CN117971953A

CN117971953A - Data analysis result visualization method, device, equipment and storage medium

Info

Publication number: CN117971953A
Application number: CN202311533184.3A
Authority: CN
Inventors: 周航宇
Original assignee: Beijing Qihoo Technology Co Ltd
Current assignee: Beijing Qihoo Technology Co Ltd
Priority date: 2023-11-16
Filing date: 2023-11-16
Publication date: 2024-05-03

Abstract

The invention belongs to the technical field of data analysis, and discloses a data analysis result visualization method, a device, equipment and a storage medium. The method comprises the following steps: acquiring a data set and a corresponding data abstract; performing target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target; generating a data analysis prompt according to the recommended visual target and the data set; and inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization. Through the mode, light-weight data analysis is realized, the data set is automatically combed, the data can be combined with the intelligent assistant, the data analysis target is realized, the threshold and the learning cost of user data analysis are further reduced, the user experience is improved, and the analysis cost is reduced.

Description

Data analysis result visualization method, device, equipment and storage medium

Technical Field

The present invention relates to the field of data analysis technologies, and in particular, to a method, an apparatus, a device, and a storage medium for visualizing a data analysis result.

Background

Data analysis and visualization are an integral part of modern society and enterprise management. With the rapid development of internet and big data technologies, industries are actively exploring how to utilize data to improve efficiency and decision quality. The data analysis and visualization can help the enterprise manager to better understand the market and customer requirements, and can help the scientist to better understand the natural laws and human behaviors. However, conventional data analysis approaches have a number of drawbacks.

Firstly, the traditional data analysis mode often needs manual operation, needs a large amount of time and manpower resources, is easy to cause errors, and needs to be assisted with the traditional data analysis mode often needs professional knowledge and skills, so that the use threshold of the skill of data analysis is improved, and when a user has small-volume analysis work, the professional analyst is inconvenient to apply, and the ordinary user is difficult to use.

The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.

Disclosure of Invention

The invention mainly aims to provide a data analysis result visualization method, a device, equipment and a storage medium, and aims to solve the technical problem of low convenience of a data analysis tool in the prior art.

In order to achieve the above object, the present invention provides a data analysis result visualization method, which includes the steps of:

Acquiring a data set and a corresponding data abstract;

Performing target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target;

generating a data analysis prompt according to the recommended visual target and the data set;

And inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization.

Optionally, the acquiring the data set and the corresponding data summary includes:

Acquiring a data set;

Carrying out data field analysis on the data set to determine data identity item information, data type information and sampling data;

And generating a data abstract according to the data identity item information, the data type information and the data sample information.

Optionally, the acquiring the data set includes:

acquiring an initial data set;

performing data cleaning on the initial data set to obtain a normalized data set;

Recoding the normalized data to obtain a data set.

Optionally, the performing target analysis in the intelligent assistant according to the data summary to obtain a recommended visual target includes:

determining data identity information, data type information and sampling data according to the data abstract;

determining a prompt format according to the data identity item information and the data type information;

generating a sample analysis prompt according to the prompt format and the sampling data;

And inputting the sample analysis prompt into an intelligent assistant to obtain a recommended visual target.

Optionally, before generating the sample analysis prompt according to the prompt format and the sampling data, the method further includes:

detecting a custom visualization target;

The generating a sample analysis hint according to the hint format and the sampling data includes:

And generating a sample analysis prompt according to the prompt format, the custom visual target and the sampling data.

Optionally, the generating a data analysis prompt according to the recommended visual target and the data set includes:

matching the recommended visual target with a preset chart type library to obtain a visual target list;

Responding to a visual target list selection instruction, and determining a visual target to be displayed;

and generating a data analysis prompt according to the visual target to be displayed and the data set.

Optionally, the inputting the data analysis prompt into the intelligent assistant, completing the data analysis visualization, includes:

inputting the data analysis prompt into an intelligent assistant to obtain a visual code;

And generating a visual view according to the visual code and the data set, and completing data analysis visualization.

