Data analysis method and apparatus, computer device, storage medium and computer program product

Abstract

A data analysis method and apparatus, a computer device, a storage medium and a computer program product, relating to the technical field of computers. The method comprises: acquiring a data analysis request message and, on the basis of the data analysis request message, determining corresponding data analysis requirement information; on the basis of the data analysis requirement information, acquiring a target metric model comprising a data analysis metric and a data analysis instruction template that corresponds to the target metric model; acquiring a target data table model matching the target metric model, the target data table model comprising target analysis data that satisfies the data analysis metric; and, on the basis of the target analysis data and the data analysis instruction template, performing data analysis to obtain a data analysis result corresponding to the data analysis request message. Using the method can improve the accuracy of data analysis.

Description

Data analysis methods, apparatus, computer equipment, storage media and computer program products

[0001] This application claims priority to Chinese Patent Application No. 202411893039.0, filed on December 19, 2024, entitled "Data Analysis Method, Apparatus, Computer Equipment, Storage Medium and Computer Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of computer technology, and in particular to a data analysis method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0003] With the rapid development of computer technology, data has become a core resource in modern society. Across various industries, data structures exhibit unprecedented complexity and diversity, ranging from simple text and numbers to complex images, videos, web logs, and sensor data, with numerous data types and formats. Data analysis based on various data structures has become an important tool for decision-making, business optimization, and market insight across all industries. However, complex data structures increase the difficulty of data analysis, leading to lower accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a data analysis method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of data analysis in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a data analysis method. The method includes:

[0006] Obtain the data analysis request message and determine the corresponding data analysis requirements based on the data analysis request message;

[0007] Based on data analysis requirements, obtain the target indicator model, which includes data analysis metrics, and the corresponding data analysis instruction template;

[0008] Obtain a target data table model that matches the target indicator model. The target data table model includes target analysis data that meets the data analysis indicators.

[0009] Data analysis is performed based on the target analysis data and the data analysis instruction template to obtain the data analysis results corresponding to the data analysis request message.

[0010] Secondly, this application also provides a data analysis apparatus. The apparatus includes:

[0011] The requirement determination module is used to obtain data analysis request messages and determine the corresponding data analysis requirement information based on the data analysis request messages;

[0012] The indicator model acquisition module is used to acquire, based on data analysis requirements, the target indicator model and the corresponding data analysis instruction template, including the data analysis indicators.

[0013] The data table model acquisition module is used to obtain a target data table model that matches the target indicator model. The target data table model includes target analysis data that meets the data analysis indicators.

[0014] The analysis results acquisition module is used to perform data analysis based on the target analysis data and the data analysis instruction template, and obtain the data analysis results corresponding to the data analysis request message.

[0015] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described data analysis method.

[0016] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above data analysis method.

[0017] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described data analysis method.

[0018] The aforementioned data analysis methods, apparatus, computer equipment, storage media, and computer program products, based on data analysis requirement information determined according to a data analysis request message, acquire a target indicator model including data analysis metrics and a corresponding data analysis instruction template. They then obtain a target data table model matching the target indicator model and perform data analysis based on the target analysis data and instruction template included in the target data table model, yielding the data analysis results corresponding to the data analysis request message. In the data analysis process, by acquiring the target indicator model and corresponding data analysis instruction template through data analysis requirement information, and obtaining a matching target data table model based on the target indicator model, data analysis can be performed using the target analysis data and instruction template that meet the data analysis metrics included in the target data table model. This standardization of various data through the target data table model allows for data analysis processing on standardized data, reducing the difficulty of data analysis and thus improving its accuracy. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 is an application environment diagram of the data analysis method in one embodiment;

[0021] Figure 2 is a flowchart illustrating a data analysis method in one embodiment;

[0022] Figure 3 is a flowchart illustrating the process of determining data analysis requirements in one embodiment;

[0023] Figure 4 is a flowchart illustrating data analysis based on a large model in one embodiment;

[0024] Figure 5 is a flowchart illustrating the data analysis method in another embodiment;

[0025] Figure 6 is a schematic diagram of the data preprocessing flow in one embodiment;

[0026] Figure 7 is a schematic diagram of the intent recognition process in one embodiment;

[0027] Figure 8 is a schematic diagram of the comparison of data analysis results in one embodiment;

[0028] Figure 9 is a structural block diagram of a data analysis device in one embodiment;

[0029] Figure 10 is an internal structure diagram of a computer device in one embodiment;

[0030] Figure 11 is an internal structure diagram of a computer device in another embodiment. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0032] The data analysis method provided in this application embodiment can be applied to the application environment shown in Figure 1. The terminal 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be set up independently, integrated into the server 104, or placed in the cloud or on another server. Users can send data analysis request messages to the server 104 through the terminal 102. The server 104 can determine the corresponding data analysis requirement information based on the data analysis request message, and obtain a target indicator model including data analysis indicators and a corresponding data analysis instruction template based on the data analysis requirement information. The server 104 can obtain a target data table model that matches the target indicator model, and perform data analysis based on the target analysis data and data analysis instruction template included in the target data table model to obtain the data analysis result corresponding to the data analysis request message. The server 104 can also return the data analysis result to the terminal 102 for display.

