CN115587161A - Entity extraction method for intelligent dialogue system and intelligent dialogue system - Google Patents
Entity extraction method for intelligent dialogue system and intelligent dialogue system Download PDFInfo
- Publication number
- CN115587161A CN115587161A CN202211126920.9A CN202211126920A CN115587161A CN 115587161 A CN115587161 A CN 115587161A CN 202211126920 A CN202211126920 A CN 202211126920A CN 115587161 A CN115587161 A CN 115587161A
- Authority
- CN
- China
- Prior art keywords
- entity
- extraction
- model
- relation
- corpus
- 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
- G06F16/3331—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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses an entity extraction method for an intelligent dialogue system and the intelligent dialogue system, belonging to the technical field of deep learning and natural language processing, and the method is realized in the following way: 1) Using a similarity calculation method based on grammar to carry out primary screening recall on a corpus defined by a user in advance and determine a part of corpora similar to a text input by the user in a platform corpus; 2) Calculating a corpus which is most similar to the input of the user in the result obtained in the step 1) by using a similarity calculation model based on semantics and determining an intention; 3) And using a joint relation extraction model to perform entity extraction on the result obtained in the step 2), and obtaining and returning an extraction result. The method and the system can extract various types of entities in the corpus, especially inexhaustible types which cannot be predefined by a user, and can improve the efficiency of the overall architecture of the intelligent dialog system.
Description
Technical Field
The invention relates to the technical field of deep learning and natural language processing, in particular to an entity extraction method for an intelligent dialogue system and the intelligent dialogue system.
Background
Entity extraction is crucial for the intention recognition of intelligent dialog systems. Especially for the situation that the corpus comprises inexhaustible entities, accurate and efficient entity extraction can remarkably improve the user experience of the intelligent dialogue system.
Conventionally, a similarity model based on grammar and semantics is used, so that the intent recognition of a corpus can be efficiently performed, and entity values predefined by a user can be extracted. However, using only such methods, it is difficult to extract an inexhaustible type of entity. Entities of types such as date, time, numerator, etc. are realized only by a method defined in advance by a user, and will be a disaster for the user experience of the intelligent dialogue system. Therefore, it is an inevitable key task to incorporate an accurate and efficient entity extraction method in the framework implementation of an intelligent dialog system.
Disclosure of Invention
The technical task of the invention is to provide an entity extraction method for an intelligent dialogue system and the intelligent dialogue system aiming at the defects, so that various types of entities in a corpus can be extracted, especially inexhaustible types which cannot be predefined by a user, and the efficiency of the whole framework of the intelligent dialogue system can be improved.
The technical scheme adopted by the invention for solving the technical problems is as follows:
an entity extraction method for an intelligent dialog system is implemented as follows:
1) Performing primary screening recall on a corpus which is predefined by a user by using a grammar-based similarity calculation method, and determining a part of corpora which are similar to the text input by the user in a platform corpus;
2) Calculating a corpus which is most similar to the input of the user in the result obtained in the step 1) by using a similarity calculation model based on semantics and determining an intention;
3) And 3, using a joint relation extraction model to perform entity extraction on the result obtained in the step 2), and obtaining and returning an extraction result.
The method is suitable for entity extraction in the intention recognition of the intelligent dialogue system, and can extract various types of entities in the corpus, particularly non-exhaustive types which cannot be predefined by a user. By integrating the method into the framework of the intelligent dialogue system, the intention recognition module based on the similarity model of grammar and semantics can be effectively matched and used, thereby improving the efficiency of the whole framework.
Preferably, the joint relationship extraction model is PRGC, and the PRGC model decomposes relationship extraction into three subtasks: relationship judgment, entity extraction and subject-object alignment.
Further, the joint relation extraction model PRGC,
firstly, coding a text of a speech by using a pre-trained BERT model and obtaining a vector representation of the text;
then, the relation which is possibly present in the text is predicted through the subtask judged by the relation, and the relation which is not possible to be present is filtered in the later entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host-guest alignment subtask, thereby extracting the triple corresponding to the text.
