CN118468994A - Method and system for automatically generating knowledge map based on content of generated AI - Google Patents
Method and system for automatically generating knowledge map based on content of generated AI Download PDFInfo
- Publication number
- CN118468994A CN118468994A CN202410556151.9A CN202410556151A CN118468994A CN 118468994 A CN118468994 A CN 118468994A CN 202410556151 A CN202410556151 A CN 202410556151A CN 118468994 A CN118468994 A CN 118468994A
- Authority
- CN
- China
- Prior art keywords
- content
- knowledge map
- knowledge
- document
- generated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000010276 construction Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 18
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/027—Frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method and a system for automatically generating a knowledge map based on content of a generation type AI, and relates to the technical field of data processing. The method comprises the following steps: acquiring a document uploaded by a user; reading and analyzing document content; slicing the parsed document content according to a preset text slicing strategy to obtain a plurality of sliced content; constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points; analyzing text content of a corresponding paragraph through a pre-trained generation type AI model to obtain and fill the analysis content into an initialization structure to generate a final knowledge map. The invention automatically analyzes the document catalogue and generates a comprehensive and effective knowledge map by combining the generation type AI technology, thereby providing effective support for subsequent project management.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for automatically generating a knowledge map based on content of a generation type AI.
Background
The knowledge map is one of the core functional modules of the knowledge base system, can extract words representing the core content of the knowledge set from the knowledge set composed of a plurality of pieces of knowledge, and is assembled into a network structure to display each piece of knowledge, so that the relationship between the core content of the knowledge set and the plurality of pieces of knowledge can be rapidly known through the knowledge map.
In enterprise management, users need to sort and generalize the enterprise-related information to form an effective knowledge map for effective enterprise project management. However, in the prior art, only knowledge is collected, and a comprehensive and detailed knowledge map cannot be generated efficiently and accurately in combination with the actual situation of the project content, so that knowledge cannot be effectively utilized, and the project management effect of an enterprise is not high, and the project situation cannot be accurately mastered.
Disclosure of Invention
In order to overcome the problems or at least partially solve the problems, the invention provides a method and a system for automatically generating a knowledge map based on the content of a generated AI, which automatically analyze a document catalog and generate a comprehensive and effective knowledge map by combining the generated AI technology so as to provide effective support for subsequent project management.
In order to solve the technical problems, the invention adopts the following technical scheme:
In a first aspect, the present invention provides a method for automatically generating a knowledge map based on content of a generated AI, including the steps of:
acquiring a document uploaded by a user;
reading and analyzing document content;
slicing the parsed document content according to a preset text slicing strategy to obtain a plurality of sliced content;
Constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points;
Analyzing text content of a corresponding paragraph through a pre-trained generation type AI model to obtain and fill the analysis content into an initialization structure to generate a final knowledge map.
The invention automatically analyzes the document catalogue, and generates a knowledge map by combining the generation type AI technology, thereby providing the follow-up test question library and project management. In combination with the generation-type AI technique, the invention can generate the knowledge map with high recognition degree. The nodes in the knowledge map can accurately reflect the content and the structure in the document, so that a user can quickly understand the theme, the key points and the association relationship of the document. The automatic analysis of the document catalogue can greatly reduce the time and effort for manually arranging knowledge and improve the efficiency of knowledge arrangement. By combining the generation type AI technology, a knowledge map can be quickly generated, and the knowledge management efficiency is further improved. The AI technology plays an important role in the knowledge map generation process, reduces manual operation, improves the generation efficiency, and can also guarantee the accuracy and the integrity of the knowledge map to a certain extent.
Based on the first aspect, further, the text slicing strategy includes: and generating knowledge nodes with different numbers according to the word numbers of the document content, wherein the knowledge nodes comprise a plurality of knowledge node generation numbers corresponding to a plurality of word number ranges.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
and acquiring manual marking information and editing the knowledge map in a self-defined mode.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
And carrying out content recommendation and relationship analysis based on the generated AI model by combining the knowledge map edited by the user, and assisting the user in generating knowledge map nodes.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
and updating the document uploaded by the user according to the knowledge map.
Based on the first aspect, the method for updating the document uploaded by the user according to the knowledge map further comprises the following steps:
According to the corresponding map content nodes in the knowledge map, a third-party AI model is called in batches based on the AI-PaaS service, AI intelligent analysis is carried out, and node names and knowledge points are generated;
And warehousing the node names and the knowledge points, and updating the document.