Optionally, after inputting the data analysis prompt into the intelligent assistant to obtain the visual code, the method further includes:

Determining error information of the visual code when the visual code cannot be executed;

generating a code error correction prompt according to the error information and the visual code;

inputting the code error correction prompt into an intelligent assistant to obtain an adjusted visual code;

the generating a visual view according to the visual code and the data set comprises the following steps:

And generating a visual view according to the adjusted visual codes and the data set.

Optionally, the generating a code error correction prompt according to the error information and the visual code includes:

responding to a code repair input instruction, and determining annotation requirements and logic requirements according to the input instruction;

and generating a code error correction prompt according to the annotation requirement, the logic requirement, the error information and the visual code.

Responding to an analysis demand input instruction, and determining a result summary demand, an abnormal analysis demand and a trend prediction demand;

determining analysis result demand prompts according to the result summary demands, the abnormal analysis demands and the trend prediction demands;

And generating a data analysis prompt according to the analysis result demand prompt, the recommended visual target and the data set.

In addition, in order to achieve the above object, the present invention also proposes a data analysis result visualization apparatus including:

The acquisition module is used for acquiring the data set and the corresponding data abstract;

The processing module is used for carrying out target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target;

The processing module is further used for generating a data analysis prompt according to the recommended visual target and the data set;

and the processing module is also used for inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization.

Optionally, the acquiring module is further configured to acquire a data set;

Optionally, the acquiring module is further configured to acquire an initial data set;

Recoding the normalized data to obtain a data set.

Optionally, the processing module is further configured to determine data identity information, data type information and sampling data according to the data summary;

Optionally, the processing module is further configured to detect a custom visualization target;

Optionally, the processing module is further configured to match the recommended visual target with a preset chart type library to obtain a visual target list;

Optionally, the processing module is further configured to input the data analysis prompt into an intelligent assistant to obtain a visual code;

Optionally, the processing module is further configured to determine error information of the visual code when the visual code cannot be executed;

In addition, in order to achieve the above object, the present invention also proposes a data analysis result visualization apparatus including: a memory, a processor, and a data analysis result visualization program stored on the memory and executable on the processor, the data analysis result visualization program configured to implement the steps of the data analysis result visualization method as described above.

In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a data analysis result visualization program which, when executed by a processor, implements the steps of the data analysis result visualization method as described above.

The method comprises the steps of acquiring a data set and a corresponding data abstract; performing target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target; generating a data analysis prompt according to the recommended visual target and the data set; and inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization. Through the mode, light-weight data analysis is realized, the data set is automatically combed, the data can be combined with the intelligent assistant, the data analysis target is realized, the threshold and the learning cost of user data analysis are further reduced, the user experience is improved, and the analysis cost is reduced.

Drawings

FIG. 1 is a schematic diagram of a data analysis result visualization device of a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a flow chart of a first embodiment of a method for visualizing data analysis results according to the present invention;

FIG. 3 is a schematic diagram of a visualization flow chart of an embodiment of a method for visualizing data analysis results according to the present invention;

FIG. 4 is a schematic diagram of a recommendation visualization target according to an embodiment of the data analysis result visualization method of the present invention;

FIG. 5 is a schematic diagram illustrating a code error correction process according to an embodiment of the data analysis result visualization method of the present invention;

FIG. 6 is a schematic diagram of an analysis result of an embodiment of a method for visualizing data analysis results according to the present invention;

FIG. 7 is a flow chart of a second embodiment of a method for visualizing data analysis results according to the present invention;

FIG. 8 is a schematic diagram of a data summary of an embodiment of a method for visualizing data analysis results according to the present invention;

fig. 9 is a block diagram of a first embodiment of a data analysis result visualization device according to the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

Referring to fig. 1, fig. 1 is a schematic diagram of a data analysis result visualization device of a hardware running environment according to an embodiment of the present invention.

As shown in fig. 1, the data analysis result visualization apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.

It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the data analysis result visualization apparatus, and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.

As shown in fig. 1, an operating system, a network communication module, a user interface module, and a data analysis result visualization program may be included in the memory 1005 as one type of storage medium.

In the data analysis result visualization apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the data analysis result visualization device of the present invention may be disposed in the data analysis result visualization device, where the data analysis result visualization device invokes a data analysis result visualization program stored in the memory 1005 through the processor 1001, and executes the data analysis result visualization method provided by the embodiment of the present invention.

