CN111966807A - Text processing method and device of question-answering system - Google Patents
Text processing method and device of question-answering system Download PDFInfo
- Publication number
- CN111966807A CN111966807A CN202010830585.5A CN202010830585A CN111966807A CN 111966807 A CN111966807 A CN 111966807A CN 202010830585 A CN202010830585 A CN 202010830585A CN 111966807 A CN111966807 A CN 111966807A
- Authority
- CN
- China
- Prior art keywords
- processed
- message
- question
- word segmentation
- text
- 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
Images
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
- 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
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a text processing method and a text processing device for a question-answering system, wherein the method comprises the following steps: acquiring text content of a message to be processed in a question-answering system; performing word segmentation processing on the text content of the message to be processed, and extracting word segmentation elements of a preset part-of-speech tag; performing syntactic analysis on word segmentation elements extracted from the message to be processed, and determining missing part-of-speech tags; extracting word segmentation elements of corresponding part-of-speech tags from the text content of the historical message according to the missing part-of-speech tags, wherein the historical message comprises: one or more messages appearing in the question-and-answer system before the message to be processed; and combining the word segmentation elements extracted from the historical messages with the messages to be processed to obtain the standardized text content corresponding to the messages to be processed. The invention updates the knowledge base of the question-answering system by using the standardized question text content, so that the question-answering system can answer more user questions and the service effect of the question-answering system is improved.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to a text processing method and device of a question-answering system.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The intelligent question-answering system can accurately position the question knowledge required by the website user in a question-answer mode, and provides personalized information service for the website user by interacting with the website user.
In order to improve the service effect, the intelligent question-answering system usually collects some questions that are not answered, maintains the answers to the questions in a manual or automatic manner, and updates the answers to the questions to the intelligent question-answering system.
The problems provided by the client often have randomness, the space is possibly too long, and the situation of omitting certain words can also occur, which can cause the problems collected by the intelligent question-answering system to be difficult to be used for updating the knowledge of the intelligent question-answering system, and particularly under an automatic reading and understanding mode, the quality of answers provided by the intelligent question-answering system is very low, and the service effect of the intelligent question-answering system cannot be effectively improved.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a text processing method of a question-answering system, which is used for solving the technical problem that the existing question-answering system can not update the knowledge base of the question-answering system by using unsolved user problems, and comprises the following steps: acquiring text content of a message to be processed in a question-answering system; performing word segmentation processing on the text content of the message to be processed, and extracting word segmentation elements of a preset part-of-speech tag; performing syntactic analysis on word segmentation elements extracted from the message to be processed, and determining missing part-of-speech tags; extracting word segmentation elements of corresponding part-of-speech tags from the text content of the historical message according to the missing part-of-speech tags, wherein the historical message comprises: one or more messages appearing in the question-and-answer system before the message to be processed; and combining the word segmentation elements extracted from the historical messages with the messages to be processed to obtain the standardized text content corresponding to the messages to be processed.
The embodiment of the invention also provides a text processing device of a question-answering system, which is used for solving the technical problem that the existing question-answering system can not update the knowledge base of the question-answering system by using the unsolved user problems, and comprises the following components: the system comprises a to-be-processed text acquisition module, a question answering system and a message processing module, wherein the to-be-processed text acquisition module is used for acquiring text contents of to-be-processed messages in the question answering system; the first word segmentation element extraction module is used for performing word segmentation processing on the text content of the message to be processed and extracting word segmentation elements of a preset part-of-speech tag; the syntactic analysis module is used for carrying out syntactic analysis on the word segmentation elements extracted from the message to be processed and determining the missing part-of-speech tags; the second word segmentation element extraction module is used for extracting word segmentation elements of corresponding part of speech tags from the text content of the historical message according to the missing part of speech tags, and the historical message comprises: one or more messages appearing in the question-and-answer system before the message to be processed; and the word segmentation element combination module is used for combining the word segmentation elements extracted from the historical messages with the messages to be processed to obtain the standardized text content corresponding to the messages to be processed.
The embodiment of the invention also provides computer equipment for solving the technical problem that the conventional question-answering system cannot update the knowledge base of the question-answering system by using unsolved user problems.
