Depth data visualization method and system based on artificial intelligence, and program product
Through the deep data visualization method based on artificial intelligence, the inefficiency of traditional methods is solved, and efficient data mining and visualization processing is achieved.
Patent Information
- Application Number
- CN202411862284.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-04-11
AI Technical Summary
Traditional data visualization methods rely on manual interpretation and processing, and are inefficient and difficult to effectively extract and visualize in-depth information in massive data.
Using a deep data visualization method based on artificial intelligence, data extraction and visualization processing are automated through optical character recognition, text encoding processing, target string sequence extraction, topic keyword extraction and vectorization processing.
It realizes intelligent analysis and automated visual processing of massive data, improves the efficiency of deep data mining and visual processing, and replaces traditional manual interpretation methods.
Smart Images
Figure CN119807405A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of data analysis technology, and specifically relates to a deep data visualization method, system and program product based on artificial intelligence. Background Art
[0002] With the advent of the big data era, the amount of data has exploded, and how to extract valuable information from massive data has become an important topic. Data visualization has important significance and role in the big data era, and has become an indispensable part of data analysis and decision-making. Data visualization refers to presenting data in the form of charts, making the data intuitive and easy to understand. Data visualization can help people quickly understand the meaning and internal relationship of data.
[0003] Most traditional data visualization methods extract and organize deep data through manual interpretation of relevant information, and then select corresponding visualization methods to perform visual editing on the organized data. The data extraction, organization and classification process all rely on data analysts to complete, and the efficiency needs to be improved. Summary of the invention
[0004] The purpose of the present invention is to provide a deep data visualization method, system and program product based on artificial intelligence to solve the above-mentioned problems existing in the prior art.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] First, we provide a deep data visualization method based on artificial intelligence, including:
[0007] Obtaining a target file to be processed, and performing optical character recognition on the target file to obtain corresponding text content;
[0008] Encoding the text content, converting the text content into a string set, and determining each digital string and each separator string in the string set;
[0009] Based on each digital character string, each separator character string and the set target determination condition, a target character string sequence is extracted from the character string set, wherein the target character string sequence includes the first and last two groups of first-class separator character strings, a plurality of target digital character strings sequentially arranged between the two groups of first-class separator character strings, and second-class separator character strings spaced apart between the target digital character strings;
[0010] Determine the first separator, target numbers and second separators in the text content based on the target character string sequence, and extract the subject keyword and the content label corresponding to each target number from the text content according to the first separator, target numbers and second separators;
[0011] Summarize each target number and its content label in turn to obtain the corresponding subject content set;
[0012] Perform vectorization processing on the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into the preset topic classification model for classification and identification to obtain the corresponding topic classification result;
[0013] According to the subject classification results, corresponding visualization tools are used to edit the subject content collection into a visualization chart to obtain the corresponding visualization chart, and the visualization chart is associated with the corresponding subject keywords and outputted.
[0014] In one possible design, the method further includes:
[0015] Substitute the topic vectors of any two topic content sets into the preset vector similarity formula for calculation to obtain the vector similarity between the two topic vectors. The vector similarity formula is:
[0016]
[0017] Among them, S represents the vector similarity, C is the set similarity coefficient, X and Y represent two topic vectors respectively, and ||·||2 represents the two-norm operation;
[0018] When the vector similarity between two topic vectors reaches a set similarity threshold, the topic content sets corresponding to the two topic vectors are determined to be similar, and the visualization charts corresponding to the two similar topic content sets are combined and output.
[0019] In a possible design, the encoding process of the text content, converting the text content into a string set, and determining each digital string and each separator string in the string set includes:
[0020] Import the text content into a preset text encoder for encoding, and convert the text content into a string set;
[0021] According to a set string comparison table, each numeric string and each separator string are traversed from the string set to find out, wherein the string comparison table contains a plurality of numeric strings and a plurality of separator strings, and the separator strings include a first type of separator strings and a second type of separator strings.