[0033] In some embodiments, the data analysis method can also be implemented independently by the terminal 102 or the server 104. For example, the terminal 102 can directly perform data analysis processing based on the user-configured data analysis request message to obtain the corresponding data analysis results. Alternatively, the server 104 can directly obtain the data analysis request message from the data storage system to perform data analysis processing based on the data analysis request message.

[0034] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0035] In an exemplary embodiment, as shown in FIG2, a data analysis method is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is described using the server in FIG1 as an example, and includes the following steps 202 to 208. Wherein:

[0036] Step 202: Obtain the data analysis request message and determine the corresponding data analysis requirement information based on the data analysis request message.

[0037] The data analysis request message is a request message requesting data analysis processing of business data, which can be sent by the user to the server through a terminal. Data analysis requirement information characterizes the user's intent in requesting data analysis through the data analysis request message. This information may include the business data targeted by the data analysis, the analysis indicators for the data segment, and the metrics for the data analysis. The data analysis requirement information can be determined based on the data analysis request message. For example, the server can receive the data analysis request message sent by the user through the terminal. The server can perform requirement analysis on the data analysis request message to determine the corresponding data analysis requirement information. For instance, the user can edit a data analysis question, such as "How was the revenue of Sales Department One this month?" or "Why did revenue decline this month?". The terminal can generate a data analysis request message based on the user's edited question and send it to the server. The server can perform intent recognition based on the data analysis question included in the data analysis request message to determine the corresponding data analysis requirement information. For example, for the data analysis question "How was the revenue of Sales Department One this month?", the corresponding data analysis requirement information could be data analysis of the revenue data of Sales Department One within the current month's time frame.

[0038] Step 204: Based on the data analysis requirements information, obtain the target indicator model, which includes data analysis indicators, and the corresponding data analysis instruction template.

[0039] The target indicator model is an indicator model determined from various indicator models that corresponds to the data analysis requirements. This model includes data analysis indicators to perform data analysis on business data. Data analysis indicators can be any metrics used for analyzing business data, including but not limited to at least one of various indicators such as indicator name, statistical period, analysis dimension, filtering conditions, data comparison conditions, and data prediction conditions. Different indicator models can include different data analysis indicators to address diverse data analysis needs. The data analysis instruction template is a template for generating data analysis instructions. This template corresponds to the target indicator model, thus addressing different data analysis requirements. Using the data analysis instruction template, corresponding data analysis instructions can be generated based on the business data requiring analysis, thereby achieving data analysis processing.

[0040] Optionally, the server can perform matching based on data analysis requirement information to obtain a target indicator model and a data analysis instruction template. The target indicator model includes data analysis indicators, and business data requiring data analysis can be obtained based on these indicators. In some embodiments, the server can match the data analysis requirement information with each pre-configured indicator model separately to determine the matching target indicator model from among the various indicator models, and further determine the data analysis instruction template corresponding to the target indicator model. In some embodiments, the same indicator model can be configured with at least one data analysis instruction template. When the target indicator model corresponds to multiple data analysis instruction templates, the server can match from the multiple data analysis instruction templates corresponding to the target indicator model based on the data analysis requirement information to obtain a data analysis instruction template that meets the data analysis requirement information, and then generate corresponding data analysis instructions based on the data analysis instruction template for data analysis processing.

[0041] Step 206: Obtain the target data table model that matches the target indicator model. The target data table model includes target analysis data that meets the data analysis indicators.

[0042] The target data table model is a data table model that matches the target indicator model, which is determined from various pre-configured data table models. The data table model can include target analysis data that needs to be processed for data analysis. The target analysis data meets the data analysis indicators in the target indicator model, so that data analysis can be performed on the target analysis data in the target data table model to meet the data analysis requirements.

[0043] Specifically, the server can determine a pre-configured data table model and match the target indicator model with each data table model, thereby identifying the target data table model that matches the target indicator model from among the various data table models. The target data table model includes target analysis data that needs to be analyzed and meets the data analysis indicators. In some embodiments, the server can pre-process the business data in the business system to transform it into a data table model. The business data in the data table model can be structured data, such as including a single header and single body structure, thereby reducing the difficulty of understanding various types of business data. In some embodiments, the server can filter the business data in the original data tables of the business system to obtain the business data in the original data tables that needs to be analyzed. The server can construct a corresponding data table model based on the filtered business data, thereby storing the filtered business data through the standardized structure of the data table model.

[0044] Step 208: Perform data analysis based on the target analysis data and the data analysis instruction template to obtain the data analysis results corresponding to the data analysis request message.