The embodiment of the invention also provides a computer readable storage medium, which is used for solving the technical problem that the existing question-answering system cannot update the knowledge base of the question-answering system by using the unsolved user problems.
The embodiment of the invention provides a text processing scheme of a question-answering system, which is characterized in that text contents of user problems which are not solved in the question-answering system are subjected to standardized processing, and then a knowledge base of the question-answering system is updated by using the text contents of the problems subjected to the standardized processing, so that the question-answering system can answer more user problems, and the service effect of the question-answering system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart of a text processing method of a question answering system according to an embodiment of the present invention;
fig. 2 is a flowchart of a text processing method of an optional question-answering system provided in the embodiment of the present invention;
FIG. 3 is a schematic diagram of a text processing apparatus of a question answering system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a text processing apparatus of an alternative question-answering system according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment of the present invention provides a text processing method for a question and answer system, and fig. 1 is a flowchart of a text processing method for a question and answer system provided in the embodiment of the present invention, and as shown in fig. 1, the method may include the following steps:
s101, acquiring text contents of messages to be processed in a question answering system.
It should be noted that the question-answering system in the embodiment of the present invention may be a system that automatically answers or replies to a user question in various application scenarios, and may be, but is not limited to, various intelligent customer service systems or robots. The message to be processed in S101 may be, but is not limited to, a user question message that is not solved or solved by the question and answer system.
And under the condition that the number of words contained in the text content of the message to be processed exceeds a preset threshold value, performing abstract extraction on the text content of the message to be processed to obtain abstract content corresponding to the message to be processed, so that the abstract text content of the message to be processed is subjected to subsequent processing, and the processing efficiency of the problem text content is improved. In the embodiment of the invention, the simplification of sentences can be completed on the premise of keeping the semantics of the sentences by extracting the abstract contents.
S102, performing word segmentation processing on the text content of the message to be processed, and extracting word segmentation elements of the preset part-of-speech tag.
The part-of-speech tags preset in the embodiment of the present invention may include, but are not limited to, verbs, nouns, pronouns.
And S103, performing syntactic analysis on the word segmentation elements extracted from the message to be processed, and determining the missing part-of-speech tags.
It should be noted that the syntactic analysis is one of the key underlying technologies in natural language processing, and the basic task of the syntactic analysis is to determine the syntactic structure of a sentence or the dependency relationship between words in the sentence. The syntax structure analyzed in the embodiment of the invention includes but is not limited to a major sentence structure or a minor sentence structure. For example, word segmentation processing is performed on a certain message "how i want to cancel" to extract "cancellation" of verb part-of-speech tags, and syntactic analysis of the structure of the actor sentence is performed on the message, so that words lacking noun part-of-speech tags in the extracted word segmentation elements are found, and therefore, nouns forming the actor sentence structure with "cancellation" need to be found.
S104, extracting word segmentation elements of corresponding part-of-speech tags from the text content of the historical message according to the missing part-of-speech tags, wherein the historical message comprises: one or more messages in the question-and-answer system that precede the pending message.
In a specific implementation, the above S104 may step through the previous message appearing before the message to be processed in the question-answering system one by one until the word segmentation element with the missing part-of-speech tag is extracted. In one embodiment, after some unresolved user problem information is collected, the user problems in the previous three rounds are collected forward and backward, text abstract simplification is carried out on the unresolved user problems, missing elements are analyzed through a syntactic analysis technology, labels of the problems in the previous three rounds are extracted, reasonable combination is carried out, reference resolution is carried out, the user problems are standardized, effective knowledge point maintenance is carried out subsequently, iterative upgrade of the intelligent customer service is accelerated, and the service effect of the intelligent customer service is improved.
And S105, combining the word segmentation elements extracted from the historical messages with the messages to be processed to obtain the standardized text content corresponding to the messages to be processed.
Suppose that in the question-and-answer system dialogue, the unresolved user question message is "how do i go to logout", the last message of the message is "what is the annual fee of the credit card? "then can the message" what is the annual cost of credit card? The term 'credit card' is extracted and combined with the message 'how do i to cancel the credit card', so that a problem message 'how do i to cancel the credit card' after standardized processing is obtained.
