Data visualization method, electronic equipment, system and chip

By analyzing data intentions and preprocessing data sets, using decision tree algorithms and natural language processing to generate recommendation charts, the problems of complexity and poor user experience in the existing technology are solved, and efficient and automated data visualization processes are realized, reducing the number of data visualization processes. Cost and error risk.

CN118939893APending Publication Date: 2024-11-12SICHUAN DETUO INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410941156.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing data visualization technology has high learning cost, long development time, high iteration cost, poor user experience, cumbersome operation, large resource consumption, and difficult to quickly generate intelligent multi-dimensional visualization charts.

Method used

By obtaining the data to be converted, analyzing the data intention, preprocessing it into a data set with the same structure, using the decision tree algorithm to generate recommended charts, and combining the propt prompt engineering and natural language processing model to obtain visual rendered charts, automatically generate and insert preset applications page.

Benefits of technology

It improves the efficiency and accuracy of data processing, simplifies the data analysis process, reduces R&D and usage costs, improves user experience and data exploration capabilities, and reduces the possibility of manual operations and errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939893A_ABST
    Figure CN118939893A_ABST
Patent Text Reader

Abstract

The invention provides a data visualization method, electronic equipment, a system and a chip, and the method comprises the steps: obtaining to-be-converted data, and analyzing a data intention corresponding to the to-be-processed data; preprocessing the to-be-converted data into data with the same structure, and obtaining a corresponding data set; based on the data intention, utilizing a decision tree algorithm to generate a recommendation chart; based on the recommendation chart, utilizing a prompt prompt project and a natural language processing model to obtain a visual rendering chart corresponding to the data set; and based on a visualization result corresponding to the data set, obtaining a preset configuration chart and inserting the preset configuration chart into a page of the preset application. According to the method, the development efficiency of the visual chart can be improved, the research and development cost and the use cost of customers are reduced, and the intelligent degree is high.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of data visualization, and in particular to a data visualization method, electronic device, system and chip. Background Art

[0002] At present, the application popularity of big data is constantly increasing. After a series of data collection and governance, massive data in various industries gradually form the data assets of enterprises. How to generate visual application presentations of data more quickly and intelligently is a problem that all data manufacturers need to solve.

[0003] In the problem of generating visualization charts for traditional data, it is often necessary to develop codes based on the currently popular chart libraries such as D3 and Echarts. However, these methods have high learning costs and long development time. The development cost of iterative visualization charts is high, and the communication cost between developers and data users during the debugging process is also high, resulting in poor user experience. Therefore, how to visualize data has become an urgent problem to be solved.

[0004] Patent CN110599600B discloses a method for automatically converting a multidimensional visualization model of data, including static generation and dynamic generation. Static generation is to generate a multidimensional chart from an external table data file; dynamic generation is to dynamically obtain real-time data of scene content, provide a numerical interface, input the numerical source field, and realize dynamic generation and real-time refresh of the chart within the content; the static generation process is: import the static table data file generated by the user, perform standardized analysis on the static table data generated by the user, and obtain a multidimensional data column; map the multidimensional data column to the corresponding three-dimensional model parameters, and automatically generate the corresponding three-dimensional chart model: set the appearance attributes and VR interactive functions of the three-dimensional chart model; export a three-dimensional chart file with complete functions; import the three-dimensional chart file into a 3D interactive application; the dynamic generation process is: create a dynamic chart, and the program automatically generates a three-dimensional dynamic chart model; write the parameter fields that need to be displayed in real time in the dynamic chart model into the data interface to obtain the corresponding multidimensional data column; set the appearance attributes and VR interactive functions of the three-dimensional dynamic chart model; export the complete Functional three-dimensional chart file; import the three-dimensional chart file into the 3D interactive application; in the statically generated process, the specific execution process of the program after importing the file is: activate the logical function, generate and store the key; import the static table data file, determine whether the three-dimensional graph model to be exported is the chart type set in the program, and determine whether the static table data supports the corresponding chart type; if the three-dimensional graph model to be exported is the chart type set in the program, and the static table data dimension supports the corresponding chart type, then generate the three-dimensional graph model, otherwise, select the corresponding preset chart type and regenerate the three-dimensional graph model; edit the model properties: determine whether there is an appearance attribute record, if there is, load the last attribute setting, otherwise load the default attribute setting; provide an interface for all data to be reset to zero; in the dynamically generated process, the specific execution process of the program after writing the parameter field displayed in real time is: generate and store the key according to the chart type preset by the program; edit the data interface, and realize the mapping of the data source API by writing an array; generate a simulation model, edit the model properties; provide an interface for all data to be reset to zero. This method only involves converting data into multidimensional icons, and the operation is cumbersome and consumes a lot of resources.

[0005] Based on this, the present application provides a data visualization method, an electronic device, a system and a chip to improve the existing technology. Summary of the invention

[0006] The purpose of this application is to provide a data visualization method, electronic device, system and chip, which can enable the client to easily access the required pages and perform task operations on the pages without disconnecting the process, thereby greatly improving the client's ease of use and satisfaction.

