A hierarchical table data visualization intelligent construction method and device based on natural language question answering, a computer readable storage medium and an electronic device

Abstract

The application relates to a hierarchical table data visualization intelligent construction method and device based on natural language question answering. The method comprises the following steps: uploading hierarchical table data in an Excel format by a user; a user proposes a visualization demand for the hierarchical table by using a natural language interactive mode; a system analyzes the natural language to determine a data region and a visualization task; the system extracts an auxiliary hierarchical table transformation according to a data screening result and data insight; and the system defines row / column descriptor priorities according to a table unit specified by the user, and then realizes the visualization in an interactive mode. The method can make the user propose a data analysis demand in a natural language mode by using a natural language processing technology, help the user find valuable information in data by using automatic data insight recognition, and quickly generate a user-satisfactory visualization result by using an intelligent data visualization construction process. The application reduces a data analysis threshold, and improves data analysis efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data visualization, and particularly relates to a hierarchical table data visualization intelligent construction method and device based on natural language question answering, a computer readable storage medium, and an electronic device. BACKGROUND

[0002] With the rapid development of information technology, the amount of data is showing explosive growth, and the analysis and processing of data have become a key requirement in various fields. Among numerous data expression forms, hierarchical table data is widely used in scientific research, finance, business intelligence, medical health and other fields due to its powerful information organization capability. Hierarchical table data can express complex data relationships and multi-dimensional data characteristics through multi-level table headers of rows and columns, making data storage and query more efficient. However, existing hierarchical table data visualization technology faces a series of challenges. First, traditional visualization technology usually requires users to have certain technical background to operate complex software interfaces to filter, process and visualize data, thereby limiting the use of non-professional users and increasing the threshold of data analysis. Second, existing visualization technology often lacks the ability to understand and process natural language, and users cannot directly use natural language to describe their analysis requirements, which requires users to spend extra effort to learn how to convert natural language requirements into operation instructions that can be understood by visualization tools. In addition, the complexity of hierarchical table data also brings challenges to visualization. The data in hierarchical table is often multi-dimensional and nested, and existing visualization technology is difficult to effectively process such complex data structure, making it difficult to intuitively display the hierarchical relationship and associated information between data. Finally, existing visualization technology often has performance bottlenecks when processing large-scale data, resulting in slow or even impossible visualization process. In order to solve the above problems, researchers try to combine natural language processing technology with data visualization technology to provide more intuitive and efficient data analysis means. Through the natural language interface, users can express their query requirements in natural language, and the system automatically understands the user requirements and generates the corresponding visualization results. However, although this research direction has great potential, it still faces many challenges.

[0003] First, the ambiguity and diversity of natural language make it difficult for systems to accurately understand user query intent. For example, users may ask for the same data in multiple different ways, such as "show sales trends" or "sales changes over time." The system needs to be able to identify the common needs underlying these different expressions. Second, existing natural language visualization systems mostly focus on simple datasets and lack effective support for complex, multidimensional, and hierarchical tabular data. The complexity of hierarchical tabular data lies in its nested relationships and multi-level headers, which requires the system to deeply understand and analyze the data. Furthermore, automated data insight identification is another challenge. When analyzing data, users often hope to discover patterns, trends, and anomalies, which requires the system to possess a certain level of data insight. However, most existing systems lack this capability, and users still need to manually explore to discover this information. Finally, existing natural language visualization systems lack flexibility in the visualization construction process and have a low level of automation. After obtaining the visualization results, users often need to make multiple adjustments and optimizations, which is tedious and inefficient. Summary of the Invention

[0004] In response to the above-mentioned deficiencies in the prior art, the present invention proposes a new intelligent construction method for hierarchical tabular data visualization based on natural language question answering (natural language for hierarchical tabular data visualization, hereinafter referred to as the NL4HiTV system). This method uses natural language processing technology to enable users to express data analysis requirements in natural language; through automated data insight recognition, it helps users discover valuable information in the data; and through an intelligent data visualization construction process, it quickly generates user-satisfied visualization results. This application aims to lower the threshold for data analysis, improve the efficiency and accuracy of data analysis, and help users better understand and utilize hierarchical tabular data.