In an embodiment, as shown in fig. 2, the text processing method provided in the embodiment of the present invention may further include the following steps:
s106, under the condition that the message to be processed contains pronouns, carrying out reference resolution processing on the pronouns contained in the message to be processed according to the text content of one or more messages appearing before the message to be processed in the question-answering system.
In a specific implementation, in one case, after the text content of the message to be processed is subjected to word segmentation processing and word segmentation elements of a preset part-of-speech tag are extracted, pronouns contained in the message to be processed are subjected to reference resolution processing; in another case, after the message to be processed is processed according to the word segmentation elements extracted from the history message, the pronouns included in the text content of the processed message may be subjected to the reference resolution processing.
Suppose that in the question-and-answer system dialogue, the unresolved user question message is "how do i to log it off? "how did my credit card get lost" the message immediately before it? "how can my credit card be lost from the message? "extract the noun" credit card ", replace it with the message" how do i to logout it? "the pronouns in the sentence, get the standardized question message" how do i to log off the credit card? ".
Therefore, according to the text processing method provided by the embodiment of the invention, a user unsolved problem standardization system based on semantic understanding can be established, and the user problem is subjected to standardization processing based on syntactic analysis and text abstract extraction. After the user problems which are not solved or not solved in the question-answering system are collected, the user problems are traced back forwards, historical user problems (such as the previous three rounds of user problems) before the user problems are collected in a forward mode, the user problems which are not solved are simplified in a text abstract mode, the missing part-of-speech tags are analyzed through a syntactic analysis technology, word segmentation elements of the corresponding part-of-speech tags are extracted from the historical user problems, the extracted part-of-speech elements are reasonably combined with the user problems, and the reference resolution is carried out to obtain the standardized user problems, so that a knowledge base of the question-answering system can be updated and maintained subsequently, the iterative upgrade of the intelligent customer service is accelerated, and the service effect of the intelligent customer service is improved.
Based on the same inventive concept, the embodiment of the present invention further provides a text processing apparatus of a question and answer system, as described in the following embodiments. Because the principle of the device for solving the problems is similar to the text processing method of the question-answering system, the implementation of the device can be referred to the implementation of the text processing method of the question-answering system, and repeated parts are not described again.
Fig. 3 is a schematic diagram of a text processing apparatus of a question answering system according to an embodiment of the present invention, and as shown in fig. 3, the apparatus may include: the device comprises a text to be processed acquisition module 31, a first word segmentation element extraction module 32, a syntax analysis module 33, a second word segmentation element extraction module 34 and a word segmentation element combination module 35.
The to-be-processed text acquiring module 31 is configured to acquire text content of a to-be-processed message in the question-answering system; the first word segmentation element extraction module 32 is configured to perform word segmentation processing on the text content of the message to be processed, and extract word segmentation elements of a preset part-of-speech tag; a syntactic analysis module 33, configured to perform syntactic analysis on the word segmentation elements extracted from the message to be processed, and determine missing part-of-speech tags; a second segmentation element extracting module 34, configured to extract, according to the missing part-of-speech tag, a segmentation element corresponding to the part-of-speech tag from the text content of the history message, where the history message includes: one or more messages appearing in the question-and-answer system before the message to be processed; and the word segmentation element combination module 35 is configured to combine the word segmentation elements extracted from the historical messages with the message to be processed to obtain the standardized text content corresponding to the message to be processed.
Alternatively, the second segmentation element extraction module 34 may be specifically configured to traverse the previous message appearing before the message to be processed in the question-answering system one by one until the segmentation elements with the missing part-of-speech tags are extracted.
In an embodiment, as shown in fig. 4, the text processing apparatus of the question-answering system provided in the embodiment of the present invention may further include: and the reference resolution processing module 36 is configured to, when the message to be processed includes the pronouns, perform reference resolution processing on the pronouns included in the message to be processed according to text contents of one or more messages appearing before the message to be processed in the question-answering system.
