis on the uploaded data file and brief information, and generates an analysis plan. The analysis plan may include: which data to filter (such as the sales record of a certain product in 2023), which statistical methods to use (such as time series analysis or regional distribution analysis), and determine the type of visualization to be generated (such as a linear trend chart or a map heat map).

[0046] Step S23, based on the analysis scheme, calling the target language model to perform mathematical statistics on the data file to obtain target statistical results, wherein the target statistical results are used to record insights that match the content to be reported.

[0047] The above mathematical statistics can be a statistical analysis process achieved by combining the target language model with cloud computing resources. The above cloud computing resources can be cloud servers that provide computing services to users, or processors (such as central processing units, graphics processing units, etc.) deployed in the cloud that provide users with a usage interface. The above cloud computing resources can be used as an extension of the user's local computing resources to provide users with a stronger computing level.

[0048] By performing mathematical statistics on data files, it is possible to obtain data characteristics, data trends, and relationships between data in the data files. The above-mentioned target statistical results can be data analysis insights related to the brief information that are screened and summarized after statistical analysis.

[0049] In some specific implementations, during the process of performing mathematical statistics on a data file based on an analysis scheme, the target language model performs preprocessing, information extraction, statistical analysis, data association, context recognition, data integration and other operations on the data content in the data file to obtain the above-mentioned target statistical results.

[0050] The above data analysis insights can be information extracted from the data content that can provide support and guidance for decision-making. These data analysis insights may be about the discovery of market trends, customer behavior patterns, key issues in business processes, or the optimization direction of product performance, etc. For example, an e-commerce company analyzes users' purchase history and browsing behavior and discovers data analysis insights including: sales peaks and sales troughs of certain products in a specific time period, and common decision paths of users in the purchase process. These are data analysis insights.

[0051] Still taking the e-commerce sales application scenario as an example, according to the analysis plan, the system will call cloud computing resources to perform specific statistical calculations. For example, in order to analyze the "sales trend of a certain product in 2023", the system may choose to calculate the sales of the product in each month and apply time series analysis to identify growth or decline patterns. After the calculation is completed, the system will evaluate which statistical results are of high value to the user and filter out insights such as "sales in the third quarter showed obvious seasonal growth."

[0052] Step S24, generating a target data report based on the target statistical results.

[0053] The above target data report can combine text descriptions and visual charts to clearly and intuitively present analytical insights to users for easy understanding.

[0054] Still taking the e-commerce sales application scenario as an example, the target language model is used to convert the target statistical results into an easy-to-understand text description, and the visualization generation interface is used to generate a chart corresponding to the text description (for example, a linear trend chart is used to show the seasonal changes in the sales of a certain product in 2023). Furthermore, the above text description and chart are integrated into a data report. The chart can be an interactive chart, through which users can easily view the sales trends of each month and quarter in 2023 and the corresponding cause analysis (i.e., insights) of these trends.

[0055] Through the above steps S21 to S24, the data report generation process provided by the embodiment of the present application realizes the automation and intelligence of the whole process. In other words, the user does not need to have data science or statistical knowledge, and only by providing data files and brief information, the system can automatically complete the whole process from data understanding, solution design, data calculation to data report generation according to the scheme provided by the embodiment of the present application. Thus, the above-mentioned data report generation method provided by the embodiment of the present application can significantly improve the work efficiency of data report generation, reduce the threshold of data analysis, ensure the accuracy and professionalism of data reports, and is particularly suitable for processing complex data and refining deep insights. For example, in an e-commerce sales scenario, the system can quickly identify and report the key trends and patterns of sales data for different product lines, different time periods, and different regions, helping decision makers to quickly make data-based decisions.

[0056] In an embodiment of the present application, a data file and a brief description information are obtained, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; the target language model is called to analyze the data file and the brief description information to generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file according to the brief description information; based on the analysis plan, the target language model is called to perform mathematical statistics on the data file to obtain the target statistical results, wherein the target statistical results are used to record the insights that match the content to be reported; and the target data report is generated based on the target statistical results. Thus, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief description information, and the analysis and mathematical statistics involved in this process are all automated, ensuring that the target data report is closely related to the data content and the content to be reported, and achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the efficiency of data report generation and user-friendliness, and thus solving the technical problems of the data report generation scheme in the related technology that the process is complex, the efficiency is low, and the dependence on manual operation of technicians is strong.

[0057] In an optional embodiment, in step S22, calling the target language model to analyze the data file and the brief information to generate an analysis solution includes the following method steps:

[0058] Step S221, calling the target language model to perform intent recognition on the data file and the brief description information to obtain an intent recognition result;

[0059] Step S222, calling the target language model to generate a data overview of the intent recognition result to obtain a target data overview;

[0060] Step S223, calling the target language model to perform content analysis on the target data overview and generate an analysis plan.

[0061] The above-mentioned intent recognition refers to the process of natural language parsing of data files and brief information through a target language model. Through intent recognition, the user's specific needs and expected analysis direction can be understood.

[0062] The pre-trained target language model can also be used to generate a data overview of the intent recognition results to obtain the target data overview. The target data overview can be used to provide an overview of the data structure, data type and basic statistical information of the data content and brief information based on the intent recognition results.

[0063] The above-mentioned pre-trained target language model can also be used to perform content analysis on the target data overview, and then determine the analysis plan, which can be a mathematical statistics strategy and data visualization strategy designed based on the intent recognition results and the target data overview for extracting insights. In other words, based on the analysis plan, the system can extract data and evaluate the value of the data content according to the brief information.

[0064] Still taking the e-commerce sales application scenario as an example, the comma-separated values ​​(CSV) file uploaded by the user contains multi-dimensional data such as orders, sales, product information, customer feedback, etc. The brief information entered by the user is "Analyze the sales trend and influencing factors of a certain product in various regions in 2023". The target language model will parse keywords such as "2023", "various regions", "certain product", "sales trend" and "influencing factors" (that is, intent recognition) to understand that the user wants to see the product sales performance based on time series and the potential driving factors behind it.

[0065] Furthermore, the system uses the target language model to generate an overview of the target data, describing the variables in the dataset (CSV file in this case), data types (such as timestamps, numerical values, categorical data), data ranges (such as sales data from January to December 2023), and preliminary statistics (such as total sales, average sales, etc.).

[0066] Furthermore, based on the intent recognition results (such as "analyze the sales trends and influencing factors of a certain product in various regions in 2023") and the data overview (such as the scope and basic statistical information of the data set), the target language model will generate an analysis plan. The analysis plan may include: monthly time series analysis of the sales of a certain product, exploring the relationship between product type and sales, calculating the impact of price and promotional activities on sales, etc. The analysis plan will also make visualization suggestions, such as using a line chart to show sales trends, a heat map to represent regional sales distribution, and a scatter plot to analyze the relationship between price and sales volume.

[0067] Through the above steps S221 to S223, the technical solution provided by the embodiment of the present application can accurately understand the user's needs, conduct a comprehensive overview of the data set, and design a targeted and professional analysis solution. Compared with the user manually setting the analysis indicators and methods, the solution provided by the embodiment of the present application greatly reduces the user's initial workload, lowers the threshold for data analysis, and also ensures the comprehensiveness and accuracy of the analysis.