Preferably, the implementation process of implementing the joint relation extraction based on the PRGC model is as follows:
1) Inputting the linguistic data into a joint relation extraction model PRGC;
2) Obtaining a vector representation of a sentence based on a PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
Preferably, the process of using the method to realize entity extraction is as follows:
1) Inputting the linguistic data by a user;
2) Obtaining candidate answers according to the linguistic data input by the user through a grammar similarity model;
3) Inputting the candidate answers into a semantic similarity model to obtain a most similar corpus and determine an intention;
4) According to the most similar corpus, performing entity extraction by using a joint relation extraction model;
5) And obtaining the intention and the entity of the corpus.
The invention also claims an intelligent dialogue system, which comprises a grammar similarity calculation module, a semantic similarity calculation module and a joint relation extraction module,
the grammar similarity calculation module performs primary screening recall on a corpus which is predefined by a user through a grammar similarity model, and determines a part of corpora which are similar to the text input by the user in the platform corpus;
the semantic similarity calculation module calculates a corpus which is most similar to the input of the user in the result obtained by the grammar similarity calculation module through a semantic similarity model and determines the intention;
and the joint relation extraction module performs entity extraction on the result obtained by the semantic similarity calculation module through a joint relation extraction model to obtain an extraction result and returns the extraction result.
The entity extraction in the intention recognition of the intelligent dialogue system can be realized through the grammar similarity calculation module, the semantic similarity calculation module and the joint relation extraction module.
The system can realize entity extraction by the following modes:
1) Inputting the linguistic data by a user;
2) Obtaining candidate answers according to the linguistic data input by the user through a grammar similarity model;
3) Inputting the candidate answers into a semantic similarity model to obtain a most similar corpus and determine an intention;
4) According to the most similar corpus, performing entity extraction by using a joint relation extraction model;
5) And obtaining the intention and the entity of the corpus.
Preferably, the combined relationship extraction model is a PRGC (pre-generation, computational complexity graph), and the PRGC model decomposes the relationship extraction into three subtasks, namely relationship judgment, entity extraction and subject-object alignment;
firstly, a pre-trained BERT model is used for coding a text of a speech material and obtaining a vector representation of the text;
then, the relation which is possibly present in the text is predicted through the subtask judged by the relation, and the relation which is not possible to be present is filtered in the later entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host-guest alignment subtask, thereby extracting the triple corresponding to the text.
Further, the implementation process for implementing the joint relation extraction based on the PRGC model is as follows:
1) Inputting the corpora into a joint relation extraction model PRGC;
2) Obtaining a vector representation of the sentence based on the PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
The invention also claims an entity extraction device for an intelligent dialogue system, comprising: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is used for calling the machine readable program and executing the entity extraction method for the intelligent dialogue system.
The present invention also claims a computer readable medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the above-described entity extraction method for an intelligent dialog system.
Compared with the prior art, the entity extraction method for the intelligent dialogue system and the intelligent dialogue system have the following beneficial effects:
the method or the intelligent dialogue system can extract various types of entities in the corpus, particularly non-exhaustible types which cannot be defined by a user in advance. By integrating the method into the framework of the intelligent dialogue system, the intention recognition module based on the similarity model of grammar and semantics can be effectively used in a matched mode, and therefore the efficiency of the whole framework is improved.
Drawings
Fig. 1 is a diagram of an overall structure of an entity extraction method for an intelligent dialog system according to an embodiment of the present invention;
fig. 2 is a diagram of the overall structure of a PRGC according to an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the following specific examples.