[0005] In order to achieve the above objectives, this application provides the following technical solutions:

[0006] A first aspect of the present application provides a method for intelligently constructing hierarchical table data visualization based on natural language question answering, the method comprising:

[0007] Users upload hierarchical table data in Excel format;

[0008] Users use natural language interaction to express their needs for visualization of hierarchical tables;

[0009] The system parses natural language to determine data areas and visualization tasks;

[0010] The system extracts an auxiliary hierarchical table transformation according to a result of data screening and data insight;

[0011] The system defines row / column descriptor priority according to a table cell specified by a user, and then realizes visualization interactively.

[0012] Optionally, in the method, the user uploads hierarchical table data in Excel format, and the method comprises the following steps:

[0013] The user uploads hierarchical table data in Excel format, and the system automatically parses the hierarchical table data to generate table data in JSON format.

[0014] The table data in JSON format is converted into an input format required by a question and answer model, and is used for model input and front-end table display.

[0015] The system extracts a table header structure of the hierarchical table, integrates all data attributes in the table, and obtains a name, a type and a numerical result of each cell.

[0016] Optionally, in the method, the user proposes a visualization requirement for the hierarchical table by using a natural language interactive mode, and the method comprises the following steps:

[0017] The system provides an interface of the natural language interactive mode for the user, and supports the user to propose the visualization requirement by using the natural language interactive mode.

[0018] The user proposes the visualization requirement for the hierarchical table by using the natural language interactive mode.

[0019] The system analyzes the natural language proposed by the user by using a question and answer model and a rule-based method, and converts the natural language into an operation corresponding to a visualization system.

[0020] Optionally, in the method, the system parses the natural language to determine a data region and a visualization task, and the method comprises the following steps:

[0021] When the user inputs a query by using the natural language, the system first parses the query into data in JSON format.

[0022] The system converts an output of the question and answer model into a filtering expression, and the filtering expression is organized in a list form, and each list element represents a filtering condition and corresponds to a specific data subset in the hierarchical table.

[0023] The system optimizes and adjusts the filtering list by using a Word2Vec model and a similarity matching algorithm.

[0024] The system generates a syntactic analysis tree through a syntactic analysis tool, the tree structure of the syntactic analysis tree represents the grammatical structure of the sentence, the keywords and phrases in the user query sentence are identified according to the syntactic analysis tree, and then the data area and the visualization task are determined through syntactic analysis;

[0025] The system uses the keyword recognition method to map the natural language query sentence to the visualization task supported by the system.

[0026] Optionally, in the method of the present application, the Word2Vec model converts words in the text into vectors and identifies semantically similar words by calculating the similarity between the vectors, and the system compares the user's natural language query with the table headers in the table using the Word2Vec model to determine the most relevant data area.

[0027] The visualization tasks supported by the system include bar chart, line chart, pie chart, scatter plot, box plot, heat map, tree chart, ring chart, radar chart, dot matrix chart, stacked chart, area chart and word cloud.

[0028] Optionally, in the method of the present application, the system extracts an auxiliary hierarchical table transformation according to the results of data filtering and data insight, including:

[0029] The system reorganizes the data through a multi-dimensional transformation method and compares the data performance under different dimensional combinations.

[0030] The system uses box plot and standard deviation analysis to identify outliers, helping users to find potential data errors or important special events.

[0031] The system calculates the Pearson or Spearman correlation coefficient to quantify the linear or nonlinear relationship between different data dimensions.

[0032] The system uses regression analysis method to analyze the trend of data, identifies the linear trend, polynomial trend or seasonal pattern in the data, and provides the basis for future prediction for the user.

[0033] The system quickly locates the maximum and minimum values in the data subset through statistical functions, helping users to identify key performance indicators or abnormal situations.

[0034] The system uses a quantitative evaluation mechanism to evaluate the contribution of different transformation methods to data insight.

[0035] The system sets up a feedback mechanism, and each evaluation and adjustment of the user is used as data input to optimize the analysis algorithm of the system, realizing self-learning and continuous improvement.