[0045] The data analysis result is the processing result obtained by performing data analysis according to the data analysis request message. For example, the server can obtain target analysis data from the target data table model and perform data analysis based on the target analysis data and the data analysis instruction template to obtain the data analysis result corresponding to the data analysis request message. In some embodiments, the server can perform data analysis on the target analysis data according to the data analysis instruction template to obtain the corresponding data analysis result. For example, the data analysis instruction template may carry data analysis instructions, and the server can perform data analysis on the target analysis data according to the data analysis instructions carried in the data analysis instruction template to obtain the corresponding data analysis result. Alternatively, the server can input the target analysis data and the data analysis instruction template into a Large Language Model (LLM) to construct data analysis instructions based on the data analysis instruction template, perform data analysis on the target analysis data, and output the corresponding data analysis result. In some embodiments, the data analysis instruction template can also define the output format of the data analysis result, such as outputting the data analysis result in a natural language format, thereby obtaining data analysis results described in natural language form. In some embodiments, the data analysis instruction template can also define the output format of the data analysis results as a visualization display method, such as a table or chart, so that the data analysis results can be output in tabular or chart form.

[0046] In the aforementioned data analysis method, based on the data analysis requirement information determined according to the data analysis request message, a target indicator model including data analysis metrics and a corresponding data analysis instruction template is obtained. A target data table model matching the target indicator model is then obtained. Data analysis is performed based on the target analysis data and data analysis instruction template included in the target data table model, yielding the data analysis results corresponding to the data analysis request message. In the data analysis process, the target indicator model and corresponding data analysis instruction template are obtained through the data analysis requirement information. A matching target data table model is obtained based on the target indicator model. Data analysis is then performed using the target analysis data and data analysis instruction template included in the target data table model that meet the data analysis metrics. The target data table model can standardize various types of data, allowing for data analysis processing on standardized data, reducing the difficulty of data analysis and thus improving its accuracy.

[0047] In an exemplary embodiment, based on data analysis requirement information, obtaining a target indicator model including data analysis indicators and a data analysis instruction template corresponding to the target indicator model includes: obtaining a pre-built indicator model library, which includes at least one indicator model, and the indicator model includes at least one data analysis indicator; matching the data analysis requirement information with each indicator model in the indicator model library, and determining the target indicator model from the indicator model library based on the matching results; and obtaining the data analysis instruction template corresponding to the target indicator model.

[0048] The indicator model library is pre-built according to actual needs. It can include at least one pre-configured indicator model, and each indicator model can include at least one data analysis indicator. By configuring different data analysis indicators, different indicator models can be built to address diverse data analysis needs.

[0049] Optionally, the server can query a pre-built indicator model library, which includes pre-built indicator models, each containing corresponding data analysis indicators. In some embodiments, the indicator model may include components for storing different data analysis indicators. By configuring these components, different indicator models can be constructed. The server can match data analysis requirement information with each indicator model in the indicator model library. For example, the server can perform text matching between keywords in the data analysis requirement information and keywords of data analysis indicators in each indicator model to obtain corresponding matching results. Based on these matching results, the server can determine the target indicator model that matches the data analysis requirement information from the indicator model library. For instance, the matching results may include keyword similarity between keywords in the data analysis requirement information and keywords of data analysis indicators in the indicator models. The server can determine the indicator model that matches the data analysis requirement information based on the keyword similarity, such as determining the indicator model with the highest keyword similarity value as the target indicator model that matches the data analysis requirement information. For the target indicator model, the server can obtain the corresponding data analysis instruction template. For example, the server can query the corresponding data analysis instruction template based on the indicator model identifier of the target indicator model. The correspondence between the data analysis instruction template and the indicator model identifier can be pre-set.

[0050] In this embodiment, the server matches the data analysis requirement information with each indicator model in the indicator model library, determines the target indicator model based on the matching results, and obtains the data analysis instruction template corresponding to the target indicator model. This allows the server to obtain target analysis data based on the target indicator model and then perform data analysis using the data analysis instruction template. Standardized target analysis data can be used for data analysis processing, reducing the difficulty of data analysis and thus improving the accuracy of data analysis.

[0051] In an exemplary embodiment, the indicator model includes a core component and at least one enhancement component, wherein the core component and the enhancement component include data analysis indicators; the data analysis requirement information includes analysis intent category and labeled content; the data analysis requirement information is matched with each indicator model in the indicator model library, and a target indicator model is determined from the indicator model library based on the obtained matching results, including: matching the labeled content with the model labels of each indicator model in the indicator model library to obtain label matching results; in the indicator model library, the label matching results are represented as matching indicator models and determined as initial indicator models; based on the analysis intent category, a target enhancement component is determined from the enhancement components included in the initial indicator model; and the target indicator model is obtained based on the core component and the target enhancement component of the initial indicator model.

