CN117609460A - Intelligent question-answering method and device based on keyword semantic decomposition - Google Patents
Intelligent question-answering method and device based on keyword semantic decomposition Download PDFInfo
- Publication number
- CN117609460A CN117609460A CN202311615794.8A CN202311615794A CN117609460A CN 117609460 A CN117609460 A CN 117609460A CN 202311615794 A CN202311615794 A CN 202311615794A CN 117609460 A CN117609460 A CN 117609460A
- Authority
- CN
- China
- Prior art keywords
- keywords
- question
- answers
- model
- recall
- 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 42
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 31
- 238000004590 computer program Methods 0.000 claims description 12
- 239000004816 latex Substances 0.000 claims description 4
- 229920000126 latex Polymers 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000011218 segmentation Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and particularly provides an intelligent question-answering method and device based on keyword semantic decomposition, comprising the following steps: inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model; obtaining recall answers corresponding to the keywords from the text information index library; respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting the recall answers with the similarity larger than a preset value as answers of the keywords; and taking answers of the user question and the keywords as input of the automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model. The technical scheme provided by the invention can enable the question of the user to realize the meaning segmentation of the key words of the question and ensure the recall effect.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent question-answering method and device based on keyword semantic decomposition.
Background
With the advance of the information age, a large number of digital documents are accumulated inside enterprises, and the documents contain rich information. To better manage and utilize these documents, it is common to categorize them in a labeled manner, while using a search engine for content retrieval. However, the conventional document searching method is often limited to keyword or phrase query, and is difficult to realize higher-level semantic retrieval, and cannot meet the requirement of users for deeply understanding document contents.
With the advent of ChatGPT, significant progress was made in the field of natural language processing, particularly with the capabilities of semantic understanding, document summarization, information extraction, and logical reasoning. In the intelligent dialogue, the large model can accurately understand the demand points of the user, so that an open type best answer is given. However, in the question and answer in the professional field, the technology using only a large model mainly has the following problems: 1 when professional field information is in certain documents, the answer effect of a large model is poor; 2. in the document-based question-and-answer, when a user question contains a plurality of keywords, the answers of the user question are possibly distributed in various parts of the document in a broken chain mode, and if the original question is used for recalling text, few recalls are performed in the professional field; 3. the text structure and text information of the question and document recall result are different, so that the similarity is low, and the information is lost.
Disclosure of Invention
In order to overcome the defects, the invention provides an intelligent question-answering method and device based on keyword semantic decomposition.
In a first aspect, an intelligent question-answering method based on keyword semantic decomposition is provided, where the intelligent question-answering method based on keyword semantic decomposition includes:
inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
obtaining recall answers corresponding to the keywords from the text information index library;
respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
and taking the answers of the user question and the keywords as the input of an automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model.
Preferably, the training process of the pre-trained keyword extraction model includes:
acquiring preset keywords, and combining the preset keywords with a preset user question template to obtain training data;
and training the Bert-bilstm-crf model by using the training data to obtain the pre-trained keyword extraction model.
Further, the preset keywords include: term definitions and terms.
Preferably, the obtaining the recall answer corresponding to the keyword in the text information index library includes:
and constructing a text information index library by using the text documents.
Further, before the text information index library is constructed by using the text document, the method comprises the following steps:
analyzing the text document;
integrating the head of the enumeration in the text document and the enumeration item into a whole content;
and merging the attached table information in the text document with the text information referencing the attached table information in the document file.
Further, the parsing the text document includes:
analyzing a table in a text document into a markdown format, and analyzing a formula into a latex format;
and removing the cover, the header page and the watermark in the text document.
Preferably, the training process of the pre-trained similarity recognition model includes:
taking the title of the text document as a simulated question sentence, taking the text content under the title as a recall answer set, and constructing training data;
and training the coset model by using the training data to obtain the pre-trained similarity recognition model.
Preferably, the automatic summary analysis model is a chatglm2-6b model.
In a second aspect, an intelligent question-answering device based on keyword semantic decomposition is provided, where the intelligent question-answering device based on keyword semantic decomposition includes:
the first analysis module is used for inputting a user question into the pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
the obtaining module is used for obtaining recall answers corresponding to the keywords from the text information index library;
the second analysis module is used for respectively forming question-answer pairs from the keywords and the corresponding recall answers thereof and taking the question-answer pairs as input of a pre-trained similarity recognition model to obtain the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
and the third analysis module is used for taking the user question and the answers of the keywords as the input of the automatic summarization analysis model to obtain the user question answer result output by the automatic summarization analysis model.