The embodiment of the invention provides a data analysis result visualization method, referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the data analysis result visualization method of the invention.

In this embodiment, the data analysis result visualization method includes the following steps:

step S10: a data set and a corresponding data digest are obtained.

The execution body of the embodiment is an intelligent terminal, which may be a server, a computer, or other devices having the same or similar functions as the server, and the embodiment is not limited thereto, and only a server is taken as an example for illustration.

It should be noted that, in the process of data analysis, the data analysis and visualization are an indispensable part of modern society and enterprise management. With the rapid development of internet and big data technologies, industries are actively exploring how to utilize data to improve efficiency and decision quality. The data analysis and visualization can help the enterprise manager to better understand the market and customer requirements, and can help the scientist to better understand the natural laws and human behaviors. However, conventional data analysis approaches have a number of drawbacks. First, the conventional data analysis method often needs manual operation, requires a lot of time and manpower resources, and is prone to errors. Secondly, the data analysis mode lacks a visual function, and information and trends in the data are difficult to present. Third, conventional data analysis methods often require expertise and skills, which are difficult for an average user. In order to overcome the defects of the traditional data analysis modes, a scheme for automatically realizing the visualization of the data analysis by using AI is provided. The scheme not only can automate the data analysis process and reduce human errors, but also can present the trend and information of the data, so that the common user can use the data easily.

It can be understood that the data set is the data content that needs to be analyzed by the user, and may be a data set in a database or may be text content recorded in a certain arrangement mode, and the expression form of the data set is not limited in this embodiment.

Specifically, the data summary is information with guiding property according to the related information of the data set, and the summary of the data set refers to that the summary calculation is performed on the whole data set, so that summary information representing the characteristics of the whole data set is obtained. Specifically, the summary of the data set may include some data features, such as: the summary may be made for a particular feature in the dataset. For example: for a text data set, word frequency or keyword occurrence frequency can be counted; for an image dataset, the mean, variance, feature vector, or the like of the image may be calculated. The abstract of the data set can help us obtain the overall impression and characteristics of the data set, quickly understand its distribution and statistical properties, and thus support subsequent data analysis and decision making. The different summarization methods and index selections will vary depending on the particular data set and target. The purpose of the data summary is to allow the intelligent assistant to better understand the content of the data in order to generate better visual target options. In this embodiment, the content of the data summary is mainly information guiding the intelligent assistant to perform data analysis, for example: all column names of the dataset, data types of the various data, and so forth.

Step S20: and carrying out target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target.

It should be noted that, in order to enhance the information processing capability, in some embodiments, an intelligent assistant may be installed on the terminal device, and the intelligent assistant may be a program constructed based on natural language processing technology of a generated pre-training converter (GENERATIVE PRE-trained Transformer, GPT) model, and the intelligent assistant may receive input text of a user, parse the input text into a data format understandable by a computer, and then generate a response text using a pre-trained neural network model.

In a specific implementation, the intelligent assistant uses a neural network in the deep learning technology to train through a large amount of corpus data, so that the structure, grammar rules and semantic information of the language can be learned. After the user enters the text, the intelligent assistant first performs word segmentation and parsing on the text, converts it into a computer-readable vector form, and then enters the pre-trained neural network model for inference. In the inference process, the intelligent assistant predicts the most likely next response based on the text entered by the user and the previous context. The prediction process is based on the learning of a model from a large amount of corpus data, so that the manner of human natural language expression can be restored to a great extent, and highly coherent and natural response text can be generated. And finally, the intelligent assistant returns the generated response text to the user to complete one dialogue interaction. Throughout the process, the intelligent assistant also continuously learns and optimizes to provide more accurate and user-appropriate answers.