[0007] The purpose of this application is achieved by the following technical solutions:

[0008] In a first aspect, the present application provides a data visualization method for automatically realizing multi-dimensional visualization of data, the method comprising:

[0009] Obtain the data to be converted and analyze the data intent corresponding to the data to be processed;

[0010] Preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set;

[0011] Based on the data intent, generating a recommendation chart using a decision tree algorithm;

[0012] Based on the recommended chart, a prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set;

[0013] Based on the visualization results corresponding to the data set, obtain the preset configuration chart and insert it into the page of the preset application.

[0014] The beneficial effects of the technical solution are as follows: by acquiring and analyzing the intent of the data, the intrinsic meaning and relevance of the data can be more deeply understood, providing a clear direction for subsequent data processing and analysis; converting data of different structures into a unified data set with the same structure helps to simplify the data processing process, reduce the workload of data cleaning, and ensure the consistency and accuracy of subsequent analysis; the recommended charts generated by the decision tree algorithm can intuitively display the relationship and pattern between the data, helping decision makers to quickly identify information and make more scientific decisions; combining prompt engineering and natural language processing models, more vivid and intuitive visual rendering charts can be generated, making the data analysis results easier to understand and disseminate; by acquiring the visualization results corresponding to the data set and extracting preset configuration charts from them, these charts can be easily integrated into the preset application page to improve user experience and application efficiency; the entire process promotes the interaction between people and data, making complex data intuitive through visualization, thereby improving users' ability to explore and understand data; according to different data intents and user needs, the generated visualization charts can be personalized and displayed to meet the customized needs of different users; the automated data processing and visualization process reduces manual operations, improves work efficiency, and also reduces the possibility of human errors. This method can improve the development efficiency of visual charts, reduce R&D costs and customer usage costs, and has a high degree of intelligence.

[0015] In some optional implementations, preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set includes:

[0016] Converting and integrating the data to be converted into a data set, wherein the structure of the data set is a two-dimensional array structure;

[0017] Determine whether the field information in the data set meets the preset information, the field information includes date, attribute and value;

[0018] If the field information in the data set does not conform to the preset information, the field information that does not conform to the preset information is screened and removed;

[0019] If the field information in the data set meets the preset information, then the field information meeting the preset information is saved;

[0020] Handle outliers and missing values ​​in the dataset.

[0021] The beneficial effects of the technical solution are: by integrating the data to be converted into a data set, especially by using a two-dimensional array structure, it is helpful to unify the format of data from different sources, which is convenient for subsequent processing and analysis; by judging whether the field information in the data set conforms to the preset information, the accuracy and consistency of the data can be ensured, and errors in the data can be discovered and corrected in time; if the field information in the data set does not conform to the preset information, these fields can be screened and eliminated to prevent invalid or erroneous data from affecting the analysis results; the field information that conforms to the preset information can be saved for subsequent data analysis and processing to ensure the reliability of the analysis results; by processing the outliers and missing values ​​in the data set, the integrity and reliability of the data can be improved, and the interference of outliers on the analysis results can be avoided; the data set in a unified format helps to automate the data processing process and improve the efficiency and speed of data processing; the cleaned and integrated data set provides a good foundation for machine learning and helps to discover patterns and associations in the data; eliminating data fields that do not conform to the preset information and processing outliers and missing values ​​can improve the accuracy and credibility of data analysis, and can provide users with a more intuitive and accurate data view by ensuring the quality and consistency of the data, thereby improving the user experience. Data preprocessing helps to achieve data governance and ensure the compliance and quality of data.

[0022] In some optional implementations, generating a recommendation chart based on the data intent using a decision tree algorithm includes:

[0023] Performing feature recognition on the data set to obtain data feature information;

[0024] Based on the data feature information and the data intent, a recommendation chart is generated using a decision tree algorithm.

[0025] The beneficial effects of this technical solution are: by performing feature recognition on the data set, the feature information of the data can be effectively extracted, which is crucial for understanding the data and subsequent analysis; using the extracted data feature information and data intent, the decision tree algorithm can be constructed more accurately to better reflect the relationship and pattern between the data, and the generation of recommendation charts can quickly display the key information of the data; according to different data features and intents, personalized recommendation charts can be generated for different users or scenarios to improve user satisfaction and experience. The application of feature recognition and decision tree algorithms can simplify the data analysis process, reduce the workload of manual analysis, and improve work efficiency.

[0026] In some optional implementations, the data feature information includes data dimension, data quantity, data type and data characteristics.

[0027] The beneficial effect of this technical solution is that by identifying the dimensions, quantity, type and characteristics of the data, the structure and content of the data can be fully understood, providing a solid foundation for subsequent data analysis and processing.

[0028] In some optional implementations, generating a recommendation chart using a decision tree algorithm based on the data feature information and the data intent includes:

[0029] Summarize the chart usage information to form a chart knowledge base;

[0030] Based on the data feature information, the chart knowledge base is used as a training set, and a decision tree algorithm is used to train a decision tree model;

[0031] Based on the data intent, a recommended chart is generated.

