CN113094472A - Knowledge base generation method based on artificial intelligence and intelligent robot response method - Google Patents
Knowledge base generation method based on artificial intelligence and intelligent robot response method Download PDFInfo
- Publication number
- CN113094472A CN113094472A CN202110413925.9A CN202110413925A CN113094472A CN 113094472 A CN113094472 A CN 113094472A CN 202110413925 A CN202110413925 A CN 202110413925A CN 113094472 A CN113094472 A CN 113094472A
- Authority
- CN
- China
- Prior art keywords
- target
- knowledge base
- database
- alternative
- answer
- 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 53
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 54
- 230000002457 bidirectional effect Effects 0.000 claims description 15
- 238000010276 construction Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
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
- G06F16/3331—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
- G06F16/332—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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a knowledge base generation method and an intelligent robot response method based on artificial intelligence, which are used for acquiring knowledge base generation instructions, acquiring a target database from the initial database according to a knowledge base generation instruction, acquiring a target text from the target database according to the target database, wherein the target text is a related text for generating the target knowledge base, the target text is analyzed to obtain the target knowledge base, and accordingly, the intelligent robot response can be carried out according to the obtained target knowledge base, the knowledge base generation method provided by the invention is a method for automatically generating the knowledge base according to data, compared with a mode of manually constructing the knowledge base, the efficiency is greatly improved, and the method is not influenced by the scale of the knowledge base, even if the knowledge base is large in scale, the efficiency cannot be reduced, and therefore the knowledge base generation method provided by the invention can adapt to the current increasingly accurate question and answer requirements.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a knowledge base generation method based on artificial intelligence and an intelligent robot response method.
Background
When the question-answering intelligent robot answers, the accuracy of the answers obtained based on the questions depends on a knowledge base in the robot, and generally, the more comprehensive the knowledge base is, the higher the accuracy of the answers is. The conventional knowledge base generation mode is usually constructed manually, however, the manual construction needs a large data volume, and the larger the scale of the required knowledge base is, the more the data volume is needed for construction, so that the manual construction mode of the knowledge base is low in efficiency and large in workload, and cannot adapt to the more and more accurate response requirements at present.
Disclosure of Invention
The invention provides a knowledge base generation method based on artificial intelligence and an intelligent robot response method, which are used for solving the technical problem that the existing knowledge base generation mode is low in efficiency.
A knowledge base generation method based on artificial intelligence comprises the following steps:
acquiring a knowledge base generation instruction, wherein the knowledge base generation instruction comprises a target field to which a target knowledge base belongs;
acquiring a target database related to the target field from an initial database according to the knowledge base generation instruction;
acquiring a target text from the target database according to the target database, wherein the target text is a related text for generating the target knowledge base;
and analyzing the target text to obtain the target knowledge base.
Preferably, the obtaining a target database related to the target field from an initial database according to the knowledge base generation instruction specifically includes:
inputting the target field into a preset field knowledge map according to the knowledge base generation instruction, and determining an associated field related to the target field;
and acquiring the target database from the initial database, wherein the target database comprises a database corresponding to the target field and a database corresponding to the associated field.
Preferably, the analyzing the target text to obtain the target knowledge base specifically comprises:
acquiring a target sentence containing alternative answers in the target text and the position of each alternative answer in the target sentence;
coding the positions of the target statement and the alternative answers in the target statement to obtain a target semantic vector;
and decoding the target semantic vector to obtain the target knowledge base.
Preferably, the encoding of the positions of the target sentence and the alternative answers in the target sentence to obtain a target semantic vector specifically includes:
and coding the positions of the target statement and the alternative answers in the target statement by a preset encoder with a bidirectional LSTM structure to obtain a target semantic vector.
Preferably, the encoding of the target sentence and the position of each alternative answer in the target sentence by using an encoder of a preset bidirectional LSTM structure is performed to obtain a target semantic vector, and specifically, the encoding is performed by:
obtaining a tree structure sequence of alternative answers according to the dependency relationship of each alternative answer in the target statement;
calculating the position vector of each alternative answer in the alternative answer tree structure sequence;
inputting the position vector of each alternative answer in the alternative answer tree structure sequence into the bidirectional LSTM structure;
according to the bidirectional LSTM structure, semantic coding is carried out on each alternative answer to obtain a semantic vector corresponding to each alternative answer;
and generating a target semantic vector of each alternative answer according to the bidirectional LSTM structure and the position vector and the semantic vector of each alternative answer in the alternative answer tree structure sequence.
