Intelligent chart generation system and method based on big data

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent chart generation system and method based on big data. The data acquisition module is used for acquiring a to-be-processed text input by a user; the data analysis module is used for extracting a plurality of intermediate keywords; the data retrieval module is used for determining key texts and determining a first data coverage degree between each key text and the to-be-processed text; the to-be-processed picture determination module is used for determining a plurality of to-be-processed pictures; the picture processing module is used for obtaining a plurality of feature texts; the data matching module is used for determining the key matching degree of the to-be-processed text and the feature text and determining the retrieval completion degree of the to-be-processed text; and the target chart generation module is used for determining target data and generating a target chart corresponding to the to-be-processed text according to the target data and a preset chart generation rule. The chart generation efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a system and method for intelligently generating charts based on big data. Background Art

[0002] With the advent of the big data era, data visualization has become an important means of data analysis and decision-making. As a common data visualization method, charts can intuitively display data distribution, trends, relationships and other information. Traditional chart generation tools require users to manually select chart types, specify data sources, adjust styles, etc., and require users to collect a large amount of information, and then further screen and analyze to sort out the relevant data needed to make charts. However, many relevant data are not recorded in text form, but directly drawn into charts. It will be more time-consuming and labor-intensive for users to collect and screen data, and users are required to have certain data analysis and visualization knowledge, and the efficiency of making charts is relatively low. Summary of the invention

[0003] To this end, the present invention provides a system and method for intelligently generating charts based on big data, so as to overcome the problem of low efficiency in chart data screening caused by low retrieval matching rate in the prior art when retrieving data from massive graphic data to make charts.

[0004] To achieve the above objectives, on the one hand, the present invention provides a system for intelligently generating charts based on big data, comprising:

[0005] A first text library stores a plurality of original texts; each original text includes at least one picture;

[0006] A data acquisition module is used to acquire the text to be processed input by the user;

[0007] A data analysis module, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed and extract a number of intermediate keywords;

[0008] a data retrieval module, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts, and determine a first data coverage between each key text and the text to be processed;

[0009] A module for determining images to be processed, which is connected to the data retrieval module and is used to determine a number of images to be processed in each of the key texts based on a semantic matching relationship;

[0010] An image processing module, which is connected to the image-to-be-processed determining module, and is used to process a number of the images to be processed according to a preset image-text conversion method to obtain a number of feature texts;

[0011] a data matching module, which is connected to the data acquisition module, the data retrieval module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and the feature text, and to determine the retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage;

[0012] A target chart generation module is respectively connected to the data matching module and the image processing module, and is used to determine the target data in the key text and the feature text according to the retrieval completion degree, and to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

[0013] Furthermore, the data analysis module includes:

[0014] A semantic analysis submodule, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed according to a preset semantic analysis method to obtain the corresponding relationship between the definition variables and data of the text to be processed;

[0015] The intermediate keyword determination submodule is connected to the semantic analysis submodule and is used to extract a number of intermediate keywords from the text to be processed according to the semantic analysis result of the semantic analysis submodule, wherein the intermediate keywords are determined according to the definition variables.

[0016] Furthermore, the data retrieval module includes:

[0017] A key text determination submodule, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts;

[0018] A first data coverage determination submodule, which is connected to the key text determination submodule and is used to determine the first data coverage of each of the key texts and the text to be processed;

[0019] The first data coverage is determined according to the matching percentage of the corresponding relationship between the variables and the corresponding data corresponding to each of the key texts and the defined variables and the data obtained by the semantic analysis in the text to be processed.

[0020] Furthermore, the module for determining the image to be processed includes:

[0021] A target text determination submodule, which is connected to the data retrieval module and is used to determine a number of target text paragraphs matching the intermediate keyword in each of the key texts based on the intermediate keyword;

[0022] The to-be-processed picture determination submodule is connected to the target text determination submodule and is used to determine a number of to-be-processed pictures according to the position of each target text paragraph.