[0068] In an optional embodiment, in step S23, calling the target language model to perform mathematical statistics on the data file to obtain the target statistical result includes the following method steps:

[0069] Step S231, determining an analysis object from a data file based on an analysis plan, and obtaining a target data statistical method corresponding to the analysis object based on the analysis plan;

[0070] Step S232, calling the target language model to perform a feasibility assessment on the analysis object to obtain an assessment result, wherein the assessment result is used to assess whether the analysis object supports the analysis solution;

[0071] Step S233, in response to the evaluation result satisfying the preset evaluation condition, calling the cloud computing resources to perform mathematical statistics on the analysis object according to the target data statistics method to obtain an initial statistical result;

[0072] Step S234, calling the target language model to perform statistical analysis on the initial statistical results to obtain target statistical results.

[0073] In the above optional embodiments, in the process of the target language model and the cloud computing resources performing mathematical statistics on the data file, an analysis object is determined from the data file based on the analysis plan, and the analysis object may be a specific data subset or a specific data dimension selected in the data file for in-depth statistical analysis; a target data statistical method corresponding to the analysis object is obtained based on the analysis plan, and the target data statistical method may be a specific mathematical statistics method for processing the analysis object, such as regression analysis, variance analysis, time series analysis, and the like.

[0074] Furthermore, calling the target language model to perform a feasibility assessment on the analysis object can be to check whether the analysis object is suitable for the analysis scheme specified in the analysis scheme before performing the statistical analysis, so as to ensure the effectiveness and accuracy of the analysis, thereby obtaining the above-mentioned assessment result. The assessment result can be a feasibility score corresponding to the analysis object and the analysis scheme.

[0075] When the above evaluation results meet the preset evaluation conditions, it is considered that the above evaluation and analysis object supports the analysis plan. At this time, the cloud computing resources are called to perform mathematical statistics on the analysis object according to the target data statistical method, and then the initial statistical results corresponding to the above target data statistical method are obtained. In other words, the above preset evaluation conditions can be necessary conditions before statistical analysis set to ensure the quality of analysis, such as data integrity conditions, data distribution characteristics conditions, etc.

[0076] Furthermore, the target language model is called to conduct a comprehensive analysis and interpretation of the initial statistical results, and meaningful insights (that is, insights that match the content to be reported) are extracted from the initial statistical results. These insights are used as key information in generating data reports to obtain target statistical results.

[0077] Still taking the e-commerce sales application scenario as an example, the analysis plan may include "analyzing the sales trend of a certain product in various regions in 2023" and exploring the "relationship between product type and sales". In this regard, the system will determine the "sales records of a certain product in various regions" from the data file as the trend analysis object, and the "sales data under different product types" as the analysis object of the influencing factors. For "sales trend", the target data statistical method may be set to time series analysis; for "relationship between product type and sales", the target data statistical method may be set to regression analysis.

[0078] Furthermore, the system evaluates the analysis object by calling the target language model, checks whether the data corresponding to the analysis object meets the applicable conditions of the target data statistical method, and obtains the evaluation result. For example, confirm whether the "sales records of a certain product in various regions" contain complete time series data to support trend analysis; check whether the "sales data under different product types" has sufficient variability to ensure the effectiveness of regression analysis.

[0079] Furthermore, after confirming that the analysis object supports the analysis scheme based on the evaluation results, the system will call cloud computing resources to execute the target data statistics method. Taking the time series analysis of "sales trend" as an example, cloud computing resources will process "sales records of a certain product in each region", calculate the average monthly sales, and predict future sales trends through the time series analysis model. The preliminary statistical results may reveal that the sales of region A have obvious seasonal fluctuations.

[0080] Furthermore, the target language model is called to conduct an in-depth analysis of the initial statistical results. The target language model will parse the output of the time series analysis model and identify the seasonal variation of sales. For example, it may generate "sales in region A peak in summer and drop significantly in winter" to form the target statistical results.

[0081] Through the above steps S231 to S234, the technical solution provided by the embodiment of the present application realizes an automated and intelligent data analysis process, ensuring the accuracy and professionalism of each step from data screening to statistical analysis, while also speeding up the speed of the entire analysis process. Through the deep involvement of the target language model, the system can not only understand the user's intentions, but also self-evaluate the effectiveness of the analysis, further utilize cloud computing resources to efficiently perform statistical calculations, and ultimately generate target statistical results with clear insights. The technical solution provided by the embodiment of the present application reduces the data analysis burden of non-professional users, improves the efficiency and accuracy of the analysis, and enables users to quickly obtain information that has direct guiding significance for their business, such as the seasonal analysis results of e-commerce sales can directly guide future inventory management and promotion strategies.

[0082] In an optional embodiment, in step S231, obtaining a target data statistical method corresponding to the analysis object based on the analysis scheme includes the following method steps:

[0083] Step S2311, selecting a target data statistical method from a data analysis knowledge base based on an analysis plan, wherein the data analysis knowledge base is used to provide a plurality of candidate data statistical methods, and the plurality of candidate data statistical methods are obtained after being classified according to a preset classification standard.

[0084] The above-mentioned data analysis knowledge base can be a pre-built database containing a variety of mathematical and statistical methods, which are designed for different types of data and common analysis scenarios, such as time series analysis, cluster analysis, regression analysis, etc.

[0085] The above-mentioned preset classification standards may include multi-dimensional classification standards such as data type (numeric, classification, time series, etc.), statistical purpose (trend analysis, correlation analysis, anomaly detection, etc.) and visualization effect (line chart, scatter plot, heat map, etc.).

[0086] The statistical methods in the data analysis knowledge base are classified according to the preset classification standards. For example, time series analysis is classified into the "trend analysis" category, while regression analysis is classified into the "correlation analysis" category. This helps the system quickly match the most relevant analysis method to ensure that the analysis plan can be effectively implemented.

[0087] Still taking the e-commerce sales application scenario as an example, the analysis plan requires analysis of "the sales trend of a certain product in various regions in 2023" and "the impact of product type on sales", and the system will select the most suitable mathematical statistics method from the data analysis knowledge base. For example, for sales trend analysis, the system may search for statistical methods suitable for time series data from the data analysis knowledge base and select the Autoregressive Integrated MovingAverage Model (ARIMA model for short) for time series analysis. For example, for the analysis of the impact of product type on sales, the system may select "regression analysis" to evaluate the relationship between product type and sales.

[0088] Through the above step S2311, the technical solution provided by the embodiment of the present application helps to automatically select the most appropriate mathematical statistics method for data analysis based on the specific needs of the user and the characteristics of the uploaded data by constructing and utilizing the data analysis knowledge base. The above technical solution not only reduces the requirement for users to have advanced statistical knowledge, but also ensures the professionalism and accuracy of data analysis (because the selection of statistical methods is based on the preset classification standards of field experts).

[0089] In an optional embodiment, the preset classification criteria include at least some of the following options: the type of data to which the data statistical method is applicable; the usage scenarios associated with the data statistical method; and the visualization scheme supporting the data statistical method.

[0090] Preset classification standards are the key organizing principles in the data analysis knowledge base. Preset classification standards can help the system select the most appropriate statistical method according to the specific situation when processing data. These preset classification standards include the type of data applicable to the statistical method, the associated usage scenarios, and the supporting visualization solutions.

[0091] For data types that are applicable to data statistics methods, the data types may include numerical, categorical, time series, etc. Different data statistics methods are applicable to different types of data. For example, numerical data can use descriptive statistical analysis (such as calculating the mean, median, standard deviation, etc.) or inferential statistical analysis (such as T test (Student's t-test), Analysis of Variance (ANOVA), etc.) to explore the distribution and differences of data. For example, categorical data can use frequency analysis or chi-square test to analyze the distribution and correlation between categories. For another example, time series data can use time series analysis (such as ARIMA model or Seasonal Autoregressive Integrated Moving Average (SARIMA) model) to identify the trend and seasonality of data.