Preferably, the decoding the target semantic vector to obtain the target knowledge base specifically comprises:
and decoding and outputting a target answer in the unidirectional LSTM structure by taking the target semantic vector as an initial state through a preset unidirectional LSTM structure decoder to obtain the target knowledge base.
An intelligent robot response method, comprising:
acquiring a question to be answered;
inputting the question to be answered into a target knowledge base, and acquiring an answer corresponding to the question to be answered;
the target knowledge base is generated according to the knowledge base generation method based on artificial intelligence.
The technical effects of the invention comprise: the knowledge base generation instruction comprises a target domain to which a target knowledge base belongs, a target database corresponding to the target domain is obtained from an initial database according to the knowledge base generation instruction, the target database is a database closely related to the target knowledge base, a target text is obtained from the target database according to the target database, the target text is a related text for generating the target knowledge base, and finally the target text is analyzed to obtain the target knowledge base, so that the knowledge base generation method provided by the invention is a method for automatically generating the knowledge base according to the data, compared with a method for manually constructing the knowledge base, a worker is not required to arrange the data related to the generated knowledge base, the knowledge base generation efficiency is greatly improved, the method is not influenced by the scale of the knowledge base, namely the large-scale knowledge base, the efficiency is not reduced, so that the knowledge base generation method provided by the invention can adapt to the current more and more accurate response requirements.
Drawings
FIG. 1 is a flow chart of a knowledge base generation method based on artificial intelligence provided by the invention;
fig. 2 is a flowchart of an intelligent robot response method provided by the invention.
Detailed Description
The embodiment of the knowledge base generation method based on artificial intelligence comprises the following steps:
the embodiment provides a knowledge base generation method based on artificial intelligence, and the knowledge base generation method can be applied to servers, computer equipment and the like. As shown in fig. 1, the knowledge base generation method includes the following steps:
step 1: acquiring a knowledge base generation instruction, wherein the knowledge base generation instruction comprises a target field to which a target knowledge base belongs:
and acquiring a knowledge base generation instruction, wherein the knowledge base generation instruction is used for starting the generation process of the knowledge base. The knowledge base generation instructions may be input by a signal input device, such as a keyboard, a touch screen device, or the like.
The knowledge base generation method provided by the invention is used for generating the target knowledge base, in the embodiment, the target knowledge base corresponds to a specific field, and the specific field corresponding to the target knowledge base is the target field to which the target knowledge base belongs. The knowledge base generation instruction includes a target domain to which the target knowledge base belongs.
Step 2: according to the knowledge base generation instruction, acquiring a target database related to the target field from an initial database:
an initial database is preset, the initial database is a data base for generating a target knowledge base, the initial database is a database group and comprises databases in a plurality of fields, and as a specific implementation mode, the initial database comprises databases in all known fields at present or databases in a plurality of fields possibly used in the generation process of the target knowledge base. Each database comprises at least one text, the number of the texts and the length of each text are set according to actual conditions, and the target knowledge base is generated by the texts. The present embodiment does not limit the format of each text in each database.
And acquiring a target database related to the target field from the initial database according to the knowledge base generation instruction. As a specific embodiment, a domain knowledge graph is preset, and the domain knowledge graph includes domains related to all currently known knowledge bases and relationships between the domains, and from the domain knowledge graph, the relationships between any two domains can be obtained, such as: whether or not there is a correlation between any two domains, and how that correlation is. Then, the target domain is input into a preset domain knowledge graph, and an associated domain related to the target domain is determined.
And then inputting the target field and the obtained associated field into an initial database, and acquiring a target database from the initial database, wherein the target database comprises two parts, one part is a database corresponding to the target field, and the other part is a database corresponding to the associated field.
Through the target database acquisition mode, the database corresponding to the target field can be obtained, other databases related to the target field can also be obtained, irrelevant data cannot be obtained, the comprehensiveness of the database acquisition can be improved, the comprehensiveness of a subsequent target knowledge base is further improved, and the accuracy of robot response according to the target knowledge base is further improved.
As another embodiment, only the database corresponding to the target domain may be acquired, and the database may be a target database.