In a third aspect, there is provided a computer device comprising: one or more processors;
the processor is used for storing one or more programs;
when the one or more programs are executed by the one or more processors, the intelligent question-answering method based on keyword semantic decomposition is implemented.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored, the computer program, when executed, implementing the intelligent question-answering method based on keyword semantic decomposition.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
the invention relates to the technical field of artificial intelligence, and particularly provides an intelligent question-answering method and device based on keyword semantic decomposition, comprising the following steps: inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model; obtaining recall answers corresponding to the keywords from the text information index library; respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords; and taking the answers of the user question and the keywords as the input of an automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model. The keyword extraction model in the technical scheme provided by the invention can identify a plurality of keywords, solves the problem that a plurality of keywords exist in question sentences in the question-answering of a large model document, cannot locate a plurality of question answers in document recall, and ensures recall effect.
Drawings
Fig. 1 is a schematic flow chart of main steps of an intelligent question-answering method based on keyword semantic decomposition according to an embodiment of the present invention.
Detailed Description
The following describes the embodiments of the present invention in further detail with reference to the drawings.
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. 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.
As disclosed in the background art, with the advancement of the information age, enterprises have accumulated a large number of digital documents that contain rich information. To better manage and utilize these documents, it is common to categorize them in a labeled manner, while using a search engine for content retrieval. However, the conventional document searching method is often limited to keyword or phrase query, and is difficult to realize higher-level semantic retrieval, and cannot meet the requirement of users for deeply understanding document contents.
With the advent of ChatGPT, significant progress was made in the field of natural language processing, particularly with the capabilities of semantic understanding, document summarization, information extraction, and logical reasoning. In the intelligent dialogue, the large model can accurately understand the demand points of the user, so that an open type best answer is given. However, in the question and answer in the professional field, the technology using only a large model mainly has the following problems: 1 when professional field information is in certain documents, the answer effect of a large model is poor; 2. in the document-based question-and-answer, when a user question contains a plurality of keywords, the answers of the user question are possibly distributed in various parts of the document in a broken chain mode, and if the original question is used for recalling text, few recalls are performed in the professional field; 3. the text structure and text information of the question and document recall result are different, so that the similarity is low, and the information is lost.
In order to improve the problems, the invention relates to the technical field of artificial intelligence, and particularly provides an intelligent question-answering method and device based on keyword semantic decomposition, comprising the following steps: inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model; obtaining recall answers corresponding to the keywords from the text information index library; respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords; and taking the answers of the user question and the keywords as the input of an automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model. The keyword extraction model in the technical scheme provided by the invention can identify a plurality of keywords, solves the problem that a plurality of keywords exist in question sentences in the question-answering of a large model document, cannot locate a plurality of question answers in document recall, and ensures recall effect.
The above-described scheme is explained in detail below.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of an intelligent question-answering method based on keyword semantic decomposition according to an embodiment of the present invention. As shown in fig. 1, the intelligent question-answering method based on keyword semantic decomposition in the embodiment of the invention mainly comprises the following steps:
step S101: inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
step S102: obtaining recall answers corresponding to the keywords from the text information index library;
step S103: respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
step S104: and taking the answers of the user question and the keywords as the input of an automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model.
In this embodiment, the training process of the pre-trained keyword extraction model includes:
acquiring preset keywords, and combining the preset keywords with a preset user question template to obtain training data;
and training the Bert-bilstm-crf model by using the training data to obtain the pre-trained keyword extraction model.
Wherein, the preset keywords comprise: term definitions and terms.
In this embodiment, the number of keywords output by the keyword extraction model that is trained in advance may be plural;
in this embodiment, the obtaining recall answers corresponding to the keywords in the text information index library includes:
and constructing a text information index library by using the text documents.
In one embodiment, before the text information index base is constructed by using the text document, the method comprises the following steps:
analyzing the text document;
integrating the head of the enumeration in the text document and the enumeration item into a whole content;
and merging the attached table information in the text document with the text information referencing the attached table information in the document file.
In one embodiment, the parsing the text document includes:
analyzing a table in a text document into a markdown format, and analyzing a formula into a latex format;
and removing the cover, the header page and the watermark in the text document.
