CN117421403A - Intelligent dialogue method and device and electronic equipment - Google Patents
Intelligent dialogue method and device and electronic equipment Download PDFInfo
- Publication number
- CN117421403A CN117421403A CN202311311457.XA CN202311311457A CN117421403A CN 117421403 A CN117421403 A CN 117421403A CN 202311311457 A CN202311311457 A CN 202311311457A CN 117421403 A CN117421403 A CN 117421403A
- Authority
- CN
- China
- Prior art keywords
- current
- question
- determining
- dialogue
- 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
- 238000000034 method Methods 0.000 title claims abstract description 85
- 230000004044 response Effects 0.000 claims abstract description 65
- 230000008569 process Effects 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 32
- 230000011218 segmentation Effects 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
The disclosure provides an intelligent dialogue method, an intelligent dialogue device and electronic equipment, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, natural language processing, intelligent searching and the like. The specific implementation scheme is as follows: acquiring a current problem in a current dialogue process, a dialogue object corresponding to the current problem and a response role for carrying out response processing on the current problem; acquiring role related data of a response role; determining a prompt text corresponding to the current problem according to the current problem and the role related data; according to the current question and the prompt text corresponding to the current question, an answer corresponding to the current question is determined, so that the answer can be determined by combining external role related data, the authenticity and naturalness of a designated role can be better simulated, the matching degree between the answer obtained by determination and the current question is improved, and the accuracy of the answer obtained by determination is improved.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, natural language processing, intelligent searching and the like, and particularly relates to an intelligent dialogue method, an intelligent dialogue device and electronic equipment.
Background
At present, with the continuous development of large model technology, a large model has stronger generalization capability, and can learn more abstract and general characteristics, so that the behaviors and languages of appointed roles can be better simulated. The existing large model only simulates the behavior or language of a designated character based on the features learned in the training process, the considered features are fewer, the reality and naturalness of the designated character are poorer, the matching degree between the answers given to the questions and the questions is poorer, and the accuracy of the given answers is lower.
Disclosure of Invention
The disclosure provides an intelligent dialogue method, an intelligent dialogue device and electronic equipment.
According to an aspect of the present disclosure, there is provided an intelligent dialog method, the method including: acquiring a current problem in a current dialogue process, a dialogue object corresponding to the current problem and a response role for performing response processing on the current problem; acquiring role related data of the response role; determining a prompt text corresponding to the current problem according to the current problem and the role related data; and determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
According to another aspect of the present disclosure, there is provided an intelligent dialog device, the device comprising: the first acquisition module is used for acquiring a current problem in a current dialogue process, a dialogue object corresponding to the current problem and a response role for carrying out response processing on the current problem; the second acquisition module is used for acquiring the role related data of the response role; the first determining module is used for determining a prompt text corresponding to the current problem according to the current problem and the role related data; and the second determining module is used for determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the intelligent dialog method set forth above in the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the intelligent dialogue method proposed above by the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the intelligent dialog method set forth above in the present disclosure.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a flow diagram of a smart dialog;
FIG. 5 is a schematic diagram according to a fourth embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing the intelligent conversation method of embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
At present, with the continuous development of large model technology, a large model has stronger generalization capability, and can learn more abstract and general characteristics, so that the behaviors and languages of appointed roles can be better simulated. The existing large model only simulates the behavior or language of a designated character based on the features learned in the training process, the considered features are fewer, the reality and naturalness of the designated character are poorer, the matching degree between the answers given to the questions and the questions is poorer, and the accuracy of the given answers is lower.
Aiming at the problems, the disclosure provides an intelligent dialogue method, an intelligent dialogue device and electronic equipment.
Fig. 1 is a schematic diagram of a first embodiment of the present disclosure, and it should be noted that the intelligent dialogue method according to the embodiment of the present disclosure may be applied to an intelligent dialogue apparatus, where the apparatus may be disposed in an electronic device, so that the electronic device may perform an intelligent dialogue function.
The electronic device may be any device with computing capability, for example, may be a personal computer (Personal Computer, abbreviated as PC), a mobile terminal, a server, etc., and the mobile terminal may be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a smart speaker, a robot, etc., and have various hardware devices such as an operating system, a touch screen, and/or a display screen.
The intelligent dialogue device may be software in the electronic device. For example, search software, chat software, dialogue software, etc. The dialogue object can log in the software through account numbers and the like to perform dialogue with the software.
In the following embodiments, an execution body is described as an example of an electronic device. The electronic device may be a hardware device used when the dialogue object logs in the software through the account, or a background server corresponding to the software, etc.