[0023] Furthermore, the data matching module includes:

[0024] A key matching degree determination submodule, which is connected to the data acquisition module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and each of the feature texts;

[0025] wherein, semantic analysis is performed on the feature text to extract a number of variables, and the variables are compared with a number of the intermediate keywords to determine the key matching degree between the text to be processed and the feature text;

[0026] A retrieval completion determination submodule is connected to the key matching determination submodule and the data retrieval module respectively, and is used to determine the retrieval completion of the text to be processed based on the key matching degree and the first data coverage.

[0027] Furthermore, the target chart generation module includes:

[0028] A target data determination submodule, which is connected to the data matching module and is used to determine target data in each of the key texts and each of the feature texts according to the search completion degree;

[0029] The target chart generation submodule is connected to the target data determination submodule and is used to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

[0030] Furthermore, the target text determination submodule determines a number of target text paragraphs in each of the key texts according to a comparison result of the paragraph coverage with a preset coverage threshold;

[0031] Among them, if the paragraph coverage corresponding to a single paragraph of any key text is greater than a preset coverage threshold, the paragraph where the single paragraph is located is determined as the target text paragraph, and the preset coverage threshold is less than or equal to the first data coverage.

[0032] Furthermore, the retrieval completion determination submodule calculates the retrieval completion according to the following formula:

[0033] P = a × A + b × B;

[0034] Among them, P is the retrieval completion, A is the key matching degree, B is the first data coverage, a is the first weight coefficient, and b is the second weight coefficient.

[0035] Further, the target data determination submodule determines the target data according to the retrieval completion degree and a preset retrieval completion degree threshold;

[0036] If the retrieval completion is greater than a preset retrieval completion threshold, the data in the key text and feature text corresponding to the retrieval completion are integrated to obtain the target data.

[0037] On the other hand, the present invention also provides a method for intelligently generating a chart, comprising:

[0038] Step S1, obtaining the text to be processed input by the user;

[0039] Step S2, performing semantic analysis on the text to be processed and extracting a number of intermediate keywords;

[0040] Step S3, retrieving corresponding original texts from the first text library according to the intermediate keywords, determining them as key texts, and determining a first data coverage between each key text and the text to be processed;

[0041] Step S4, determining a number of to-be-processed pictures in each of the key texts based on the first data coverage;

[0042] Step S5, processing the plurality of images to be processed according to a preset image-text conversion method to obtain a plurality of feature texts;

[0043] Step S6, determining a key matching degree between the text to be processed and the feature text, and determining a retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage;

[0044] Step S7, determining target data in the key text and the feature text according to the retrieval completion, and generating a target graph corresponding to the text to be processed according to the target data and a preset graph generation rule.

[0045] Compared with the prior art, the beneficial effect of the present invention is that the present invention determines several intermediate keywords by setting a data analysis module, and determines the key text according to the intermediate keywords through the data retrieval module. It only needs to search and filter according to several keywords, without full-text retrieval, which can improve the efficiency of text search, and by determining the first data coverage, it can further judge the data overlap between the determined key text and the text to be processed, so as to determine the accuracy of the retrieved key text. By setting a to-be-processed picture determination module to determine several to-be-processed pictures, and then processing the to-be-processed pictures through the picture processing module to obtain several feature texts, the efficiency of screening the required data can be improved. By setting a data matching module to determine the key matching degree between the to-be-processed text and the feature text, and determining the retrieval completion degree of the to-be-processed text based on the key matching degree and the first data coverage, the accuracy of the retrieved data can be improved, and the comprehensiveness of the retrieved data can be ensured, thereby ensuring the comprehensiveness and accuracy of the generated chart. By setting a target chart generation module to determine the target data, and generating a target chart corresponding to the to-be-processed text according to the target data, the efficiency of chart generation can be improved.