The embodiment of the invention provides an entity extraction method for an intelligent dialog system, which is realized in the following way:
1. using a similarity calculation method based on grammar to carry out primary screening recall on a corpus which is defined by a user in advance and determine a part of corpora which are similar to a text input by the user in a platform corpus;
2. calculating a corpus which is most similar to the input of the user in the result obtained in the step 1 by using a similarity calculation model based on semantics and determining an intention;
3. and (3) performing entity extraction on the result obtained in the step (2) by using a joint relation extraction model, obtaining an extraction result and returning.
As shown in fig. 1, the process of using the method to realize entity extraction is as follows:
1) Inputting the linguistic data by the user;
2) Obtaining candidate answers according to the linguistic data input by the user through a grammar similarity model;
3) Inputting the candidate answers into a semantic similarity model to obtain a most similar corpus and determine an intention;
4) According to the most similar corpus, performing entity extraction by using a joint relation extraction model;
5) And obtaining the intention and the entity of the corpus.
The joint relation extraction model is a PRGC (probabilistic graphical user control) model, and the PRGC model decomposes relation extraction into three subtasks: judging the relationship, extracting the entity and aligning the subject and the object.
Firstly, a pre-trained BERT model is used for coding a text of a speech material and obtaining a vector representation of the text;
then, the relation which is possibly present in the text is predicted through the subtask judged by the relation, and the relation which is not possible to be present is filtered in the later entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host-guest alignment subtask, thereby extracting the triple corresponding to the text.
As shown in fig. 2, the implementation process of implementing the joint relation extraction based on the PRGC model is as follows:
1) Inputting the corpora into a joint relation extraction model PRGC;
2) Obtaining a vector representation of a sentence based on a PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
The method is suitable for entity extraction in the intention recognition of the intelligent dialogue system, and can extract various types of entities in the corpus, particularly non-exhaustible types which cannot be predefined by a user. By integrating the method into the framework of the intelligent dialogue system, the intention recognition module based on the similarity model of grammar and semantics can be effectively matched and used, thereby improving the efficiency of the whole framework.
The embodiment of the invention also provides an intelligent dialogue system which comprises a grammar similarity calculation module, a semantic similarity calculation module and a joint relation extraction module,
the grammar similarity calculation module performs primary screening recall on a corpus which is predefined by a user through a grammar similarity model, and determines a part of corpora which are similar to the text input by the user in the platform corpus;
the semantic similarity calculation module calculates a corpus which is most similar to the input of the user in the result obtained by the grammar similarity calculation module through a semantic similarity model and determines the intention;
and the joint relation extraction module performs entity extraction on the result obtained by the semantic similarity calculation module through a joint relation extraction model to obtain an extraction result and returns the extraction result.
The entity extraction in the intention recognition of the intelligent dialogue system can be realized through the grammar similarity calculation module, the semantic similarity calculation module and the joint relation extraction module.
The system can realize entity extraction by the following modes:
1) Inputting the linguistic data by a user;
2) Obtaining candidate answers according to the linguistic data input by the user through a grammar similarity model;
3) Inputting the candidate answers into a semantic similarity model to obtain a most similar corpus and determine an intention;
4) According to the most similar corpus, performing entity extraction by using a joint relation extraction model;
5) And obtaining the intention and the entity of the corpus.
The system comprises a joint relation extraction model, a physical relation analysis model and a physical relation matching model, wherein the joint relation extraction model is a PRGC (physical resource control), and the PRGC model decomposes the relation extraction into three subtasks, namely relation judgment, entity extraction and subject-object alignment;
firstly, a pre-trained BERT model is used for coding a text of a speech material and obtaining a vector representation of the text;
then, the subtask judged through the relation predicts the relation possibly appearing in the text, and the relation which is not possible to exist is filtered out in the entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host-guest alignment subtask, thereby extracting the triple corresponding to the text.
The implementation process for realizing the extraction of the joint relation based on the PRGC model is as follows:
1) Inputting the linguistic data into a joint relation extraction model PRGC;
2) Obtaining a vector representation of the sentence based on the PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
An embodiment of the present invention further provides an entity extraction apparatus for an intelligent dialog system, including: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine readable program to perform the entity extraction method for the intelligent dialog system described in the above embodiments.