As shown in fig. 1, the intelligent dialogue method may include the steps of:
step 101, obtaining a current problem in a current dialogue process, a dialogue object corresponding to the current problem, and a response role for performing response processing on the current problem.
In the embodiments of the present disclosure, the current session may be a session between the session object and the electronic device playing the role of the response. The current dialogue process may include one or more rounds of dialogue. The current question may be a question currently posed by the dialog object.
The dialog object corresponding to the current problem may be an object that presents the current problem. The response role of performing response processing on the current problem may be a role played by the electronic device when performing response processing on the current problem. Wherein the response role is, for example, miss Mild Miss tongqin, etc. Wherein, different response roles have different response styles.
Step 102, acquiring role related data of the response role.
In an embodiment of the present disclosure, the role related data may include at least one of the following data: character attribute data, character extension knowledge data, and each round of history conversations between a conversation object and a response character.
The character attribute data may include a plurality of character attribute items and attribute contents under the character attribute items. Among them are character attribute items such as name, alias, hobbies, special skills, place of birth, etc. Taking a role attribute item as an example, the attribute content under the role attribute item may be a specific name.
The role-expanding knowledge data may be knowledge data in a page obtained by searching in a search engine by taking a role as a keyword. The pages include, for example, pages of characters and the like.
The history dialogs of each round between the dialog object and the response role may refer to history dialogs of each round in a current dialog process between the dialog object and the response role, and/or history dialogs of each round in a history dialog process between the dialog object and the response role.
The method comprises the steps of combining character attribute data, character expansion knowledge data, at least one data in each round of history dialogue between a dialogue object and a response character, determining a prompt text, and further determining an answer corresponding to a question, so that the electronic equipment can simulate the behavior or language of a designated character by combining external data, the considered characteristics are more, the authenticity and naturalness of the designated character are better, and the accuracy of the answer given to the question is high.
And step 103, determining a prompt text corresponding to the current question according to the current question and the role related data.
In the embodiment of the present disclosure, in the case where the role related data includes role attribute data, the process of executing step 103 by the electronic device may be, for example, performing word segmentation on the current problem, and obtaining each word segmentation word in the current problem; acquiring target role attribute items matched with word segmentation words in the plurality of role attribute items; and determining the attribute content under the attribute item of the target role as a prompt text corresponding to the current problem.
The target role attribute items matched with the word segmentation words can be words which are completely the same as the word segmentation words; alternatively, words having the same meaning or similar meaning to the word-segmentation words may be used. Taking the word segmentation word as a name as an example, the target role attribute item matched with the word segmentation word can be, for example, the name.
Specifically, the electronic device may obtain a vectorized representation of each word segmentation term in the current problem; obtaining vectorization representation of each character attribute item in the character attribute data; determining vector similarity between the vectorized representation of each word and the vectorized representation of each character attribute term; and selecting target character attribute items matched with the word segmentation words from the character attribute items according to the vector similarity.
The character attribute data of the character attribute data are searched by combining word segmentation words in the current question, target character attribute items matched with the word segmentation words are obtained, further attribute contents under the target character attribute items are determined to be prompt texts, and an answer corresponding to the current question can be accurately generated according to the attribute contents under the condition that the current question is the query of the attribute contents, so that the accuracy of determining the obtained answer is further improved.
Step 104, determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
In the embodiment of the present disclosure, in the case where the character related data includes character attribute data, the prompt text corresponding to the current question may be attribute content under a target character attribute item matched with the current question in the character attribute data. Correspondingly, the electronic device may perform the process of step 104 by, for example, inputting the current question and the attribute content into the question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
The question-answer dialogue model can fully extract the characteristics of the current question and the attribute content, and the answer corresponding to the current question is determined by combining the characteristics, so that the matching degree between the current question and the answer can be further improved, and the accuracy of determining the obtained answer is further improved.
According to the intelligent dialogue method, the current problem in the current dialogue process, the dialogue object corresponding to the current problem and the response role for carrying out response processing on the current problem are obtained; acquiring role related data of a response role; determining a prompt text corresponding to the current problem according to the current problem and the role related data; according to the current question and the prompt text corresponding to the current question, an answer corresponding to the current question is determined, so that the answer can be determined by combining external role related data, the authenticity and naturalness of a designated role can be better simulated, the matching degree between the answer obtained by determination and the current question is improved, and the accuracy of the answer obtained by determination is improved.