[0046] Furthermore, the data analysis module determines the correspondence between the definition variables and data of the text to be processed by setting a semantic analysis submodule, and determines the intermediate keywords according to the definition variables through the intermediate keyword determination submodule, which can improve the efficiency and accuracy of data screening and analysis.

[0047] Furthermore, the data retrieval module determines the first data coverage by determining the matching percentage between the variables and the corresponding data corresponding to each of the key texts and the corresponding relationship between the defined variables and the data obtained by the semantic analysis in the text to be processed, thereby ensuring that the retrieved key texts have relatively complete coverage of the text to be processed, thereby improving the accuracy and comprehensiveness of subsequently generated charts.

[0048] Furthermore, the module for determining the image to be processed determines several target text paragraphs by setting a target text determination submodule, and sets a submodule for determining the image to be processed to determine several images to be processed according to the positions of each target text paragraph, which can further improve the accuracy and efficiency of determining the relevant data required for the target chart.

[0049] Furthermore, the data matching module can improve the accuracy of the determined feature text by setting a key matching degree determination submodule to compare the variables of the feature text with the defined variables of the text to be processed to determine the key matching degree between the text to be processed and the feature text. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural block diagram of the intelligent chart generation system based on big data of the present invention;

[0051] Figure 2is a structural block diagram of a data analysis module according to an embodiment of the present invention;

[0052] Figure 3 is a structural block diagram of a data retrieval module according to an embodiment of the present invention;

[0053] Figure 4 This is a structural block diagram of a module for determining a picture to be processed according to an embodiment of the present invention;

[0054] Figure 5 is a structural block diagram of a data matching module according to an embodiment of the present invention;

[0055] Figure 6 A structural block diagram of a target chart generation module according to an embodiment of the present invention;

[0056] Figure 7 The present invention is a flowchart of the method for intelligently generating charts. DETAILED DESCRIPTION

[0057] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0059] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0060] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] See also Figure 1 As shown, it is a structural block diagram of a chart intelligent generation system based on big data of the present invention; the present invention provides a chart intelligent generation system based on big data, including:

[0062] A first text library stores a plurality of original texts; each original text includes at least one picture;

[0063] In practice, the original text may be text data combined with pictures and texts, such as scientific research papers, popular science articles, official statistical data, and related teaching materials.

[0064] A data acquisition module is used to acquire the text to be processed input by the user;

[0065] In implementation, the text to be processed is text that needs to be inserted with a chart for auxiliary analysis, and there is at least one paragraph in the text to be processed.

[0066] A data analysis module, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed and extract a number of intermediate keywords;

[0067] In implementation, the intermediate keywords include keywords directly obtained through semantic analysis, synonyms obtained through semantic analysis by synonymous replacement, and related words obtained through semantic correlation analysis.

[0068] It should be noted that those skilled in the art know that any method in the prior art that can perform semantic analysis on text to determine keywords, and any method that analyzes keywords to obtain related words, all fall within the scope of protection of the present invention and will not be described in detail herein.

[0069] a data retrieval module, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts, and determine a first data coverage between each key text and the text to be processed;

[0070] A module for determining images to be processed, which is connected to the data retrieval module and is used to determine a number of images to be processed in each of the key texts based on a semantic matching relationship;

[0071] An image processing module, which is connected to the image-to-be-processed determining module, and is used to process a number of the images to be processed according to a preset image-text conversion method to obtain a number of feature texts;

[0072] During implementation, actual implementers can set a preset image-text conversion method based on the expert system according to actual conditions. It should be noted that those skilled in the art know that any method capable of performing image-text conversion in the prior art falls within the protection scope of the present invention and will not be described in detail here.

[0073] a data matching module, which is connected to the data acquisition module, the data retrieval module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and the feature text, and to determine the retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage;

[0074] A target chart generation module is respectively connected to the data matching module and the image processing module, and is used to determine the target data in the key text and the feature text according to the retrieval completion degree, and to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

[0075] In practice, those skilled in the art know that any method in the prior art that can automatically generate a chart based on relevant data falls within the protection scope of the present invention and will not be described in detail here.