It should be noted that, the target analysis is to analyze a proper visual target of the current data set through the intelligent assistant, and further recommend visual targets are visual targets recommended by the intelligent assistant, where the intelligent assistant can return a specified number of data analysis targets, and a format recommended by the recommended visual targets may be, for example: [ { "task_index":0, "visual analysis target task description": "time versus revenue", "chart type": "line graph" }, { } ] here, the designated intelligent assistant returns 10 visual targets. From the above description, it is understood that the visualization task target refers to a specific target or task to be achieved in the data visualization process. The visual task targets can have various forms and layers according to different application scenes and requirements. The representation of the visualization target may be, for example: discovering patterns and associations, exploring hidden patterns, trends and associations in data through visual analysis, and revealing regularity and relativity in the data. This helps to obtain new insight and knowledge from the data. Comparison and contrast of pairs of data, differences and similarities between different data sets or data subsets are compared by visualization. This may help identify disparate, outliers or special patterns of data. The single data is displayed in a distribution and trend mode, and the data is visualized into a column diagram, a line diagram, a scatter diagram and the like for displaying the distribution and trend of the data. This can help observe the concentration, trend, and outliers of the data. Support decision making and interpretation of data, with the insight that data is visually presented, support decision making and interpretation of data. The visual result can be presented in the form of a chart, a graph and an interactive interface, so that the data is more visual and understandable, and the user is helped to make a basis and credible decision. Different visualization task targets need to select proper visualization technologies and methods, and corresponding charts, graphs or interaction interfaces are designed according to requirements, so that the required data display and analysis purposes are achieved.

Further, different recommended visualization targets may also be combined with different visualization chart types to form, for example: [ { "task_index":0, "visual analysis target task description": "time versus revenue", "chart type": "line graph" }, { }, ],. Data analysis cues, visual chart type of target may be, for example: bar graph, radar graph, funnel graph, cake graph, nested ring graph, instrument panel, scatter graph, calendar graph, water polo graph, relationship graph, word cloud graph, tree graph, rectangular tree graph. The 10 pieces of data are presented to the user, who is given the choice of the target to be visualized. If the user has a particular data analysis object, the object may be entered directly.

In this embodiment, determining data identity information, data type information and sampling data according to the data summary; determining a prompt format according to the data identity item information and the data type information; generating a sample analysis prompt according to the prompt format and the sampling data; and inputting the sample analysis prompt into an intelligent assistant to obtain a recommended visual target.

It should be noted that, according to the data summary, data identity information, data type information and sampling data are determined, where the data identity information is a representation of data, for example: column name, entry name, etc.; the data type information is information representing the data type, for example: numerical items, date items, category items, character classes, and the like; sample data is exemplary data extracted on a regular basis, such as: each data column randomly extracts a plurality of numerical values and corresponding association information thereof; taking the relation between time and income as an example, a certain data table in the data set can be extracted, a plurality of pairs of column names, income and time data pairs are randomly extracted in the data table, and the data is sampled in a small sample, so that specific data content can be roughly displayed to the model, and data leakage can not be caused.

The prompt format is determined according to the data identity information and the data type information, because prompts generated by different data identities and data types may be different, so that contents of sample analysis prompts generated according to the prompt format and the sampling data are also different, specifically, the prompt format is that prompt information for guiding intelligent analysis is determined and generated according to the data identity information and the data type information, and the intelligent assistant analyzes the sampling data according to the contents of the sample analysis prompts and the sampling data contained in the middle to obtain a recommended visual target, for example: in prompt, the intelligent assistant can simulate an experienced data analyst, who can mine potential relationships between various data in the sampled data, know which data analysis tasks can be used to adequately display the main content of the sampled data, and can display the target of each data analysis by using the most suitable chart. Finally, the data analysis targets with the specified number and the specified format are returned.

In this embodiment, a custom visualization target is detected; the generating a sample analysis hint according to the hint format and the sampling data includes: and generating a sample analysis prompt according to the prompt format, the custom visual target and the sampling data.

It should be noted that, by means of the method, a personalized interface is provided for the scheme for the user to select or input the desired visual target, and the user-defined visual target is combined to obtain the prompt, so that the analysis task of the visual target can be completed according to the user's thought for better guiding the model.

Step S30: and generating a data analysis prompt according to the recommended visual target and the data set.