In an embodiment, as shown in fig. 4, the text processing apparatus of the question-answering system provided in the embodiment of the present invention may further include: the text abstract extracting module 37 is configured to, when the number of words included in the text content of the message to be processed exceeds a preset threshold, extract an abstract of the text content of the message to be processed, so as to obtain an abstract content corresponding to the message to be processed.
Based on the same inventive concept, a computer device is further provided in the embodiments of the present invention to solve the technical problem that the existing question-answering system cannot update the knowledge base of the question-answering system by using the unsolved user problem, fig. 5 is a schematic diagram of a computer device in the embodiments of the present invention, as shown in fig. 5, the computer device 50 includes a memory 501, a processor 502, and a computer program stored in the memory 501 and operable on the processor 502, and the processor 502 implements the text processing method of the question-answering system when executing the computer program.
Based on the same inventive concept, the embodiment of the present invention further provides a computer-readable storage medium, which is used for solving the technical problem that the existing question-answering system cannot update the knowledge base of the question-answering system by using the unsolved user problem, and the computer-readable storage medium stores a computer program for executing the text processing method of the question-answering system.
In summary, embodiments of the present invention provide a text processing method and apparatus for a question-answering system, a computer device, and a computer readable storage medium, in which text content of an unresolved user question in the question-answering system is standardized, and then a knowledge base of the question-answering system is updated by using the standardized text content of the question, so that the question-answering system can answer more user questions, and a service effect of the question-answering system is improved.
As will be appreciated by one skilled in the art, 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 flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A text processing method of a question-answering system is characterized by comprising the following steps:
acquiring text content of a message to be processed in a question-answering system;
performing word segmentation processing on the text content of the message to be processed, and extracting word segmentation elements of a preset part-of-speech tag;
performing syntactic analysis on the word segmentation elements extracted from the message to be processed, and determining missing part-of-speech tags;
extracting word segmentation elements of corresponding part-of-speech tags from text contents of historical messages according to the missing part-of-speech tags, wherein the historical messages comprise: one or more messages appearing in the question-and-answer system before the message to be processed;
and combining the word segmentation elements extracted from the historical information with the information to be processed to obtain the standardized text content corresponding to the information to be processed.
2. The method of claim 1, wherein extracting word segmentation elements of corresponding part-of-speech tags from text content of the historical message based on the missing part-of-speech tags comprises:
and traversing the previous message appearing before the message to be processed in the question-answering system one by one until the word segmentation elements of the missing part of speech tags are extracted.
3. The method of claim 1, wherein the method further comprises:
and under the condition that the message to be processed contains pronouns, performing reference resolution processing on the pronouns contained in the message to be processed according to the text content of one or more messages appearing before the message to be processed in the question-answering system.
4. The method of claim 1, wherein the method further comprises:
and under the condition that the number of words contained in the text content of the message to be processed exceeds a preset threshold value, performing abstract extraction on the text content of the message to be processed to obtain abstract content corresponding to the message to be processed.
5. A text processing apparatus of a question-answering system, comprising:
the system comprises a to-be-processed text acquisition module, a question answering system and a message processing module, wherein the to-be-processed text acquisition module is used for acquiring text contents of to-be-processed messages in the question answering system;
the first word segmentation element extraction module is used for carrying out word segmentation on the text content of the message to be processed and extracting word segmentation elements of a preset part-of-speech tag;
the syntactic analysis module is used for carrying out syntactic analysis on the word segmentation elements extracted from the message to be processed and determining the missing part-of-speech tags;
a second word segmentation element extraction module, configured to extract word segmentation elements corresponding to part of speech tags from text content of a history message according to the missing part of speech tags, where the history message includes: one or more messages appearing in the question-and-answer system before the message to be processed;
and the word segmentation element combination module is used for combining the word segmentation elements extracted from the historical messages with the messages to be processed to obtain the standardized text content corresponding to the messages to be processed.
6. The apparatus of claim 5, wherein the second segmentation element extraction module is further configured to traverse a previous message appearing before the message to be processed in the question-and-answer system one by one until a segmentation element lacking part-of-speech tags is extracted.