Under the condition that the character related data comprises character expansion knowledge data, the answer corresponding to the current question can be determined by combining the target paragraph text matched with the current question in the character expansion knowledge data, and the accuracy of determining the obtained answer is further improved. As shown in fig. 2, fig. 2 is a schematic diagram of a second embodiment according to the present disclosure, and the embodiment shown in fig. 2 may include the following steps:
step 201, obtaining a current problem in a current dialogue process, a dialogue object corresponding to the current problem, and a response role for performing response processing on the current problem.
Step 202, acquiring role related data of a response role; the character related data includes character extension knowledge data.
In the embodiment of the disclosure, the role-expanding knowledge data may be knowledge data in a page obtained by searching in a search engine by using a role as a keyword. The pages include, for example, pages of characters, such as encyclopedia pages, and the like.
Step 203, obtaining each paragraph text in the character extension knowledge data.
In the embodiments of the present disclosure, to ensure that subsequent electronic devices are able to vectorize paragraph text, the total number of words of the paragraph text needs to be limited to ensure the accuracy of determining the resulting vectorized representation. Correspondingly, after step 203, the electronic device may also perform the following procedure: determining the total word number of the paragraph text aiming at each paragraph text in the character expansion knowledge data; splitting paragraph text by taking sentences as a unit under the condition that the total word number is greater than or equal to a preset word number threshold value to obtain a plurality of sub-paragraph text; and determining the sub-paragraph text as paragraph text in the character extension knowledge data.
The step of splitting the paragraph text by taking the sentence as a unit means that the sentence in the paragraph text is not destroyed during the splitting process, and the sentence in each sub paragraph text needs to be complete so as to ensure the integrity of the semantics in the sentence.
Step 204, obtaining the target paragraph text matched with the current question in each paragraph text.
In the embodiment of the present disclosure, the electronic device performs the process of step 204 may be, for example, obtaining a first vector representation of the current problem; acquiring a second vector representation of each paragraph text in the character extension knowledge data; for each paragraph text in the character expansion knowledge data, determining a vector similarity between a second vector representation of the paragraph text and a first vector representation of the current question; in the event that the vector similarity is greater than or equal to the first similarity threshold, the paragraph text is determined to be the target paragraph text.
Wherein, in case the number of the target paragraph texts is large, the electronic device may further perform the following procedure: performing descending order sorting treatment on the multiple target paragraph texts according to the vector similarity to obtain a sorting result; and filtering the target paragraph text with the rear sequence in the sequence result.
The method comprises the steps of combining vector representation, and determining vector similarity between each paragraph text and a current problem in character expansion knowledge data; and then the target paragraph text is selected by combining the vector similarity, so that the matching degree between the selected target paragraph text and the current question can be improved, the accuracy of the determined prompt text is improved, and the accuracy of the determined answer is improved.
In step 205, the target paragraph text is determined as the prompt text corresponding to the current question.
Step 206, determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
In the embodiment of the present disclosure, in the case where the character related data includes character expansion knowledge data, the prompt text corresponding to the current question may be a target paragraph text matching the current question in the character expansion knowledge data. Correspondingly, the electronic device may perform the process of step 206, for example, by inputting the current question and the text of the target paragraph into the question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
In the case that the character related data includes character attribute data and character expansion knowledge data, the prompt text corresponding to the current question may include attribute content under a target character attribute item matched with the current question in the character attribute data, and a target paragraph text matched with the current question in the character expansion knowledge data. Correspondingly, the electronic device may perform the process of step 206, for example, by performing a splicing process on the attribute content and the target paragraph text to obtain a spliced text; and inputting the spliced text and the current question into a question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
It should be noted that, for details of step 201 to step 202, and step 206, reference may be made to step 101 to step 102, and step 104 in the embodiment shown in fig. 1, and detailed description thereof will not be provided here.
According to the intelligent dialogue method, the current problem in the current dialogue process, the dialogue object corresponding to the current problem and the response role for carrying out response processing on the current problem are obtained; acquiring role related data of a response role; the role related data includes role extension knowledge data; acquiring each paragraph text in the character expansion knowledge data; obtaining target paragraph texts matched with the current problem in each paragraph text; determining a target paragraph text as a prompt text corresponding to the current problem; according to the current question and the prompt text corresponding to the current question, an answer corresponding to the current question is determined, so that the answer can be determined by combining external role related data, the authenticity and naturalness of a designated role can be better simulated, the matching degree between the answer obtained by determination and the current question is improved, and the accuracy of the answer obtained by determination is improved.