[0036] Optionally, in the method of the present application, the system defines the row / column descriptor priority according to the user-specified table cell, and then realizes the visualization interaction, including:

[0037] When a user inputs a query sentence through natural language, the system first parses the sentence to determine the user's visualization needs, then automatically selects a matching visualization library to generate a corresponding chart and embed it in the appropriate location in the user interface;

[0038] The system provides interactive visualization editing functions. The user clicks on the embedded visualization result and selects different visualization types or adjusts the current visualization parameters through the pop-up editing panel;

[0039] The system recommends the use of the same visualization form for similar areas based on the similarity of data structures and the user's historical interaction behavior by identifying patterns in the data;

[0040] The system recommends visualization forms according to the dimensions and types of data.

[0041] The second aspect of the present application provides a natural language question and answer-based hierarchical table data visualization intelligent construction device, which comprises:

[0042] A data uploading and processing module is configured to upload Excel format hierarchical table data and parse, extract and process the data;

[0043] A request receiving module is configured to receive the user's visualization requirements for the hierarchical table in the form of natural language interaction;

[0044] A task confirmation module is configured to parse the natural language to determine the data area and the visualization task;

[0045] A task conversion module is configured to extract auxiliary hierarchical table transformation according to the results of data filtering and data insight;

[0046] A task execution module is configured to interactively implement visualization by defining row / column descriptors priority according to the user-specified table cells.

[0047] The device realizes the steps of the aforementioned natural language question and answer-based hierarchical table data visualization intelligent construction method when running.

[0048] The third aspect of the present application provides an electronic device comprising a memory and a processor;

[0049] The memory is configured to store a computer program;

[0050] The processor is configured to execute the computer program to realize the steps of the aforementioned natural language question and answer-based hierarchical table data visualization intelligent construction method.

[0051] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the aforementioned intelligent construction method for hierarchical table data visualization based on natural language question answering.

[0052] In summary, the present application proposes a new intelligent construction method for hierarchical table data visualization based on natural language question answering, which has the following advantages:

[0053] (1) The present method realizes intelligent visualization construction of hierarchical table data through natural language question answering, reduces the requirement for user's technical background, solves the problem that non-professional users cannot operate complex software interfaces for data visualization, improves the efficiency of data processing and visualization, and ensures the accuracy and usability of the analysis results.

[0054] (2) The present method supports modeling of complex table data with hierarchical structure, which can be used as the basis for data transformation and visualization range recommendation. By transforming table data, users can easily explore different aspects of the same data, and the rich visualization results created on this basis can assist users in understanding complex table data. In the process of creating visualization, flexible table visualization unit declaration and recommendation mechanism make users no longer need to repeatedly select data areas and specify visualization parameters, which improves the exploration efficiency and reduces the operation burden.

[0055] (3) The present method can automatically parse hierarchical table data in Excel format and convert it into JSON format for easy processing. This process not only provides a basis for subsequent data processing and visualization, but also realizes seamless connection between user demand and data operation through natural language processing technology. Users can express their needs through natural language, and the system can accurately understand and convert them into corresponding data operation instructions, greatly simplifying the user's operation process.

[0056] (4) In terms of dynamic data visualization, the present method can intelligently recommend and generate appropriate visualization charts according to user needs and data characteristics. This dynamic recommendation mechanism, combined with interactive editing functions, enables users to easily adjust the parameters of visualization charts, such as color, axis labels, etc., to meet individual display needs. In addition, the present method also provides intelligent recommendation and flexibility for data visualization, and users can freely define the priority of row / column descriptors, and the system realizes visualization accordingly.

[0057] (5) The intelligent recommendation and reusability function of the method allows the user's visualization settings for specific data to be recorded and applied to other similar structured data, thereby improving work efficiency. The system learns and optimizes itself through user feedback, continuously improving the accuracy of data processing and visualization, and ensuring the reliability of the analysis results.