[0092] For usage scenarios related to data statistics methods, the usage scenarios can be application scenarios of data statistics methods in specific business or research contexts. These usage scenarios help the system understand which statistical methods are more effective in a specific problem domain. For example, for market trend analysis scenarios, time series analysis may be used to predict the future trend of commodity sales. For another example, for user behavior research scenarios, cluster analysis may be used to identify the characteristics of different user groups.

[0093] For visualization solutions that match data statistics, visualization solutions can be chart types and design principles that display statistical results, which can help users intuitively understand the results of data analysis. For example, a line chart in a chart type is used to display the trend of time series data, such as the change in product sales over time. A scatter plot in a chart type is used to explore the relationship between two numerical variables, such as the correlation between product prices and product sales. A bar chart or pie chart in a chart type is used to display the distribution of categorical data.

[0094] Through the setting strategy of the above-mentioned preset classification standards, the embodiment of the present application combines these preset classification standards, and the system can automatically identify the type of data and the user's demand scenario after receiving the user's data file and brief information, thereby intelligently selecting the appropriate data statistics method and supporting visualization solution. The above-mentioned technical solution not only greatly simplifies the process of data analysis, allowing non-professional users to quickly obtain professional-level data reports, but also ensures the accuracy of the analysis results and the comprehensibility of the visualization effect, and improves the efficiency and quality of obtaining data insights.

[0095] In an optional embodiment, in step S234, calling the target language model to perform statistical analysis on the initial statistical results to obtain the target statistical results includes the following method steps:

[0096] Step S2341, simplifying and summarizing the initial statistical results to obtain a summarized and simplified result;

[0097] Step S2342, calling the target language model to perform statistical analysis on the summary and simplification results to obtain analysis results, wherein the analysis results are used to filter out partial statistical results that are adapted to the domain requirements from the summary and simplification results and determine the classification method corresponding to the partial statistical results;

[0098] Step S2343, classify and count some statistical results based on the classification method to obtain target statistical results.

[0099] Simplifying and summarizing the initial statistical results may be to screen, merge and summarize the initial statistical results to reduce the amount of data and highlight key information. The target language model analyzes and screens out some statistical results that are compatible with the domain requirements based on the summarized and simplified results obtained after the simplification and summarization process, and determines the classification method corresponding to the partial statistical results. Furthermore, according to the classification method determined by the target language model, the selected partial statistical results are further classified and analyzed to reveal the deep structure and pattern of the data.

[0100] Still taking the e-commerce sales application scenario as an example, assume that the initial statistical results include the sales volume, sales volume, product type distribution, etc. of a certain product in each region every day in 2023. The simplification and aggregation processing will involve the following filtering operations, aggregation operations, and summarization operations. In the filtering operation, data directly related to the user's brief information (such as sales trends), such as monthly sales, is retained, and irrelevant or redundant information is eliminated. In the aggregation operation, the data is aggregated by month or quarter, and the average, sum, etc. are calculated to reduce the amount of data and provide a more macro perspective. In the summarization operation, the key features of the statistical data are extracted, such as seasonal fluctuations in sales volume, significant growth points in sales, etc.

[0101] The target language model will conduct in-depth analysis of the summarized and simplified results. For example, in an e-commerce scenario, the target language model may identify that sales in several regions, such as Region A and Region B, have significant seasonal fluctuations, while other regions have less obvious fluctuations. The target language model will also determine which statistical results are most valuable for analyzing sales trends and influencing factors, and which results can be grouped together (such as all regions that show seasonal fluctuations are grouped together as "seasonal sales regions") to provide clearer and more targeted insights.

[0102] Further, the statistical results are classified according to the classification method, such as further analyzing the specific fluctuation patterns of the data of all seasonal sales regions. This may include calculating statistical indicators such as the mean and median within each classification to highlight the differences between different classifications. For example, the system may generate a target statistical result of "Region A and Region B have sales growth of more than 20% in the summer, while Region C has an increase of less than 10%."

[0103] Through the above steps S2341 to S2343, the technical solution provided by the embodiment of the present application realizes automated big data processing and complex statistical analysis, which not only greatly reduces the amount of data and highlights key information, but also screens and classifies the statistical results that best meet the user's field needs through intelligent analysis of the target language model. The above technical solution ensures the refinement, professionalism and pertinence of the data report, helping users with non-technical backgrounds to quickly understand the insights behind the data and effectively guide decision-making.

[0104] In an optional embodiment, in step S2341, the initial statistical results are simplified and summarized to obtain a summary and simplified result, including the following method steps:

[0105] Step S2344, filtering the initial statistical results based on a preset filtering standard to obtain a filtering result, wherein the preset filtering standard is determined according to the feature value of the initial statistical results and the importance of the data involved in the initial statistical results;

[0106] Step S2345, classifying and integrating the approximate results in the screening results to obtain an integrated result;

[0107] Step S2346, summarize the integration results to obtain a summarized and simplified result.

[0108] The above-mentioned preset screening criteria can be a set of defined rules or indicators for evaluating the relevance and importance of statistical results to ensure that the output information is highly targeted to user needs. The above-mentioned feature value can be the contribution of each feature in the statistical results to the analysis target, such as significance, explanatory power, etc. The above-mentioned data importance can be the influence of data on business decisions or analysis goals, which is usually related to the scope, time span or business criticality of the data.

[0109] The above-mentioned approximate results can be data items or analysis results of similar or related nature in the statistical results obtained after the screening process. The above-mentioned classification and integration can be to classify and merge similar or related screening results to reveal deeper patterns or trends. The above-mentioned summary processing can be used to further refine and summarize the classified and integrated data to form a more concise and insightful summary and simplified result.

[0110] Still taking the e-commerce sales application scenario as an example, assume that the initial statistical results include time series analysis of sales data of a certain product in various regions in 2023, analysis of the impact of product type on sales, analysis of the relationship between customer feedback and sales, etc. The above preset screening criteria may include significance criteria, explanatory power criteria, and business criticality criteria. The significance criteria are used to ensure that regional sales data with significant change trends or obvious seasonality are retained in time series analysis. The explanatory power criteria are used to ensure that product types that can significantly explain sales changes are retained in the correlation analysis between product type and sales. The business criticality criteria are used to ensure that regions and product types with high sales or high feedback rates are retained when analyzing the relationship between user feedback and sales.

[0111] Furthermore, the results may include seasonal trend analysis of sales data for multiple regions. Categorization will group all regions that show similar seasonal fluctuations into one category, such as "Summer Hot Sales Region", and distinguish it from other categories such as "Winter Hot Sales Region" to more clearly show the sales patterns of different regions.

[0112] In the e-commerce sales application scenario, the integration results are summarized, such as calculating the average sales and sales growth rate from the data of the "summer hot-selling regions" category to provide a general view and obtain the summary and simplified results. The summary and simplified results may include calculating the average sales growth percentage of all hot-selling regions throughout the summer (such as June, July, and August), as well as the sales peak and sales valley of each hot-selling region.

[0113] Through the above steps S2344 to S2346, the technical solution provided in the embodiment of the present application can automatically identify and highlight those statistical results that are most valuable to user needs, and further refine the data through classification, integration and summary processing to help users quickly understand the inherent patterns and key information of the data. The above technical solution effectively reduces information overload and improves the clarity of data insights and the efficiency of decision support. For example, in an e-commerce sales analysis report, users can immediately see which regions have significantly increased sales in a specific season and which product types have the greatest impact on sales without having to find this information in a large amount of data and analysis results, thereby providing strong data support for formulating seasonal promotion strategies and optimizing inventory management.