Under the condition that the role related data comprises each round of history dialogue between the dialogue object and the response role, the answer corresponding to the current question can be determined by combining the target history dialogue matched with the current question in each round of history dialogue, and the accuracy of determining the obtained answer is further improved. As shown in fig. 3, fig. 3 is a schematic diagram of a third embodiment according to the present disclosure, and the embodiment shown in fig. 3 may include the following steps:
Step 301, obtaining a current problem in a current dialogue process, a dialogue object corresponding to the current problem, and a response role for performing response processing on the current problem.
Step 302, acquiring role related data of a response role; the role related data includes each round of historical dialog between a dialog object and a response role.
In the embodiment of the disclosure, each round of history dialogue between the dialogue object and the response role may refer to each round of history dialogue in the current dialogue process between the dialogue object and the response role, and/or each round of history dialogue in the history dialogue process between the dialogue object and the response role.
Step 303, obtaining a target historical problem matched with the current problem in the historical problems of each round of historical conversations.
In the embodiment of the present disclosure, the electronic device performs the process of step 303 may, for example, be to obtain a first vector representation of the current problem; acquiring a third vector representation of the history problems in each round of history dialogue; for each historical problem in each round of historical conversations, determining a vector similarity between a third vector representation of the historical problem and a first vector representation of the current problem; in the event that the vector similarity is greater than or equal to the second similarity threshold, the historical problem is determined to be a target historical problem.
Wherein, in case the number of target history problems is large, the electronic device may further perform the following procedure: performing descending order sorting treatment on the plurality of target history problems according to the vector similarity to obtain a sorting result; and filtering the target history problems with the later sequencing in the sequencing result.
The method comprises the steps of combining vector representation, and determining vector similarity between a historical problem and a current problem in each round of historical dialogue between a dialogue object and a response role; and then, the target historical problems are selected by combining the vector similarity, so that the matching degree between the selected target historical problems and the current problems can be improved, the accuracy of the prompt text obtained by determination is improved, and the accuracy of the answer obtained by determination is improved.
And 304, determining a target history dialogue to which the target history problem belongs as a prompt text corresponding to the current problem.
Step 305, determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
In the embodiment of the disclosure, in the case that the role related data includes each round of history dialogs between the dialog object and the response role, the prompt text corresponding to the current problem may be a target history dialog matching the current problem in each round of history dialogs. Correspondingly, the electronic device may perform the process of step 305, for example, by inputting the current question and the target history dialogue into the question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
In the case that the character related data includes character attribute data, character expansion knowledge data and each round of history dialogue between the dialogue object and the response character, the prompt text corresponding to the current problem may include attribute content under a target character attribute item matched with the current problem in the character attribute data, a target paragraph text matched with the current problem in the character expansion knowledge data, and a target history dialogue matched with the current problem in each round of history dialogue. Correspondingly, the electronic device may perform the step 305, for example, by performing a splicing process on the attribute content, the target paragraph text, and the target history dialogue to obtain a spliced text; and inputting the spliced text and the current question into a question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
In the embodiment of the disclosure, each round of history dialogue, and a third vector representation of the history problem in each round of history dialogue, are obtained from the vector index. Correspondingly, after step 305, the electronic device may also perform the following procedure: determining a current dialogue according to the current question and an answer corresponding to the current question; the current dialog and the first vector representation of the current problem in the current dialog are updated into the vector index.
The method comprises the steps of updating a vector index according to a current question and an answer corresponding to the current question; when the electronic equipment is combined with the vector index to determine the target history dialogue, the dialogue closest to the current problem can be considered, so that the accuracy of the determined target history dialogue can be further improved, and the accuracy of the determined answer is further improved.
It should be noted that, for the details of step 301 to step 302 and step 305, reference may be made to step 101 to step 102 and step 104 in the embodiment shown in fig. 1, and the details will not be described here.
According to the intelligent dialogue method, the current problem in the current dialogue process, the dialogue object corresponding to the current problem and the response role for carrying out response processing on the current problem are obtained; acquiring role related data of a response role; the role related data comprises each round of history dialogue between dialogue objects and response roles; acquiring target historical problems matched with the current problems in the historical problems of each round of historical conversations; determining a target history dialogue to which the target history problem belongs as a prompt text corresponding to the current problem; according to the current question and the prompt text corresponding to the current question, an answer corresponding to the current question is determined, so that the answer can be determined by combining external role related data, the authenticity and naturalness of a designated role can be better simulated, the matching degree between the answer obtained by determination and the current question is improved, and the accuracy of the answer obtained by determination is improved.