In this embodiment, the training process of the pre-trained similarity recognition model includes:
taking the title of the text document as a simulated question sentence, taking the text content under the title as a recall answer set, and constructing training data;
and training the coset model by using the training data to obtain the pre-trained similarity recognition model.
In this embodiment, the automatic summary analysis model is a chatglm2-6b model.
Example 2
Based on the same inventive concept, the invention also provides an intelligent question-answering device based on keyword semantic decomposition, which comprises:
the first analysis module is used for inputting a user question into the pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
the obtaining module is used for obtaining recall answers corresponding to the keywords from the text information index library;
the second analysis module is used for respectively forming question-answer pairs from the keywords and the corresponding recall answers thereof and taking the question-answer pairs as input of a pre-trained similarity recognition model to obtain the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
and the third analysis module is used for taking the user question and the answers of the keywords as the input of the automatic summarization analysis model to obtain the user question answer result output by the automatic summarization analysis model.
Preferably, the training process of the pre-trained keyword extraction model includes:
acquiring preset keywords, and combining the preset keywords with a preset user question template to obtain training data;
and training the Bert-bilstm-crf model by using the training data to obtain the pre-trained keyword extraction model.
Further, the preset keywords include: term definitions and terms.
Preferably, the obtaining the recall answer corresponding to the keyword in the text information index library includes:
and constructing a text information index library by using the text documents.
Further, before the text information index library is constructed by using the text document, the method comprises the following steps:
analyzing the text document;
integrating the head of the enumeration in the text document and the enumeration item into a whole content;
and merging the attached table information in the text document with the text information referencing the attached table information in the document file.
Further, the parsing the text document includes:
analyzing a table in a text document into a markdown format, and analyzing a formula into a latex format;
and removing the cover, the header page and the watermark in the text document.
Preferably, the training process of the pre-trained similarity recognition model includes:
taking the title of the text document as a simulated question sentence, taking the text content under the title as a recall answer set, and constructing training data;
and training the coset model by using the training data to obtain the pre-trained similarity recognition model.
Preferably, the automatic summary analysis model is a chatglm2-6b model.
Example 3
Based on the same inventive concept, the invention also provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application SpecificIntegrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular to load and execute one or more instructions in a computer storage medium to implement the corresponding method flow or corresponding functions, to implement the steps of an intelligent question-answering method based on keyword semantic decomposition in the above embodiments.
Example 4
Based on the same inventive concept, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a computer device, for storing programs and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the steps of an intelligent question-answering method based on keyword semantic decomposition in the above embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. An intelligent question-answering method based on keyword semantic decomposition is characterized by comprising the following steps:
inputting a user question into a pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
obtaining recall answers corresponding to the keywords from the text information index library;
respectively forming question-answer pairs by the keywords and the corresponding recall answers thereof, inputting the question-answer pairs as a pre-trained similarity recognition model, obtaining the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
and taking the answers of the user question and the keywords as the input of an automatic summarization analysis model to obtain a user question answer result output by the automatic summarization analysis model.
2. The method of claim 1, wherein the training process of the pre-trained keyword extraction model comprises:
acquiring preset keywords, and combining the preset keywords with a preset user question template to obtain training data;
training a Bert-bilstm-crf model by using the training data to obtain the pre-trained keyword extraction model;
the preset keywords include: term definitions and terms.
3. The method of claim 1, wherein the obtaining recall answers corresponding to the keywords in the text information index base comprises, before:
and constructing a text information index library by using the text documents.
4. The method of claim 3, wherein prior to constructing the text information index base using the text document, comprising:
analyzing the text document;
integrating the head of the enumeration in the text document and the enumeration item into a whole content;
and merging the attached table information in the text document with the text information referencing the attached table information in the document file.
5. The method of claim 4, wherein parsing the text document comprises:
analyzing a table in a text document into a markdown format, and analyzing a formula into a latex format;
and removing the cover, the header page and the watermark in the text document.
6. The method of claim 1, wherein the training process of the pre-trained similarity recognition model comprises:
taking the title of the text document as a simulated question sentence, taking the text content under the title as a recall answer set, and constructing training data;
and training the coset model by using the training data to obtain the pre-trained similarity recognition model.