It should be noted that, the data analysis prompt is a prompt (prompt) for performing data analysis guidance, and when speaking "prompt" we refer to an instruction, a problem, or a statement provided by a user when interacting with the large language model trained by OpenAI. The prompt may be a complete question or may be just a keyword or phrase. By providing an explicit prompt to the model, the user can guide the topic and direction of the dialog to get the relevant answer. The model understands the user's intent based on the prompt and generates the appropriate answer or content to continue the conversation. The quality and specificity of campt is important for the model to generate accurate and useful answers. A clear, specific prompt may help the model better understand the user's needs and answer in a corresponding manner. Thus, providing detailed and explicit prompt may improve the quality of dialog results. In summary, campt is an indication provided by a user when interacting with a model as a basis for guiding the understanding and answering of the model.

It can be appreciated that the present embodiment achieves a better analysis effect by recommending the process of generating the data analysis prompt by the visual target, that is, by providing a detailed and clear prompt to improve the quality of the dialog result.

In this embodiment, matching the recommended visual target with a preset chart type library to obtain a visual target list; responding to a visual target list selection instruction, and determining a visual target to be displayed; and generating a data analysis prompt according to the visual target to be displayed and the data set.

It should be noted that the preset chart type library stores a large number of chart types, different analysis target types are suitable for different chart types, and mapping relations between analysis target types and chart types calibrated in advance are stored in the preset chart type library, for example: the analysis object types, which typically have time variations, are matched to the line graph.

Specifically, as shown in fig. 4, after the information extracted in the data abstract is input into the intelligent assistant, a plurality of recommended visual targets are obtained, and then a new campt can be generated by selecting the visual targets and the corresponding chart types, so that the code to be operated is finally obtained.

It will be appreciated that generating data analysis cues from the recommended visualization targets and datasets, in combination with the prot generated by the visualization code, causes the intelligent assistant to generate python code that implements the visualization. For example: please generate a section of Python code, perform data analysis on a given data set and generate a visualization chart of recommended visualization target requirements. The dataset file name is [ dataset file name ], the dataset contains the following fields: [ field 1], [ field 2], [ field 3]. Please complete this task using Pandas and pyecharts libraries. "last return generated code.

In the embodiment, in response to an analysis demand input instruction, a result summary demand, an abnormal analysis demand and a trend prediction demand are determined; determining analysis result demand prompts according to the result summary demands, the abnormal analysis demands and the trend prediction demands; and generating a data analysis prompt according to the analysis result demand prompt, the recommended visual target and the data set.

It should be noted that, in general, the intelligent assistant is guided to conduct data analysis directly through the analysis target and the data set, but in order to make the analysis result more detailed and comprehensive, the present embodiment proposes that the intelligent assistant is guided to give a more detailed and comprehensive answer by adding the requirement information to the prompt, and the result obtained by summarizing the requirement, the abnormal analysis requirement and the trend prediction requirement may be as follows: and combining the calculation result of the codes and the visual target selected or input by the user, and then generating a final data analysis result by combining the prompt of the result analysis module. The data analysis prompt contains guide content which can be: summary of analysis results, a summary of the content of the overall result, so that the user can clearly understand the general condition of the current data analysis; if one of the data analysis results is more prominent or abnormal, the cause of the data analysis result is analyzed, so that the user is helped to improve; trend prediction, which can predict future development trend according to current data distribution, and help users to adjust development plans and planning; and improving suggestions, and providing relevant suggestions for the user according to the data analysis result.

It should be noted that, as shown in fig. 6, after the data analysis prompt is input to the intelligent assistant to obtain the returned result, the analysis result requirement prompt may be determined according to the result summary requirement, the abnormal analysis requirement and the trend prediction requirement, and the analysis result may be directly obtained according to the analysis result requirement prompt. This is similar to the results obtained by combining the analysis result requirement cues with the recommendation visualization target and the data set to generate the data analysis cues to determine the results.

Step S40: and inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization.

It should be noted that, the general intelligent assistant returns a message meeting the prompt result by inputting the prompt, so the process of inputting the data analysis prompt into the intelligent assistant may, for example: "please write a piece of code for XX. "so that the intelligent assistant can return a piece of code to meet the needs of the user.

In this embodiment, the data analysis prompt is input into an intelligent assistant to obtain a visual code; and generating a visual view according to the visual code and the data set, and completing data analysis visualization.

It should be noted that, for the visualization of data, since a general intelligent assistant may have a certain obstacle to the output of graphics or recommend inaccuracy, the embodiment obtains a visualization scheme suitable for the dataset by obtaining the visualization code, and then visualizes the dataset according to the visualization code, thereby completing the visualization of data analysis.