The following examples are illustrative. As shown in fig. 4, a flow chart of the intelligent dialogue is shown. In fig. 4, the following steps may be included: (1) The plug-in knowledge (character related data) is acquired, including character attributes (character attribute data), key dialogs (history dialogs between dialog objects and response characters), and documents (character expansion knowledge data). (2) For the character attribute, the inverted index of the character attribute (including the second vector representation of each character attribute item in the character attribute) is searched in combination with the first vector representation of the question (current question), and a search result (attribute content under the matched target character attribute item) is obtained. (3) Performing an Embedding calculation on the historical problems in the key dialogue, and obtaining a third-level representation of the historical problems; carrying out document segmentation processing on the document to obtain each paragraph text; and performing an encoding calculation on each paragraph text to obtain a second vector representation of each paragraph text. (4) In combination with the first vector representation of the question, a dialog index (which includes a third vector representation of each history question and a second vector representation of each paragraph text) is retrieved to obtain a retrieval result (a matching target paragraph text and a matching target history dialog). (5) And integrating the search results, organizing a dialogue, obtaining a prompt (prompt text corresponding to the current question), requesting a large model (question-answer dialogue model), and returning an answer (answer corresponding to the current question).
In order to implement the above embodiment, the present disclosure further provides an intelligent dialogue device. As shown in fig. 5, fig. 5 is a schematic diagram according to a fourth embodiment of the present disclosure. The intelligent dialog device 50 may include: a first acquisition module 501, a second acquisition module 502, a first determination module 503, and a second determination module 504.
The first obtaining module 501 is configured to obtain a current problem in a current dialogue process, a dialogue object corresponding to the current problem, and a response role for performing response processing on the current problem; a second obtaining module 502, configured to obtain role related data of the response role; a first determining module 503, configured to determine a prompt text corresponding to the current question according to the current question and the role related data; a second determining module 504, configured to determine an answer corresponding to the current question according to the current question and a prompt text corresponding to the current question.
As one possible implementation of the embodiments of the present disclosure, the role related data includes at least one of the following data: character attribute data, character extension knowledge data, and each round of historical dialog between the dialog object and the response character.
As one possible implementation of the embodiments of the present disclosure, the role related data includes role attribute data; the character attribute data comprises a plurality of character attribute items and attribute contents under the character attribute items; the first determining module 503 is specifically configured to perform word segmentation processing on the current problem, and obtain each word segmentation word in the current problem; acquiring target role attribute items matched with the word segmentation words in the plurality of role attribute items; and determining the attribute content under the attribute item of the target role as a prompt text corresponding to the current problem.
As one possible implementation of the embodiments of the present disclosure, the role related data includes role extension knowledge data; the character extension knowledge data comprises a plurality of paragraph texts; the first determining module 503 includes: a first acquisition unit, a second acquisition unit, and a first determination unit; the first obtaining unit is used for obtaining each paragraph text in the character expansion knowledge data; the second obtaining unit is used for obtaining target paragraph texts matched with the current problem in the paragraph texts; the first determining unit is configured to determine the target paragraph text as a prompt text corresponding to the current question.
As one possible implementation manner of the embodiment of the present disclosure, the first determining module 503 further includes: the system comprises a second determining unit, a splitting processing unit and a third determining unit; the second determining unit is configured to determine, for each paragraph text in the character expansion knowledge data, a total word number of the paragraph text; the splitting processing unit is used for splitting the paragraph text by taking a sentence as a unit to obtain a plurality of sub-paragraph texts under the condition that the total word number is greater than or equal to a preset word number threshold value; the third determining unit is configured to determine the sub-paragraph text as a paragraph text in the role extension knowledge data.
As one possible implementation manner of the embodiments of the present disclosure, the second obtaining unit is specifically configured to obtain a first vector representation of the current problem; acquiring a second vector representation of each paragraph text in the character extension knowledge data; for each paragraph text in the character expansion knowledge data, determining a vector similarity between a second vector representation of the paragraph text and a first vector representation of the current question; and determining the paragraph text as the target paragraph text under the condition that the vector similarity is greater than or equal to a first similarity threshold value.
As one possible implementation of the embodiments of the present disclosure, the role related data includes, for each round of historical conversations between the conversation object and the response role; the first determining module 503 includes: a third acquisition unit and a fourth determination unit; the third obtaining unit is used for obtaining a target historical problem matched with the current problem in the historical problems of each round of historical conversations; the fourth determining unit is configured to determine, as a prompt text corresponding to the current question, a target history dialogue to which the target history question belongs.