[0032] The beneficial effect of this technical solution is that by aggregating chart usage information and forming a chart knowledge base, a rich data resource is provided for subsequent model training and chart recommendation. As a training set, the chart knowledge base provides a solid foundation for the model training of the decision tree algorithm, which helps to improve the accuracy and generalization ability of the model. The decision tree model can automatically generate recommended charts based on data feature information and data intent, thereby improving the efficiency of data analysis. The decision tree model can learn and capture the complex relationship between data features and chart generation, thereby improving the accuracy of chart recommendations. Based on the user's data intent and data feature information, the decision tree model can generate personalized chart recommendations that meet user needs. By automatically generating recommended charts, the data analysis process can be greatly simplified and manual operations and interventions can be reduced.

[0033] In some optional implementations, based on the recommendation chart, using prompt engineering and a natural language processing model to obtain a visual rendering chart corresponding to the data set includes:

[0034] Performing basic rendering on the recommended chart to obtain a basic rendering chart;

[0035] Based on the basic rendering chart, a prompt prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set.

[0036] The beneficial effects of this technical solution are: through basic rendering charts, visual representations of data sets can be quickly generated to improve the efficiency of data analysis; by using prompt engineering and natural language processing models, higher-quality visual rendering charts can be obtained to make data visualization more vivid and intuitive; the generation of basic rendering charts and visual rendering charts provides a more intuitive and easy-to-understand data view, optimizes the user experience; and through basic rendering and further visual optimization of recommended charts, it can meet the personalized visualization needs of different users.

[0037] In some optional implementations, based on the basic rendering chart, using prompt engineering and a natural language processing model to obtain a visual rendering chart corresponding to the data set includes:

[0038] Entering multiple prompt words in the prompt project to perform directional stimulation on the basic rendering chart;

[0039] Performing text preprocessing on the plurality of prompt words to obtain prompt text;

[0040] Input the prompt text into a word vector model, and use the word vector model to convert the prompt text into a vector;

[0041] Using the natural language model to perform feature extraction on the vector to obtain text features and obtain the contextual relationship of the prompt text;

[0042] Based on the text feature and the context relationship, obtain a prompt intention prompt;

[0043] According to the prompt intention prompt, the visual rendering chart is obtained using CSS.

[0044] The beneficial effects of the technical solution are as follows: by inputting multiple prompt words through the prompt prompt project, the basic rendering chart can be stimulated in a targeted manner to achieve more accurate chart rendering results. Inputting multiple prompt words is helpful to capture the diverse needs of users for charts and improve the personalization of chart rendering. The text preprocessing of multiple prompt words can obtain more accurate and appropriate prompt texts, which provides high-quality input for subsequent word vector models and natural language processing models. The prompt text is converted into a vector by using the word vector model to achieve quantitative representation of the prompt word, which is convenient for subsequent feature extraction and analysis. The vector is feature extracted by the natural language model to obtain text features and contextual relationships of the prompt text. Based on the text features and contextual relationships, prompt intention prompts are accurately obtained to provide clear guidance for subsequent chart rendering. According to the prompt intention prompt, CSS is used to automatically obtain the corresponding visual rendering chart, simplifying user operations and improving rendering efficiency. The automated and accurate chart rendering process provides users with a more convenient and efficient experience and reduces the user's learning cost for chart rendering. By obtaining prompt intention prompts and rendering charts that meet user needs, the interpretability and credibility of data analysis results are improved.

[0045] In a second aspect, the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor being configured to implement the following steps when executing the computer program:

[0046] Obtain the data to be converted and analyze the data intent corresponding to the data to be processed;

[0047] Preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set;

[0048] Based on the data intent, generating a recommendation chart using a decision tree algorithm;

[0049] Based on the recommended chart, a prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set;

[0050] Based on the visualization results corresponding to the data set, obtain the preset configuration chart and insert it into the page of the preset application.

[0051] In some optional embodiments, the processor is configured to preprocess the data to be converted into data with the same structure and obtain the corresponding data set in the following manner when executing the computer program:

[0052] Converting and integrating the data to be converted into a data set, wherein the structure of the data set is a two-dimensional array structure;

[0053] Determine whether the field information in the data set meets the preset information, the field information includes date, attribute and value;

[0054] If the field information in the data set does not conform to the preset information, the field information that does not conform to the preset information is screened and removed;

[0055] If the field information in the data set meets the preset information, then the field information meeting the preset information is saved;

[0056] Handle outliers and missing values ​​in the dataset.

[0057] In some optional implementations, the data feature information includes data dimension, data quantity, data type and data characteristics.

[0058] In some optional embodiments, the processor is configured to generate a recommendation chart using a decision tree algorithm based on the data feature information and the data intent in the following manner when executing the computer program, including:

[0059] Summarize the chart usage information to form a chart knowledge base;

[0060] Based on the data feature information, the chart knowledge base is used as a training set, and a decision tree algorithm is used to train a decision tree model;

[0061] Based on the data intent, a recommended chart is generated.

[0062] In some optional embodiments, the processor is configured to execute the computer program in the following manner to obtain a visual rendering chart corresponding to the data set based on the recommendation chart using prompt engineering and a natural language processing model:

[0063] Performing basic rendering on the recommended chart to obtain a basic rendering chart;

[0064] Based on the basic rendering chart, a prompt prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set.