[0076] The present invention determines several intermediate keywords by setting a data analysis module, and determines key texts according to the intermediate keywords through a data retrieval module. It only needs to search and filter according to several keywords, without full-text retrieval, which can improve the efficiency of text search, and by determining the first data coverage, it can further judge the data overlap between the determined key text and the text to be processed, so as to determine the accuracy of the retrieved key text. By setting a to-be-processed picture determination module to determine several to-be-processed pictures, and then processing the to-be-processed pictures through a picture processing module to obtain several feature texts, the efficiency of screening required data can be improved. By setting a data matching module to determine the key matching degree between the to-be-processed text and the feature text, and determining the retrieval completion degree of the to-be-processed text based on the key matching degree and the first data coverage, the accuracy of the retrieved data can be improved, and the comprehensiveness of the retrieved data can be ensured, thereby ensuring the comprehensiveness and accuracy of the generated chart. By setting a target chart generation module to determine the target data, and generating a target chart corresponding to the to-be-processed text according to the target data, the efficiency of chart generation can be improved.

[0077] See also Figure 2 As shown, it is a structural block diagram of a data analysis module according to an embodiment of the present invention; specifically, the data analysis module includes:

[0078] A semantic analysis submodule, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed according to a preset semantic analysis method to obtain the corresponding relationship between the definition variables and data of the text to be processed;

[0079] In implementation, the definition variables of the text to be processed are the variables required to construct the chart, for example: the annual population migration in Hebei in the past ten years, the definition variables include the years in the past ten years, the corresponding population migration in Hebei, and the corresponding population migration in each year of each city corresponding to the establishment of Hebei Province. It can be understood that the corresponding relationship between the definition variables and the data is the population migration of a certain year (in the past ten years) and the corresponding year of Hebei Province, and the population migration of a certain year (in the past ten years) and a certain place (cities in Hebei Province) in the corresponding year after Hebei is split.

[0080] The intermediate keyword determination submodule is connected to the semantic analysis submodule and is used to extract a number of intermediate keywords from the text to be processed according to the semantic analysis result of the semantic analysis submodule, wherein the intermediate keywords are determined according to the definition variables.

[0081] The data analysis module of the present invention determines the corresponding relationship between the definition variables and data of the text to be processed by setting a semantic analysis submodule, and determines the intermediate keywords according to the definition variables through the intermediate keyword determination submodule, which can improve the efficiency and accuracy of data screening and analysis.

[0082] See also Figure 3 As shown, it is a structural block diagram of a data retrieval module according to an embodiment of the present invention; specifically, the data retrieval module includes:

[0083] A key text determination submodule, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts;

[0084] A first data coverage determination submodule, which is connected to the key text determination submodule and is used to determine the first data coverage of each of the key texts and the text to be processed;

[0085] The first data coverage is determined according to the matching percentage of the corresponding relationship between the variables and the corresponding data corresponding to each of the key texts and the defined variables and the data obtained by the semantic analysis in the text to be processed.

[0086] In implementation, the first data coverage determination submodule determines the total number of matches based on the number of corresponding relationships between definition variables and data obtained through semantic analysis in the text to be processed. If there are variables and corresponding data in the key text that are consistent with the corresponding relationship between the definition variables and data, the definition variable is recorded as a match, and the number of matches in all key texts is obtained. The number of matches is compared with the total number of matches to obtain the matching percentage, which is recorded as the first data coverage.

[0087] The data retrieval module of the present invention determines the first data coverage by determining the matching percentage of the corresponding relationship between the variables and the corresponding data corresponding to each of the key texts and the defined variables and data obtained by the semantic analysis in the text to be processed, thereby ensuring that the coverage of the text to be processed by the retrieved key text is relatively complete, thereby improving the accuracy and comprehensiveness of the subsequently generated charts.