[0058] (6) The method helps users quickly identify data patterns and trends through intuitive visual results, supporting more effective decision-making. The method reduces the technical threshold for using data visualization tools, making it easy for non-technical users to use the method, enhancing data insight, and helping users discover deep meanings and potential value in data.

[0059] Other features and advantages of the present application will be set forth in the following description, and in part will be apparent from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and attained by the techniques particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0061] Figure 1 The overall implementation flowchart of the hierarchical table data visualization intelligent construction method based on natural language question answering provided by an embodiment of the present application.

[0062] Figure 2 The implementation process diagram from the original complex table data to the visualization result according to the method of the embodiment of the present application.

[0063] Figure 3 The hierarchical table region selection process diagram in the method of the embodiment of the present application.

[0064] Figure 4 The overall architecture diagram of the hierarchical table question answering model in the method of the embodiment of the present application.

[0065] Figure 5 The flowchart of the table transformation algorithm in the embodiment of the present application.

[0066] Figure 6It is a visual analysis interface of the NL4HiTV system according to an embodiment of the present application. In the figure, a represents a table transformation operation part; b represents a natural language query part; c represents a visualization parameter configuration part; d represents a table visualization part; and e represents a visualization template recommended by the system for a table region.

[0067] Figure 7 The figure is a component structure diagram of the natural language question and answer based hierarchical table data visualization intelligent construction device according to an embodiment of the present application.

[0068] Figure 8 The figure is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0070] The term "comprising" and variations thereof as used in the present application are open-ended, that is, "including but not limited to"; the term "based on" is "at least partially based on"; and the term "one embodiment" means "at least one embodiment".

[0071] It should be noted that the modification of "one" and "multiple" mentioned in the present application is illustrative but not restrictive, and a person of ordinary skill in the art should understand that "one or more" should be understood unless the context clearly indicates otherwise.

[0072] Figure 1 The figure is an overall implementation flow of a natural language question and answer based hierarchical table data visualization intelligent construction method according to an embodiment of the present application. The method belongs to interactive data transformation and visualization construction technology for complex tables. Specifically, the method includes the following steps:

[0073] The user uploads hierarchical table data in an Excel format;

[0074] The user proposes a visualization requirement for the hierarchical table by using a natural language interactive mode;

[0075] The system analyzes the natural language to determine a data region and a visualization task;

[0076] The system extracts an auxiliary hierarchical table transformation according to a result of data screening and data insight;

[0077] The system defines row / column descriptor priority according to user-specified table cell, and then realizes interactive visualization.

[0078] Figure 2 The implementation process from the original complex table data to the visualization result according to the method of the embodiment of the application is shown as follows: Figure 2 As shown, the implementation process of the method of the application includes the following five steps:

[0079] (1) User uploads Excel format hierarchical table data

[0080] The user uploads the Excel format hierarchical table data, and the NL4HiTV system automatically parses the table to generate JSON format table data, converts the table data into the input format required by the question and answer model, and uses the table data for model input and front-end table display. At the same time, the system extracts the table header structure of the hierarchical table, and integrates all data attributes in the table to obtain the name, type and numerical result of each cell.

[0081] (2) User uses natural language interactive mode to propose visualization requirements for the hierarchical table

[0082] The NL4HiTV system provides an interface for natural language interaction for users, supports users to propose visualization requirements through natural language interaction, and helps users to intelligently construct visualization results. The system uses question and answer models and rule-based methods to analyze the natural language proposed by the user, so as to convert the natural language into the corresponding operation of the visualization system.

[0083] (3) System parses natural language to determine data region and visualization task

[0084] In the NL4HiTV system, when the user inputs queries through natural language, the system first parses these queries into JSON format data. This step is crucial because it allows the system to convert unstructured natural language into structured format for subsequent processing. The system then converts the output of the question and answer model into filtering expressions, which are organized in a list form, and each list element represents a filtering condition corresponding to a specific data subset in the hierarchical table. For example, if the user asks "2020 annual sales in each quarter", the system will generate a filtering expression to extract the 2020 annual sales data in each quarter from the table.