[0065] In some optional embodiments, the processor is configured to execute the computer program in the following manner to obtain a visual rendering chart corresponding to the data set based on the basic rendering chart using prompt engineering and a natural language processing model:

[0066] Entering multiple prompt words in the prompt project to perform directional stimulation on the basic rendering chart;

[0067] Performing text preprocessing on the plurality of prompt words to obtain prompt text;

[0068] Input the prompt text into a word vector model, and use the word vector model to convert the prompt text into a vector;

[0069] Using the natural language model to perform feature extraction on the vector to obtain text features and obtain the contextual relationship of the prompt text;

[0070] Based on the text feature and the context relationship, obtain a prompt intention prompt;

[0071] According to the prompt intention prompt, the visual rendering chart is obtained using CSS.

[0072] In a third aspect, the present application provides a data visualization system, the system comprising:

[0073] The above electronic equipment.

[0074] In a fourth aspect, the present application provides a chip storing a computer program, wherein the computer program implements the steps of any of the above methods when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The present application is further described below in conjunction with the accompanying drawings and implementation methods.

[0076] Figure 1 A schematic diagram of a data visualization method provided in an embodiment of the present application is shown;

[0077] Figure 2 A schematic diagram of a process for generating a recommendation chart provided in an embodiment of the present application is shown;

[0078] Figure 3 A schematic diagram of a process for generating a visual rendering chart provided in an embodiment of the present application is shown;

[0079] Figure 4 A structural framework diagram of an electronic device provided in an embodiment of the present application is shown;

[0080] Figure 5 A schematic diagram of the structure of a data visualization system provided by an embodiment of the present application is shown;

[0081] Figure 6 A schematic diagram of the structure of a program product provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0082] Below, the embodiments of the present application are further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the embodiments or technical features described below can be arbitrarily combined to form a new implementation method.

[0083] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, a and b, a and c, b and c, a and b and c, where a, b and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more items".

[0084] It should also be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any implementation or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other implementations or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0085] Method Embodiment

[0086] See also Figure 1 , Figure 1 A flow chart of a data visualization method provided in an embodiment of the present application is shown.

[0087] The embodiment of the present application provides a data visualization method for performing online wake-up, login, and task execution operations on a page of a target application, the method comprising:

[0088] Step S101: obtaining data to be converted, and analyzing the data intent corresponding to the data to be processed;

[0089] Step S102: preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set;

[0090] Step S103: Based on the data intent, a recommendation chart is generated using a decision tree algorithm;

[0091] Step S104: Based on the recommendation chart, a visual rendering chart corresponding to the data set is obtained by using prompt engineering and a natural language processing model;

[0092] Step S105: Based on the visualization result corresponding to the data set, a preset configuration chart is obtained and inserted into a page of a preset application.

[0093] Therefore, by obtaining and analyzing the intent of the data, we can have a deeper understanding of the intrinsic meaning and relevance of the data, providing a clear direction for subsequent data processing and analysis; converting data of different structures into a unified data set with the same structure can help simplify the data processing process, reduce the workload of data cleaning, and ensure the consistency and accuracy of subsequent analysis;

[0094] The recommended charts generated by the decision tree algorithm can intuitively display the relationships and patterns between data, helping decision makers quickly identify information and make more scientific decisions. Combining prompt engineering and natural language processing models can generate more vivid and intuitive visual rendering charts, making data analysis results easier to understand and disseminate. By obtaining the visualization results corresponding to the data set and extracting preset configuration charts from them, these charts can be easily integrated into the preset application page to improve user experience and application efficiency.

[0095] The entire process promotes the interaction between people and data, making complex data intuitive through visualization, thereby improving users' ability to explore and understand data; according to different data intentions and user needs, the generated visualization charts can be personalized and displayed to meet the customized needs of different users;

[0096] Automated data processing and visualization processes reduce manual operations, improve work efficiency, and also reduce the possibility of human error. This method can improve the development efficiency of visualization charts, reduce R&D costs and customer usage costs, and has a high degree of intelligence.

[0097] In the embodiments of this application, data intent refers to identifying and understanding the goals or purposes expressed by data during data processing and analysis. It involves in-depth exploration of the source, content, structure, and meaning of data in order to better use data to provide insights, support decision-making, and promote business development. Understanding data intent is critical to ensuring the effective use and value extraction of data.

[0098] In the embodiments of the present application, prompt engineering is an important technology in the field of artificial intelligence, which involves how to design, build and optimize prompts to improve the performance and user experience of artificial intelligence systems (such as chatbots, text generation models, etc.). Prompts can be seen as an interface between users and artificial intelligence systems, which can guide the model to understand the user's intentions and generate corresponding responses.

[0099] In some optional embodiments, the step of analyzing the type of data intended source may be, if the uploaded data is Excel, CSV, Txt, DBLink, then the uploaded file directly enters step S102 for data recording and processing; if the processed data is local data, such as the result and columns data drawn by the back-end server, then the step S103 is directly entered.

[0100] In some optional implementations, the chart is configured in specific details; based on the chart type and the size of the display space, the effective display load of the visualization is calculated, and the layout of each component is dynamically adjusted.