And step 3: acquiring a target text from the target database according to the target database, wherein the target text is a related text for generating the target knowledge base:
the target database may include only one database or a plurality of databases, and in this embodiment, one target database is taken as an example for description, and if the target database includes a plurality of databases, the processing procedures of the databases are the same.
And acquiring a target text from the target database according to the target database, wherein the target text is a related text for generating a target knowledge base. The target text may be all texts in the target database, that is, each text in the target database is a related text for generating the target knowledge base, or a part of texts is selected from the target database (for example, randomly selected or selected according to a preset selection mechanism), and the selected text is the target text. If there is more than one target text, the processing procedure of each target text is the same, and this embodiment takes one of the target texts as an example for explanation.
And 4, step 4: analyzing the target text to obtain the target knowledge base:
analyzing the target text to obtain a target knowledge base, setting the analysis process according to the actual situation, and performing analysis processing by adopting the existing analysis strategy, such as: and extracting keywords from the target text, and forming a target knowledge base according to the obtained keywords and the corresponding target text. As a specific embodiment, a specific implementation of the parsing is given as follows:
(4-1): acquiring a target sentence containing alternative answers in a target text and the position of each alternative answer in the target sentence:
the alternative answers are answers related to the target answer, the alternative answers may include the final target answer, and there may be more than one alternative answer.
And acquiring a target sentence containing the alternative answers in the target text and the position of each alternative answer in the target sentence. In this embodiment, a target sentence including alternative answers in a target text and a position of each alternative answer in the target sentence may be obtained according to a preset obtaining model, for example: the obtaining model is a sequence labeling model, the target text is segmented through the sequence labeling model and is divided into a plurality of sentences, then all the sentences are labeled, and the target sentences where the alternative answers are located and the positions of all the alternative answers in the target sentences are obtained.
As another embodiment, the alternative answers may be known, and then, the target sentence where the alternative answer is located may be determined directly according to the alternative answers, and the position of each alternative answer in the target sentence may be obtained.
(4-2): coding the positions of the target statement and each alternative answer in the target statement to obtain a target semantic vector:
in this embodiment, the positions of the target sentence and each alternative answer in the target sentence are processed through a preset response model, so as to obtain a target knowledge base. The response model comprises an encoder and a decoder, wherein the encoder is of a bidirectional LSTM structure. Then, the positions of the target statement and each alternative answer in the target statement are encoded by an encoder of a bidirectional LSTM structure to obtain a target semantic vector, and a specific implementation process is given as follows:
and obtaining a tree structure sequence of the alternative answers according to the dependency relationship of each alternative answer in the target statement. As a specific embodiment, the dependency relationship of each candidate answer in the target sentence may be obtained through a preset dependency analysis tool, so as to construct a candidate answer tree structure sequence, or the dependency relationship of each candidate answer in the target sentence is known, and then, the candidate answer tree structure sequence is constructed according to the dependency relationship of each candidate answer in the target sentence and the preset dependency analysis tool.
And calculating a position vector of each alternative answer in the alternative answer tree structure sequence, wherein the position vector represents the position of each alternative answer in the alternative answer tree structure sequence. As a specific embodiment, the position of each candidate answer in the candidate answer tree structure sequence may be represented by a vector of a preset dimension, so as to obtain a position vector of each candidate answer in the candidate answer tree structure sequence. The preset dimension may be set according to an actual situation, and is not specifically limited in the present application.
And inputting the position vector of each alternative answer in the alternative answer tree structure sequence into the bidirectional LSTM structure.
And according to the bidirectional LSTM structure, performing semantic coding on each alternative answer to obtain a semantic vector corresponding to each alternative answer. It should be understood that the semantic vector of each candidate answer may be a multidimensional vector, and the vector of each dimension in the semantic vector represents semantic information of the candidate answer. The dimension of the semantic vector may be set by actual conditions, and the present application is not limited specifically.
And generating a target semantic vector of each alternative answer according to the position vector and the semantic vector of each alternative answer in the alternative answer tree structure sequence according to the bidirectional LSTM structure. In this embodiment, for any one of the candidate answers, vector operation processing is performed on the position vector and the semantic vector corresponding to the candidate answer to obtain a target semantic vector corresponding to the candidate answer, and then target semantic vectors of other candidate answers are obtained.