[0088] See also Figure 4 As shown, it is a structural block diagram of a module for determining a picture to be processed according to an embodiment of the present invention; specifically, the module for determining a picture to be processed includes:

[0089] A target text determination submodule, which is connected to the data retrieval module and is used to determine a number of target text paragraphs matching the intermediate keyword in each of the key texts based on the intermediate keyword;

[0090] The to-be-processed picture determination submodule is connected to the target text determination submodule and is used to determine a number of to-be-processed pictures according to the position of each target text paragraph.

[0091] The image to be processed determination module of the present invention determines several target text paragraphs by setting a target text determination submodule, and sets a image to be processed determination submodule to determine several images to be processed according to the position of each target text paragraph, which can further improve the accuracy and efficiency of determining the relevant data required for the target chart.

[0092] See also Figure 5 As shown, it is a structural block diagram of a data matching module according to an embodiment of the present invention; specifically, the data matching module includes:

[0093] A key matching degree determination submodule, which is connected to the data acquisition module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and each of the feature texts;

[0094] wherein, semantic analysis is performed on the feature text to extract a number of variables, and the variables are compared with a number of the intermediate keywords to determine the key matching degree between the text to be processed and the feature text;

[0095] A retrieval completion determination submodule is connected to the key matching determination submodule and the data retrieval module respectively, and is used to determine the retrieval completion of the text to be processed based on the key matching degree and the first data coverage.

[0096] In implementation, the key matching degree determination submodule compares the variables extracted from the feature text with each intermediate keyword, and determines the key matching degree based on the matching degree between the extracted variables and the definition variables corresponding to each intermediate keyword.

[0097] In a specific embodiment, the key matching degree A is determined based on the following formula:

[0098] A=Na / N; wherein N is the total number of defined variables corresponding to each intermediate keyword, and Na is the number of valid variables matching the defined variables, wherein the valid variables are variables having corresponding data among the variables extracted from the feature text.

[0099] The data matching module of the present invention can improve the accuracy of the determined feature text by setting a key matching degree determination submodule to compare the variables of the feature text and the definition variables of the text to be processed to determine the key matching degree between the text to be processed and the feature text.

[0100] See also Figure 6 As shown, it is a structural block diagram of a target chart generation module according to an embodiment of the present invention; specifically, the target chart generation module includes:

[0101] The target data determination submodule is connected to the data matching module and is used to determine the target data in each of the key texts and each of the feature texts according to the retrieval completion degree; it can be understood that the target data is the variables and their corresponding data extracted from each of the key texts and each of the feature texts that match the corresponding relationship between the definition variables and the data corresponding to the intermediate keyword.

[0102] The target chart generation submodule is connected to the target data determination submodule and is used to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

[0103] It should be noted that those skilled in the art know that any method in the prior art that can generate a table / graph according to the correspondence between variables and data is included in the preset chart generation rules in the present invention, which falls within the protection scope of the present invention and will not be repeated here.

[0104] Specifically, the target text determination submodule determines a number of target text paragraphs in each of the key texts according to the comparison result of the paragraph coverage and the preset coverage threshold;

[0105] Among them, if the paragraph coverage corresponding to a single paragraph of any key text is greater than a preset coverage threshold, the paragraph where the single paragraph is located is determined as the target text paragraph, and the preset coverage threshold is less than or equal to the first data coverage.

[0106] In implementation, the paragraph coverage corresponding to a single paragraph is determined based on the matching percentage between the keywords extracted from the paragraph and each intermediate keyword. The preset coverage is preferably set to 60% to 80% of the calculated first data coverage, which can perform preliminary screening of the semantics of each paragraph of the key text and determine the range of paragraphs with similar semantics.