[0085] To improve the accuracy and relevance of the filtering process, the system employs a Word2Vec model and a similarity matching algorithm to optimize the filtering list. The Word2Vec model can convert words in the text into vectors and identify semantically similar words by calculating the similarity between vectors. The system uses this feature to compare the user's natural language query with the table headers in the table to determine the most relevant data area. The similarity matching algorithm further refines the filtering conditions to ensure that the system can accurately identify and extract the data subset that the user is interested in. After the optimization of the filtering list is complete, the system generates a syntactic analysis tree using a syntactic analysis tool. This tree structure can represent the grammatical structure of the sentence, including phrase structure and dependency relationships. The system analyzes these structures to identify keywords and phrases, which are essential for understanding the user's query intent.

[0086] Finally, the system uses the keyword recognition method to map the natural language query sentence to one of the 13 visualization tasks supported by the system. For example, if the user's query contains a comparison of data trends in different time periods, the system will map this query to a trend analysis task and select an appropriate visualization form (such as a line chart) to display the data. This mapping process ensures that the user's query intent can be accurately understood and executed.

[0087] (4) The system extracts auxiliary hierarchical table transformations based on the results of data filtering and data insight

[0088] In the process of extracting auxiliary hierarchical table transformations based on the results of data filtering and data insight, first, the system reorganizes the data through multi-dimensional transformation methods to explore the data performance under different dimension combinations, such as cross-analysis of time series and region categories. In terms of outlier detection, the system uses statistical methods such as box plots and standard deviation analysis to identify values that are significantly different from most data, helping users to discover potential data errors or important special events.

[0089] For correlation analysis between data, the system calculates Pearson or Spearman correlation coefficients to quantify the linear or nonlinear relationship between different data dimensions. For example, analyzing the correlation between sales and advertising spending can reveal the potential impact of marketing activities. Trend analysis is achieved through regression analysis methods, and the system can identify linear trends, polynomial trends, or seasonal patterns in data to provide the basis for future predictions for users.

[0090] In the extreme value analysis, the system quickly locates the maximum and minimum values in the data subset through statistical functions, which helps users to identify key performance indicators or abnormal situations. To evaluate the contribution of different transformation methods to data insight, the system uses a quantitative evaluation mechanism that can train models based on historical data and user feedback to score data transformation methods based on machine learning algorithms.

[0091] In addition, the system provides rich user interaction functions, including drag-and-drop, selection, and transformation, allowing users to manually adjust the data hierarchy and layout. Through intuitive data visualization tools such as bar charts, line charts, scatter plots, and box plots, users can more intuitively understand the results of data transformation and verify the accuracy of system analysis.

[0092] The system also designs a feedback mechanism, where each user evaluation and adjustment serves as data input to optimize the system's analysis algorithms, enabling self-learning and continuous improvement. This design philosophy that combines automated analysis and user feedback not only improves data processing efficiency but also ensures the accuracy and usability of analysis results, greatly enhancing user control and understanding of the data analysis process.

[0093] (5) The system defines row / column descriptor priority based on user-specified table cells and interactively implements visualization

[0094] To meet the diverse needs of users in the data analysis process, the system supports 13 different visualization forms, including bar charts, line charts, pie charts, scatter plots, box plots, heat maps, tree maps, ring charts, radar charts, dot matrix charts, stacked charts, area charts, and word clouds. These visualization forms cover a wide range of data analysis tasks from basic comparison and distribution analysis to complex pattern recognition.

[0095] When users input query statements through natural language, the system first parses these statements to determine the user's visualization needs. For example, if the user's query is "show the sales trend of each product category," the system will identify this as a time series analysis task and recommend using a line chart to display the data. The system will automatically select the appropriate visualization library (such as D3.js or Echarts) to generate the corresponding chart and embed it in the appropriate location in the user interface.

[0096] To improve user experience, the system provides interactive visualization editing functions. Users can click on the embedded visualization results and select different visualization types or adjust the parameters of the current visualization through the pop-up editing panel. For example, users can change the color of the bar chart, adjust the axis labels, modify the display of data series, or switch to the stacking mode to view the contribution of each part to the total. These adjustments can be achieved through simple sliders, drop-down menus, or color selectors, allowing users to easily customize the visualization display without professional knowledge.