In a second aspect, the present invention provides a system for automatically generating a knowledge map based on content of a generated AI, including a user uploading module, a document parsing module, a slicing processing module, an initial map construction module, and a knowledge map generation module, wherein:
the user uploading module is used for acquiring the document uploaded by the user;
The document analysis module is used for reading and analyzing the document content;
the slicing processing module is used for slicing the analyzed document content according to a preset text slicing strategy so as to obtain a plurality of slice contents;
the initial map construction module is used for constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points;
and the knowledge map generation module is used for analyzing the text content of the corresponding paragraph through the pre-trained generation type AI model so as to obtain and fill the analysis content into the initialization structure to generate a final knowledge map.
The system automatically analyzes the document catalogue through the cooperation of a plurality of modules such as a user uploading module, a document analyzing module, a slicing processing module, an initial map construction module, a knowledge map generation module and the like, generates a knowledge map by combining a generation type AI technology, and provides subsequent test question libraries and project management. In combination with the generation-type AI technique, the invention can generate the knowledge map with high recognition degree. The nodes in the knowledge map can accurately reflect the content and the structure in the document, so that a user can quickly understand the theme, the key points and the association relationship of the document. The automatic analysis of the document catalogue can greatly reduce the time and effort for manually arranging knowledge and improve the efficiency of knowledge arrangement. By combining the generation type AI technology, a knowledge map can be quickly generated, and the knowledge management efficiency is further improved. The AI technology plays an important role in the knowledge map generation process, reduces manual operation, improves the generation efficiency, and can also guarantee the accuracy and the integrity of the knowledge map to a certain extent.
In a third aspect, the present application provides an electronic device comprising a memory for storing one or more programs; a processor; the method of any of the first aspects described above is implemented when one or more programs are executed by a processor.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as in any of the first aspects described above.
The invention has at least the following advantages or beneficial effects:
1. the knowledge map is generated by automatically analyzing the document catalogue and combining the generation type AI technology, and the follow-up test question library and project management are provided for use.
2. By combining the generation type AI technology, the invention can generate the knowledge map with high recognition degree, and the nodes in the knowledge map can accurately reflect the content and the structure in the document, so that the user can quickly understand the theme, the key points and the association relationship of the document.
3. The automatic analysis of the document catalogue can greatly reduce the time and effort for manually arranging knowledge and improve the efficiency of knowledge arrangement; by combining the generation type AI technology, a knowledge map can be quickly generated, and the knowledge management efficiency is further improved.
4. The AI technology plays an important role in the knowledge map generation process, reduces manual operation, improves the generation efficiency, and can also guarantee the accuracy and the integrity of the knowledge map to a certain extent.
5. The user-defined editing and AI-aided knowledge map generation are supported, so that each user can customize the knowledge map according to own requirements, and the knowledge map generation method is more personalized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for automatically generating a knowledge map based on content of a generated AI, in accordance with an embodiment of the invention;
FIG. 2 is a schematic block diagram of a system for automatically generating knowledge maps based on content of a generated AI in accordance with an embodiment of the invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a knowledge map in an embodiment of the invention.
Reference numerals illustrate: 100. a user uploading module; 200. a document parsing module; 300. a slice processing module; 400. an initial map construction module; 500. a knowledge map generation module; 101. a memory; 102. a processor; 103. a communication interface.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. 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 apparatus that comprises the element.
In the description of the embodiments of the present invention, "plurality" means at least 2.
Examples:
As shown in fig. 1-2, in a first aspect, an embodiment of the present invention provides a method for automatically generating a knowledge map based on content of a generated AI, including the steps of:
S1, acquiring a document uploaded by a user;
S2, reading and analyzing document contents;
the method for analyzing the document content specifically comprises the following steps:
Step one: determining attachment formats
And determining the format of the attachment by intercepting the extension name in the URL according to the URL of the attachment. And acquiring the file type corresponding to the extension by utilizing the predefined format enumeration type.
Step two: reading attachment content
And according to the determined accessory format, adopting a corresponding method to read the accessory content. The specific implementation is as follows:
for RTF format attachments:
RTFEditorKit objects are created for processing documents in RTF format.
A DefaultStyledDocument object is created for storing the parsed document content.