[0022] In a possible design, extracting a target string sequence from a string set based on each digital string, each separation string, and a set target determination condition includes:
[0023] Determine the length of the character interval between each numeric character string, and extract the first type of separation character string and the second type of separation character string from each separation character string;
[0024] The target digital string is a continuous number of digital strings located between two groups of first-type separator strings, whose character interval length is within the set interval range and are separated by second-type separator strings;
[0025] The two groups of first-type separation character strings, each target digital character string and each second-type separation character string are combined in sequence to obtain a target character string sequence.
[0026] In a possible design, the first separator, each target number, and each second separator in the text content are determined based on the target character string sequence, and the subject keyword and the content label corresponding to each target number are extracted from the text content according to the first separator, each target number, and each second separator, including:
[0027] The numbers corresponding to the target digital strings in the target string sequence in the text content are used as the target numbers, the symbols or characters corresponding to the first-type separator strings at the beginning of the target string sequence in the text content are used as the first separator marks, and the symbols or characters corresponding to the second-type separator strings in the target string sequence in the text content are used as the second separator marks;
[0028] Keywords are extracted from the sentences before the first separator in the text content to obtain the subject keywords, and keywords are extracted from the text before and after each target number and between two adjacent second separators or between the adjacent first separator and second separator to obtain the content label of the corresponding target number.
[0029] In a possible design, when subject keywords are vectorized, the subject keywords are input into an ACGE model for vectorization to obtain corresponding subject vectors; the subject classification model uses a trained artificial neural network model.
[0030] In a possible design, the subject content set is edited into a visualization chart using a corresponding visualization tool according to the subject classification result to obtain a corresponding visualization chart, including:
[0031] Substituting the subject classification result into a preset visualization tool table for search and determining a matching visualization tool number, wherein the visualization tool table includes a number of subject classification results and a visualization tool number corresponding to each subject classification result;
[0032] Based on the matched visualization tool number, the corresponding visualization tool is called to perform visualization chart editing on the subject content collection to obtain the corresponding visualization chart.
[0033] In the second aspect, a deep data visualization system based on artificial intelligence is provided, including a text acquisition unit, a text encoding unit, a character extraction unit, a content extraction unit, a topic aggregation unit, a topic classification unit and a visual output unit, wherein:
[0034] A text acquisition unit is used to acquire a target file to be processed and perform optical character recognition on the target file to obtain corresponding text content;
[0035] A text encoding unit, used to encode the text content, convert the text content into a string set, and determine each digital string and each separator string in the string set;
[0036] A character extraction unit is used to extract a target character string sequence from the character string set based on each numeric character string, each separator character string and a set target determination condition, wherein the target character string sequence includes two groups of first-class separator character strings, a plurality of target numeric character strings sequentially arranged between the two groups of first-class separator character strings, and second-class separator character strings spaced between each target numeric character string;
[0037] A content extraction unit, configured to determine a first separator, target numbers, and second separators in the text content based on a target character string sequence, and extract a subject keyword and a content tag corresponding to each target number from the text content according to the first separator, target numbers, and second separators;
[0038] The subject aggregation unit is used to aggregate each target number and its content label in sequence to obtain a corresponding subject content set;
[0039] The topic classification unit is used to vectorize the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into a preset topic classification model for classification and identification to obtain the corresponding topic classification result;
[0040] The visual output unit is used to edit the visual chart of the subject content set using corresponding visualization tools according to the subject classification results, obtain the corresponding visual chart, and associate the visual chart with the corresponding subject keywords for output.
[0041] Third, we provide a deep data visualization system based on artificial intelligence, including:
[0042] A memory for storing instructions;
[0043] A processor is used to read the instructions stored in the memory and execute any one of the methods described in the first aspect according to the instructions.
[0044] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored on the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes any one of the methods described in the first aspect. In addition, a computer program product is provided, and when the computer program product is executed on a computer, the computer executes any one of the methods described in the first aspect.