[0097] In addition, the system also has an intelligent recommendation function, which can identify patterns in the data and recommend visualization forms. For example, if a user is viewing sales data for a specific region and selects a bar chart to display, the system will automatically analyze other similar data areas in the table (such as sales data for other regions) and recommend using the same bar chart visualization form. This recommendation mechanism is based on the similarity of data structures and the user's historical interaction behavior, aiming to strengthen the comparison and analysis between data through consistent visualization methods.

[0098] When recommending visualizations, the system also considers the dimensions and types of data. For categorical data, the system may recommend using pie charts or bar charts to display proportions and distributions; for numerical data, it may recommend using line charts or area charts to display trends and changes. For data containing multiple dimensions, the system may recommend using scatter plots or heat maps to display the relationship between variables.

[0099] In terms of technical implementation, the system backend builds a mapping model of visualization tasks and visualization forms, which selects the most suitable visualization method based on the natural language processing results of user input, combined with data content and structural characteristics. The front end is responsible for dynamically rendering the selected visualization form to the user interface and providing rich interactive controls to meet the user's individual needs.

[0100] Figure 3 The figure shows the hierarchical table region selection process in the embodiment of the application. The region selection process includes two functions (filter_tree h) and (filter_level l). Wherein, h represents the table header of the hierarchical table, and l represents the level of the hierarchical table. The functions should be called in order, and the subsequent function filters the returned region of the previous function. The function (filter_tree h) selects the corresponding subtree in the tree structure according to the table header cell. If h is a leaf table header, it directly filters the corresponding row or column of the region, otherwise it filters the corresponding region of the table header index. The function (filter_level l) selects the subtree from the input structure according to the level in the hierarchical table, and returns the sub-region of the table header index at this level.

[0101] Figure 4 The figure shows the overall architecture of the hierarchical table question and answer model in the embodiment of the application. In the whole process, the parser of the table question and answer model needs to use BERT to encode the natural language question and the table header of the hierarchical table data, and then input the encoded result into the parsing framework for processing. The parsing framework combines the question and the table header data to generate a logical form expression. Finally, the executor with hierarchical structure form uses the logical expression to query and operate the table to produce the final answer.

[0102] Figure 5The flow of the table transformation algorithm in the embodiment of the application is shown. After the data area of the natural language query interpretation module is received by the data transformation module, it is necessary to first determine whether the data is a cell area or a data block area, so as to determine which algorithm to use to determine the table transformation method.

[0103] Figure 6 The visual analysis interface of the NL4HiTV system in the embodiment of the application is shown. In the figure, a represents a table transformation operation part; b represents a natural language query part; c represents a visual parameter configuration part; d represents a table visualization part; and e represents a visualization template recommended by the system for the table area.

[0104] Further, on the basis of the above technical solutions of the application, the following technical extensions can be made:

[0105] (1) Further enhance the natural language processing capability: by integrating more advanced natural language processing technology, such as context-aware question and answer system, the understanding ability of the system to the user query intention can be improved, so as to provide more accurate data visualization results.

[0106] (2) Multi-modal data fusion: in addition to text data, image, sound and other data types can be fused to provide more rich data visualization forms.

[0107] (3) Enhance cross-platform compatibility: further develop cross-platform data visualization tools, so that they can run on different operating systems and devices to meet the needs of different users.

[0108] Figure 7 The hierarchical table data visualization intelligent construction device based on natural language question and answer proposed in the application comprises:

[0109] Data uploading and processing module: for uploading Excel format hierarchical table data, and parsing, extracting and processing the data;

[0110] Request receiving module: for receiving the visualization demand of the hierarchical table proposed by the user in the form of natural language interaction;

[0111] Task confirmation module: for analyzing natural language to determine the data area and the visualization task;

[0112] Task conversion module: for extracting auxiliary hierarchical table transformation according to the results of data screening and data insight;

[0113] Task execution module: for defining row / column descriptor priority according to the table cell specified by the user, and then realizing the visualization interactively.