As one possible implementation manner of the embodiments of the present disclosure, the third obtaining unit is specifically configured to obtain a first vector representation of the current problem; acquiring a third vector representation of the history problems in each round of history dialogue; for each historical question in each round of historical conversations, determining a vector similarity between a third vector representation of the historical question and a first vector representation of the current question; and determining the history problem as the target history problem in the case that the vector similarity is greater than or equal to a second similarity threshold.
As one possible implementation manner of the embodiment of the present disclosure, each round of history dialogue, and a third vector representation of a history problem in each round of history dialogue are obtained from a vector index; the apparatus further comprises: a third determination module and an update module; the third determining module is configured to determine a current dialogue according to the current question and an answer corresponding to the current question; the updating module is configured to update the current dialogue and a first vector representation of the current problem in the current dialogue into the vector index.
As one possible implementation of the embodiments of the present disclosure, the prompt text includes: attribute contents under a target character attribute item matched with the current problem in the character attribute data, target paragraph text matched with the current problem in the character expansion knowledge data, and target history dialogue matched with the current problem in each round of history dialogue; the second determining module 504 is specifically configured to perform a stitching process on the attribute content under the attribute item of the target role, the target paragraph text, and the target history dialogue, so as to obtain a stitched text; and inputting the current question and the spliced text into a question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
According to the intelligent dialogue device, the current problem in the current dialogue process, the dialogue object corresponding to the current problem and the response role for carrying out response processing on the current problem are obtained; acquiring role related data of a response role; determining a prompt text corresponding to the current problem according to the current problem and the role related data; according to the current question and the prompt text corresponding to the current question, an answer corresponding to the current question is determined, so that the answer can be determined by combining external role related data, the authenticity and naturalness of a designated role can be better simulated, the matching degree between the answer obtained by determination and the current question is improved, and the accuracy of the answer obtained by determination is improved.
In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user are performed on the premise of proving the consent of the user, and all the processes accord with the regulations of related laws and regulations, and the public welfare is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the intelligent dialog method. For example, in some embodiments, the intelligent dialog method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the intelligent dialog method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the intelligent dialog method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (23)
1. A method of intelligent dialog, the method comprising:
acquiring a current problem in a current dialogue process, a dialogue object corresponding to the current problem and a response role for performing response processing on the current problem;
acquiring role related data of the response role;
determining a prompt text corresponding to the current problem according to the current problem and the role related data;
And determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
2. The method of claim 1, wherein the persona-related data includes at least one of: character attribute data, character extension knowledge data, and each round of historical dialog between the dialog object and the response character.
3. A method according to claim 1 or 2, wherein the role related data comprises role attribute data; the character attribute data comprises a plurality of character attribute items and attribute contents under the character attribute items;
the determining, according to the current question and the role related data, a prompt text corresponding to the current question includes:
performing word segmentation processing on the current problem to obtain each word segmentation word in the current problem;
acquiring target role attribute items matched with the word segmentation words in the plurality of role attribute items;
and determining the attribute content under the attribute item of the target role as a prompt text corresponding to the current problem.
4. The method of claim 1 or 2, wherein the role related data includes role extension knowledge data; the character extension knowledge data comprises a plurality of paragraph texts;
The determining, according to the current question and the role related data, a prompt text corresponding to the current question includes:
acquiring each paragraph text in the character expansion knowledge data;
obtaining target paragraph texts matched with the current problem in each paragraph text;
and determining the target paragraph text as a prompt text corresponding to the current problem.
5. The method of claim 4, wherein after obtaining the respective paragraph text in the persona extension knowledge data, the method further comprises:
determining the total word number of each paragraph text in the character expansion knowledge data;
splitting the paragraph text by taking a sentence as a unit under the condition that the total word number is greater than or equal to a preset word number threshold value to obtain a plurality of sub-paragraph texts;
and determining the sub-paragraph text as paragraph text in the character extension knowledge data.
6. The method of claim 4, wherein the obtaining the target paragraph text of the respective paragraph text that matches the current question comprises:
acquiring a first vector representation of the current problem;
Acquiring a second vector representation of each paragraph text in the character extension knowledge data;
for each paragraph text in the character expansion knowledge data, determining a vector similarity between a second vector representation of the paragraph text and a first vector representation of the current question;
and determining the paragraph text as the target paragraph text under the condition that the vector similarity is greater than or equal to a first similarity threshold value.