7. The apparatus of claim 5, wherein the apparatus further comprises:
and the pronouns are referred to and resolved by the aid of the processing module, and when the messages to be processed contain pronouns, the pronouns contained in the messages to be processed are referred to and resolved according to text contents of one or more messages appearing before the messages to be processed in the question-answering system.
8. The apparatus of claim 5, wherein the apparatus further comprises:
and the text abstract extracting module is used for extracting the abstract of the text content of the message to be processed under the condition that the number of words contained in the text content of the message to be processed exceeds a preset threshold value, so as to obtain the abstract content corresponding to the message to be processed.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a text processing method of the question-answering system according to any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium characterized by storing a computer program for executing the text processing method of the question-answering system according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830585.5A CN111966807A (en) | 2020-08-18 | 2020-08-18 | Text processing method and device of question-answering system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830585.5A CN111966807A (en) | 2020-08-18 | 2020-08-18 | Text processing method and device of question-answering system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111966807A true CN111966807A (en) | 2020-11-20 |
Family
ID=73388310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010830585.5A Pending CN111966807A (en) | 2020-08-18 | 2020-08-18 | Text processing method and device of question-answering system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966807A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777080A (en) * | 2016-12-13 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Short abstraction generating method, database building method and interactive method |
| WO2020119075A1 (en) * | 2018-12-10 | 2020-06-18 | 平安科技（深圳）有限公司 | General text information extraction method and apparatus, computer device and storage medium |
| CN111325034A (en) * | 2020-02-12 | 2020-06-23 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for semantic completion in multi-round conversation |
-
2020
- 2020-08-18 CN CN202010830585.5A patent/CN111966807A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777080A (en) * | 2016-12-13 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Short abstraction generating method, database building method and interactive method |
| WO2020119075A1 (en) * | 2018-12-10 | 2020-06-18 | 平安科技（深圳）有限公司 | General text information extraction method and apparatus, computer device and storage medium |
| CN111325034A (en) * | 2020-02-12 | 2020-06-23 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for semantic completion in multi-round conversation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807960B (en) | Intelligent customer service method, electronic device and computer readable storage medium | |
| CN108073587B (en) | Automatic question answering method and device and electronic equipment | |
| CN111079408B (en) | Language identification method, device, equipment and storage medium | |
| CA2360067A1 (en) | Any-to-any component computing system | |
| CN110413753B (en) | Question-answer sample expansion method and device | |
| CN111832318B (en) | Single sentence natural language processing method and device, computer equipment and readable storage medium | |
| CN114757176A (en) | Method for obtaining target intention recognition model and intention recognition method | |
| CN112579466A (en) | Test case generation method and device and computer readable storage medium | |
| CN108256870A (en) | Description information and update, data processing method and device are generated based on topological structure | |
| CN111831920A (en) | User demand analysis method and device, computer equipment and storage medium | |
| CN110727803A (en) | Text event extraction method and device | |
| CN117669717A (en) | Knowledge enhancement-based large model question-answering method, device, equipment and medium | |
| CN109033082B (en) | Learning training method and device of semantic model and computer readable storage medium | |
| CN111966807A (en) | Text processing method and device of question-answering system | |
| CN109558580B (en) | Text analysis method and device | |
| CN110110050B (en) | Method for generating news event generating type question-answer data set | |
| CN114302227B (en) | Method and system for collecting and analyzing network video based on container collection | |
| US11423228B2 (en) | Weakly supervised semantic entity recognition using general and target domain knowledge | |
| US20220262353A1 (en) | Method and device for Processing Voice Information, Storage Medium and Electronic Apparatus | |
| JP2001044412A (en) | Semiconductor simulation apparatus | |
| CN113434631A (en) | Emotion analysis method and device based on event, computer equipment and storage medium | |
| CN111859148A (en) | Theme extraction method, device and equipment and computer readable storage medium | |
| CN112949283B (en) | Text processing method, device, nonvolatile storage medium and processor | |
| US11100412B2 (en) | Extending question and answer samples | |
| CN110618809B (en) | Front-end webpage input constraint extraction method and device |
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 |