[0052] The indicator model includes core components and enhancement components. There can be one or more enhancement components. Each core component and enhancement component includes data analysis indicators. Core components are essential components of the indicator model, and the data analysis indicators included in core components can serve as essential data analysis indicators for the indicator model. Enhancement components are supplementary components of the indicator model, and the data analysis indicators included in enhancement components can serve as supplementary data analysis indicators for the indicator model. The data analysis indicators in each indicator model can be derived from both essential and supplementary data analysis indicators. The analysis intent category represents the category of data analysis needs, and may include, but is not limited to, at least one of various categories such as current situation analysis, cause analysis, early warning analysis, and predictive analysis. The annotation content can be content obtained by annotating data analysis request messages, and may include, but is not limited to, at least one of various annotation contents such as time, scope, object, correlation, and cause.

[0053] Model tags are configured labels for indicator models and are used for indicator model matching. Specifically, they are used to filter indicator models by matching model tags with the labeled content in the data analysis requirement information. The tag matching result is the matching result of the individual model tags of each indicator model in the indicator model library with the labeled content in the data analysis requirement information. The initial indicator model is an indicator model selected from the indicator model library based on the labeled content. The target enhancement component is an enhancement component determined from the various enhancement components of the initial indicator model that matches the category of analysis intent. The target indicator model is an indicator model determined from the indicator model library that matches the data analysis requirement information, and can be obtained by combining the core components of the initial indicator model and the target enhancement component.

[0054] For example, each indicator model in the indicator model library includes necessary core components and optional configurable enhancement components. The server can determine the analysis intent category and labeled content based on the data analysis request message. The analysis intent category can be obtained by the server performing intent analysis on the data analysis request message, such as by performing intent analysis on the data analysis request message using a pre-trained intent classification model. For labeled content, the server can perform word segmentation on the data analysis request message and label it according to the segmentation results to obtain the corresponding labeled content. The server can obtain data analysis requirement information based on the analysis intent category and labeled content. The server can match the labeled content with each indicator model in the indicator model library, such as matching the labeled content with the model labels of each indicator model to obtain label matching results. Based on the label matching results, the server can determine the indicator model that matches the labeled content from the indicator model library and use this matching indicator model as the initial indicator model. The server can filter the enhancement components included in the initial indicator model based on the analysis intent category to determine the target enhancement component corresponding to the analysis intent category from among the various enhancement components. The server can combine the core components and target enhancement components of the initial indicator model to obtain the target indicator model.

[0055] In this embodiment, the server determines an initial indicator model from the indicator model library based on the labeled content in the data analysis requirement information and the model labels of each indicator model. Based on the analysis intent category in the data analysis requirement information, it determines a target enhancement component from the enhancement components included in the initial indicator model. Based on the core components of the initial indicator model and the target enhancement component, it obtains a target indicator model. Thus, the server can configure a corresponding target indicator model based on the analysis intent category and labeled content, ensuring the relevance of the target indicator model. After obtaining the target analysis data based on the target indicator model, the server can perform data analysis in conjunction with the data analysis instruction template. The server can perform data analysis processing through standardized target analysis data, reducing the difficulty of data analysis and improving the accuracy of data analysis.

[0056] In an exemplary embodiment, the data analysis method further includes: acquiring a pre-built data table model library, the data table model library including at least one data table model, the data table model including structured data; acquiring at least one data analysis indicator, and configuring each data table model in the data table model library according to the data analysis indicator to obtain an indicator model that satisfies different data analysis indicators.

[0057] The data table model library is pre-built according to actual needs. It can include at least one data table model, and each model can contain structured data. This structured data is obtained by processing business data in a structured manner. By configuring different structured data, different data table models can be built. For example, a data table model can have a single header and a single body structure, thus recording the corresponding business data through these structures.

[0058] For example, the server can query a pre-built data table model library and obtain data analysis indicators. It can then configure the data table models in the library according to these indicators. For instance, based on the needs of the data analysis indicators, corresponding structured data can be added to the data table models to obtain different indicator models. These different indicator models can include different data analysis indicators. In some embodiments, the indicator model can include core components and enhancement components. The output data table model must conform to the structural requirements of the core components, i.e., it needs to be configured according to the core component structure: "indicator name, statistical period, analysis dimension, and filtering conditions." Enhancement components can include year-on-year, month-on-month, target, and attribution data analysis indicators, and the corresponding structured data needs to be configured in the data table model.

[0059] In this embodiment, the server configures the data table models in the data table model library based on data analysis indicators to construct indicator models that include different data analysis indicators. After determining the target indicator model, the server can obtain target analysis data based on the target indicator model and then perform data analysis in conjunction with the data analysis instruction template. Data analysis can be performed through standardized target analysis data, which reduces the difficulty of data analysis and improves the accuracy of data analysis.

[0060] In one exemplary embodiment, obtaining a target data table model that matches the target indicator model includes: acquiring a pre-built data table model library, which includes at least one data table model, and the data table model includes structured data; and matching the target data table model from the data table model library according to the target indicator model.