An embodiment of the present invention further provides a computer-readable medium, where the computer-readable medium stores computer instructions, and when the computer instructions are executed by a processor, the processor is enabled to execute the entity extraction method for an intelligent dialog system described in the foregoing embodiment. Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the embodiments described above are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
While the invention has been particularly shown and described with reference to the preferred embodiments and drawings, it is not intended to be limited to the specific embodiments disclosed, and it will be understood by those skilled in the art that various other combinations of code approval means and various embodiments described above may be made, and such other embodiments are within the scope of the present invention.
Claims (10)
1. An entity extraction method for an intelligent dialogue system is characterized by being realized as follows:
1) Performing primary screening recall on a corpus which is predefined by a user by using a grammar-based similarity calculation method, and determining a part of corpora which are similar to the text input by the user in a platform corpus;
2) Calculating a corpus which is most similar to the input of the user in the result obtained in the step 1) by using a similarity calculation model based on the semantics and determining the intention;
3) And 3, using a joint relation extraction model to perform entity extraction on the result obtained in the step 2), and obtaining and returning an extraction result.
2. The entity extraction method for the intelligent dialog system according to claim 1, wherein the joint relationship extraction model is PRGC, and the PRGC model decomposes the relationship extraction into three subtasks: relationship judgment, entity extraction and subject-object alignment.
3. The entity extraction method for intelligent dialogue system according to claim 2, wherein the joint relation extraction model PRGC,
firstly, a pre-trained BERT model is used for coding a text of a speech material and obtaining a vector representation of the text;
then, the relation which is possibly present in the text is predicted through the subtask judged by the relation, and the relation which is not possible to be present is filtered in the later entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host and guest alignment subtask, thereby extracting the triple corresponding to the text.
4. The entity extraction method for intelligent dialog system of claim 3, wherein the implementation process of the joint relationship extraction based on the PRGC model is as follows:
1) Inputting the linguistic data into a joint relation extraction model PRGC;
2) Obtaining a vector representation of a sentence based on a PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
5. An entity extraction method for intelligent dialogue system according to any of claims 1-4, characterized in that, the entity extraction process using the method is as follows:
1) Inputting the linguistic data by a user;
2) Obtaining candidate answers according to the linguistic data input by the user through a grammar similarity model;
3) Inputting the candidate answers into a semantic similarity model to obtain a most similar corpus and determine an intention;
4) According to the most similar corpus, performing entity extraction by using a joint relation extraction model;
5) And obtaining the intention and the entity of the corpus.
6. An intelligent dialogue system is characterized by comprising a grammar similarity calculation module, a semantic similarity calculation module and a joint relation extraction module,
the grammar similarity calculation module performs primary screening recall on a corpus which is predefined by a user through a grammar similarity model, and determines a part of corpora which are similar to the text input by the user in the platform corpus;
the semantic similarity calculation module calculates a corpus which is most similar to the input of the user in the result obtained by the grammar similarity calculation module through a semantic similarity model and determines the intention;
and the joint relation extraction module performs entity extraction on the result obtained by the semantic similarity calculation module through a joint relation extraction model to obtain an extraction result and returns the extraction result.
7. The intelligent dialogue system of claim 6, wherein the joint relationship extraction model is a PRGC, and the PRGC model decomposes relationship extraction into three subtasks, namely relationship judgment, entity extraction and subject-object alignment;
firstly, coding a text of a speech by using a pre-trained BERT model and obtaining a vector representation of the text;
then, the subtask judged through the relation predicts the relation possibly appearing in the text, and the relation which is not possible to exist is filtered out in the entity extraction stage;
adding the relationship information into an entity extraction module, and extracting corresponding subject entities and object entities from each relationship;
and finally, aligning the host entity and the guest entity by using the global entity correlation matrix obtained by the host and guest alignment subtask, thereby extracting the triple corresponding to the text.