[0114] In an optional embodiment, in step S24, generating a target data report based on the target statistical result includes the following method steps:

[0115] Step S241, obtaining a target visualization scheme of the target statistical result;

[0116] Step S242, calling the target language model to perform text summary on the target statistical results to obtain a target summary text;

[0117] Step S243, generating a target data report based on the target visualization scheme and the target summary text.

[0118] The above target statistical results may be statistical analysis results that are determined to be valuable and highly matched with user needs after mathematical statistics and intelligent screening. The above target visualization scheme may be a chart type and design strategy tailored for displaying the target statistical results. The target visualization scheme is used to make the data analysis results more intuitive and easier to understand.

[0119] The target summary text may be a concise description of the target statistical results generated by the target language model. The target summary text may be used to provide supplementary information for the chart to help users understand data insights. The target data report may be a data analysis report that integrates visualization and text description of the target statistical results. The target data report may be used to provide data insights in a user-friendly manner.

[0120] Still taking the e-commerce sales application scenario as an example, suppose the target statistical results reveal the sales trends of "summer hot-selling areas" and "winter hot-selling areas", the significant impact of certain product types on sales, etc. The process of obtaining the target visualization solution may include the following operations: determining the chart type, such as selecting a suitable chart type according to the nature of the target statistical results; designing chart details (including axis labels, legends, color coding, etc.) to ensure that the chart accurately conveys the meaning of the statistical results; customized design, such as adding seasonal annotations when designing a line chart based on the sales trend, and using size or color in a scatter plot to indicate the sales influence of a product type.

[0121] Furthermore, the target language model is called to conduct an in-depth analysis of the target statistical results, extract key information, and generate a target summary text. For example, the target summary text generated by the target language model may be: "Sales in regions A and B increased by 20% in the summer, but stabilized at a lower level in the winter, indicating that seasonal factors have a significant impact on sales in these regions." The above target summary text provides a clear explanation of the data trends shown in the chart.

[0122] Furthermore, the target visualization scheme (such as line chart, scatter plot) and the target summary text (a concise description of the statistical results) are combined to generate a comprehensive and intuitive target data report. In the target data report, each chart will be accompanied by a corresponding text description to explain the data trend or insight shown in the chart.

[0123] Through the above steps S241 to S243, the technical solution provided by the embodiment of the present application can automatically generate a data report that contains both intuitive visual charts and refined text summaries, thereby improving the quality and readability of the report. The above technical solution not only reduces the difficulty for users to understand and interpret complex data, but also ensures the accurate communication of data analysis results, so that users with non-technical backgrounds can easily obtain data insights. For example, in e-commerce sales analysis, users do not need to have professional statistical knowledge, but can understand key information such as sales trends and product influence through clear charts and text descriptions in the report, providing a basis for decision-making for inventory management, promotion strategy formulation, etc.

[0124] In an optional embodiment, in step S241, obtaining a target visualization scheme of the target statistical result includes the following method steps:

[0125] Step S2411, selecting a target visualization scheme from the data analysis knowledge base based on the target statistical result, wherein the data analysis knowledge base is used to provide a plurality of candidate visualization schemes, and the plurality of candidate visualization schemes are respectively matched with different candidate data statistical methods.

[0126] The data analysis knowledge base may be a database or system that centrally stores a variety of mathematical statistics methods and their corresponding visualization solutions. The data analysis knowledge base is used to quickly match data statistics methods with optimal visualization expressions.

[0127] The candidate visualization schemes can be a set of chart types and design strategies that match specific candidate data statistical methods. These candidate visualization schemes can be pre-defined in the knowledge base to adapt to different types of statistical analysis results.

[0128] Still taking the e-commerce sales application scenario as an example, assume that the target statistical results include an analysis of the significant increase in sales of a certain product in various regions in the summer of 2023, and also include statistical conclusions on the relationship between product type and sales. Based on the target statistical results, select the most appropriate visualization scheme from the data analysis knowledge base. Specifically, identify the type of target statistical results (such as time series analysis results or correlation analysis results), and then search for candidate visualization schemes matching the type in the knowledge base. For example, time series analysis results are suitable for display with a line chart, while correlation analysis results are more suitable for display with a scatter plot or heat map. Furthermore, according to the characteristics of the target statistical results and the target visualization effect, select the appropriate chart type and design strategy from the candidate visualization schemes. For example, for statistical results with a significant increase in sales, you may choose to use a marked line chart to highlight the growth trend and key time points.

[0129] According to the above step S2411, the embodiment of the present application can provide the most appropriate chart presentation method for complex data statistical results by intelligently selecting the target visualization scheme from the data analysis knowledge base, ensuring the intuitiveness and comprehensibility of data insights. The above technical solution not only reduces the user's workload and professional requirements in chart design, but also improves the quality and professionalism of data reports, allowing users to quickly capture key information in the data and provide strong support for e-commerce operations, sales strategies and other decisions. For example, in the report, users can intuitively see a line chart of summer sales growth and a scatter plot of the correlation between product type and sales. Without additional data analysis or chart design, they can understand the meaning of the data and the business insights behind it.

[0130] In an optional embodiment, in step S243, generating a target data report based on the target visualization scheme and the target summary text includes the following method steps:

[0131] Step S2431, calling the view recommendation model to perform visualization view analysis on the target visualization scheme and the target summary text, and generating a target data report.

[0132] The view recommendation model may be an algorithm model based on machine learning, and the view recommendation model is used to recommend suitable visualization views according to data features, text descriptions, and user preferences.

[0133] Still taking the e-commerce sales application scenario as an example, assume that the target statistical results reveal the sales growth of a certain product in various regions in the summer of 2023 and the significant correlation between product type and sales. The target visualization scheme may include a line chart to show the time series changes in sales, and a scatter plot to show the impact of product type. The target summary text contains a concise description of these statistical results, such as "In the summer, sales in regions A and B increased significantly, by 20%, while region C increased by only 10%; the sales growth of electronic products and household products was the most obvious." On this basis, the process of calling the view recommendation model to perform visualization view analysis can specifically include: first, analyzing data features. The model will analyze the features that the chart should display based on the data type, distribution and trend of the target statistical results and the key information mentioned in the text. For example, it is determined that the changing trend of the time series should be emphasized in the line chart, and the linear or nonlinear relationship between variables should be highlighted in the scatter plot; second, recommending the best view. The model will recommend the chart design that best suits the current data and text description (including color coding, legends, axis labels and other design details) to ensure that the view can accurately reflect the data and meet the requirements of user readability and aesthetics; further, generating a data report. The model integrates the recommended visualization view and the target summary text into the data report to form an analysis report that contains both intuitive charts and detailed explanations. For example, the report can include a line chart that clearly shows the time series changes in the sales of a certain product in various regions in summer. The line chart is accompanied by a text description to explain the growth trend. The report can also include a scatter plot that shows the relationship between product type and sales. The scatter plot is accompanied by a text description to highlight the product type with a stronger correlation.