[0061] The data table model library can include at least one data table model, and each data table model can include structured data. The structured data is obtained by structuring business data. Different data table models can be constructed by configuring different structured data. Specifically, the server can perform matching in the data table model library based on the target indicator model. For example, the target indicator model can be matched with each data table model in the library to obtain a matching target data table model. In some embodiments, the server can match the target indicator model with the data analysis indicators included in each data table model to obtain matching results. The server can then determine the data table model corresponding to the matching results as the target data table model that matches the target indicator model.

[0062] In this embodiment, the server matches the target data table model from the data table model library based on the target indicator model. After obtaining the target analysis data based on the target indicator model, it combines the data analysis instruction template to perform data analysis. Data analysis can be performed using standardized target analysis data, which reduces the difficulty of data analysis and thus improves the accuracy of data analysis.

[0063] In one exemplary embodiment, the data analysis method further includes: acquiring various data tables and performing structured configuration on the business data included in the data tables to obtain at least one data table model.

[0064] In this context, a data table can be a data structure within a database used to store business data. Specifically, the server can retrieve various data tables containing business data and perform structured configuration on the business data within each table. For example, the business data in a data table can be configured as a single-header, single-body data structure to obtain the corresponding data table model. Different data table models can be configured based on the various business data within the data tables according to different structured configuration methods.

[0065] In this embodiment, the server can perform structured configuration on the business data in the data table to build a data table model. This data table model can then be used to standardize the business data, enabling data analysis based on the standardized data. This reduces the difficulty of data analysis and improves its accuracy.

[0066] In an exemplary embodiment, as shown in Figure 3, the process of determining data analysis requirement information, i.e., determining the corresponding data analysis requirement information based on the data analysis request message, includes:

[0067] Step 302: Classify the intent based on the data analysis request message to obtain the analysis intent category corresponding to the data analysis request message.

[0068] The analysis intent category is used to characterize the type of data analysis requirement, specifically obtained by classifying the intent of the data analysis request message. For example, the server can classify the intent based on the data analysis request message, such as by using a pre-trained intent classification model to analyze the intent of the data analysis request message and thus obtain the analysis intent category corresponding to the data analysis request message.

[0069] Step 304: Perform word segmentation on the data analysis request message to obtain the word segmentation results.

[0070] Optionally, the server can perform word segmentation on the data analysis request message to divide it into different fields and obtain the corresponding word segmentation results. For example, for the data analysis request message "How is the revenue of Sales Department 1 this month?", after performing word segmentation, the obtained word segmentation results may include "this month", "Sales Department 1", "revenue", and "how".

[0071] Step 306: Annotate the word segmentation results to obtain the annotation content corresponding to the word segmentation results.

[0072] Specifically, the server can perform annotation based on the word segmentation results, specifically annotating each field in the word segmentation results to obtain the corresponding annotation content. For example, the obtained annotation content may include "time", "range", "object", and "reason".

[0073] Step 308: Based on the analysis intent category and labeled content, obtain the data analysis requirement information corresponding to the data analysis request message.

[0074] For example, the server can obtain data analysis requirement information based on the analysis intent category and the labeled content. For instance, the server can combine the analysis intent category and the labeled content to obtain the data analysis requirement information corresponding to the data analysis request message.

[0075] In this embodiment, the server performs intent classification on the data analysis request message to obtain the analysis intent category, annotates the word segmentation results of the data analysis request message to determine the annotation content, and comprehensively analyzes the intent category and the annotation content to obtain data analysis requirement information. Based on the data analysis requirement information, the server determines the target indicator model and data analysis instruction template for data analysis, which can ensure the accuracy of data analysis.

[0076] In an exemplary embodiment, data analysis is performed based on target analysis data and a data analysis instruction template to obtain data analysis results corresponding to the data analysis request message. This includes: generating model question number information based on the target analysis data and the data analysis instruction template; inputting the model question number information into a pre-trained large language model for data analysis to obtain the data analysis results output by the large language model corresponding to the data analysis request message.

[0077] The model question count information can be used as input to the large language model, specifically generated based on the target analysis data and data analysis instruction template. Optionally, the server can generate the model question count information based on the target analysis data and data analysis instruction template, and input the model question count information into the pre-trained large language model, so that the large language model can perform data analysis on the model question count information and output the corresponding data analysis results.

[0078] In this embodiment, the server generates model question information based on target analysis data and data analysis instruction templates, and performs data analysis on the model question information using a large language model. The large language model can be used to perform data analysis processing on standardized data, which reduces the difficulty of data analysis and thus improves the accuracy of data analysis.