(4-3) decoding the target semantic vector to obtain a target knowledge base:
the decoder of the answer model is a decoder of a unidirectional LSTM structure. Then, decoding the target semantic vector through a decoder with a unidirectional LSTM structure to obtain a target knowledge base, specifically: and decoding and outputting a target answer by taking the target semantic vector as an initial state in the unidirectional LSTM structure to obtain a target knowledge base. In the process of decoding and outputting the target answers, decoding may be performed in sequence according to a preset sequence (such as a time sequence), and the target answers are output until the decoding is finished, or until other preset conditions are met. It should be understood that, in the parsing process of any one candidate answer, the target semantic vector of the candidate answer is decoded to obtain a target answer corresponding to the candidate answer, specifically: and performing similarity operation on the target semantic vector corresponding to the alternative answer and semantic vectors of all target alternative answers stored in a preset database to obtain a similarity operation result, and taking the target alternative answer corresponding to the semantic vector of which the similarity operation result in the preset database meets a preset similarity threshold as the target answer corresponding to the alternative answer. Further, the similarity operation may be a dot product operation, the dot product result is used as a similarity operation result, the dot product result is subjected to probabilistic operation to obtain a probabilistic operation result, and a target candidate answer with the probabilistic operation result meeting a preset probability threshold is selected as a target answer corresponding to the candidate answer.
Therefore, the target answers corresponding to the alternative answers can be obtained through the process, and further the target knowledge base containing the target answers is obtained.
The embodiment of the intelligent robot response method comprises the following steps:
the embodiment provides an intelligent robot response method, which is applied to an intelligent robot and used for processing an acquired problem to be responded to obtain a corresponding answer. Then, as shown in fig. 2, the present embodiment provides an intelligent robot responding method, including:
step 1: acquiring a question to be answered:
the voice signal of the question to be answered can be acquired through a microphone and then recognized as a text signal.
Step 2: inputting the question to be answered into a target knowledge base, and acquiring an answer corresponding to the question to be answered:
and inputting the questions to be answered into a target knowledge base, and acquiring answers corresponding to the questions to be answered. The target knowledge base is generated according to the artificial intelligence based knowledge base generation method given in the above embodiment of the artificial intelligence based knowledge base generation method, and the artificial intelligence based knowledge base generation method is not described in detail since the detailed description is given above.
Claims (7)
1. A knowledge base generation method based on artificial intelligence is characterized by comprising the following steps:
acquiring a knowledge base generation instruction, wherein the knowledge base generation instruction comprises a target field to which a target knowledge base belongs;
acquiring a target database related to the target field from an initial database according to the knowledge base generation instruction;
acquiring a target text from the target database according to the target database, wherein the target text is a related text for generating the target knowledge base;
and analyzing the target text to obtain the target knowledge base.
2. The method for generating the knowledge base based on the artificial intelligence according to claim 1, wherein the target database related to the target field is obtained from an initial database according to the knowledge base generation instruction, and specifically comprises:
inputting the target field into a preset field knowledge map according to the knowledge base generation instruction, and determining an associated field related to the target field;
and acquiring the target database from the initial database, wherein the target database comprises a database corresponding to the target field and a database corresponding to the associated field.
3. The artificial intelligence based knowledge base generation method according to claim 1, wherein the target text is analyzed to obtain the target knowledge base, and specifically:
acquiring a target sentence containing alternative answers in the target text and the position of each alternative answer in the target sentence;
coding the positions of the target statement and the alternative answers in the target statement to obtain a target semantic vector;
and decoding the target semantic vector to obtain the target knowledge base.
4. The artificial intelligence based knowledge base generation method according to claim 3, wherein the encoding of the positions of the target sentence and the alternative answers in the target sentence obtains a target semantic vector, specifically:
and coding the positions of the target statement and the alternative answers in the target statement by a preset encoder with a bidirectional LSTM structure to obtain a target semantic vector.
5. The artificial intelligence based knowledge base generation method of claim 4, wherein the target sentence and the position of each alternative answer in the target sentence are encoded by an encoder of a preset bidirectional LSTM structure to obtain a target semantic vector, and specifically, the method comprises:
obtaining a tree structure sequence of alternative answers according to the dependency relationship of each alternative answer in the target statement;
calculating the position vector of each alternative answer in the alternative answer tree structure sequence;
inputting the position vector of each alternative answer in the alternative answer tree structure sequence into the bidirectional LSTM structure;
according to the bidirectional LSTM structure, semantic coding is carried out on each alternative answer to obtain a semantic vector corresponding to each alternative answer;
and generating a target semantic vector of each alternative answer according to the bidirectional LSTM structure and the position vector and the semantic vector of each alternative answer in the alternative answer tree structure sequence.