7. The method of claim 1, wherein the automatic summary analysis model is a chatglm2-6b model.
8. An intelligent question-answering device based on keyword semantic decomposition, which is characterized by comprising:
the first analysis module is used for inputting a user question into the pre-trained keyword extraction model to obtain keywords output by the pre-trained keyword extraction model;
the obtaining module is used for obtaining recall answers corresponding to the keywords from the text information index library;
the second analysis module is used for respectively forming question-answer pairs from the keywords and the corresponding recall answers thereof and taking the question-answer pairs as input of a pre-trained similarity recognition model to obtain the similarity between the keywords output by the pre-trained similarity recognition model and the corresponding recall answers thereof, and selecting recall answers with the similarity larger than a preset value as answers of the keywords;
and the third analysis module is used for taking the user question and the answers of the keywords as the input of the automatic summarization analysis model to obtain the user question answer result output by the automatic summarization analysis model.
9. A computer device, comprising: one or more processors;
the processor is used for storing one or more programs;
the intelligent question-answering method based on keyword semantic decomposition of any one of claims 1 to 7 is implemented when the one or more programs are executed by the one or more processors.
10. A computer readable storage medium, having stored thereon a computer program which, when executed, implements the intelligent question-answering method based on keyword semantic decomposition according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311615794.8A CN117609460A (en) | 2023-11-29 | 2023-11-29 | Intelligent question-answering method and device based on keyword semantic decomposition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311615794.8A CN117609460A (en) | 2023-11-29 | 2023-11-29 | Intelligent question-answering method and device based on keyword semantic decomposition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117609460A true CN117609460A (en) | 2024-02-27 |
Family
ID=89959467
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311615794.8A Pending CN117609460A (en) | 2023-11-29 | 2023-11-29 | Intelligent question-answering method and device based on keyword semantic decomposition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117609460A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117875413A (en) * | 2024-03-13 | 2024-04-12 | 之江实验室 | Concept construction method, device, medium and equipment in knowledge graph ontology |
-
2023
- 2023-11-29 CN CN202311615794.8A patent/CN117609460A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117875413A (en) * | 2024-03-13 | 2024-04-12 | 之江实验室 | Concept construction method, device, medium and equipment in knowledge graph ontology |
CN117875413B (en) * | 2024-03-13 | 2024-05-24 | 之江实验室 | Concept construction method, device, medium and equipment in knowledge graph ontology |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20170235841A1 (en) | Enterprise search method and system | |
CN116701431A (en) | Data retrieval method and system based on large language model | |
CN111190997A (en) | Question-answering system implementation method using neural network and machine learning sequencing algorithm | |
US11875585B2 (en) | Semantic cluster formation in deep learning intelligent assistants | |
CN110188349A (en) | A kind of automation writing method based on extraction-type multiple file summarization method | |
WO2024131054A1 (en) | Rich-media document auxiliary generation apparatus | |
CN117609460A (en) | Intelligent question-answering method and device based on keyword semantic decomposition | |
CN118170894B (en) | Knowledge graph question-answering method, knowledge graph question-answering device and storage medium | |
CN116881425A (en) | Universal document question-answering implementation method, system, device and storage medium | |
CN113742446A (en) | Knowledge graph question-answering method and system based on path sorting | |
Hassani et al. | LVTIA: A new method for keyphrase extraction from scientific video lectures | |
CN116484808A (en) | Method and device for generating controllable text for official document | |
CN117591661A (en) | Question-answer data construction method and device based on large language model | |
CN117668180A (en) | Document question-answering method, document question-answering device, and readable storage medium | |
CN111046649A (en) | Text segmentation method and device | |
CN118260393A (en) | Question-answering method and system in vertical field based on large model | |
CN112613612B (en) | Method and device for constructing green design knowledge base based on patent library | |
CN114297143A (en) | File searching method, file displaying device and mobile terminal | |
CN113157887A (en) | Knowledge question-answering intention identification method and device and computer equipment | |
CN110750632B (en) | Improved Chinese ALICE intelligent question-answering method and system | |
CN117216214A (en) | Question and answer extraction generation method, device, equipment and medium | |
CN111881695A (en) | Audit knowledge retrieval method and device | |
CN114676775A (en) | Sample information labeling method, device, equipment, program and storage medium | |
CN114741088A (en) | App source code linking method based on user comments and developer intelligence | |
de Campos et al. | An integrated system for managing the Andalusian Parliament's digital library |
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 |