[0079] This application also provides an application scenario in which the above-described data analysis method is applied. Specifically, the data analysis method is applied in this scenario as follows:

[0080] This application scenario involves LLM querying based on form-based data, where different forms have varying data structures. Traditional methods, after identifying user intent, often directly retrieve data results from the forms and return relevant content. Even large models require fine-tuning through prompts and other methods, needing to be adjusted for different data conditions. However, directly matching and retrieving data tables yields significantly different results for diverse forms, with complex forms returning poor data. Furthermore, large models are not adept at data analysis and statistics, making it difficult to directly obtain statistical results based on existing data forms. In addition, traditional solutions can only apply a limited set of large model instruction templates, limiting their applicability to broader scenarios. Moreover, practical applications involve data tables and structures with diverse formats; existing solutions can only perform superficial interpretation and analysis, failing to support broader LLM data analysis scenarios and generate deeper insights, resulting in limited accuracy in data analysis. As shown in Figure 4, in practical application scenarios, the business data requiring data analysis can include various data structures such as numerical data, pie charts, and bar charts. Data analysis based on LLM involves both direct reading of business data and data interpretation. The LLM model is an artificial intelligence model capable of processing and generating natural language. It typically has a large number of parameters and powerful computing capabilities, enabling it to learn and understand large amounts of text data and generate natural and fluent text to answer questions, engage in dialogues, and complete various language tasks.

[0081] The data analysis method provided in this application embodiment performs precise data analysis and processing based on LLM (Local Management Model). It can output in-depth and intelligent analysis for different types of data structure tables and can be reused in a wider range of query scenarios. The data analysis method provided in this application embodiment is designed and created specifically for LLM query methods involving differentiated form data. It improves the user intent recognition and relevant data acquisition processes, adds a data processing center, and through the comprehensive design and creation of the solution, enables it to be widely adaptable to LLM data analysis scenarios, resulting in more accurate results.

[0082] Specifically, as shown in Figure 5, the server can receive user questions, which can serve as data analysis request messages. The server can understand and identify user intent based on these questions to obtain corresponding data analysis requirements. The server can then match these requirements within the data processing center to determine the target indicator model, including data analysis indicators, from various indicator models within the center. Furthermore, it can obtain the corresponding data analysis instruction template for the target indicator model. The server can then obtain a target data table model that matches the target indicator model and input the target analysis data and the data analysis instruction template from the target data table model into the larger model for data analysis, generating a response result to be sent back to the user—that is, obtaining the data analysis result. The server can pre-process the business data in the database using a computing service to construct the indicator model and data table model for the data processing center, and pre-train the corresponding data analysis instruction template for the larger model.

[0083] Specifically, the data analysis method provided in this application adds a data processing center step, which enables the application and matching of differentiated data forms. Furthermore, based on the indicator model of the data processing center, the user intent recognition, matching, and data acquisition steps are modified. The data processing center comprises three parts: an indicator model, a data table model, and a computational service. The data processing center connects with various differentiated forms in the underlying database. Its main function is to process and organize the differentiated data tables to output them according to the assemblable structure of the indicator model, thus addressing various data intents and corresponding to different data analysis needs.

[0084] Further, as shown in Figure 6, in the data processing center, the various differentiated data tables in the database are first pre-processed to obtain a data table model. The data table model has a single header and single body structure, and its design effectively reduces the difficulty of understanding large models. The pre-processing process involves extracting the analytical data from the original data tables, processing and statistically analyzing it through computing services, and storing it according to the data table model structure. Non-analytical data from the original data tables is not retained and is not stored in the data table model. Further, the data table model undergoes secondary processing through an indicator model and is output according to the indicator model structure. The indicator model includes core components and enhanced components. When the data table model is output, it must conform to the structural requirements of the core components, requiring output according to the core component structure: "indicator name, statistical period, analysis dimension, and filtering conditions." Other data content is output according to the enhanced components, which include year-on-year, month-on-month, target, and attribution, making the indicator model scalable. Enhanced components depend on core components, and enhanced components can be assembled on the basis of core components, i.e., core components + enhanced components (which can be assembled), to match different user intentions to obtain target analytical data for data analysis and processing. After constructing the indicator model, the business data in the data table undergoes pre-processing and is then pre-trained on the large model to form a data analysis instruction template. Once the corresponding data analysis requirement information is determined based on the data analysis request message, such as obtaining the user's question and identifying the user's intent, the corresponding data analysis instruction template is matched according to the intent classification to quickly realize high-quality, organized natural language questions, thereby achieving fast and accurate data analysis processing.

[0085] In the user intent recognition and processing, as shown in Figure 7, an intent classification step is added based on the data template structure, including but not limited to current status analysis, cause analysis, early warning analysis, and predictive analysis. When different user intent categories are identified, data is obtained by matching the core components of the indicator template with assemblable enhancement components, enabling adaptation to and support for a wider range of question scenarios. For example, when the user intent is cause analysis, the core components of the indicator model plus the "attribution" enhancement component are obtained and called, thus enabling broader application of user intent recognition to support richer question scenarios. In addition, after obtaining the data analysis request message, i.e., after obtaining the user question, the user question can be segmented and then labeled. The labeled content is matched with the components of the indicator model, making the labeled content more effective and enabling more accurate data acquisition. In the matching and data acquisition processing, the incoming labels and intent categories are judged simultaneously and matched with the indicator library and indicator model in the data processing center. If a match is found, the corresponding target analysis data is obtained; otherwise, the target analysis data is not obtained. When the user intent recognition step identifies the need for computation services, the corresponding data components and computation services are called to process the data before returning it to the large model for data analysis.