[0134] According to the above step S2431, the embodiment of the present application can automatically generate professional, user-friendly visualization views for complex data statistical results by calling the view recommendation model, and at the same time combine refined text descriptions to improve the quality and readability of data reports. The above technical solution not only reduces the workload of users in data analysis and report production, but also ensures the accuracy and professionalism of the report, allowing users to obtain in-depth data insights at the lowest learning cost. For example, in e-commerce sales analysis, users do not need to have professional knowledge of data visualization design, but can clearly understand the sales trends and influencing factors of different regions and product types through the charts and text descriptions in the report, providing a basis for formulating sales strategies, product positioning, etc.

[0135] In an exemplary application scenario, the following is provided: Figure 3 A data report generation process is shown in FIG. Figure 3As shown in the figure, the links corresponding to the black boxes are implemented by the large language model, and the links corresponding to the white boxes are implemented by the content generation interface. Data preparation is completed through the content generation interface. The data prepared here includes a data analysis knowledge base, which is used to provide candidate mathematical statistics methods. The large language model performs intent recognition based on user input (including data files and brief information), obtains intent recognition results, generates a data overview based on the intent recognition results, and performs content analysis on the data overview to generate an analysis plan. Next, enter the link of "selecting several analysis objects based on user input".

[0136] In the process of selecting several analysis objects based on user input, the content generation interface determines the analysis object based on data extraction of the analysis plan, and selects the target data statistical method from the data analysis knowledge base. The large language model performs a feasibility assessment on the analysis object and the target data statistical method to obtain the evaluation results. Next, the content generation interface traverses all calculations that may have value, which involves multiple mathematical statistical calculations in the traversal, to obtain the initial statistical results. Then, the content generation interface summarizes and simplifies the initial statistical results to obtain a summarized and simplified result. Furthermore, the large language model will perform result analysis on the summarized and simplified results to obtain the analysis results. Next, several valuable results are extracted from the analysis results for display.

[0137] Specifically, in the process of extracting several valuable results for display, the content generation interface integrates relevant calculation results. Specifically, the content generation interface integrates some relevant calculation results in the analysis results based on the classification method to obtain the classification statistical results (that is, the target statistical results). Then, the large language model summarizes the classification statistical results and generates a description text. Furthermore, the content generation interface visualizes the description text based on the pre-selected target visualization scheme, that is, the visualization generation interface is realized.

[0138] Still like Figure 3 As shown, after selecting several analysis objects based on user input, a summary text is generated by a large language model, and a sharing function is provided by a content generation interface. Specifically, it can support sharing of target data reports in the form of pictures, documents, etc.

[0139] In summary, the technical solution proposed in the embodiment of the present application creatively integrates a large language model, a professional visual analysis knowledge base, and a self-developed visualization generation interface to achieve automated and intelligent data report generation. Compared with traditional business intelligence (BI) tools, the technology provided by this application simplifies the user's learning process, lowers the threshold for technology use, shortens the cycle from data import to report generation, and significantly improves the efficiency and convenience of data processing. In particular, the solution provided by this application cleverly combines text descriptions with visual charts to present data insights in an intuitive and easy-to-understand form, which not only enhances the attractiveness of the report, but also improves the efficiency and readability of information transmission, ensuring that users can quickly and accurately understand the deep meaning behind the data.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0141] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0143] In the aforementioned operating environment, the present application also provides Figure 4A method for generating a data report is shown. Figure 4 is a flow chart of a data report generation method according to an embodiment of the present application, such as Figure 4 As shown, the data report generation method includes:

[0144] Step S41, obtaining a commodity sales data file and commodity sales brief information, wherein the commodity sales data file is used to provide commodity sales data content prepared for generating a data report that meets commodity sales requirements, and the commodity sales brief information is used to briefly describe the commodity sales content to be reported;

[0145] Step S42, calling the target language model to analyze the commodity sales data file and the commodity sales brief information, and generating a commodity sales analysis plan, wherein the commodity sales analysis plan is used to extract commodity sales data and evaluate commodity sales value from the commodity sales data file based on the commodity sales brief information;

[0146] Step S43, based on the commodity sales analysis solution, calling the target language model to perform mathematical statistics on the commodity sales data file to obtain commodity sales statistical results, wherein the commodity sales statistical results are used to record commodity sales insights that match the commodity sales content to be reported;

[0147] Step S44, generating a commodity sales data report based on the commodity sales statistics results.

[0148] The embodiments of the present application can be used to provide data report generation services in commodity sales scenarios. The whole process of data report generation in commodity sales scenarios is automated and intelligent. In other words, users do not need to have knowledge of data science or statistics. By simply providing commodity sales data files and commodity sales brief information, the system can automatically complete the whole process from data understanding, solution design, data calculation to data report generation according to the solution provided by the embodiments of the present application. Therefore, the above-mentioned data report generation method provided by the embodiments of the present application can significantly improve the work efficiency of commodity sales data report generation, lower the threshold of commodity sales data analysis, ensure the accuracy and professionalism of commodity sales data reports, and is particularly suitable for processing complex commodity sales data and extracting deep commodity sales insights.

[0149] In an embodiment of the present application, a commodity sales data file and commodity sales summary information are obtained, wherein the commodity sales data file is used to provide commodity sales data content prepared for generating a data report that meets commodity sales requirements, and the commodity sales summary information is used to briefly describe the commodity sales content to be reported; a target language model is called to analyze the commodity sales data file and the commodity sales summary information to generate a commodity sales analysis plan, wherein the commodity sales analysis plan is used to extract commodity sales data and evaluate commodity sales value from the commodity sales data file based on the commodity sales summary information; based on the commodity sales analysis plan, the target language model is called to perform mathematical statistics on the commodity sales data file to obtain commodity sales statistical results, wherein the commodity sales statistical results are used to record commodity sales insights that match the commodity sales content to be reported; and a commodity sales data report is generated based on the commodity sales statistical results. Therefore, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief information. The analysis and mathematical statistics involved in this process are automated, ensuring that the target data report is closely related to the data content and the content to be reported, thereby achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the data report generation efficiency and user-friendliness, and further solving the technical problems in the related technology that the data report generation solution has a complex process, low efficiency, and a strong reliance on manual operation of technical personnel.

[0150] It should be noted that the preferred implementation of the above steps S41 to S44 can be found in the above-mentioned related descriptions and will not be repeated here.

[0151] In the aforementioned operating environment, this application provides the following Figure 5 A method for generating a data report is shown. Figure 5 is a flow chart of a data report generation method according to an embodiment of the present application, such as Figure 5 As shown, the data report generation method includes:

[0152] Step S51, obtaining a data report generation request through a first application programming interface, wherein the request data carried in the data report generation request includes: a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the field requirements, and the brief description information is used to briefly describe the content to be reported;

[0153] Step S52, returning a data report generation response through the second application programming interface, wherein the response data carried in the data report generation response includes: a target data report, the target data report is generated based on the target statistical results, the target statistical results are obtained after the analysis plan calls the target language model to perform mathematical statistics on the data file, the target statistical results are used to record insights that match the content to be reported, the analysis plan calls the target language model to analyze the data file and the brief description information and then generates it, and the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information.

[0154] The first application programming interface and the second application programming interface may be the same application programming interface or different application programming interfaces. In an optional embodiment, the interface parameters in the first application programming interface and the second application programming interface may include but are not limited to: interface global identifier, interface signature key, interface timestamp, interface request identifier, system call credential identifier, etc. The first application programming interface may use GET or POST as the interface request method to obtain the file processing request. The second application programming interface may use JSON format to feedback the file processing response.