8. The intelligent dialog system of claim 7, wherein the PRGC-based implementation of the joint relationship extraction is as follows:
1) Inputting the linguistic data into a joint relation extraction model PRGC;
2) Obtaining a vector representation of the sentence based on the PRGC encoder;
3) Obtaining a potential relation through potential relation prediction; and forming a global entity correlation matrix;
4) Adding the potential relations into an entity extraction model, extracting corresponding subject entities and object entities from each relation respectively, and carrying out sequence marking on specific relations;
5) And acquiring the global entity correlation matrix, and aligning the host entity and the guest entity so as to extract the host-guest triple corresponding to the text.
9. An entity extraction apparatus for an intelligent dialogue system, comprising: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor, configured to invoke the machine readable program to perform the entity extraction method for an intelligent dialog system of any of claims 1 to 5.
10. Computer readable medium, characterized in that it has stored thereon computer instructions which, when executed by a processor, cause the processor to execute the entity extraction method for intelligent dialog systems of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211126920.9A CN115587161A (en) | 2022-09-16 | 2022-09-16 | Entity extraction method for intelligent dialogue system and intelligent dialogue system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211126920.9A CN115587161A (en) | 2022-09-16 | 2022-09-16 | Entity extraction method for intelligent dialogue system and intelligent dialogue system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115587161A true CN115587161A (en) | 2023-01-10 |
Family
ID=84778387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211126920.9A Pending CN115587161A (en) | 2022-09-16 | 2022-09-16 | Entity extraction method for intelligent dialogue system and intelligent dialogue system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115587161A (en) |
-
2022
- 2022-09-16 CN CN202211126920.9A patent/CN115587161A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096570B (en) | Intention identification method and device applied to intelligent customer service robot | |
| CN109033305B (en) | Question answering method, device and computer readable storage medium | |
| US8798990B2 (en) | Methods and systems for natural language understanding using human knowledge and collected data | |
| US8332205B2 (en) | Mining transliterations for out-of-vocabulary query terms | |
| KR20200108775A (en) | Training corpus generating method, apparatus, device and storage medium | |
| US20140163951A1 (en) | Hybrid adaptation of named entity recognition | |
| CN108710704B (en) | Method and device for determining conversation state, electronic equipment and storage medium | |
| CN114580382A (en) | Text error correction method and device | |
| CN112967144B (en) | Financial credit risk event extraction method, readable storage medium and device | |
| CN111611349A (en) | Voice query method and device, computer equipment and storage medium | |
| CN111414745A (en) | Text punctuation determination method and device, storage medium and electronic equipment | |
| CN112101032A (en) | Named entity identification and error correction method based on self-distillation | |
| CN114020886A (en) | Speech intention recognition method, device, equipment and storage medium | |
| CN113380223A (en) | Method, device, system and storage medium for disambiguating polyphone | |
| CN103678270A (en) | Semantic unit extracting method and semantic unit extracting device | |
| CN113705207A (en) | Grammar error recognition method and device | |
| CN112633007A (en) | Semantic understanding model construction method and device and semantic understanding method and device | |
| CN112380861A (en) | Model training method and device and intention identification method and device | |
| CN115587161A (en) | Entity extraction method for intelligent dialogue system and intelligent dialogue system | |
| CN115936010A (en) | Text abbreviation data processing method and device | |
| CN116186219A (en) | Man-machine dialogue interaction method, system and storage medium | |
| CN115309994A (en) | Location search method, electronic device, and storage medium | |
| CN115689603A (en) | User feedback information collection method and device and user feedback system | |
| CN114492396A (en) | Text error correction method for automobile proper nouns and readable storage medium | |
| CN114528851A (en) | Reply statement determination method and device, electronic equipment and storage medium |
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 |