[0114] The device realizes the steps of the natural language question and answer based hierarchical table data visualization intelligent construction method disclosed in the application.

[0115] The flowcharts and block diagrams in the drawings illustrate the possible architectural, functional, and operational scenarios of apparatuses, methods, and computer program products in accordance with various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that each block in the block diagrams and / or flowcharts, as well as a combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0116] As shown in Figure 8 The embodiments of the present application also disclose an electronic device, which comprises a processor 310, a communication interface 320, a memory 330 for storing a processor-executable computer program, and a communication bus 340. The processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 realizes the steps of the natural language question and answer based hierarchical table data visualization intelligent construction method disclosed in the application by running the executable computer program.

[0117] It can be understood that, in addition to the memory and the processor, the electronic device can also comprise an input device such as a keyboard, an output device such as a display, and other communication modules. The input device, the output device, and the other communication modules communicate with the processor through an I / O interface (i.e., an input / output interface).

[0118] The computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including an object-oriented, such as Java, Smalltalk, C++, or conventional procedural, such as the "C" language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0119] Further, the present application also discloses a computer readable storage medium, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device can perform each step of the natural language question and answer based hierarchical table data visualization intelligent construction method disclosed by the present application.

[0120] In the context of the present application, the computer readable storage medium can be a tangible medium, and more specific examples will include a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0121] In particular, according to the embodiments of the present application, the processes described by the flowcharts can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for executing the natural language question and answer based hierarchical table data visualization intelligent construction method disclosed by the present application. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of the embodiments of the present application are executed.

[0122] Although several implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. The above description is merely a preferred embodiment of the present application and an explanation of the principles of the technology applied. Those skilled in the art should understand that the disclosed scope of the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the disclosed concept.

[0123] Those skilled in the art should also understand that the technical solutions described in the foregoing embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligently constructing hierarchical table data visualization based on natural language question answering, characterized in that: The method comprises: Users upload hierarchical table data in Excel format; Users use natural language interaction to express their needs for visualization of hierarchical tables; The system parses natural language to determine data areas and visualization tasks, which include: When users enter queries in natural language, the system first parses these queries into JSON formatted data; The system converts the output of the question-answering model into a filter expression, which is organized in a list format. Each list element represents a filter condition, corresponding to a specific data subset in the hierarchical table. The system uses the Word2Vec model and similarity matching algorithm to optimize and adjust the filter list; The system uses a syntactic analysis tool to generate a syntactic analysis tree. The tree structure of the syntactic analysis tree represents the grammatical structure of the sentence. The system identifies keywords and phrases in the user query sentence based on the syntactic analysis tree, and then determines the data area and visualization task through syntactic analysis. The system uses keyword recognition to map natural language query statements to visualization tasks supported by the system; The system extracts auxiliary hierarchical table transformations based on the results of data screening and data insights, including: The system reorganizes the data through multi-dimensional transformation methods and compares the data performance under different dimensional combinations; The system uses box plots and standard deviation analysis to identify outliers, helping users discover potential data errors or important special events; The system quantifies the linear or nonlinear relationship between different data dimensions by calculating the Pearson or Spearman correlation coefficient; The system uses regression analysis to analyze data trends, identify linear trends, polynomial trends or seasonal patterns in the data, and provide users with a basis for future predictions; The system uses statistical functions to quickly locate the maximum and minimum values ​​in data subsets, helping users identify key performance indicators or abnormal situations; The system uses a quantitative evaluation mechanism to assess the contribution of different transformation methods to data insights; The system has a feedback mechanism where every user's evaluation and adjustment is used as data input to optimize the system's analysis algorithm, enabling self-learning and continuous improvement. The system interactively implements visualization based on the row / column descriptor priorities defined by the user-specified table cells.

2. The method according to claim 1, characterized in that The user uploads hierarchical table data in Excel format, including: The user uploads hierarchical table data in Excel format, and the system automatically parses the hierarchical table data and generates table data in JSON format; Convert JSON-formatted tabular data into the input format required by the question-answering model for model input and front-end table display. The system extracts the header structure of the hierarchical table and integrates all the data attributes in the table to obtain the name, type and numerical result of each cell.