In this embodiment, when the visual code cannot be executed, determining error information of the visual code; generating a code error correction prompt according to the error information and the visual code; inputting the code error correction prompt into an intelligent assistant to obtain an adjusted visual code; the generating a visual view according to the visual code and the data set comprises the following steps: and generating a visual view according to the adjusted visual codes and the data set.

It will be appreciated that since the code recommended by the intelligent assistant may also be problematic, the visual code may be further repaired, and a specific repairing process may be to determine the error information of the visual code when the visual code cannot be executed. The error information of the program is a prompt in the process of software development and debugging and is used for indicating problems or errors encountered by the program in the process of execution. Error information is typically generated by a programming language, compiler, interpreter, or debugging tool and output to a developer to help him locate and solve the problem. A new hint may be generated based on the error information to direct the intelligent assistant to find errors in the code, such as: a code error correction prompt is generated, namely a code is written for repairing the code which is currently in failure. Wherein the error is caused by XXX, and the error position is XXX'.

In this embodiment, in response to a code repair input instruction, determining annotation requirements and logic requirements from the input instruction; and generating a code error correction prompt according to the annotation requirement, the logic requirement, the error information and the visual code.

It should be noted that, because the accuracy of the code directly affects the effect of the implementation, the error correction prompt of the code can be supplemented according to the set requirement information to better guide the intelligent assistant, where the annotation requirement is that what content needs to be annotated to help the user understand whether the logic requirement should ensure that the logic of the code is correct, and whether the logic conflict will not occur in each running branch, and specifically, the error correction prompt of the code can be, for example, "please write a section of code, used for repairing the code that is currently running in failure. The code should include the steps of: 1. errors and problems in the code are checked and necessary changes and repairs are made. 2. Ensure that the logic of the code is correct and test its operation under various conditions. 3. Necessary annotations are added so that others can understand the function and purpose of the code. 4. The repaired code is submitted to the code library and all tests are guaranteed to pass. Note that you may have to write the repair code using python language, but should ensure that it is compatible with the original code and that no new problems or errors are introduced after repair. Please enter your repair code as follows: and finally, combining the visual codes to input prompts.

Further, as shown in fig. 5, the intelligent assistant can repair the error code according to the current error, and can acquire error information by executing the code by using the python core, and the process can be performed for a plurality of times until the code is successfully executed. The process has a regulatory mechanism that regenerates the code when the code has failed to be restored 3 times, re-runs the code, returns the view to the user if it is successful, and allows the user to retry or re-select a new visualization task if it is failed.

It should be noted that, in the complete visualization process, as shown in fig. 3, a certain data cleaning is performed by uploading a data set in a file, for example: the method comprises the steps of a data cleaning module and a data abstract extraction process to obtain a data abstract, performing visual analysis to obtain a visual code, adjusting the code through a code running and repairing module to obtain a visual view after analysis and a content description obtained by an intelligent AI description module, wherein the AI result description module is visual data content description obtained by guiding a question-answering module by adding a requirement after completing data analysis.

The embodiment obtains a data set and a corresponding data abstract; performing target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target; generating a data analysis prompt according to the recommended visual target and the data set; and inputting the data analysis prompt into an intelligent assistant to complete data analysis visualization. Through the mode, light-weight data analysis is realized, the data set is automatically combed, the data can be combined with the intelligent assistant, the data analysis target is realized, the threshold and the learning cost of user data analysis are further reduced, the user experience is improved, and the analysis cost is reduced.

Referring to fig. 7, fig. 7 is a flowchart of a second embodiment of a data analysis result visualization method according to the present invention.

Based on the above first embodiment, the data analysis result visualization method in this embodiment further includes, in the step S10:

step S11: acquiring a data set;

it should be noted how to facilitate the analysis of the intelligent assistant, improve the accuracy and efficiency of data analysis, and the quality of the data summary is very important, which directly affects the final analysis effect.

It should be noted that, the data set is data content that can be used for data analysis, and the data set may be obtained by searching from a local database or directly obtained from a cloud platform, which is not limited in this embodiment.