[0155] In an embodiment of the present application, a data report generation request is obtained through a first application programming interface, wherein the request data carried in the data report generation request includes: a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; a data report generation response is returned through a second application programming interface, wherein the response data carried in the data report generation response includes: a target data report, the target data report is generated based on a target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief description information and then generates it, and the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief description information. Therefore, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief information. The analysis and mathematical statistics involved in this process are automated, ensuring that the target data report is closely related to the data content and the content to be reported, thereby achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the data report generation efficiency and user-friendliness, and further solving the technical problems in the related technology that the data report generation solution has a complex process, low efficiency, and a strong reliance on manual operation of technical personnel.

[0156] It should be noted that the preferred implementation of the above steps S51 to S52 can refer to the relevant descriptions in the above embodiments, which will not be repeated here.

[0157] In the aforementioned operating environment, this application provides the following Figure 6 A data report generation method is shown. A graphical user interface is provided through a terminal device, Figure 6 is a flow chart of a data report generation method according to an embodiment of the present application, such as Figure 6 As shown, the data report generation method includes:

[0158] Step S61, in response to a first control operation performed on the graphical user interface, uploading a data file and inputting brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the field requirements, and the brief description information is used to briefly describe the content to be reported;

[0159] Step S62, in response to the second control operation performed on the graphical user interface, a target data report is generated, the target data report is generated based on the target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record the insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief information, and the analysis scheme is used to extract data and evaluate the value of the data content in the data file according to the brief information;

[0160] Step S63: display the target data report in the graphical user interface.

[0161] According to the above method steps, a visualization scheme for data report generation function is provided. The terminal device provides a graphical user interface, and at least a data report generation scene is displayed in the graphical user interface. The display content of the graphical user interface also includes an input component (such as a text input box, a voice input control, etc.) and a display component (such as a text display window, an image display window, etc.). The user performs a first control operation on the input component, uploads a data file and enters a brief description information to specify the data content prepared in the data report generation task to generate a data report that meets the field requirements and briefly describes the content to be reported. The above graphical user interface may also include a trigger component, and the user may trigger the generation of a target data report by performing a second control operation on the trigger component. Further, the above graphical user interface may also include a display component, and when the target data report is generated, it automatically triggers the display of the target data report in the display component of the graphical user interface. The above visualization scheme is user-friendly and convenient for users, and has a good user experience.

[0162] In an embodiment of the present application, in response to a first control operation performed on a graphical user interface, a data file is uploaded and brief description information is input, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; in response to a second control operation performed on the graphical user interface, a target data report is generated, the target data report is generated based on target statistical results, the target statistical results are obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical results are used to record insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief description information and generates it, the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief description information; the target data report is displayed in the graphical user interface. Therefore, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief information. The analysis and mathematical statistics involved in this process are automated, ensuring that the target data report is closely related to the data content and the content to be reported, thereby achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the data report generation efficiency and user-friendliness, and further solving the technical problems in the related technology that the data report generation solution has a complex process, low efficiency, and a strong reliance on manual operation of technical personnel.

[0163] It should be noted that the preferred implementation of the above steps S61 to S63 can be found in the relevant descriptions in the above embodiments, and will not be repeated here.

[0164] According to an embodiment of the present application, a device embodiment for implementing the above-mentioned data report generating method is also provided. Figure 7 is a structural diagram of a data report generating device according to an embodiment of the present application, such as Figure 7 As shown, the device includes: an acquisition module 701, which is used to acquire data files and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; an analysis module 702, which is used to call the target language model to analyze the data file and the brief description information and generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information; a statistical module 703, which is used to call the target language model to perform mathematical statistics on the data file based on the analysis plan to obtain a target statistical result, wherein the target statistical result is used to record insights that match the content to be reported; a generation module 704, which is used to generate a target data report based on the target statistical result.

[0165] Optionally, the above-mentioned analysis module 702 is also used to: call the target language model to perform intent recognition on the data file and brief description information to obtain the intent recognition result; call the target language model to generate a data overview of the intent recognition result to obtain a target data overview; call the target language model to perform content analysis on the target data overview to generate an analysis plan.

[0166] Optionally, the above-mentioned statistical module 703 is also used to: determine the analysis object from the data file based on the analysis plan, and obtain the target data statistical method corresponding to the analysis object based on the analysis plan; call the target language model to perform a feasibility assessment on the analysis object to obtain an assessment result, wherein the assessment result is used to evaluate whether the analysis object supports the analysis plan; in response to the assessment result satisfying the preset assessment condition, call the cloud computing resources to perform mathematical statistics on the analysis object according to the target data statistical method to obtain an initial statistical result; call the target language model to perform statistical analysis on the initial statistical result to obtain the target statistical result.

[0167] Optionally, the statistical module 703 is further used to select a target data statistical method from a data analysis knowledge base based on an analysis plan, wherein the data analysis knowledge base is used to provide a plurality of candidate data statistical methods, and the plurality of candidate data statistical methods are obtained after being classified according to a preset classification standard.

[0168] Optionally, in the above-mentioned data report generating device, the preset classification standard includes at least some of the following options: the type of data applicable to the data statistical method; the usage scenario associated with the data statistical method; and the visualization scheme supporting the data statistical method.

[0169] Optionally, the above-mentioned statistical module 703 is also used to: simplify and summarize the initial statistical results to obtain summarized and simplified results; call the target language model to perform statistical analysis on the summarized and simplified results to obtain analysis results, wherein the analysis results are used to filter out partial statistical results that are adapted to domain requirements from the summarized and simplified results and determine the classification method corresponding to the partial statistical results; classify and count the partial statistical results based on the classification method to obtain the target statistical results.

[0170] Optionally, the above-mentioned statistical module 703 is also used to: filter the initial statistical results based on preset filtering criteria to obtain filtering results, wherein the preset filtering criteria are determined according to the characteristic value of the initial statistical results and the importance of the data involved in the initial statistical results; classify and integrate the approximate results in the filtering results to obtain integrated results; summarize the integrated results to obtain summarized and simplified results.

[0171] Optionally, the above-mentioned generation module 704 is also used to: obtain a target visualization scheme for the target statistical results; call the target language model to perform text summary on the target statistical results to obtain a target summary text; and generate a target data report based on the target visualization scheme and the target summary text.

[0172] Optionally, the generation module 704 is further used to select a target visualization scheme from a data analysis knowledge base based on the target statistical results, wherein the data analysis knowledge base is used to provide a plurality of candidate visualization schemes, and the plurality of candidate visualization schemes are respectively matched with different candidate data statistical methods.

[0173] Optionally, the generating module 704 is further used to: call the view recommendation model to perform a visualization view analysis on the target visualization scheme and the target summary text, and generate a target data report.

[0174] It should be noted here that the above-mentioned acquisition module 701, analysis module 702, statistics module 703 and generation module 704 correspond to steps S21 to S24 in the embodiment, and the four modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the aforementioned embodiments.

[0175] According to an embodiment of the present application, a device embodiment for implementing the data report generating method in the above embodiment is also provided. Figure 8 is a structural diagram of another data report generating device according to an embodiment of the present application, such as Figure 8 As shown, the device includes: an acquisition module 801, which is used to acquire a commodity sales data file and a commodity sales brief information, wherein the commodity sales data file is used to provide commodity sales data content prepared for generating a data report that meets the commodity sales requirements, and the commodity sales brief information is used to briefly describe the commodity sales content to be reported; an analysis module 802, which is used to call the target language model to analyze the commodity sales data file and the commodity sales brief information, and generate a commodity sales analysis plan, wherein the commodity sales analysis plan is used to extract commodity sales data and evaluate commodity sales value from the commodity sales data file based on the commodity sales brief information; a statistical module 803, which is used to call the target language model to perform mathematical statistics on the commodity sales data file based on the commodity sales analysis plan, and obtain commodity sales statistical results, wherein the commodity sales statistical results are used to record commodity sales insights that match the commodity sales content to be reported; a generation module 804, which is used to generate a commodity sales data report based on the commodity sales statistical results.