[0107] In a specific embodiment, if the paragraph coverage corresponding to a certain paragraph is greater than a preset coverage threshold, the paragraph in which the single paragraph is located is determined as the target text paragraph, the position of the paragraph in the corresponding key text is determined, and based on the correspondence between the image and the text, the pictures corresponding to the positions of each target text paragraph are determined, and these pictures are determined as pictures to be processed.

[0108] Specifically, the search completion determination submodule calculates the search completion according to the following formula:

[0109] P = a × A + b × B;

[0110] Among them, P is the retrieval completion, A is the key matching degree, B is the first data coverage, a is the first weight coefficient, and b is the second weight coefficient.

[0111] In implementation, it is preferred to record the P value calculated when the key matching degree is 100% and the first data coverage is 60% as the preset search completion threshold. Generally, a+b=1, a≥2×b, which can ensure good search efficiency.

[0112] Specifically, the target data determination submodule determines the target data according to the retrieval completion degree and a preset retrieval completion degree threshold;

[0113] If the retrieval completion is greater than a preset retrieval completion threshold, the data in the key text and feature text corresponding to the retrieval completion are integrated to obtain the target data.

[0114] See also Figure 7 As shown, it is a flow chart of the intelligent chart generation method of the present invention.

[0115] In a specific embodiment, the present invention provides a method for intelligently generating a chart, comprising:

[0116] Step S1, obtaining the text to be processed input by the user;

[0117] Step S2, performing semantic analysis on the text to be processed and extracting a number of intermediate keywords;

[0118] Step S3, retrieving corresponding original texts from the first text library according to the intermediate keywords, determining them as key texts, and determining a first data coverage between each key text and the text to be processed;

[0119] Step S4, determining a number of to-be-processed pictures in each of the key texts based on the first data coverage;

[0120] Step S5, processing the plurality of images to be processed according to a preset image-text conversion method to obtain a plurality of feature texts;

[0121] Step S6, determining a key matching degree between the text to be processed and the feature text, and determining a retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage;

[0122] Step S7, determining target data in the key text and the feature text according to the retrieval completion, and generating a target graph corresponding to the text to be processed according to the target data and a preset graph generation rule.

[0123] Specifically, the intelligent chart generation method provided by the present invention can be applied to the above-mentioned big data-based intelligent chart generation system to achieve the same technical effect, which will not be repeated here.

[0124] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A big data-based intelligent chart generation system, characterized in that: include: A first text library stores a plurality of original texts; each original text includes at least one picture; A data acquisition module is used to acquire the text to be processed input by the user; A data analysis module, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed and extract a number of intermediate keywords; a data retrieval module, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts, and determine a first data coverage between each key text and the text to be processed; A module for determining images to be processed, which is connected to the data retrieval module and is used to determine a number of images to be processed in each of the key texts based on a semantic matching relationship; An image processing module, which is connected to the image-to-be-processed determining module, and is used to process a number of the images to be processed according to a preset image-text conversion method to obtain a number of feature texts; a data matching module, which is connected to the data acquisition module, the data retrieval module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and the feature text, and to determine the retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage; A target chart generation module is respectively connected to the data matching module and the image processing module, and is used to determine the target data in the key text and the feature text according to the retrieval completion degree, and to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

2. The intelligent chart generation system based on big data according to claim 1 is characterized in that: The data analysis module includes: A semantic analysis submodule, which is connected to the data acquisition module and is used to perform semantic analysis on the text to be processed according to a preset semantic analysis method to obtain the corresponding relationship between the definition variables and data of the text to be processed; The intermediate keyword determination submodule is connected to the semantic analysis submodule and is used to extract a number of intermediate keywords from the text to be processed according to the semantic analysis result of the semantic analysis submodule, wherein the intermediate keywords are determined according to the definition variables.