3. The method according to claim 1, characterized in that The user proposes a visualization requirement for a hierarchical table using a natural language interaction method, including: The system provides users with a natural language interaction interface, supporting users to propose visualization requirements through natural language interaction; Users use natural language interaction to express their needs for visualization of hierarchical tables; The system uses a question-answering model and a rule-based approach to analyze the natural language raised by users and convert the natural language into operations corresponding to the visualization system.

4. The method according to claim 1, wherein The Word2Vec model converts words in a text into vectors and identifies semantically similar words by calculating the similarity between the vectors. The system uses the Word2Vec model to compare the user's natural language query with the table headers in the table to determine the most relevant data areas; The visualization tasks supported by the system include: bar charts, line charts, pie charts, scatter plots, box plots, heat maps, tree maps, ring charts, radar charts, dot plots, stacked charts, area charts and word clouds.

5. The method according to claim 1, wherein The system interactively implements visualization based on user-specified table cell row / column descriptor priorities, including: When users enter query statements in natural language, the system first parses these statements to determine the user's visualization requirements, then automatically selects a matching visualization library to generate the corresponding chart and embeds it in the appropriate location in the user interface; The system provides interactive visualization editing functions. Users click on the embedded visualization results and select different visualization types or adjust the current visualization parameters through the pop-up editing panel. Based on the similarity of data structure and the user's historical interaction behavior, the system recommends similar areas using the same visualization form by identifying patterns in the data; The system recommends visualizations based on the dimensions and type of data.

6. A device for intelligently constructing hierarchical table data visualization based on natural language question answering, characterized in that: The device comprises: Data upload and processing module: used to upload hierarchical table data in Excel format and parse, extract and process the data; Request receiving module: used to receive the visualization requirements of hierarchical tables proposed by users in a natural language interaction mode; Task confirmation module: used to parse natural language to determine data areas and visualization tasks, including: When users enter queries in natural language, the system first parses these queries into JSON formatted data; The system converts the output of the question-answering model into a filter expression, which is organized in a list format. Each list element represents a filter condition, corresponding to a specific data subset in the hierarchical table. The system uses the Word2Vec model and similarity matching algorithm to optimize and adjust the filter list; The system uses a syntactic analysis tool to generate a syntactic analysis tree. The tree structure of the syntactic analysis tree represents the grammatical structure of the sentence. The system identifies keywords and phrases in the user query sentence based on the syntactic analysis tree, and then determines the data area and visualization task through syntactic analysis. The system uses keyword recognition to map natural language query statements to visualization tasks supported by the system; Task transformation module: used to extract auxiliary hierarchical table transformations based on data screening results and data insights. This includes the system reorganizing data through multi-dimensional transformation methods and comparing data performance under different dimensional combinations. The system uses box plots and standard deviation analysis to identify outliers, helping users discover potential data errors or important special events; The system quantifies the linear or nonlinear relationship between different data dimensions by calculating the Pearson or Spearman correlation coefficient; The system uses regression analysis to analyze data trends, identify linear trends, polynomial trends or seasonal patterns in the data, and provide users with a basis for future predictions; The system uses statistical functions to quickly locate the maximum and minimum values ​​in data subsets, helping users identify key performance indicators or abnormal situations; The system uses a quantitative evaluation mechanism to assess the contribution of different transformation methods to data insights; The system has a feedback mechanism where every user's evaluation and adjustment is used as data input to optimize the system's analysis algorithm, enabling self-learning and continuous improvement. Task execution module: used to define row / column descriptor priorities based on user-specified table cells and interactively implement visualization.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligently constructing hierarchical table data visualization based on natural language question answering as described in any one of claims 1 to 6 are implemented.

8. An electronic device, characterized in that: include: memory and processor; Memory: used to store computer programs; Processor: used to execute the computer program to implement the steps of the method for intelligently constructing hierarchical table data visualization based on natural language question answering as described in any one of claims 1 to 6.

Images