7. The method of claim 1 or 2, wherein the persona-related data includes a respective round of historical dialog between the dialog object and the responsive persona;
the determining, according to the current question and the role related data, a prompt text corresponding to the current question includes:
acquiring target historical problems matched with the current problems in the historical problems of each round of historical conversations;
and determining the target history dialogue to which the target history problem belongs as a prompt text corresponding to the current problem.
8. The method of claim 7, wherein the obtaining a target historical question that matches the current question from among the historical questions of each round of historical conversations comprises:
Acquiring a first vector representation of the current problem;
acquiring a third vector representation of the history problems in each round of history dialogue;
for each historical question in each round of historical conversations, determining a vector similarity between a third vector representation of the historical question and a first vector representation of the current question;
and determining the history problem as the target history problem in the case that the vector similarity is greater than or equal to a second similarity threshold.
9. The method of claim 8, wherein each round of history conversations, and a third vector representation of history problems in each round of history conversations, are obtained from a vector index; after determining the answer corresponding to the current question according to the current question and the prompt text corresponding to the current question, the method further comprises:
determining a current dialogue according to the current question and an answer corresponding to the current question;
and updating the current dialogue and the first vector representation of the current problem in the current dialogue into the vector index.
10. The method of claim 2, wherein the hint text comprises: attribute contents under a target character attribute item matched with the current problem in the character attribute data, target paragraph text matched with the current problem in the character expansion knowledge data, and target history dialogue matched with the current problem in each round of history dialogue;
The determining the answer corresponding to the current question according to the current question and the prompt text corresponding to the current question includes:
performing splicing processing on the attribute content under the attribute item of the target role, the target paragraph text and the target history dialogue to obtain a spliced text;
and inputting the current question and the spliced text into a question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
11. An intelligent dialog device, the device comprising:
the first acquisition module is used for acquiring a current problem in a current dialogue process, a dialogue object corresponding to the current problem and a response role for carrying out response processing on the current problem;
the second acquisition module is used for acquiring the role related data of the response role;
the first determining module is used for determining a prompt text corresponding to the current problem according to the current problem and the role related data;
and the second determining module is used for determining an answer corresponding to the current question according to the current question and the prompt text corresponding to the current question.
12. The apparatus of claim 11, wherein the persona-related data comprises at least one of: character attribute data, character extension knowledge data, and each round of historical dialog between the dialog object and the response character.
13. The apparatus of claim 11 or 12, wherein the role related data includes role attribute data; the character attribute data comprises a plurality of character attribute items and attribute contents under the character attribute items; the first determining module is specifically configured to,
performing word segmentation processing on the current problem to obtain each word segmentation word in the current problem;
acquiring target role attribute items matched with the word segmentation words in the plurality of role attribute items;
and determining the attribute content under the attribute item of the target role as a prompt text corresponding to the current problem.
14. The apparatus of claim 11 or 12, wherein the persona-related data includes persona extension knowledge data; the character extension knowledge data comprises a plurality of paragraph texts; the first determining module includes: a first acquisition unit, a second acquisition unit, and a first determination unit;
the first obtaining unit is used for obtaining each paragraph text in the character expansion knowledge data;
the second obtaining unit is used for obtaining target paragraph texts matched with the current problem in the paragraph texts;
the first determining unit is configured to determine the target paragraph text as a prompt text corresponding to the current question.
15. The apparatus of claim 14, wherein the first determination module further comprises: the system comprises a second determining unit, a splitting processing unit and a third determining unit;
the second determining unit is configured to determine, for each paragraph text in the character expansion knowledge data, a total word number of the paragraph text;
the splitting processing unit is used for splitting the paragraph text by taking a sentence as a unit to obtain a plurality of sub-paragraph texts under the condition that the total word number is greater than or equal to a preset word number threshold value;
the third determining unit is configured to determine the sub-paragraph text as a paragraph text in the role extension knowledge data.
16. The apparatus of claim 14, wherein the second acquisition unit is configured to,
acquiring a first vector representation of the current problem;
acquiring a second vector representation of each paragraph text in the character extension knowledge data;
for each paragraph text in the character expansion knowledge data, determining a vector similarity between a second vector representation of the paragraph text and a first vector representation of the current question;
and determining the paragraph text as the target paragraph text under the condition that the vector similarity is greater than or equal to a first similarity threshold value.