The attachment content is read into DefaultStyledDocument using the read method of RTFEditorKit.
Text content in DefaultStyledDocument is converted to a string and returned. In the conversion process, a specific coding mode (such as ISO 8859_1) is adopted for coding conversion so as to ensure correct character display.
For DOC format attachments:
using HWPFDocument classes, the class is specific to handling Word 97-2003 (.doc) format documents.
The attachment content is loaded into the document by the constructor of HWPFDocument.
And calling getDocumentText a method, acquiring text content in the document, and returning.
For DOCX format attachments:
using XWPFDocument classes, the class is dedicated to handling Word 2007 and above version (.docx) format documents.
The attachment content is loaded into the document by the constructor of XWPFDocument.
XWPFWordExtractor objects are created for extracting text content in the document.
And calling a getText method, acquiring text content in the document, and returning.
For PDF format attachments:
Using PDDocument classes, the class is the core class in the Apache fbox library for processing PDF documents.
The attachment content is read as an array of bytes and the PDF document is loaded using the Loader's loadPDF method.
PDFTextStripper objects are created for extracting text content from the PDF document.
The getText method of PDFTextStripper is called, the text content in the PDF document is obtained, and returned.
S3, slicing the analyzed document content according to a preset text slicing strategy to obtain a plurality of sliced content;
S4, constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points; initializing structure of knowledge map: the tree structure knows the specific paragraph number and knowledge point number, but the names of the paragraphs and knowledge points are uncertain, and the text content of the corresponding paragraphs needs to be returned after being analyzed through an AI model and refilled. The initialization structure is not presented to the user, who will only see the knowledge map structure that is ultimately generated, as shown in fig. 4.
S5, analyzing the text content of the corresponding paragraph through a pre-trained generation type AI model to obtain and fill the analysis content into an initialization structure to generate a final knowledge map.
The user uploads the document in the appointed format through the document uploading module, the automatic analysis module reads and analyzes the document content, and the content slicing module performs slicing processing according to a preset strategy; then, the knowledge map generation service constructs the sliced content into an initialization structure of the AI knowledge map. Finally, the generated knowledge map can provide subsequent question bank management and project management use, and the knowledge can be effectively organized and utilized.
The invention automatically analyzes the document catalogue, and generates a knowledge map by combining the generation type AI technology, thereby providing the follow-up test question library and project management. In combination with the generation-type AI technique, the invention can generate the knowledge map with high recognition degree. The nodes in the knowledge map can accurately reflect the content and the structure in the document, so that a user can quickly understand the theme, the key points and the association relationship of the document. The automatic analysis of the document catalogue can greatly reduce the time and effort for manually arranging knowledge and improve the efficiency of knowledge arrangement. By combining the generation type AI technology, a knowledge map can be quickly generated, and the knowledge management efficiency is further improved. The AI technology plays an important role in the knowledge map generation process, reduces manual operation, improves the generation efficiency, and can also guarantee the accuracy and the integrity of the knowledge map to a certain extent.
The text slicing strategy described above is shown in table 1 below:
TABLE 1
Based on the first aspect, further, the text slicing strategy includes: and generating knowledge nodes with different numbers according to the word numbers of the document content, wherein the knowledge nodes comprise a plurality of knowledge node generation numbers corresponding to a plurality of word number ranges.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
and acquiring manual marking information and editing the knowledge map in a self-defined mode.
In some embodiments of the invention, a user may generate a map through AI, supporting editing on its basis; the user can also select a non-AI mode to generate, so that independent editing is allowed, and the adaptability is stronger and more flexible.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
And carrying out content recommendation and relationship analysis based on the generated AI model by combining the knowledge map edited by the user, and assisting the user in generating knowledge map nodes.
In some embodiments of the present invention, the user may also edit the knowledge map by customizing the manual tagging module, while the AI-assistance module provides intelligent content recommendation and relationship analysis to assist the user in generating knowledge map nodes. The invention supports user-defined editing and AI-aided generation of the knowledge map, so that each user can customize the knowledge map according to own requirements and has individuation. The method for editing the map comprises the following steps: each map node corresponds to the strategically-sliced text content, and the program obtains the content of the designated map node, combines the questioning templates, questions the AI model for auxiliary analysis and returns the results.
Based on the first aspect, the method for automatically generating the knowledge map based on the content of the generated AI further comprises the following steps:
and updating the document uploaded by the user according to the knowledge map.