[0101] The specific configuration details include automatic rotation of X-axis and Y-axis labels when they are too long, automatic cutting of text when it exceeds the visible area, etc.

[0102] Step S105 specifically includes: according to the prompt word result of the prompt project, using it as the input of the language processing model for further processing, and submitting the result after the model processing to the software program for processing and presenting it to the page display.

[0103] In some optional implementations, preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set includes:

[0104] Converting and integrating the data to be converted into a data set, wherein the structure of the data set is a two-dimensional array structure;

[0105] Determine whether the field information in the data set meets the preset information, the field information includes date, attribute and value;

[0106] If the field information in the data set does not conform to the preset information, the field information that does not conform to the preset information is screened and removed;

[0107] If the field information in the data set meets the preset information, then the field information meeting the preset information is saved;

[0108] Handle outliers and missing values ​​in the dataset.

[0109] Therefore, by integrating the data to be converted into a data set, especially using a two-dimensional array structure, it is helpful to unify the format of data from different sources, which is convenient for subsequent processing and analysis; by judging whether the field information in the data set conforms to the preset information, the accuracy and consistency of the data can be ensured, and errors in the data can be discovered and corrected in a timely manner;

[0110] If the field information in the data set does not meet the preset information, these fields can be screened and removed to prevent invalid or erroneous data from affecting the analysis results. Field information that meets the preset information can be saved for subsequent data analysis and processing to ensure the reliability of the analysis results. By processing outliers and missing values ​​in the data set,

[0111] It can improve the integrity and reliability of data and avoid the interference of outliers on analysis results; data sets in a unified format can help automate the data processing process and improve the efficiency and speed of data processing; cleaned and integrated data sets provide a good foundation for machine learning and help discover patterns and associations in data;

[0112] Eliminating data fields that do not conform to preset information and processing outliers and missing values ​​can improve the accuracy and credibility of data analysis. By ensuring the quality and consistency of data, it can provide users with a more intuitive and accurate data view and enhance the user experience.

[0113] Data preprocessing helps achieve data governance and ensure data compliance and quality.

[0114] In some optional implementations, during the data preparation phase, all input data are uniformly converted into a data set with a two-dimensional array structure, the validity and legality of the numeric and date fields are judged and processed, the type information of each field is recorded, and missing values ​​and abnormal values ​​are processed to ensure data quality.

[0115] This stage mainly involves data conversion and cleaning. If the analysis intention involves map-type charts, the data will be converted into coordinates. First, the data will be mapped. Each piece of data will be uniformly mapped to a unique postal code, and then the latitude and longitude information of the corresponding area will be found through the postal code.

[0116] In some optional implementations, generating a recommendation chart based on the data intent using a decision tree algorithm includes:

[0117] Performing feature recognition on the data set to obtain data feature information;

[0118] Based on the data feature information and the data intent, a recommendation chart is generated using a decision tree algorithm.

[0119] Therefore, by performing feature recognition on the data set, the characteristic information of the data can be effectively extracted, which is crucial for understanding the data and subsequent analysis;

[0120] By utilizing the extracted data feature information and data intent, we can more accurately construct a decision tree algorithm to better reflect the relationships and patterns between data. The generation of recommendation charts can quickly display the key information of the data. Based on different data features and intents, we can generate personalized recommendation charts for different users or scenarios to improve user satisfaction and experience.

[0121] The application of feature recognition and decision tree algorithms can simplify the data analysis process, reduce the workload of manual analysis, and improve work efficiency.

[0122] In some optional implementations, the data feature information includes data dimension, data quantity, data type and data characteristics.

[0123] Therefore, by identifying the dimensions, quantity, type and characteristics of the data, we can fully understand the structure and content of the data, providing a solid foundation for subsequent data analysis and processing.

[0124] In some optional embodiments, the types and number of fields in the data set are analyzed, and the data characteristics of the data set are recorded. The data characteristics include dimensions, number of values, data types or numerical characteristics, and the relationship between fields is further analyzed to filter out related data fields, and then calculate basic statistics, such as mean, variance, correlation, etc.

[0125] See also Figure 2 , Figure 2 A schematic diagram of a process for generating a recommendation chart provided in an embodiment of the present application is shown.

[0126] In some optional implementations, generating a recommendation chart using a decision tree algorithm based on the data feature information and the data intent includes:

[0127] Step S201: Summarize chart usage information to form a chart knowledge base;

[0128] Step S202: Based on the data feature information, the chart knowledge base is used as a training set, and a decision tree algorithm is used to train a decision tree model;

[0129] Step S203: Generate a recommendation chart based on the data intent.

[0130] Therefore, by summarizing the usage information of charts, a chart knowledge base is formed, which provides rich data resources for subsequent model training and chart recommendations. As a training set, the chart knowledge base provides a solid foundation for the model training of the decision tree algorithm, which helps to improve the accuracy and generalization ability of the model.

[0131] The decision tree model can be used to automatically generate recommended charts based on data feature information and data intent, improving the efficiency of data analysis. The decision tree model can learn and capture the complex relationship between data features and chart generation, thereby improving the accuracy of chart recommendations.