[0176] It should be noted here that the above-mentioned acquisition module 801, analysis module 802, statistics module 803 and generation module 804 correspond to the aforementioned steps S41 to S44, and the instances and application scenarios implemented by the four modules are the same as the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0177] According to an embodiment of the present application, a device embodiment for implementing the data report generating method in the above embodiment is also provided. Fig. 9 is a structural diagram of another data report generating device according to an embodiment of the present application, such as Fig. 9 As shown, the device comprises:

[0178] The acquisition module 901 is used to acquire a data report generation request through a first application programming interface, wherein the request data carried in the data report generation request includes: a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the field requirements, and the brief description information is used to briefly describe the content to be reported;

[0179] Return module 902 is used to return a data report generation response through a second application programming interface, wherein the response data carried in the data report generation response includes: a target data report, the target data report is generated based on the target statistical results, the target statistical results are obtained after the analysis plan calls the target language model to perform mathematical statistics on the data file, the target statistical results are used to record insights that match the content to be reported, the analysis plan calls the target language model to analyze the data file and the brief description information and then generates it, and the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information.

[0180] It should be noted here that the above-mentioned acquisition module 901 and return module 902 correspond to the aforementioned steps S51 to S52, and the instances and application scenarios implemented by the two modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0181] According to an embodiment of the present application, a device embodiment for implementing the data report generating method in the above embodiment is also provided. Fig.10 is a structural diagram of another data report generating device according to an embodiment of the present application, such as Fig.10As shown, the device includes: a first response module 1001, which is used to respond to a first control operation performed on a graphical user interface, upload a data file and input brief information, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief information is used to briefly describe the content to be reported; a second response module 1002, which is used to respond to a second control operation performed on the graphical user interface, generate a target data report, the target data report is generated based on a target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief information and then generates it, and the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief information; a display module 1003, which is used to display the target data report in the graphical user interface.

[0182] It should be noted here that the above-mentioned first response module 1001, second response module 1002 and display module 1003 correspond to the aforementioned steps S61 to S63, and the instances and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments.

[0183] It should be noted that the above modules or units may be hardware components or software components stored in a memory and processed by one or more processors, and the above modules may also be run in a computer terminal as a part of the device.

[0184] It should be noted that the preferred implementation of this embodiment can refer to the relevant descriptions in the aforementioned embodiments, which will not be repeated here.

[0185] According to an embodiment of the present application, an electronic device is also provided, which can be any terminal device in a computer terminal group. Optionally, in this embodiment, the electronic device can also be replaced by a terminal device such as a mobile terminal.

[0186] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0187] In this embodiment, the electronic device can execute the program code of the following steps in the data report generation method: obtaining a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; calling the target language model to analyze the data file and the brief description information to generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information; based on the analysis plan, calling the target language model to perform mathematical statistics on the data file to obtain target statistical results, wherein the target statistical results are used to record insights that match the content to be reported; and generating a target data report based on the target statistical results.

[0188] Optionally, Fig.11 is a structural block diagram of an electronic device according to an embodiment of the present application, such as Fig.11 As shown, the electronic device 110 may include: one or more (only one is shown in the figure) processors 1102, a memory 1104, a storage controller 1106, and a peripheral interface 1108, wherein the peripheral interface 1108 is connected to a radio frequency module, an audio module, and a display.

[0189] Among them, the memory 1104 can be used to store software programs and modules, such as program instructions / modules corresponding to the data report generation method and device in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned data report generation method. The memory 1104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device 110 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The processor 1102 can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain data files and brief description information, wherein the data files are used to provide data content prepared for generating data reports that meet field requirements, and the brief description information is used to briefly describe the content to be reported; call the target language model to analyze the data files and the brief description information to generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of the data content in the data file based on the brief description information; based on the analysis plan, call the target language model to perform mathematical statistics on the data file to obtain target statistical results, wherein the target statistical results are used to record insights that match the content to be reported; and generate a target data report based on the target statistical results.

[0191] According to an embodiment of the present application, a scheme of an electronic device for implementing the above-mentioned data report generation method is provided. A data file and brief description information are obtained, wherein the data file is used to provide data content prepared for generating a data report that meets the needs of the field, and the brief description information is used to briefly describe the content to be reported; a target language model is called to analyze the data file and the brief description information to generate an analysis scheme, wherein the analysis scheme is used to extract data and evaluate the value of the data content in the data file based on the brief description information; based on the analysis scheme, the target language model is called to perform mathematical statistics on the data file to obtain a target statistical result, wherein the target statistical result is used to record insights that match the content to be reported; a target data report is generated based on the target statistical result. Therefore, the embodiment of the present application can combine the use of the target language model and cloud computing resources to generate a target data report corresponding to the data file and the brief information. The analysis and mathematical statistics involved in this process are automated, ensuring that the target data report is closely related to the data content and the content to be reported, thereby achieving the purpose of automatically generating the target data report, thereby achieving the technical effect of reducing the complexity of the data report generation process, improving the data report generation efficiency and user-friendliness, and further solving the technical problems in the related technology that the data report generation solution has a complex process, low efficiency, and a strong reliance on manual operation of technical personnel.

[0192] It can be understood by those skilled in the art that Fig.11 The structure shown is for illustration only, and the electronic device may also be a terminal device such as a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, and a mobile Internet device (Mobile Internet Devices, MID). Fig.11 The structure of the electronic device is not limited. For example, the electronic device 110 may also include Fig.11 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Fig.11 Different configurations are shown.

[0193] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0194] According to an embodiment of the present application, a computer-readable storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the data report generation method provided in the above embodiment.

[0195] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0196] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for executing the following steps: obtaining a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets domain requirements, and the brief description information is used to briefly describe the content to be reported; calling a target language model to analyze the data file and the brief description information to generate an analysis plan, wherein the analysis plan is used to extract data and perform value assessment on the data content in the data file based on the brief description information; based on the analysis plan, calling the target language model to perform mathematical statistics on the data file to obtain target statistical results, wherein the target statistical results are used to record insights that match the content to be reported; and generating a target data report based on the target statistical results.

[0197] The embodiment of the present application further provides a computer program product. Optionally, in this embodiment, the computer program product may include a computer program, and the computer program implements the method provided in the embodiment when executed by a processor.

[0198] The embodiments of the present application also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which may be used to store a computer program, and when the computer program is executed by a processor, the method provided in the embodiments is implemented.

[0199] The embodiment of the present application further provides a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, the method provided in the above embodiment is implemented.

[0200] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0201] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0202] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0203] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0204] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, ROM, RAM, mobile hard disks, magnetic disks or optical disks.