Based on the first aspect, the method for updating the document uploaded by the user according to the knowledge map further comprises the following steps:
According to the corresponding map content nodes in the knowledge map, a third-party AI model is called in batches based on the AI-PaaS service, AI intelligent analysis is carried out, and node names and knowledge points are generated;
And warehousing the node names and the knowledge points, and updating the document.
In some embodiments of the present invention, an AI-PaaS service is provided that provides an interface function that invokes a third party AI model, performs AI intelligent analysis, generates node names and knowledge points, and persists the node names and knowledge points to a database, which may be mysql, mongodb.
As shown in fig. 2, in a second aspect, an embodiment of the present invention provides a system for automatically generating a knowledge map based on content of a generation AI, which includes a user uploading module 100, a document parsing module 200, a slice processing module 300, an initial map construction module 400, and a knowledge map generation module 500, wherein:
The user uploading module 100 is configured to obtain a document uploaded by a user;
the document parsing module 200 is used for reading and parsing document contents;
The slicing processing module 300 is configured to perform slicing processing on the parsed document content according to a preset text slicing policy, so as to obtain a plurality of slice contents;
An initial map construction module 400 for constructing a plurality of slice contents into an initialization structure of the AI knowledge map, the initialization structure including a number of paragraphs and a number of knowledge points;
The knowledge map generation module 500 is configured to parse text content of a corresponding paragraph through a pre-trained generated AI model, so as to obtain and fill the parsed content into an initialization structure, and generate a final knowledge map.
The system automatically analyzes the document catalogue through the cooperation of a plurality of modules such as the user uploading module 100, the document analyzing module 200, the slicing processing module 300, the initial map construction module 400, the knowledge map generation module 500 and the like, generates a knowledge map by combining the generation type AI technology, and provides the follow-up test question library and project management. In combination with the generation-type AI technique, the invention can generate the knowledge map with high recognition degree. The nodes in the knowledge map can accurately reflect the content and the structure in the document, so that a user can quickly understand the theme, the key points and the association relationship of the document. The automatic analysis of the document catalogue can greatly reduce the time and effort for manually arranging knowledge and improve the efficiency of knowledge arrangement. By combining the generation type AI technology, a knowledge map can be quickly generated, and the knowledge management efficiency is further improved. The AI technology plays an important role in the knowledge map generation process, reduces manual operation, improves the generation efficiency, and can also guarantee the accuracy and the integrity of the knowledge map to a certain extent.
As shown in fig. 3, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The method of any of the first aspects described above is implemented when one or more programs are executed by the processor 102.
And a communication interface 103, where the memory 101, the processor 102 and the communication interface 103 are electrically connected directly or indirectly to each other to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules that are stored within the memory 101 for execution by the processor 102 to perform various functional applications and data processing. The communication interface 103 may be used for communication of signaling or data with other node devices.
The Memory 101 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system may be implemented in other manners. The above-described method and system embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by the processor 102, implements a method as in any of the first aspects described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (9)
1. A method for automatically generating a knowledge map based on content of a generated AI, comprising the steps of:
acquiring a document uploaded by a user;
reading and analyzing document content;
slicing the parsed document content according to a preset text slicing strategy to obtain a plurality of sliced content;
Constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points;
Analyzing text content of a corresponding paragraph through a pre-trained generation type AI model to obtain and fill the analysis content into an initialization structure to generate a final knowledge map.
2. The method for automatically generating a knowledge map based on content of a generated AI of claim 1, wherein the text slicing strategy comprises: and generating knowledge nodes with different numbers according to the word numbers of the document content, wherein the knowledge nodes comprise a plurality of knowledge node generation numbers corresponding to a plurality of word number ranges.
3. The method for automatically generating a knowledge map based on content of a generated AI of claim 1, further comprising the steps of:
and acquiring manual marking information and editing the knowledge map in a self-defined mode.
4. The method for automatically generating a knowledge map based on content of a generated AI as set forth in claim 3, further comprising the steps of:
And carrying out content recommendation and relationship analysis based on the generated AI model by combining the knowledge map edited by the user, and assisting the user in generating knowledge map nodes.
5. The method for automatically generating a knowledge map based on content of a generated AI of claim 1, further comprising the steps of:
and updating the document uploaded by the user according to the knowledge map.