[0132] According to the user's data intention and data feature information, the decision tree model can generate personalized chart recommendations that meet the user's needs. By automatically generating recommended charts, the data analysis process can be greatly simplified and manual operations and interventions can be reduced.

[0133] In an optional embodiment, the generation of basic charts can be that the chart usage information is summarized in advance to form a chart knowledge base, which contains the names, categories, definitions, analysis intentions or data requirements of different charts; then, based on the analysis intentions and the data characteristics, the chart knowledge base is used as a training set to obtain a decision tree model for judging the chart type using a decision tree algorithm; then, the intention keyword is input to generate the chart type with the highest matching degree.

[0134] This stage mainly generates basic charts, such as the attached Figure 2 As shown, it mainly includes the following steps:

[0135] Input data type: excel, csv, txt, dblink, etc.

[0136] Feature selection: attribute labeling.

[0137] Attribute annotation is a means of formatting data so that the data can be presented more intuitively from a mathematical perspective. To annotate the data set, in addition to the default id and key values, the name, date, type, description, age and other attributes of the remaining fields need to be annotated.

[0138] Empirical entropy calculation:

[0139] Empirical entropy is used to measure the uncertainty and confusion of random variables. In our example, we calculate the empirical entropy of each field in the attribute annotation one by one to obtain the degree of discreteness in the corresponding data set.

[0140] Empirical entropy formula:

[0141] H(X)=-∑i=1nP(xi)log2P(xi)

[0142] The empirical entropy of each field is calculated by the above formula, and then the field of the dimension suitable for visualization is determined according to the discrete degree of the calculated field empirical entropy.

[0143] Information gain calculation:

[0144] The degree to which the uncertainty of a random variable is reduced under certain conditions. In other words, information gain represents the degree to which the information complexity (uncertainty) is reduced under certain conditions. Now we can understand that in the decision tree algorithm, the key is to select a feature each time. If there are multiple features, then what criteria should be used to select which feature? This problem can be measured by information gain. If the information gain is the largest (the degree of information uncertainty reduction is the largest) after selecting a feature, then we will select this feature. Information gain calculation formula:

[0145] g(D,A)=H(D)-H(D|A)

[0146] Decision trees generate columns suitable for dimensions and measures:

[0147] Based on the decision tree, dimensions, metric combinations (dimensions, metrics) and visualization material template libraries are generated to generate visualization recommendation charts of different styles and dimensions.

[0148] In some optional implementations, based on the recommendation chart, using prompt engineering and a natural language processing model to obtain a visual rendering chart corresponding to the data set includes:

[0149] Performing basic rendering on the recommended chart to obtain a basic rendering chart;

[0150] Based on the basic rendering chart, a prompt prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set.

[0151] Therefore, through basic rendering charts, we can quickly generate visual representations of data sets and improve the efficiency of data analysis. By using prompt engineering and natural language processing models, we can obtain higher-quality visual rendering charts, making data visualization more vivid and intuitive.

[0152] The generation of basic rendering charts and visual rendering charts provides a more intuitive and easy-to-understand data view, optimizes the user experience, and meets the personalized visualization needs of different users by performing basic rendering and further visual optimization of recommended charts.

[0153] In an optional embodiment, the visualization effect is optimized by using prompt engineering and natural language processing models, as shown in the attached Figure 3 As shown, it mainly includes the following steps:

[0154] 1. Input the chart to be optimized selected by the user;

[0155] 2. Provide basic prompt template based on visual template;

[0156] 3. Stimulate the chart directionally based on the prompt template by inputting different prompt words, for example: making the color of the table darker;

[0157] 4. Perform text preprocessing on the prompt words, including but not limited to the following steps:

[0158] Word segmentation: Segment the input text "make the color of the table darker" into words, such as "need", "table", "of", "color", "become", "more", "dark", "some"

[0159] Stop word removal: Remove words that are not very helpful for semantic understanding, such as "of", "become"

[0160] Stem extraction or part-of-speech reduction: Convert the words to their basic forms, for example, convert "become" to "change";

[0161] 5. Use the processed prompt text of the visualization intention as the input to the word vector model, and use the word vector model to convert the segmented words into vectors;

[0162] 6. Extract features from the word vectors through the first few layers of the NLP model to capture context information and semantic relationships;

[0163] 7. Input the extracted features into the classification layer to judge its intention, for example: judge that the intention is to require deepening the color processing;

[0164] 8. Give relevant responses or operation suggestions regarding the prompt words. For example, based on the finally obtained prompt words, it is known that the user's expectation is to make the background color of the table darker, and use the front-end CSS to change the background-color of the table from rgb(0,176,240) to rgb(0,112,192);

[0165] 9. After modifying the style of the table using the software program, output the optimized configured chart.

[0166] See Figure 3 , Figure 3 which shows a schematic flowchart of a process for generating a visual rendering chart provided by an embodiment of the present application.