[0086] In the data analysis method provided in this application embodiment, after receiving a user question, the server understands the user question and supplements the user question description or breaks down the user question. The server then performs user intent recognition, specifically using a core component of the indicator model plus an assemblable enhancement component scheme to address a wide range of user intents, enabling the user question to more accurately match the pre-set data template. Further, the server matches the input user intent, annotation, and intent classification against the indicator library and data templates of the data processing center. If a match is found, the target analysis data is directly returned; if the matched intent requires data processing, the corresponding components and technical services of the data template are called for processing, and the corresponding target analysis data is returned. If none of the above matches, a result of no data is returned. After the large model obtains the corresponding target analysis data, it combines the data analysis instruction template to perform data analysis to obtain the corresponding data analysis results, specifically, the corresponding data conclusions can be obtained.

[0087] In traditional data analysis and processing, it is often impossible to accurately obtain data results when dealing with questions on different forms; often, only an analysis of the current state of the data can be performed. However, the data analysis method provided in this application embodiment standardizes the data by designing a data processing center where "data tables are pre-processed into data table models, and then further processed into indicator models." Through the design of the indicator model with "core components + assemblable enhancement components," the data combination capability is enhanced, enabling it to address different user data analysis intentions and thus achieve high-quality, broader intelligent data analysis of differentiated data tables. Furthermore, the data analysis method provided in this application embodiment optimizes and improves the components of the data template, enabling more accurate identification and matching of data content in the data processing center. In addition, the data analysis method provided in this application embodiment combines user intent classification and data template components to pre-set different types of data analysis instruction templates, making it adaptable to a wider range of scenarios.

[0088] The data analysis method provided in this application, through improvements in the design of the data processing center and user intent recognition, makes LLM-based data analysis more accurate and data acquisition faster. Furthermore, the data processing center provides the design of data table models and indicator models, enabling more standardized, differentiated data tables and reducing the difficulty of understanding large models. The indicator model offers a "core component + assemblable enhancement component" design, allowing it to broadly adapt to different user intents, making this technical solution more applicable and easier to promote. In addition, as shown in Figure 8, in traditional data analysis processing, LLM can only perform current state analysis on the data surface; while the data analysis method provided in this application can achieve insights into data anomalies, analysis of the causes of data problems, and analysis of data growth trends through LLM, making LLM-based data analysis more accurate and intelligent.

[0089] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0090] Based on the same inventive concept, this application also provides a data analysis apparatus for implementing the data analysis method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data analysis apparatus embodiments provided below can be found in the limitations of the data analysis method described above, and will not be repeated here.

[0091] In an exemplary embodiment, as shown in FIG9, a data analysis device 900 is provided, including: a demand determination module 902, an indicator model acquisition module 904, a data table model acquisition module 906, and an analysis result acquisition module 908, wherein:

[0092] The requirement determination module 902 is used to obtain data analysis request messages and determine the corresponding data analysis requirement information based on the data analysis request messages;

[0093] The indicator model acquisition module 904 is used to acquire, based on data analysis requirements information, the target indicator model including data analysis indicators and the corresponding data analysis instruction template for the target indicator model.

[0094] The data table model acquisition module 906 is used to obtain a target data table model that matches the target indicator model. The target data table model includes target analysis data that meets the data analysis indicators.

[0095] The analysis result acquisition module 908 is used to perform data analysis based on the target analysis data and the data analysis instruction template, and obtain the data analysis results corresponding to the data analysis request message.

[0096] In an exemplary embodiment, the indicator model acquisition module 904 is further configured to acquire a pre-built indicator model library, which includes at least one indicator model, and the indicator model includes at least one data analysis indicator; match the data analysis requirement information with each indicator model in the indicator model library respectively, and determine the target indicator model from the indicator model library based on the obtained matching results; and acquire the data analysis instruction template corresponding to the target indicator model.

[0097] In an exemplary embodiment, the indicator model includes a core component and at least one enhancement component, wherein the core component and the enhancement component include data analysis indicators; the data analysis requirement information includes analysis intent category and labeled content; the indicator model acquisition module 904 is further configured to match the labeled content with the respective model labels of each indicator model in the indicator model library to obtain label matching results; in the indicator model library, the label matching results are represented as matching indicator models and determined as initial indicator models; based on the analysis intent category, a target enhancement component is determined from the enhancement components included in the initial indicator model; and based on the core component and the target enhancement component of the initial indicator model, a target indicator model is obtained.

[0098] In an exemplary embodiment, the system further includes an indicator model configuration module, which is used to obtain a pre-built data table model library, the data table model library including at least one data table model, the data table model including structured data; obtain at least one data analysis indicator, and configure each data table model in the data table model library according to the data analysis indicator to obtain an indicator model including different data analysis indicators.