In this embodiment, an initial data set is acquired; performing data cleaning on the initial data set to obtain a normalized data set; recoding the normalized data to obtain a data set.

It should be noted that, when the obtained data set is directly used for analysis, the analysis effect may be poor due to some errors, so that the data cleaning is performed on the initial data set, and the data cleaning refers to checking, correcting, modifying or deleting the original data in the data processing process so as to eliminate the problems of errors, deletions, duplications or inconsistencies in the data, so as to ensure the quality and accuracy of the data. The specific cleaning process may be, for example: after uploading data, the user reads the data and then performs preliminary processing, which specifically comprises: removing duplicate data, outliers, etc.; the format of the standard date item is that: Y-M-D format; filling the missing values according to the data types: the missing value of the numerical item is filled in: 0, date item missing value fill: 2000-01-01, class term missing value fill: others. The above data cleansing content is used to describe the cleansing process of the data.

After the cleaned data is obtained, in order to sort the data, the data of different types is converted into an unspecified format, i.e. recoded, and the recoding process can be, for example: data type conversion, such as converting and recoding data types, can be specifically divided into different data: numerical value items, date items and category items, and are coded into forms corresponding to the items. Recoding (Reencoding) refers to the process of converting a character or numerical value in a dataset from one coding mode to another. Recoding is typically used to process data containing different character encodings or text formats to ensure proper interpretation and processing of the data between different systems or applications.

Step S12: and carrying out data field analysis on the data set to determine data identity item information, data type information and sampling data.

The data identity information is a representation of data, for example: column name, entry name, etc.; the data type information is information representing the data type, for example: numerical items, date items, category items, character classes, and the like. The position corresponding to the data can be obtained through analysis, for example: in the relational database, the column names in each column are directly acquired to obtain the data identity item information, the type information can be confirmed through the storage format of the data or the combination of the column names, and the sampled data is obtained to obtain a small part of complete data in the data set as a sample to reflect the interrelationship among different data.

The sampling data is mainly used for enabling the intelligent assistant to know about the approximate data relationship, and as the table relationships in the database are certain and only the content of the data is different, the processing efficiency of the intelligent assistant can be effectively ensured through the sample data.

Step S13: and generating a data abstract according to the data identity item information, the data type information and the data sample information.

It should be noted that, as shown in fig. 8, the data summary is generated according to the data identity information, the data type information and the data sample information, for example: the purpose of extracting the data summary is to allow the intelligent assistant to better understand the content of the data in order to generate better visual target options. The extraction of the data abstract mainly comprises the following steps: extracting all column names of the dataset, each column name being unique and often being able to determine attributes of the column data from the column names; recording the local path of the data table, wherein the characteristic is that the data can be correctly read when the code is operated at the later stage; the data types of the various data are acquired, and the intelligent assistant can better understand what type of calculation is suitable for the various data through the types; because the input length of the intelligent assistant is limited, the data is sampled in a small sample, the specific data content can be roughly displayed to the model, and the data leakage can not be caused. The extraction of the data abstract is completed through the steps, and input data is provided for the subsequent AI analysis.

The embodiment acquires a data set; carrying out data field analysis on the data set to determine data identity item information, data type information and sampling data; and generating a data abstract according to the data identity item information, the data type information and the data sample information. The received data set is processed to a certain extent, and the intelligent assistant directly inputs a complete data set very time-consuming and high in cost due to limited data processing capacity, so that the intelligent assistant is guided by processing a relatively standard data abstract, and the data analysis efficiency is improved.

In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a data analysis result visualization program, and the data analysis result visualization program realizes the steps of the data analysis result visualization method when being executed by a processor.

Referring to fig. 9, fig. 9 is a block diagram showing the structure of a first embodiment of the data analysis result visualization apparatus of the present invention.

As shown in fig. 9, a data analysis result visualization device according to an embodiment of the present invention includes:

An acquisition module 10, configured to acquire a data set and a corresponding data summary;

the processing module 20 is configured to perform target analysis in the intelligent assistant according to the data summary, so as to obtain a recommended visual target;

The processing module 20 is further configured to generate a data analysis hint according to the recommended visual target and the dataset;

the processing module 20 is further configured to input the data analysis prompt into an intelligent assistant to complete data analysis visualization.