[0167] In some alternative embodiments, the method of obtaining the visual rendering chart corresponding to the data set based on the basic rendering chart by using the prompt engineering and the natural language processing model includes:

[0168] Step S301: Input multiple prompt words in the prompt engineering to perform directional stimulation on the basic rendering chart;

[0169] Step S302: performing text preprocessing on the plurality of prompt words to obtain prompt text;

[0170] Step S303: input the prompt text into a word vector model, and convert the prompt text into a vector using the word vector model;

[0171] Step S304: using the natural language model to perform feature extraction on the vector to obtain text features and obtain the contextual relationship of the prompt text;

[0172] Step S305: obtaining a prompt intention prompt based on the text feature and the context relationship;

[0173] Step S306: according to the prompt intention prompt, use CSS to obtain the visual rendering chart.

[0174] Therefore, by inputting multiple prompt words through the prompt project, the basic rendering chart can be stimulated in a targeted manner to achieve more accurate chart rendering results. Inputting multiple prompt words helps to capture the diverse needs of users for charts and improve the personalization of chart rendering. By performing text preprocessing on multiple prompt words, more accurate and appropriate prompt texts can be obtained, providing high-quality input for subsequent word vector models and natural language processing models.

[0175] Use the word vector model to convert the prompt text into a vector to achieve quantitative representation of the prompt word, which is convenient for subsequent feature extraction and analysis. Use the natural language model to extract features from the vector, obtain text features and the contextual relationship of the prompt text, and accurately obtain prompt intent prompts based on text features and contextual relationships, providing clear guidance for subsequent chart rendering; Prompt according to prompt intent;

[0176] Use CSS to automatically obtain the corresponding visual rendering charts, simplify user operations, and improve rendering efficiency; the automated and accurate chart rendering process provides users with a more convenient and efficient experience, reducing the user's learning cost for chart rendering; by obtaining prompt intentions and rendering charts that meet user needs, the interpretability and credibility of data analysis results are improved.

[0177] Device Embodiment

[0178] The embodiment of the present application also provides an electronic device, the specific implementation of which is consistent with the implementation described in the above method embodiment and the technical effects achieved, and some contents will not be repeated here.

[0179] The present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor being configured to implement the following steps when executing the computer program:

[0180] Obtain the data to be converted and analyze the data intent corresponding to the data to be processed;

[0181] Preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set;

[0182] Based on the data intent, generating a recommendation chart using a decision tree algorithm;

[0183] Based on the recommended chart, a prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set;

[0184] Based on the visualization results corresponding to the data set, obtain the preset configuration chart and insert it into the page of the preset application.

[0185] In some optional embodiments, the processor is configured to preprocess the data to be converted into data with the same structure and obtain the corresponding data set in the following manner when executing the computer program:

[0186] Converting and integrating the data to be converted into a data set, wherein the structure of the data set is a two-dimensional array structure;

[0187] Determine whether the field information in the data set meets the preset information, the field information includes date, attribute and value;

[0188] If the field information in the data set does not conform to the preset information, the field information that does not conform to the preset information is screened and removed;

[0189] If the field information in the data set meets the preset information, then the field information meeting the preset information is saved;

[0190] Handle outliers and missing values ​​in the dataset.

[0191] In some optional implementations, the data feature information includes data dimension, data quantity, data type and data characteristics.

[0192] In some optional embodiments, the processor is configured to generate a recommendation chart using a decision tree algorithm based on the data feature information and the data intent in the following manner when executing the computer program, including:

[0193] Summarize the chart usage information to form a chart knowledge base;

[0194] Based on the data feature information, the chart knowledge base is used as a training set, and a decision tree algorithm is used to train a decision tree model;

[0195] Based on the data intent, a recommended chart is generated.

[0196] In some optional embodiments, the processor is configured to execute the computer program in the following manner to obtain a visual rendering chart corresponding to the data set based on the recommendation chart using prompt engineering and a natural language processing model:

[0197] Performing basic rendering on the recommended chart to obtain a basic rendering chart;

[0198] Based on the basic rendering chart, a prompt prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set.

[0199] In some optional embodiments, the processor is configured to execute the computer program in the following manner to obtain a visual rendering chart corresponding to the data set based on the basic rendering chart using prompt engineering and a natural language processing model:

[0200] Entering multiple prompt words in the prompt project to perform directional stimulation on the basic rendering chart;

[0201] Performing text preprocessing on the plurality of prompt words to obtain prompt text;

[0202] Input the prompt text into a word vector model, and use the word vector model to convert the prompt text into a vector;

[0203] Using the natural language model to perform feature extraction on the vector to obtain text features and obtain the contextual relationship of the prompt text;

[0204] Based on the text feature and the contextual relationship, obtain a prompt intention prompt;

[0205] According to the prompt intention prompt, the visual rendering chart is obtained using CSS.

[0206] See also Figure 4 , Figure 4 A structural framework diagram of an electronic device provided in an embodiment of the present application is shown.

[0207] The electronic device includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0208] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read only memory (ROM) 213 .

[0209] The memory 210 also stores a computer program, which can be executed by the processor 220, so that the processor 220 implements the steps of any of the above methods.

[0210] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0211] Accordingly, the processor 220 may execute the above-mentioned computer program and may execute the utility 214 .

[0212] The processor 220 may be implemented using one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), or other electronic components.