6. The artificial intelligence based knowledge base generation method of claim 4, wherein the decoding of the target semantic vector to obtain the target knowledge base specifically comprises:
and decoding and outputting a target answer in the unidirectional LSTM structure by taking the target semantic vector as an initial state through a preset unidirectional LSTM structure decoder to obtain the target knowledge base.
7. An intelligent robot response method is characterized by comprising the following steps:
acquiring a question to be answered;
inputting the question to be answered into a target knowledge base, and acquiring an answer corresponding to the question to be answered;
the target knowledge base is generated according to the artificial intelligence based knowledge base generation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110413925.9A CN113094472A (en) | 2021-04-16 | 2021-04-16 | Knowledge base generation method based on artificial intelligence and intelligent robot response method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110413925.9A CN113094472A (en) | 2021-04-16 | 2021-04-16 | Knowledge base generation method based on artificial intelligence and intelligent robot response method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113094472A true CN113094472A (en) | 2021-07-09 |
Family
ID=76678482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110413925.9A Pending CN113094472A (en) | 2021-04-16 | 2021-04-16 | Knowledge base generation method based on artificial intelligence and intelligent robot response method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113094472A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763529A (en) * | 2018-05-31 | 2018-11-06 | 苏州大学 | A kind of intelligent search method, device and computer readable storage medium |
| CN109858626A (en) * | 2019-01-23 | 2019-06-07 | 三角兽（北京）科技有限公司 | A kind of construction of knowledge base method and device |
-
2021
- 2021-04-16 CN CN202110413925.9A patent/CN113094472A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763529A (en) * | 2018-05-31 | 2018-11-06 | 苏州大学 | A kind of intelligent search method, device and computer readable storage medium |
| CN109858626A (en) * | 2019-01-23 | 2019-06-07 | 三角兽（北京）科技有限公司 | A kind of construction of knowledge base method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795543B (en) | Unstructured data extraction method, device and storage medium based on deep learning | |
| CN111581229B (en) | SQL statement generation method and device, computer equipment and storage medium | |
| CN113672708A (en) | Language model training method, question and answer pair generation method, device and equipment | |
| CN111274267A (en) | Database query method and device and computer readable storage medium | |
| CN115470338B (en) | Multi-scenario intelligent question answering method and system based on multi-path recall | |
| CN116719520B (en) | Code generation method and device | |
| CN113012822A (en) | Medical question-answering system based on generating type dialogue technology | |
| CN115858750A (en) | Power grid technical standard intelligent question-answering method and system based on natural language processing | |
| CN116561274A (en) | Knowledge question-answering method based on digital human technology and natural language big model | |
| CN115238045A (en) | Method, system and storage medium for extracting generation type event argument | |
| CN113220854B (en) | Intelligent dialogue method and device for machine reading and understanding | |
| CN112989829B (en) | Named entity recognition method, device, equipment and storage medium | |
| CN117435716A (en) | Data processing method and system of power grid man-machine interaction terminal | |
| CN111400340A (en) | Natural language processing method and device, computer equipment and storage medium | |
| CN116414958A (en) | Text corpus generation method and device, storage medium and electronic equipment | |
| CN112925889B (en) | Natural language processing method, device, electronic equipment and storage medium | |
| CN113094472A (en) | Knowledge base generation method based on artificial intelligence and intelligent robot response method | |
| CN113486160B (en) | Dialogue method and system based on cross-language knowledge | |
| CN114238595A (en) | Metallurgical knowledge question-answering method and system based on knowledge graph | |
| CN114511084A (en) | Answer extraction method and system for automatic question-answering system for enhancing question-answering interaction information | |
| CN113886520A (en) | Code retrieval method and system based on graph neural network and computer readable storage medium | |
| CN113343668B (en) | Method and device for solving selected questions, electronic equipment and readable storage medium | |
| CN115600580B (en) | Text matching method, device, equipment and storage medium | |
| CN116860940A (en) | Question-answering information processing method and device, electronic equipment and storage medium | |
| CN118051602A (en) | Intelligent question-answering method and system, medium and equipment oriented to information security field |
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 |