[0205] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data report generation method, characterized in that: include: Obtaining data files and brief description information, wherein the data files are used to provide data content prepared for generating data reports that meet field requirements, and the brief description information is used to briefly describe the content to be reported; Calling a target language model to analyze the data file and the brief information to generate an analysis plan, wherein the analysis plan is used to extract data and evaluate the value of data content in the data file according to the brief information; Determining an analysis object from the data file based on the analysis scheme, and obtaining a target data statistical method corresponding to the analysis object based on the analysis scheme; Calling the target language model to perform a feasibility assessment on the analysis object to obtain an assessment result, wherein the assessment result is used to assess whether the analysis object supports the analysis solution; In response to the evaluation result satisfying a preset evaluation condition, calling cloud computing resources to perform mathematical statistics on the analysis object according to the target data statistical method to obtain an initial statistical result; Calling the target language model to perform statistical analysis on the initial statistical results to obtain target statistical results, wherein the target statistical results are used to record data analysis insights that match the content to be reported; A target data report is generated based on the target statistical results.

2. The data report generation method according to claim 1, characterized in that: Calling the target language model to analyze the data file and the brief information to generate the analysis solution includes: Calling the target language model to perform intent recognition on the data file and the brief description information to obtain an intent recognition result; Calling the target language model to generate a data overview of the intent recognition result to obtain a target data overview; The target language model is called to perform content analysis on the target data overview to generate the analysis plan.

3. The data report generation method according to claim 1, characterized in that: The statistical method of obtaining the target data corresponding to the analysis object based on the analysis scheme includes: The target data statistical method is selected from a data analysis knowledge base based on the analysis scheme, wherein the data analysis knowledge base is used to provide a plurality of candidate data statistical methods, and the plurality of candidate data statistical methods are obtained after being classified according to a preset classification standard.

4. The data report generation method according to claim 3, characterized in that: The preset classification criteria include at least some of the following options: The type of data to which the statistical method is applicable; Usage scenarios associated with data statistics methods; A visualization solution that supports data statistics.

5. The data report generation method according to claim 1, characterized in that: Calling the target language model to perform statistical analysis on the initial statistical results to obtain the target statistical results includes: Simplifying and summarizing the initial statistical results to obtain a summarized and simplified result; Calling the target language model to perform statistical analysis on the summary and simplification results to obtain analysis results, wherein the analysis results are used to filter out partial statistical results that are adapted to the field requirements from the summary and simplification results and determine the classification method corresponding to the partial statistical results; The partial statistical results are classified and counted based on the classification method to obtain the target statistical results.

6. The data report generation method according to claim 5, characterized in that: The initial statistical results are simplified and summarized to obtain the summarized simplified results including: The initial statistical results are screened based on a preset screening standard to obtain a screening result, wherein the preset screening standard is determined according to the feature value of the initial statistical results and the importance of the data involved in the initial statistical results; Classifying and integrating the approximate results in the screening results to obtain an integrated result; The integration results are summarized to obtain the summarized simplified results.

7. The data report generation method according to any one of claims 1 to 6, characterized in that: Generating the target data report according to the target statistical result includes: Obtain a target visualization scheme for the target statistical result; Calling the target language model to perform text summary on the target statistical result to obtain a target summary text; The target data report is generated based on the target visualization scheme and the target summary text.

8. The data report generation method according to claim 7, characterized in that: The target visualization scheme for obtaining the target statistical result includes: The target visualization scheme is selected from a data analysis knowledge base based on the target statistical result, wherein the data analysis knowledge base is used to provide a plurality of candidate visualization schemes, and the plurality of candidate visualization schemes are respectively matched with different candidate data statistical methods.

9. The data report generation method according to claim 7, characterized in that: Generating the target data report based on the target visualization scheme and the target summary text includes: The view recommendation model is called to perform a visualization view analysis on the target visualization scheme and the target summary text to generate the target data report.

10. A method for generating a data report, characterized in that: include: Acquire a commodity sales data file and commodity sales brief information, wherein the commodity sales data file is used to provide commodity sales data content prepared for generating a data report that meets commodity sales requirements, and the commodity sales brief information is used to briefly describe the commodity sales content to be reported; Calling the target language model to analyze the commodity sales data file and the commodity sales brief information to generate a commodity sales analysis plan, wherein the commodity sales analysis plan is used to extract commodity sales data and evaluate commodity sales value from the commodity sales data file based on the commodity sales brief information; Determining an analysis object from the commodity sales data file based on the commodity sales analysis plan, and obtaining a target data statistical method corresponding to the analysis object based on the commodity sales analysis plan; Calling the target language model to perform a feasibility assessment on the analysis object to obtain an assessment result, wherein the assessment result is used to assess whether the analysis object supports the commodity sales analysis solution; In response to the evaluation result satisfying a preset evaluation condition, calling cloud computing resources to perform mathematical statistics on the analysis object according to the target data statistical method to obtain an initial statistical result; Calling the target language model to perform statistical analysis on the initial statistical results to obtain commodity sales statistical results, wherein the commodity sales statistical results are used to record commodity sales insights that match the commodity sales content to be reported; A commodity sales data report is generated based on the commodity sales statistical results.

11. A method for generating a data report, characterized in that: include: Obtaining a data report generation request through a first application programming interface, wherein the request data carried in the data report generation request includes: a data file and brief description information, wherein the data file is used to provide data content prepared for generating a data report that meets the requirements of the field, and the brief description information is used to briefly describe the content to be reported; A data report generation response is returned through a second application programming interface, wherein the response data carried in the data report generation response includes: a target data report, the target data report is generated based on a target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record data analysis insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief information and then generates it, and the analysis scheme is used to perform data extraction and value assessment on the data content in the data file according to the brief information; The target statistical result is obtained by calling the target language model to perform statistical analysis on the initial statistical result, the initial statistical result is obtained by calling cloud computing resources in response to the evaluation result satisfying the preset evaluation condition to perform mathematical statistics on the analysis object according to the target data statistical method, the evaluation result is obtained by calling the target language model to perform a feasibility evaluation on the analysis object, the evaluation result is used to evaluate whether the analysis object supports the analysis plan, the analysis object is determined from the data file based on the analysis plan, and the target data statistical method corresponding to the analysis object is obtained based on the analysis plan.

12. A method for generating a data report, characterized in that: A graphical user interface is provided by a terminal device, and the data report generation method includes: In response to a first control operation performed on the graphical user interface, a data file is uploaded and brief description information is input, wherein the data file is used to provide data content prepared for generating a data report that meets field requirements, and the brief description information is used to briefly describe the content to be reported; In response to a second control operation performed on the graphical user interface, a target data report is generated, the target data report is generated based on a target statistical result, the target statistical result is obtained after the analysis scheme calls the target language model to perform mathematical statistics on the data file, the target statistical result is used to record the data analysis insights that match the content to be reported, the analysis scheme calls the target language model to analyze the data file and the brief information, the analysis scheme is used to perform data extraction and value assessment on the data content in the data file according to the brief information, the target statistical result is obtained by calling the target language model to perform statistical analysis on the initial statistical result, the initial statistical result is obtained by calling the cloud computing resources in response to the evaluation result satisfying the preset evaluation condition to perform mathematical statistics on the analysis object according to the target data statistical method, the evaluation result is obtained by calling the target language model to perform feasibility assessment on the analysis object, the evaluation result is used to assess whether the analysis object supports the analysis scheme, the analysis object is determined from the data file based on the analysis scheme, and the target data statistical method corresponding to the analysis object is obtained based on the analysis scheme; The target data report is presented within the graphical user interface.

13. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program executes the data report generating method according to any one of claims 1 to 12 when running.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the data report generation method according to any one of claims 1 to 12.

15. A computer program product, characterized in that The method comprises a computer program, wherein the computer program is executed by a processor to generate a data report according to any one of claims 1 to 12.

Images