[0213] Bus 230 may be a local bus representing one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or any of a variety of bus architectures.

[0214] The electronic device may also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and may also communicate with one or more devices that can interact with the electronic device, and / or communicate with any device (such as a router, a modem, etc.) that enables the electronic device to communicate with one or more other computing devices. Such communication may be performed through the input and output interface 250. In addition, the electronic device may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 260. The network adapter 260 may communicate with other modules of the electronic device through the bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0215] System Example

[0216] See also Figure 5 , Figure 5 A structural schematic diagram of a data visualization system provided in an embodiment of the present application is shown.

[0217] The present application also provides a data visualization system, the system comprising:

[0218] The above electronic equipment.

[0219] Medium Embodiment

[0220] An embodiment of the present application also provides a chip, which stores a computer program. When the computer program is executed by a processor, the steps of any of the above methods are implemented. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above method embodiment, and some contents will not be repeated here.

[0221] See also Figure 6 , Figure 6 A schematic diagram of the structure of a program product provided in an embodiment of the present application is shown.

[0222] The program product is used to implement any of the above methods. The program product can use a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In the embodiment of the present application, the readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The program product can use any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0223] The chip may include a data signal propagated in the baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operation of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as C language, Python language, or similar programming languages. The program code may be executed entirely on a client computing device, partially on a client device, as an independent software package, partially on a client computing device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the client computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0224] This application is explained from the perspectives of purpose of use, effectiveness, progress and novelty, and has met the functional enhancement and usage requirements emphasized by the Patent Law. The above description and drawings of this application are only the preferred embodiments of this application, and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar or identical to this application, that is, all equivalent replacements or modifications made in accordance with the scope of the patent application of this application, should fall within the scope of protection of the patent application of this application.

Claims

1. A data visualization method, characterized in that: For automatically realizing multi-dimensional visualization of data, the method comprises: Obtain the data to be converted and analyze the data intent corresponding to the data to be processed; Preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set; Based on the data intent, generating a recommendation chart using a decision tree algorithm; Based on the recommended chart, a prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set; Based on the visualization results corresponding to the data set, obtain the preset configuration chart and insert it into the page of the preset application.

2. The data visualization method according to claim 1, characterized in that: The preprocessing of the data to be converted into data with the same structure and obtaining a corresponding data set includes: Converting and integrating the data to be converted into a data set, wherein the structure of the data set is a two-dimensional array structure; Determine whether the field information in the data set meets the preset information, the field information includes date, attribute and value; If the field information in the data set does not conform to the preset information, the field information that does not conform to the preset information is screened and removed; If the field information in the data set meets the preset information, then the field information meeting the preset information is saved; Handle outliers and missing values ​​in the dataset.

3. The data visualization method according to claim 1, characterized in that: The generating a recommendation chart based on the data intent using a decision tree algorithm includes: Performing feature recognition on the data set to obtain data feature information; Based on the data feature information and the data intent, a recommendation chart is generated using a decision tree algorithm.

4. The data visualization method according to claim 3, characterized in that: The data characteristic information includes data dimension, data quantity, data type and data characteristics.

5. The data visualization method according to claim 3, characterized in that: The generating a recommendation chart based on the data feature information and the data intent using a decision tree algorithm includes: Summarize the chart usage information to form a chart knowledge base; Based on the data feature information, the chart knowledge base is used as a training set, and a decision tree algorithm is used to train a decision tree model; Based on the data intent, a recommended chart is generated.

6. The data visualization method according to claim 1, characterized in that: Based on the recommendation chart, the prompt engineering and natural language processing model are used to obtain a visual rendering chart corresponding to the data set, including: Performing basic rendering on the recommended chart to obtain a basic rendering chart; Based on the basic rendering chart, a prompt prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set.

7. The data visualization method according to claim 6, characterized in that: The method of obtaining a visual rendering chart corresponding to a data set by using a prompt prompt engineering and a natural language processing model based on the basic rendering chart includes: Entering multiple prompt words in the prompt project to perform directional stimulation on the basic rendering chart; Performing text preprocessing on the plurality of prompt words to obtain prompt text; Input the prompt text into a word vector model, and use the word vector model to convert the prompt text into a vector; Using the natural language model to perform feature extraction on the vector to obtain text features and obtain the contextual relationship of the prompt text; Based on the text feature and the context relationship, obtain a prompt intention prompt; According to the prompt intention prompt, the visual rendering chart is obtained using CSS.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor is configured to implement the following steps when executing the computer program: Obtain the data to be converted and analyze the data intent corresponding to the data to be processed; Preprocessing the data to be converted into data with the same structure and obtaining a corresponding data set; Based on the data intent, generating a recommendation chart using a decision tree algorithm; Based on the recommended chart, a prompt engineering and a natural language processing model are used to obtain a visual rendering chart corresponding to the data set; Based on the visualization results corresponding to the data set, obtain the preset configuration chart and insert it into the page of the preset application.

9. A data visualization system, characterized in that: The data visualization system comprises: The electronic device as claimed in claim 8.

10. A chip, characterized in that: The chip stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Table editing processing method and device, electronic equipment and storage medium

    CN120805873A