[0045] Beneficial effects: The present invention parses and encodes the file content to obtain a string set for corresponding string determination and extraction, obtains a target string sequence, and then extracts subject keywords and subject content sets from the text content based on the target string sequence, and then uses the subject keywords to classify the subject, determines the corresponding visualization method, and finally visualizes and outputs the subject content set based on the determined visualization method to achieve deep data mining and visualization processing of the text content. The present invention can effectively extract the deep data therein for automated visualization editing by performing intelligent analysis on the file content, thereby replacing the traditional method of manually interpreting and extracting data for visualization processing, improving the efficiency of deep data mining and visualization processing, and having good applicability. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0047] Figure 1 This is a schematic diagram of the steps of the method in Example 1 of the present invention;
[0048] Figure 2 This is a schematic diagram of the structure of the system in Example 2 of the present invention;
[0049] Figure 3 Schematic diagram of the system structure in Example 3 of the present invention. DETAILED DESCRIPTION
[0050] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and it should not be understood that the present invention is limited to the embodiments set forth herein.
[0051] It should be understood that, unless otherwise clearly specified and defined, the term "connection" 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 directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meaning of the above terms in the embodiments can be understood according to specific circumstances.
[0052] In the following description, specific details are provided to facilitate a complete understanding of the exemplary embodiments. However, those of ordinary skill in the art should understand that the exemplary embodiments can be implemented without these specific details. For example, the device can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other embodiments, well-known processes, structures, and technologies can be shown without unnecessary details to avoid obscuring the embodiments.
[0053] Embodiment 1:
[0054] This embodiment provides a deep data visualization method based on artificial intelligence, which can be applied to a corresponding data processing terminal, such as Figure 1 As shown, the method includes the following steps:
[0055] S1. Obtain a target file to be processed, and perform optical character recognition on the target file to obtain the corresponding text content.
[0056] Specifically, when implementing, the data processing terminal first obtains the target file to be processed uploaded locally or transmitted online. The target file can be an electronic document or a picture, etc. Then, an optical character recognition tool is used to perform optical character recognition on the target file to obtain the corresponding text content.
[0057] S2. Perform encoding processing on the text content, convert the text content into a set of strings, and determine each numeric string and each delimiter string in the set of strings.
[0058] Specifically, when implementing, the data processing terminal uses a corresponding text encoder (such as UTF-8) to perform encoding processing on the text content and convert the text content into a set of strings. Then, each numeric string and each delimiter string in the set of strings are determined through string matching, that is, each numeric string and each delimiter string are traversed and found from the set of strings according to the set string comparison table. The string comparison table contains several numeric strings and several delimiter strings. The delimiter strings include the first type of delimiter string and the second type of delimiter string. The numeric string is the string corresponding to a number (including Chinese numbers). The first type of delimiter string is the string corresponding to a delimiter character such as ".", ":", or "such as", etc. The second type of delimiter string is the string corresponding to a delimiter character such as ",", ",", ";", or "and", etc.
[0059] S3. Based on each numeric character string, each separator character string and the set target judgment condition, a target character string sequence is extracted from the character string set, wherein the target character string sequence includes two groups of first-class separator character strings, a plurality of target numeric character strings arranged in sequence between the two groups of first-class separator character strings, and second-class separator character strings spaced apart between each target numeric character string.
[0060] In specific implementation, the data processing terminal first determines the length of the character interval between each digital string, extracts the first type of separation string and the second type of separation string from each separation string; then, multiple continuous digital strings located between two groups of first type separation strings, whose character interval length is within the set interval range and are separated by second type separation strings are taken as target digital strings; then, the two groups of first type separation strings, each target digital string and each second type separation string are sequentially combined to obtain a target string sequence. The target string sequence finally obtained includes the first and last groups of first type separation strings, a number of target digital strings sequentially arranged between the two groups of first type separation strings, and second type separation strings spaced between each target digital string.