17. The apparatus of claim 11 or 12, wherein the persona-related data includes a respective round of historical dialog between the dialog object and the responsive persona; the first determining module includes: a third acquisition unit and a fourth determination unit;
the third obtaining unit is used for obtaining a target historical problem matched with the current problem in the historical problems of each round of historical conversations;
the fourth determining unit is configured to determine, as a prompt text corresponding to the current question, a target history dialogue to which the target history question belongs.
18. The apparatus of claim 17, wherein the third acquisition unit is configured to,
acquiring a first vector representation of the current problem;
acquiring a third vector representation of the history problems in each round of history dialogue;
for each historical question in each round of historical conversations, determining a vector similarity between a third vector representation of the historical question and a first vector representation of the current question;
and determining the history problem as the target history problem in the case that the vector similarity is greater than or equal to a second similarity threshold.
19. The apparatus of claim 18, wherein each round of history conversations, and a third vector representation of history problems in each round of history conversations, are obtained from a vector index; the apparatus further comprises: a third determination module and an update module;
The third determining module is configured to determine a current dialogue according to the current question and an answer corresponding to the current question;
the updating module is configured to update the current dialogue and a first vector representation of the current problem in the current dialogue into the vector index.
20. The apparatus of claim 12, wherein the hint text comprises: attribute contents under a target character attribute item matched with the current problem in the character attribute data, target paragraph text matched with the current problem in the character expansion knowledge data, and target history dialogue matched with the current problem in each round of history dialogue; the second determining module is specifically configured to,
performing splicing processing on the attribute content under the attribute item of the target role, the target paragraph text and the target history dialogue to obtain a spliced text;
and inputting the current question and the spliced text into a question-answer dialogue model, and obtaining an answer corresponding to the current question output by the question-answer dialogue model.
21. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 10.
22. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 10.
23. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311311457.XA CN117421403A (en) | 2023-10-10 | 2023-10-10 | Intelligent dialogue method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311311457.XA CN117421403A (en) | 2023-10-10 | 2023-10-10 | Intelligent dialogue method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117421403A true CN117421403A (en) | 2024-01-19 |
Family
ID=89527578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311311457.XA Pending CN117421403A (en) | 2023-10-10 | 2023-10-10 | Intelligent dialogue method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117421403A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118093854A (en) * | 2024-04-28 | 2024-05-28 | 浙江大学 | Data processing method, device, equipment and medium based on language model |
-
2023
- 2023-10-10 CN CN202311311457.XA patent/CN117421403A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118093854A (en) * | 2024-04-28 | 2024-05-28 | 浙江大学 | Data processing method, device, equipment and medium based on language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487173B (en) | Man-machine conversation method, device and storage medium | |
| CN113590776B (en) | Knowledge graph-based text processing method and device, electronic equipment and medium | |
| CN117194730B (en) | Intention recognition and question answering method and device, electronic equipment and storage medium | |
| CN114116997A (en) | Knowledge question answering method, knowledge question answering device, electronic equipment and storage medium | |
| CN117371428A (en) | Text processing method and device based on large language model | |
| CN115062718A (en) | Language model training method and device, electronic equipment and storage medium | |
| CN117421403A (en) | Intelligent dialogue method and device and electronic equipment | |
| CN115840867A (en) | Generation method and device of mathematical problem solving model, electronic equipment and storage medium | |
| CN112860995A (en) | Interaction method, device, client, server and storage medium | |
| CN116244432B (en) | Pre-training method and device for language model and electronic equipment | |
| CN117333889A (en) | Training method and device for document detection model and electronic equipment | |
| CN118051598A (en) | Medicine knowledge question-answering method and device, electronic equipment and storage medium | |
| US20230206007A1 (en) | Method for mining conversation content and method for generating conversation content evaluation model | |
| CN117931982A (en) | Knowledge enhancement-based campt optimization method | |
| CN117609418A (en) | Document processing method, device, electronic equipment and storage medium | |
| CN117422067A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN114490969B (en) | Question and answer method and device based on table and electronic equipment | |
| CN113792230B (en) | Service linking method, device, electronic equipment and storage medium | |
| CN114328936A (en) | Method and device for establishing classification model | |
| CN114281969A (en) | Reply sentence recommendation method and device, electronic equipment and storage medium | |
| CN115129816B (en) | Question-answer matching model training method and device and electronic equipment | |
| CN116932714B (en) | Method and device for training generated dialogue model and realizing generated dialogue | |
| CN116069914B (en) | Training data generation method, model training method and device | |
| CN117666812B (en) | Prompt word processing method and device, electronic equipment and storage medium | |
| CN117421400A (en) | Dialogue interaction method and device and electronic equipment |
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 |