6. The method for automatically generating a knowledge map based on content of a generated AI of claim 5, wherein the method for updating a document uploaded by a user based on the knowledge map comprises the steps of:
According to the corresponding map content nodes in the knowledge map, a third-party AI model is called in batches based on the AI-PaaS service, AI intelligent analysis is carried out, and node names and knowledge points are generated;
And warehousing the node names and the knowledge points, and updating the document.
7. The system for automatically generating the knowledge map based on the content of the generated AI is characterized by comprising a user uploading module, a document analyzing module, a slicing processing module, an initial map constructing module and a knowledge map generating module, wherein:
the user uploading module is used for acquiring the document uploaded by the user;
The document analysis module is used for reading and analyzing the document content;
the slicing processing module is used for slicing the analyzed document content according to a preset text slicing strategy so as to obtain a plurality of slice contents;
the initial map construction module is used for constructing a plurality of slice contents into an initialization structure of the AI knowledge map, wherein the initialization structure comprises the number of paragraphs and the number of knowledge points;
and the knowledge map generation module is used for analyzing the text content of the corresponding paragraph through the pre-trained generation type AI model so as to obtain and fill the analysis content into the initialization structure to generate a final knowledge map.
8. An electronic device, comprising:
A memory for storing one or more programs;
A processor;
the method of any of claims 1-6 is implemented when the one or more programs are executed by the processor.
9. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410556151.9A CN118468994A (en) | 2024-05-07 | 2024-05-07 | Method and system for automatically generating knowledge map based on content of generated AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410556151.9A CN118468994A (en) | 2024-05-07 | 2024-05-07 | Method and system for automatically generating knowledge map based on content of generated AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118468994A true CN118468994A (en) | 2024-08-09 |
Family
ID=92154103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410556151.9A Pending CN118468994A (en) | 2024-05-07 | 2024-05-07 | Method and system for automatically generating knowledge map based on content of generated AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118468994A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119557427A (en) * | 2025-01-25 | 2025-03-04 | 深圳市金政软件技术有限公司 | Data slicing method, system, device and storage medium |
-
2024
- 2024-05-07 CN CN202410556151.9A patent/CN118468994A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119557427A (en) * | 2025-01-25 | 2025-03-04 | 深圳市金政软件技术有限公司 | Data slicing method, system, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7673235B2 (en) | Method and apparatus for utilizing an object model to manage document parts for use in an electronic document | |
| CN113609820A (en) | Method, device and equipment for generating word file based on extensible markup language file | |
| CN110737630B (en) | Method and device for processing electronic archive file, computer equipment and storage medium | |
| CN110347984B (en) | Policy page changing method and device, computer equipment and storage medium | |
| US20150106928A1 (en) | Screening of email templates in campaign management | |
| CN112527291A (en) | Webpage generation method and device, electronic equipment and storage medium | |
| CN113723063B (en) | Method for converting RTF (real time transport format) into HTML (hypertext markup language) and realizing effect in PDF (portable document format) file | |
| CN118468994A (en) | Method and system for automatically generating knowledge map based on content of generated AI | |
| CN115630618A (en) | Intelligent scene editing method, system, equipment and medium for PDF document | |
| CN112785284B (en) | Message warehousing method and device based on structured document | |
| CN113779953A (en) | Automatic document generation method and system | |
| CN112328246A (en) | Page component generation method and device, computer equipment and storage medium | |
| CN115796146A (en) | File comparison method and device | |
| CN113435178A (en) | Document analysis method and device | |
| CN118013094A (en) | Unstructured index evaluation data processing method, system and equipment | |
| CN111401005B (en) | Text conversion method, device and readable storage medium | |
| US11941350B2 (en) | Systems and methods for conversion of documents to reusable content types | |
| CN116911274A (en) | Structured document automatic generation method, device and storage medium | |
| CN115841095A (en) | Document establishing method, system, medium and equipment | |
| CN110727458A (en) | Method and device for switching page template settings through background management | |
| KR100762712B1 (en) | Rule based electronic document conversion method and system | |
| CN115934098A (en) | Object model configuration method and device and computer readable storage medium | |
| CN116227454A (en) | Universal automatic report generation method and system | |
| CN111325007B (en) | Comment analysis method and terminal for PPTX file | |
| CN114169306A (en) | A method, apparatus, device and readable storage medium for generating an electronic receipt |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |