CN117609509A - Automatic device, method and storage medium for knowledge carding and conflict resolution - Google Patents

Automatic device, method and storage medium for knowledge carding and conflict resolution Download PDF

Info

Publication number
CN117609509A
CN117609509A CN202311565227.6A CN202311565227A CN117609509A CN 117609509 A CN117609509 A CN 117609509A CN 202311565227 A CN202311565227 A CN 202311565227A CN 117609509 A CN117609509 A CN 117609509A
Authority
CN
China
Prior art keywords
sentences
sentence
database
source
language model
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
Application number
CN202311565227.6A
Other languages
Chinese (zh)
Inventor
奚霄鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Shuheng Information Technology Co ltd
Original Assignee
Shanghai Shuheng Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Shuheng Information Technology Co ltd filed Critical Shanghai Shuheng Information Technology Co ltd
Priority to CN202311565227.6A priority Critical patent/CN117609509A/en
Publication of CN117609509A publication Critical patent/CN117609509A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • 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
    • G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G06N5/022—Knowledge engineering; Knowledge acquisition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to an automatic device, a method and a storage medium for knowledge carding and conflict resolution, wherein the device comprises the following components: the data preprocessing and vectorizing unit is used for preprocessing and vectorizing all sentences in the system and storing the sentences into the vector database; the similar sentence searching unit is used for searching out a history sentence which is closest to the source sentence semantically when a new source sentence is input; the language model judging unit is used for inputting the source sentences and the retrieved similar sentences into the pre-training language model and judging the common theme category and semantic contradiction degree; the database storage unit is used for storing the source sentences, the corresponding similar sentences, the topic labels judged by the language model and the contradiction judgment results into the database in a lasting mode; compared with the prior art, the method can effectively identify and search the historical sentences with high semantic relevance with the source sentences, remarkably improve the search precision and enhance the decision support capability.

Description

Automatic device, method and storage medium for knowledge carding and conflict resolution
[ technical field ]
The invention relates to the technical field of large-scale data processing, in particular to an automatic device, a method and a storage medium for knowledge carding and conflict resolution.
[ background Art ]
In the prior art, knowledge combing and conflict resolution are mainly performed by manpower. In general, individuals or teams read a large amount of literature data, screen important information, make relevant knowledge maps, and further find conflicts or vulnerabilities. However, this method has the following significant problems and disadvantages:
(1) The information processing efficiency is low: for large complex knowledge bases, the reading and screening requires a lot of manpower and time, and especially for some complex and intersecting fields, the efficiency of this method is more questionable.
(2) Differences in knowledge background and cognitive abilities of individuals or teams may lead to deviations in understanding, such that learning is not comprehensive and may be biased.
(3) Conflict resolution generally requires deep understanding of the inherent logic of each part of knowledge, and conflicts of different knowledge may require deep comparison and analysis, which is a task that requires both expertise and logic analysis capability; however, in practice both the knowledge limits of the individual and the team's collaborative capabilities may lead to the process being fraught with difficulties.
(4) The manual knowledge combing and conflict resolution cannot adapt to the daily and monthly knowledge updating speed, so that the information quantity is rapidly increased, the new knowledge can not be processed in time, and the possible conflict between the prior knowledge and the prior knowledge is difficult and serious.
Therefore, the prior art obviously has the problems of low efficiency, low precision, difficult conflict processing, poor adaptability and the like for the knowledge conflict resolution for processing a large amount of knowledge and fast iterative updating. It would be of great importance if an apparatus and method could be devised that could automate knowledge comb and conflict resolution in view of the above problems.
[ summary of the invention ]
The invention aims to solve the defects and provide an automatic device for knowledge combing and conflict resolution, which can effectively identify and search out historical sentences with high semantic relevance with source sentences, remarkably improve the search precision, effectively help users understand and analyze sentences, enhance the decision support capability and improve the working efficiency and adaptability.
In one aspect of the present invention, an automated device for knowledge manipulation and conflict resolution is provided, comprising:
the data preprocessing and vectorizing unit is used for preprocessing and vectorizing all sentences in the system and storing the sentences into the vector database;
the similar sentence searching unit is used for searching out a history sentence which is closest to the source sentence semantically when a new source sentence is input;
the language model judging unit is used for inputting the source sentences and the retrieved similar sentences into the pre-training language model and judging the common theme category and semantic contradiction degree;
the database storage unit is used for storing the source sentences, the corresponding similar sentences, the topic labels judged by the language model and the contradiction judgment results into the database in a lasting mode.
As an embodiment, the preprocessing of the data preprocessing and vectorizing unit includes denoising and part-of-speech tagging, and then the context embedding model is used to convert the semantics of all sentences into numerical vectors and store the numerical vectors in a vector database.
As an embodiment, the similar sentence searching unit uses a cosine similarity method to search a history sentence which is semantically closest to the source sentence from a vector database according to the semantic vector of the sentence.
As an embodiment, the system further comprises a user query unit, configured to query the database by a user, and obtain information such as topic category of the sentence, related similar sentences, and whether there is a semantic contradiction.
In another aspect of the present invention, a method for knowledge manipulation and conflict resolution is provided, comprising the steps of: firstly, preprocessing all sentences in a system, vectorizing and storing the sentences into a vector database; when a new source sentence is input, searching a semantically closest historical sentence; then, putting the source sentences and the retrieved sentences into a pre-training language model, and judging the common theme category and semantic contradiction degree; finally, the information is stored in a database for users to inquire.
As an embodiment, the method for knowledge combing and conflict resolution comprises the following steps:
1) Data preprocessing and vectorization: preprocessing all sentences in the system, vectorizing, and storing the sentences into a vector database;
2) Searching similar sentences: when a new source sentence is input, according to the semantic vector of the sentence, a cosine similarity method is used for retrieving a historical sentence which is closest to the source sentence in terms of semantics from a vector database;
3) Judging a language model: inputting the source sentences and the retrieved similar sentences into a pre-training language model;
4) And (3) storing a database: the source sentences and the corresponding similar sentences are stored in a database in a lasting mode through the topic labels judged by the language model and the contradiction judgment results;
5) User query: and the user acquires the topic category of the sentence, related similar sentences, whether semantic contradiction exists or not and other information by querying the database.
As an embodiment, in step 1), the preprocessing includes denoising and part-of-speech tagging, and then the semantics of all sentences are converted into numerical vectors using a context embedding model and stored in a vector database.
As an embodiment, in the pre-training language model of step 3), the first model is used for labeling which category or topic the source sentence and the retrieved similar sentence belong together, and the second model is used for judging whether there is a contradiction or conflict between the two sentences semantically.
In a third aspect of the present invention, a computer-readable storage medium is presented, the computer-readable storage medium comprising a stored program, the program performing the above-described method.
In a fourth aspect, the present invention provides a computer device, comprising: a processor, a memory, and a bus; the processor is connected with the memory through the bus; the memory is used for storing a program, and the processor is used for running the program, and the program runs to execute the method.
Compared with the prior art, the invention has the following advantages:
(1) And (3) improving the retrieval precision: by means of semantic vectorization, the method and the device can effectively identify and search the historical sentences with high semantic relevance with the source sentences, and remarkably improve the accuracy of an information retrieval system.
(2) Dynamically updating: the invention adopts an online learning mode, when a new sentence is input, the system can automatically update the knowledge base and the knowledge map, and the real-time performance of the system is improved.
(3) Enhancing decision making capability: the invention judges the category and contradiction of sentences by using the pre-training language model, thereby effectively helping users understand and analyze sentences and enhancing the decision support capability.
(4) Large scale throughput: the invention can effectively process and analyze large-scale text data, has high expansibility and adaptability, and can cope with challenges in a big data environment.
(5) The method is widely applied: the invention can be widely applied to tasks such as information retrieval, text classification, semantic analysis and the like, and the practicability and the working efficiency are improved.
[ description of the drawings ]
FIG. 1 is a schematic diagram of the principles of the present invention;
FIG. 2 is a diagram of the method steps of the present invention;
FIG. 3 is a schematic view of the apparatus of the present invention;
fig. 4 is a schematic structural diagram of a computer device in the present invention.
Detailed description of the preferred embodiments
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the invention. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described below with reference to the accompanying drawings and specific embodiments:
as shown in the accompanying drawings, the invention provides a method for knowledge combing and conflict resolution, which comprises the following steps: firstly, preprocessing all sentences in a system, vectorizing and storing the sentences into a vector database; when a new source sentence is input, searching a semantically closest historical sentence; then, putting the source sentences and the retrieved sentences into a pre-training language model, and judging the common theme category and semantic contradiction degree; finally, the information is stored in a database for users to inquire.
The invention provides a knowledge graph technical scheme based on a large-scale pre-training language model and a vector database, wherein the system compares the similarity between an input source sentence and a historical sentence stored in the database, further compares the classification and cooperativity of the sentences through the language model, forms a structured knowledge graph and stores related information in a lasting manner for subsequent inquiry.
In other embodiments, the method for knowledge combing and conflict resolution specifically comprises the following steps:
1) Data preprocessing and vectorization: preprocessing all sentences in the system, including denoising, part-of-speech tagging and the like; the context embedding model is then used to convert the semantics of all sentences into numerical vectors and store them in a vector database.
2) Searching similar sentences: when a new source sentence is input, according to the semantic vector of the sentence, a historical sentence which is closest to the source sentence semantically is searched from a vector database by using a cosine similarity method and the like.
3) Judging a language model: inputting the source sentences and the retrieved similar sentences into a pre-training language model; the task of the first model is to annotate which category or topic the two sentences belong together; the second model is used to determine whether there is a semantic contradiction or conflict between the two sentences.
4) And (3) storing a database: and storing the source sentences and the corresponding similar sentences thereof into a database in a lasting manner through the topic labels judged by the language model and the contradiction judgment results.
5) User query: the user can obtain the topic category of the sentence, related similar sentences, whether semantic contradiction exists or not and other information by querying the database.
In still other embodiments, the present invention provides an automated apparatus for knowledge grooming and conflict resolution, comprising:
the data preprocessing and vectorizing unit is used for preprocessing and vectorizing all sentences in the system and storing the sentences into the vector database;
the similar sentence searching unit is used for searching out a history sentence which is closest to the source sentence semantically when a new source sentence is input;
the language model judging unit is used for inputting the source sentences and the retrieved similar sentences into the pre-training language model and judging the common theme category and semantic contradiction degree;
the database storage unit is used for storing the source sentences, the corresponding similar sentences, the topic labels judged by the language model and the contradiction judgment results into the database in a lasting mode;
the user inquiry unit is used for users to inquire the database and acquire the information such as the topic category of sentences, related similar sentences, whether semantic contradiction exists or not and the like.
As a further embodiment, in the data preprocessing and vectorization unit, the preprocessing includes denoising and part-of-speech tagging, and then the semantics of all sentences are converted into numerical vectors using a context embedding model and stored in a vector database. In the similar sentence searching unit, according to the semantic vector of the sentence, a cosine similarity method is used to search the historical sentence which is closest to the source sentence in terms of semantics from a vector database.
The invention solves some challenges of traditional knowledge graph construction, such as processing large-scale text data, realizing accurate semantic matching, dynamically updating knowledge graph and the like. In addition, the method can be widely applied to tasks such as information retrieval, text classification, semantic analysis and the like.
The invention is further described in connection with a specific example as follows:
suppose that the news portal receives a news story a on the first day: "conflict in north of a country, government army successfully driven against government armed forces". The system firstly carries out preprocessing and vectorization on the news to obtain semantic vectors of the article A and stores the semantic vectors into a vector database.
The next day, the web site receives another report B: "the same place is successfully countered against the government's arming, and the government's army is driven. And in the same step, the system preprocesses and vectorizes the news B and stores the news B into a vector library.
The system then compares report B to all the historical news semantic vectors in the vector database, finding that news a's semantic vector is very close to news B. Thus, the system fetches news a as a similar article.
The system then delivers news a and news B together into two pre-trained language models for processing. The first model predicts that news a and news B both belong to the category of "military conflict", and the second model verifies that there is a semantic conflict between news a and news B.
Finally, all information is recorded in the database, e.g., news B's related article is news a, both belonging to the "military conflict" category, but there is a significant contradiction between the two articles. The website administrator may obtain this information from the database for further review and processing.
In still other embodiments, FIG. 4 is a schematic diagram of a computer device of the present invention. The computer device includes a processor, a memory, and a bus; the processor is connected with the memory through a bus, the memory is used for storing a program, and the processor is used for running the program and executing the knowledge combing and conflict resolving method provided by the invention when the program runs. Further, the invention also provides a computer readable storage medium, the computer readable storage medium comprises a stored program, and the program executes the knowledge carding and conflict resolution method provided by the invention.
The computer equipment can be desktop computers, notebooks, palm computers, cloud servers and other computing equipment. It will be appreciated by those skilled in the art that fig. 4 is merely an example of a computer device and is not intended to limit the computer device, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., a computer device may also include an input-output device, a network access device, a bus, etc.
The processor may be a central processing unit CPU, or may be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor may be a microprocessor or any conventional processor or the like, which is a control center of the computer device, and which connects various parts of the entire computer device using various interfaces and lines.
The memory may be used to store computer programs and/or modules/units and the processor may perform various functions of the computer device by executing or executing the computer programs and/or modules/units stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer device (such as audio data, phonebooks, etc.), and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card SMC, secure digital SD card, flash memory card, at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The functions of the methods of the embodiments of the present invention, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer device readable storage medium. Based on such understanding, a part of the present invention that contributes to the prior art or a part of the technical solution may be embodied 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 mobile computing device or a network device, etc.) to perform all or part of the steps of the method described in the various embodiments of the present invention; the storage medium includes various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limited thereto; the technical features of the above embodiments or in different embodiments may also be combined under the idea of the invention, the steps may be implemented in any order, and many other variations exist in different aspects of the invention as described above; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.
The present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principles of the invention should be made in the equivalent manner and are included in the scope of the invention.

Claims (10)

1. An automated device for knowledge manipulation and conflict resolution, comprising:
data preprocessing and vectorizing unit: all sentences in the system are preprocessed and vectorized, and are stored in a vector database;
a similar sentence searching unit: the method is used for searching out a history sentence which is closest to the source sentence semantically when a new source sentence is input;
language model judging unit: the method comprises the steps of inputting a source sentence and a retrieved similar sentence into a pre-training language model, and judging the common theme category and semantic contradiction degree;
a database storage unit: and the method is used for storing the source sentences, the similar sentences corresponding to the source sentences, the topic labels judged by the language model and the contradiction judgment results into a database in a lasting manner.
2. The apparatus of claim 1, wherein: in the data preprocessing and vectorizing unit, preprocessing comprises denoising and part-of-speech tagging, and then the semantics of all sentences are converted into numerical vectors by using a context embedding model and stored in a vector database.
3. The apparatus of claim 1, wherein: in the similar sentence searching unit, according to the semantic vector of the sentence, a cosine similarity method is used for searching a historical sentence which is closest to the source sentence in terms of semantics from a vector database.
4. The apparatus of claim 1, wherein: the system also comprises a user query unit which is used for users to query the database and obtain the information such as the topic category of sentences, related similar sentences, whether semantic contradiction exists or not and the like.
5. A method for knowledge grooming and conflict resolution comprising the steps of: firstly, preprocessing all sentences in a system, vectorizing and storing the sentences into a vector database; when a new source sentence is input, searching a semantically closest historical sentence; then, putting the source sentences and the retrieved sentences into a pre-training language model, and judging the common theme category and semantic contradiction degree; finally, the information is stored in a database for users to inquire.
6. The method of claim 5, comprising the steps of:
1) Data preprocessing and vectorization: preprocessing all sentences in the system, vectorizing, and storing the sentences into a vector database;
2) Searching similar sentences: when a new source sentence is input, according to the semantic vector of the sentence, a cosine similarity method is used for retrieving a historical sentence which is closest to the source sentence in terms of semantics from a vector database;
3) Judging a language model: inputting the source sentences and the retrieved similar sentences into a pre-training language model;
4) And (3) storing a database: the source sentences and the corresponding similar sentences are stored in a database in a lasting mode through the topic labels judged by the language model and the contradiction judgment results;
5) User query: and the user acquires the topic category of the sentence, related similar sentences, whether semantic contradiction exists or not and other information by querying the database.
7. The method of claim 6, wherein: in the step 1), preprocessing comprises denoising and part-of-speech tagging, and then the semantics of all sentences are converted into numerical vectors by using a context embedding model and stored in a vector database.
8. The method of claim 6, wherein: in the pre-training language model of the step 3), the first model is used for marking which category or topic the source sentence and the retrieved similar sentence belong to together, and the second model is used for judging whether the two sentences have contradiction or conflict semantically.
9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program that performs the method of any one of claims 5 to 8.
10. A computer device, comprising: a processor, a memory, and a bus; the processor is connected with the memory through the bus; the memory is for storing a program, the processor is for running the program, which when run performs the method of any one of claims 5 to 8.
CN202311565227.6A 2023-11-22 2023-11-22 Automatic device, method and storage medium for knowledge carding and conflict resolution Pending CN117609509A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311565227.6A CN117609509A (en) 2023-11-22 2023-11-22 Automatic device, method and storage medium for knowledge carding and conflict resolution

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311565227.6A CN117609509A (en) 2023-11-22 2023-11-22 Automatic device, method and storage medium for knowledge carding and conflict resolution

Publications (1)

Publication Number Publication Date
CN117609509A true CN117609509A (en) 2024-02-27

Family

ID=89943550

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311565227.6A Pending CN117609509A (en) 2023-11-22 2023-11-22 Automatic device, method and storage medium for knowledge carding and conflict resolution

Country Status (1)

Country Link
CN (1) CN117609509A (en)

Similar Documents

Publication Publication Date Title
US9418144B2 (en) Similar document detection and electronic discovery
CN107491518B (en) Search recall method and device, server and storage medium
CN108932294B (en) Resume data processing method, device, equipment and storage medium based on index
US9471874B2 (en) Mining forums for solutions to questions and scoring candidate answers
US11651014B2 (en) Source code retrieval
CN111797214A (en) FAQ database-based problem screening method and device, computer equipment and medium
CN109783631B (en) Community question-answer data verification method and device, computer equipment and storage medium
Elliott Survey of author name disambiguation: 2004 to 2010
US20220342950A1 (en) System and method for searching based on text blocks and associated search operators
CN114722137A (en) Security policy configuration method and device based on sensitive data identification and electronic equipment
CN111353005A (en) Drug research and development reporting document management method and system
Owen et al. Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections.
CN110895587B (en) Method and device for determining target user
CN117421333A (en) Enterprise document library construction and retrieval method and system
CN112035723A (en) Resource library determination method and device, storage medium and electronic device
US9342809B2 (en) Method and apparatus to populate asset variant relationships in repositories
CN111859042A (en) Retrieval method and device and electronic equipment
US20210034704A1 (en) Identifying Ambiguity in Semantic Resources
CN117609509A (en) Automatic device, method and storage medium for knowledge carding and conflict resolution
CN114328844A (en) Text data set management method, device, equipment and storage medium
CN114139530A (en) Synonym extraction method and device, electronic equipment and storage medium
CN113627161A (en) Data processing method and device, storage medium and electronic equipment
CN113761213A (en) Data query system and method based on knowledge graph and terminal equipment
US20240220528A1 (en) System and method for generating ontologies for enhanced search
CN118503454B (en) Data query method, device, storage medium and computer program product

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