It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.

The acquiring module 10 of the present embodiment acquires a data set and a corresponding data abstract; the processing module 20 performs target analysis in the intelligent assistant according to the data abstract to obtain a recommended visual target; processing module 20 generates a data analysis hint from the recommended visualization target and the dataset; the processing module 20 inputs the data analysis prompt into the intelligent assistant to complete data analysis visualization. Through the mode, light-weight data analysis is realized, the data set is automatically combed, the data can be combined with the intelligent assistant, the data analysis target is realized, the threshold and the learning cost of user data analysis are further reduced, the user experience is improved, and the analysis cost is reduced.

It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.

In addition, technical details not described in detail in this embodiment may refer to the data analysis result visualization method provided in any embodiment of the present invention, which is not described herein.

Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

The invention also discloses A1, a data analysis result visualization method, which comprises the following steps:

Acquiring a data set and a corresponding data abstract;

A2, the method of A1, the obtaining the data set and the corresponding data summary, includes:

Acquiring a data set;

A3, the method of A2, the acquiring a dataset comprising:

acquiring an initial data set;

Recoding the normalized data to obtain a data set.

A4, carrying out target analysis in an intelligent assistant according to the data abstract to obtain a recommended visual target according to the method of A1, wherein the method comprises the following steps:

A5, the method of A4, before generating a sample analysis hint according to the hint format and sample data, further comprises:

detecting a custom visualization target;

A6, the method of A1, wherein the generating the data analysis prompt according to the recommended visual target and the data set comprises:

A7, the method of A1, wherein inputting the data analysis prompt into an intelligent assistant, completing data analysis visualization, comprises:

A8, the method of A7, after inputting the data analysis prompt into the intelligent assistant to obtain the visual code, further comprises:

A9, the method of A8, the generating code error correction prompt according to the error information and the visualized code, includes:

A10, the method of A1, wherein generating the data analysis prompt according to the recommended visual target and the data set comprises:

The invention also discloses a B11, a data analysis result visualization device, the data analysis result visualization device comprises:

B12, the apparatus of B11, wherein the acquiring module is further configured to acquire a data set;

B13, the apparatus of B12, the acquisition module further configured to acquire an initial data set;

Recoding the normalized data to obtain a data set.

B14, the device of B11, the said processing module, is used for confirming the data identity item information, data type information and sampled data according to the said data abstract;

B15, the device as described in B14, the processing module further configured to detect a custom visualization target;

B16, the device of B11, the processing module is further configured to match the recommended visual target with a preset chart type library to obtain a visual target list;

B17, the device as described in B11, the processing module further configured to input the data analysis prompt into an intelligent assistant to obtain a visual code;

B18, the apparatus of B17, the processing module further configured to determine error information of the visual code when the visual code cannot be executed;

Claims

1. A data analysis result visualization method, characterized in that the data analysis result visualization method comprises:

Acquiring a data set and a corresponding data abstract;

2. The method of claim 1, wherein the acquiring the data set and the corresponding data digest comprises:

Acquiring a data set;

3. The method of claim 2, wherein the acquiring the data set comprises:

acquiring an initial data set;

Recoding the normalized data to obtain a data set.

4. The method of claim 1, wherein performing target analysis in an intelligent assistant based on the data summary to obtain a recommended visualization target comprises:

5. The method of claim 4, wherein prior to generating a sample analysis hint from the hint format and sample data, further comprising:

detecting a custom visualization target;

6. The method of claim 1, wherein the generating a data analysis hint from the recommended visualization target and a dataset comprises:

7. The method of claim 1, wherein inputting the data analysis prompt into an intelligent assistant, completing data analysis visualization, comprises:

8. A data analysis result visualization apparatus, characterized by comprising:

9. A data analysis result visualization apparatus, the apparatus comprising: a memory, a processor and a data analysis result visualization program stored on the memory and executable on the processor, the data analysis result visualization program being configured to implement the steps of the data analysis result visualization method of any of claims 1 to 7.

10. A storage medium having stored thereon a data analysis result visualization program which, when executed by a processor, implements the steps of the data analysis result visualization method of any of claims 1 to 7.