3. The intelligent chart generation system based on big data according to claim 2 is characterized in that: The data retrieval module comprises: A key text determination submodule, which is connected to the first text library and the data analysis module respectively, and is used to retrieve a number of corresponding original texts from the first text library according to a number of the intermediate keywords, and determine them as key texts; A first data coverage determination submodule, which is connected to the key text determination submodule and is used to determine the first data coverage of each of the key texts and the text to be processed; The first data coverage is determined according to the matching percentage of the corresponding relationship between the variables and the corresponding data corresponding to each of the key texts and the defined variables and the data obtained by the semantic analysis in the text to be processed.

4. The intelligent chart generation system based on big data according to claim 3 is characterized in that: The module for determining the image to be processed includes: A target text determination submodule, which is connected to the data retrieval module and is used to determine a number of target text paragraphs matching the intermediate keyword in each of the key texts based on the intermediate keyword; The to-be-processed picture determination submodule is connected to the target text determination submodule and is used to determine a number of to-be-processed pictures according to the position of each target text paragraph.

5. The intelligent chart generation system based on big data according to claim 4 is characterized in that: The data matching module comprises: A key matching degree determination submodule, which is connected to the data acquisition module and the image processing module respectively, and is used to determine the key matching degree between the text to be processed and each of the feature texts; wherein, semantic analysis is performed on the feature text to extract a number of variables, and the variables are compared with a number of definition variables of the text to be processed to determine the key matching degree between the text to be processed and the feature text; A retrieval completion determination submodule is connected to the key matching determination submodule and the data retrieval module respectively, and is used to determine the retrieval completion of the text to be processed based on the key matching degree and the first data coverage.

6. The intelligent chart generation system based on big data according to claim 5 is characterized in that: The target chart generation module includes: A target data determination submodule, which is connected to the data matching module and is used to determine target data in each of the key texts and each of the feature texts according to the search completion degree; The target chart generation submodule is connected to the target data determination submodule and is used to generate a target chart corresponding to the text to be processed according to the target data and preset chart generation rules.

7. The intelligent chart generation system based on big data according to claim 4 is characterized in that: The target text determination submodule determines a number of target text paragraphs in each of the key texts according to a comparison result between the paragraph coverage and a preset coverage threshold; Among them, if the paragraph coverage corresponding to a single paragraph of any key text is greater than a preset coverage threshold, the paragraph where the single paragraph is located is determined as the target text paragraph, and the preset coverage threshold is less than or equal to the first data coverage.

8. The intelligent chart generation system based on big data according to claim 5 is characterized in that: The retrieval completion determination submodule calculates the retrieval completion according to the following formula: P = a × A + b × B; Among them, P is the retrieval completion, A is the key matching degree, B is the first data coverage, a is the first weight coefficient, and b is the second weight coefficient.

9. The big data-based intelligent chart generation system according to claim 6, characterized in that: The target data determination submodule determines the target data according to the retrieval completion degree and a preset retrieval completion degree threshold; If the retrieval completion is greater than a preset retrieval completion threshold, the data in the key text and feature text corresponding to the retrieval completion are integrated to obtain the target data.

10. A method for intelligently generating a chart applied to the system for intelligently generating a chart based on big data as claimed in any one of claims 1 to 9, characterized in that: include: Step S1, obtaining the text to be processed input by the user; Step S2, performing semantic analysis on the text to be processed and extracting a number of intermediate keywords; Step S3, retrieving corresponding original texts from the first text library according to the intermediate keywords, determining them as key texts, and determining a first data coverage between each key text and the text to be processed; Step S4, determining a number of to-be-processed pictures in each of the key texts based on the first data coverage; Step S5, processing the plurality of images to be processed according to a preset image-text conversion method to obtain a plurality of feature texts; Step S6, determining a key matching degree between the text to be processed and the feature text, and determining a retrieval completion degree of the text to be processed based on the key matching degree and the first data coverage; Step S7, determining target data in the key text and the feature text according to the retrieval completion, and generating a target graph corresponding to the text to be processed according to the target data and a preset graph generation rule.

Images