[0061] S4. Determine the first separator, target numbers and second separators in the text content based on the target character string sequence, and extract the subject keywords and content tags corresponding to the target numbers from the text content according to the first separator, target numbers and second separators.
[0062] In specific implementation, the data processing terminal uses the numbers corresponding to each target digital string in the target string sequence in the text content as the target numbers, uses the symbols or words corresponding to the first-class separator string at the head end of the target string sequence in the text content as the first separator mark, and uses the symbols or words corresponding to each second-class separator string in the target string sequence in the text content as the second separator mark. Then, the sentence before the first separator mark in the text content is subjected to keyword extraction to obtain the subject keywords, and the words before and after each target number and between two adjacent second separator marks or between the adjacent first separator mark and the second separator mark are subjected to keyword extraction to obtain the content label corresponding to the target number.
[0063] S5. Summarize each target number and its content label in turn to obtain a corresponding subject content set.
[0064] In specific implementation, the data processing terminal may summarize each target number and its content label in sequence in the form of a 2×N matrix to obtain a corresponding theme content set.
[0065] S6. Perform vectorization processing on the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into a preset topic classification model for classification and identification to obtain the corresponding topic classification result.
[0066] In specific implementation, the data processing terminal can input the topic keywords into the corresponding vector conversion model for vectorization processing to obtain the corresponding topic vector. The vector conversion model can adopt the ACGE model or other vectorization models according to actual needs. Then the topic vector is input into the preset topic classification model for classification and identification to obtain the corresponding topic classification result. The topic classification model can adopt the trained artificial neural network model or other classification models according to actual needs.
[0067] S7. Use corresponding visualization tools to edit the subject content collection into a visualization chart according to the subject classification results to obtain a corresponding visualization chart, and associate the visualization chart with the corresponding subject keywords for output.
[0068] In specific implementation, the data processing terminal can substitute the subject classification results into a preset visualization tool table for search to determine the matching visualization tool number, wherein the visualization tool table contains several subject classification results and the corresponding visualization tool number associated with each subject classification result; then, based on the matching visualization tool number, the corresponding visualization tool is called to perform visualization chart editing on the subject content collection to obtain the corresponding visualization chart; finally, the visualization chart is associated with the corresponding subject keyword and output.
[0069] In addition, the data processing terminal can also substitute the subject vectors of any two subject content sets into a preset vector similarity formula for calculation to obtain the vector similarity between the two subject vectors. The vector similarity formula is:
[0070]
[0071] Among them, S represents the vector similarity, C is the set similarity coefficient, X and Y represent two topic vectors respectively, and ||·||2 represents the two-norm operation;
[0072] When the vector similarity between two topic vectors reaches a set similarity threshold, the topic content sets corresponding to the two topic vectors are determined to be similar, and the visualization charts corresponding to the two similar topic content sets are combined and output.
[0073] The method of this embodiment can effectively extract deep data from the file for automated visual editing by performing intelligent analysis of the file content, thereby replacing the traditional method of manually interpreting and extracting data for visual processing, thereby improving the efficiency of deep data mining and visual processing, and has good applicability.
[0074] Embodiment 2:
[0075] This embodiment provides a deep data visualization system based on artificial intelligence, such as Figure 2 As shown, it includes a text acquisition unit, a text encoding unit, a character extraction unit, a content extraction unit, a topic summary unit, a topic classification unit and a visual output unit, wherein:
[0076] A text acquisition unit is used to acquire a target file to be processed and perform optical character recognition on the target file to obtain corresponding text content;
[0077] A text encoding unit, used to encode the text content, convert the text content into a string set, and determine each digital string and each separator string in the string set;
[0078] A character extraction unit is used to extract a target character string sequence from the character string set based on each numeric character string, each separator character string and a set target determination condition, wherein the target character string sequence includes two groups of first-class separator character strings, a plurality of target numeric character strings sequentially arranged between the two groups of first-class separator character strings, and second-class separator character strings spaced between each target numeric character string;
[0079] A content extraction unit, configured to determine a first separator, target numbers, and second separators in the text content based on a target character string sequence, and extract a subject keyword and a content tag corresponding to each target number from the text content according to the first separator, target numbers, and second separators;
[0080] The subject aggregation unit is used to aggregate each target number and its content label in sequence to obtain a corresponding subject content set;
[0081] The topic classification unit is used to vectorize the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into a preset topic classification model for classification and identification to obtain the corresponding topic classification result;
[0082] The visual output unit is used to edit the visual chart of the subject content set using corresponding visualization tools according to the subject classification results, obtain the corresponding visual chart, and associate the visual chart with the corresponding subject keywords for output.
[0083] Embodiment 3:
[0084] This embodiment provides a deep data visualization system based on artificial intelligence, such as Figure 3 As shown, at the hardware level, it includes:
[0085] Data interface, used to establish data connection between the processor and the external data terminal;
[0086] A memory for storing instructions;
[0087] The processor is used to read the instructions stored in the memory and execute the depth data visualization method in Example 1 according to the instructions.
[0088] Optionally, the system further includes an internal bus, through which the processor, the memory and the data interface can be interconnected, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.
[0089] The memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO), etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0090] Embodiment 4:
[0091] This embodiment provides a computer-readable storage medium, on which instructions are stored, and when the instructions are executed on a computer, the computer executes the deep data visualization method in Embodiment 1. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0092] This embodiment also provides a computer program product, which, when running on a computer, executes the deep data visualization method in Embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
[0093] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A deep data visualization method based on artificial intelligence, characterized in that: include: Obtaining a target file to be processed, and performing optical character recognition on the target file to obtain corresponding text content; Encoding the text content, converting the text content into a string set, and determining each digital string and each separator string in the string set; Based on each digital character string, each separator character string and the set target determination condition, a target character string sequence is extracted from the character string set, wherein the target character string sequence includes the first and last two groups of first-class separator character strings, a plurality of target digital character strings sequentially arranged between the two groups of first-class separator character strings, and second-class separator character strings spaced apart between the target digital character strings; Determine the first separator, target numbers and second separators in the text content based on the target character string sequence, and extract the subject keyword and the content label corresponding to each target number from the text content according to the first separator, target numbers and second separators; Summarize each target number and its content label in turn to obtain the corresponding subject content set; Perform vectorization processing on the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into the preset topic classification model for classification and identification to obtain the corresponding topic classification result; According to the subject classification results, corresponding visualization tools are used to edit the subject content collection into a visualization chart to obtain the corresponding visualization chart, and the visualization chart is associated with the corresponding subject keywords and outputted.
2. The artificial intelligence-based deep data visualization method according to claim 1, characterized in that: The method further comprises: Substitute the topic vectors of any two topic content sets into the preset vector similarity formula for calculation to obtain the vector similarity between the two topic vectors. The vector similarity formula is: Among them, S represents the vector similarity, C is the set similarity coefficient, X and Y represent two topic vectors respectively, and ||·||2 represents the two-norm operation; When the vector similarity between two topic vectors reaches a set similarity threshold, the topic content sets corresponding to the two topic vectors are determined to be similar, and the visualization charts corresponding to the two similar topic content sets are combined and output.
3. The artificial intelligence-based deep data visualization method according to claim 1, characterized in that: The encoding process of the text content, converting the text content into a string set, and determining each digital string and each separator string in the string set includes: Import the text content into a preset text encoder for encoding, and convert the text content into a string set; According to a set string comparison table, each numeric string and each separator string are traversed from the string set to find out, wherein the string comparison table contains a plurality of numeric strings and a plurality of separator strings, and the separator strings include a first type of separator strings and a second type of separator strings.
4. The artificial intelligence-based deep data visualization method according to claim 3, characterized in that: The step of extracting a target string sequence from a string set based on each digital string, each separation string and a set target determination condition includes: Determine the length of the character interval between each numeric character string, and extract the first type of separation character string and the second type of separation character string from each separation character string; The target digital string is a continuous number of digital strings located between two groups of first-type separator strings, whose character interval length is within the set interval range and are separated by second-type separator strings; The two groups of first-type separation character strings, each target digital character string and each second-type separation character string are combined in sequence to obtain a target character string sequence.
5. The artificial intelligence-based deep data visualization method according to claim 1, characterized in that: The method of determining the first separator, target numbers and second separators in the text content based on the target character string sequence, and extracting the subject keyword and the content label corresponding to each target number from the text content according to the first separator, target numbers and second separators, includes: The numbers corresponding to the target digital strings in the target string sequence in the text content are used as the target numbers, the symbols or characters corresponding to the first-type separator strings at the beginning of the target string sequence in the text content are used as the first separator marks, and the symbols or characters corresponding to the second-type separator strings in the target string sequence in the text content are used as the second separator marks; Keywords are extracted from the sentences before the first separator in the text content to obtain the subject keywords, and keywords are extracted from the text before and after each target number and between two adjacent second separators or between the adjacent first separator and second separator to obtain the content label of the corresponding target number.
6. The artificial intelligence-based deep data visualization method according to claim 1, characterized in that: When the subject keywords are vectorized, the subject keywords are input into the ACGE model for vectorization to obtain corresponding subject vectors; the subject classification model adopts a trained artificial neural network model.
7. The artificial intelligence-based deep data visualization method according to claim 1, characterized in that: The method of using corresponding visualization tools to edit the subject content set into a visualization chart according to the subject classification results to obtain a corresponding visualization chart includes: Substituting the subject classification result into a preset visualization tool table for search and determining a matching visualization tool number, wherein the visualization tool table includes a number of subject classification results and a visualization tool number corresponding to each subject classification result; Based on the matched visualization tool number, the corresponding visualization tool is called to perform visualization chart editing on the subject content collection to obtain the corresponding visualization chart.
8. The deep data visualization system based on artificial intelligence is characterized by: It includes a text acquisition unit, a text encoding unit, a character extraction unit, a content extraction unit, a topic summary unit, a topic classification unit and a visual output unit, wherein: A text acquisition unit is used to acquire a target file to be processed and perform optical character recognition on the target file to obtain corresponding text content; A text encoding unit, used to encode the text content, convert the text content into a string set, and determine each digital string and each separator string in the string set; A character extraction unit is used to extract a target character string sequence from the character string set based on each numeric character string, each separator character string and a set target determination condition, wherein the target character string sequence includes two groups of first-class separator character strings, a plurality of target numeric character strings sequentially arranged between the two groups of first-class separator character strings, and second-class separator character strings spaced between each target numeric character string; A content extraction unit, configured to determine a first separator, target numbers, and second separators in the text content based on a target character string sequence, and extract a subject keyword and a content tag corresponding to each target number from the text content according to the first separator, target numbers, and second separators; The subject aggregation unit is used to aggregate each target number and its content label in sequence to obtain a corresponding subject content set; The topic classification unit is used to vectorize the topic keywords to obtain the topic vector of the corresponding topic content set, and input the topic vector into a preset topic classification model for classification and identification to obtain the corresponding topic classification result; The visual output unit is used to edit the visual chart of the subject content set using corresponding visualization tools according to the subject classification results, obtain the corresponding visual chart, and associate the visual chart with the corresponding subject keywords for output.
9. The deep data visualization system based on artificial intelligence is characterized by: include: A memory for storing instructions; A processor, configured to read the instructions stored in the memory and execute the artificial intelligence-based deep data visualization method according to any one of claims 1 to 7 according to the instructions.
10. A computer program product, characterized in that When the computer program product runs on a computer, the artificial intelligence-based deep data visualization method described in any one of claims 1 to 7 is executed.