[0099] In an exemplary embodiment, the data table model acquisition module 906 is further configured to acquire a pre-built data table model library, which includes at least one data table model, and the data table model includes structured data; and to obtain a target data table model by matching it from the data table model library according to the target indicator model.

[0100] In one exemplary embodiment, a structured configuration module is further included, which is used to obtain various data tables and perform structured configuration on the business data included in the data tables to obtain at least one data table model.

[0101] In an exemplary embodiment, the requirement determination module 902 is further configured to classify the intent according to the data analysis request message to obtain the analysis intent category corresponding to the data analysis request message; perform word segmentation on the data analysis request message to obtain the word segmentation result; annotate the word segmentation result to obtain the annotation content corresponding to the word segmentation result; and obtain the data analysis requirement information corresponding to the data analysis request message based on the analysis intent category and the annotation content.

[0102] In an exemplary embodiment, the analysis result acquisition module 908 is further configured to generate model question number information based on the target analysis data and the data analysis instruction template; input the model question number information into the pre-trained large language model for data analysis, and obtain the data analysis result corresponding to the data analysis request message output by the large language model.

[0103] Each module in the aforementioned data analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0104] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram is shown in Figure 10. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores various data involved in data analysis methods. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a data analysis method.

[0105] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram is shown in Figure 11. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a data analysis method. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0106] Those skilled in the art will understand that the structures shown in Figure 10 or Figure 11 are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0107] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0108] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0109] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0110] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0111] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data analysis method, characterized by, The method comprises: acquiring a data analysis request message and determining corresponding data analysis requirement information based on the data analysis request message; based on the data analysis requirement information, acquiring a target index model including a data analysis index and a data analysis instruction template corresponding to the target index model; obtaining a target data table model matched with the target index model, the target data table model including target analysis data satisfying the data analysis index; based on the target analysis data and the data analysis instruction template, performing data analysis to obtain a data analysis result corresponding to the data analysis request message.

2. The method of claim 1, wherein, The method comprises: acquiring a pre-constructed index model library, the index model library including at least one index model, the index model including at least one data analysis index; matching the data analysis requirement information with each index model in the index model library respectively, and determining a target index model from the index model library according to the obtained matching result; acquiring a data analysis instruction template corresponding to the target index model.

3. The method of claim 2, wherein, The index model includes a core component and at least one enhanced component, and the core component and the enhanced component include data analysis indexes; the data analysis requirement information includes an analysis intent category and a labeled content; The method comprises: matching the labeled content with the model label of each index model in the index model library respectively to obtain a label matching result; in the index model library, the label matching result is represented as a matched index model to determine an initial index model; based on the analysis intent category, determining a target enhanced component from the enhanced components included in the initial index model; according to the core component of the initial index model and the target enhanced component, obtaining a target index model.

4. The method of claim 2, wherein, The method further comprises: acquiring a pre-constructed data table model library, the data table model library including at least one data table model, the data table model including structured data; acquiring at least one data analysis index and configuring each data table model in the data table model library according to the data analysis index to obtain an index model including different data analysis indexes.

5. The method of claim 1, wherein, The method comprises: acquiring a pre-constructed data table model library, the data table model library including a plurality of data table models, and each data table model including structured data; according to the target index model, matching a target data table model from the data table model library.

6. The method of claim 5, wherein, The method further comprises: acquiring various data tables and structuring and configuring business data included in the data tables to obtain at least one data table model.

7. The method of claim 1, wherein, The method comprises: According to the data analysis request message, an intention classification is performed to obtain an analysis intention category corresponding to the data analysis request message; The data analysis request message is segmented to obtain a segmentation result; The segmentation result is labeled to obtain labeled content corresponding to the segmentation result; Based on the analysis intention category and the labeled content, data analysis requirement information corresponding to the data analysis request message is obtained.

8. The method according to any one of claims 1 to 7, characterized in that, The data analysis result corresponding to the data analysis request message is obtained by performing data analysis on the target analysis data and the data analysis instruction template, including: Based on the target analysis data and the data analysis instruction template, model question information is generated; The model question information is input into a pre-trained large language model to perform data analysis, and a data analysis result corresponding to the data analysis request message output by the large language model is obtained.

9. A data analysis device, characterized by The device includes: A requirement determination module configured to obtain a data analysis request message and determine corresponding data analysis requirement information based on the data analysis request message; An index model acquisition module configured to acquire a target index model including a data analysis index and a data analysis instruction template corresponding to the target index model based on the data analysis requirement information; A data table model acquisition module configured to acquire a target data table model matching the target index model, the target data table model including target analysis data satisfying the data analysis index; An analysis result acquisition module configured to perform data analysis on the target analysis data and the data analysis instruction template to obtain a data analysis result corresponding to the data analysis request message. 10.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-9. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

Images