CN113553412A - Question and answer processing method and device, electronic equipment and storage medium - Google Patents
Question and answer processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113553412A CN113553412A CN202110738564.5A CN202110738564A CN113553412A CN 113553412 A CN113553412 A CN 113553412A CN 202110738564 A CN202110738564 A CN 202110738564A CN 113553412 A CN113553412 A CN 113553412A
- Authority
- CN
- China
- Prior art keywords
- question
- query statement
- word
- candidate
- answer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/3322—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a question and answer processing method and device, electronic equipment and a storage medium, relates to the technical field of computers, and particularly relates to the artificial intelligence fields of natural language processing, deep learning and the like. The implementation scheme is as follows: acquiring a first query statement and a historical query statement currently input by a user; acquiring a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement; inputting each candidate question, the first query statement and the historical query statement into a network model generated by training so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement; extracting a target question from a plurality of candidate questions according to each first matching degree; and obtaining answers corresponding to the target questions from the question and answer set. Therefore, when a plurality of candidate questions are obtained from the question and answer set and the matching degree is obtained by utilizing the network model, the historical query sentences are fully considered, the question recall effect is improved, and the accuracy of answers returned by the question and answer system is further improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to the fields of artificial intelligence such as natural language processing and deep learning, and specifically relates to a question and answer processing method and device, electronic equipment and a storage medium.
Background
With the development of computer technology and internet technology, human-computer interaction is more and more widely applied to the life of people. The intelligent question-answering system is one of the core technologies of man-machine interaction. When the user inputs a question to be queried, the question-answering system can recall the most similar question according to the matching degree of the questions in the question-answering set and the questions queried by the user, and further displays the answer corresponding to the question.
Therefore, how to improve the accuracy of the recall problem is an urgent problem to be solved.
Disclosure of Invention
The application provides a question and answer processing method and device, electronic equipment and a storage medium.
According to an aspect of the present application, there is provided a question-answering processing method including:
acquiring a first query statement and a historical query statement currently input by a user;
acquiring a plurality of candidate questions from a preset question-answer set according to the first query statement and the historical query statement, wherein the question-answer set comprises a plurality of question-answer pairs, and each question-answer pair comprises a question and a corresponding answer;
inputting each candidate question, the first query statement and the historical query statement into a network model generated by training so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement;
extracting a target question from the plurality of candidate questions according to each first matching degree;
and obtaining answers corresponding to the target questions from the question and answer set.
According to another aspect of the present application, there is provided a question and answer processing apparatus including:
the first acquisition module is used for acquiring a first query statement and a historical query statement currently input by a user;
a second obtaining module, configured to obtain a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement, where the question and answer set includes a plurality of question and answer pairs, and each question and answer pair includes a question and a corresponding answer;
a third obtaining module, configured to input each candidate question, the first query statement, and the historical query statement into a network model generated by training, so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement;
an extraction module, configured to extract a target question from the multiple candidate questions according to each of the first matching degrees;
and the fourth acquisition module is used for acquiring answers corresponding to the target questions from the question and answer set.
According to another aspect of the present application, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the above embodiments.
According to another aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method according to the above-described embodiments.
According to another aspect of the present application, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method according to the above embodiments.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
fig. 1 is a schematic flow chart of a question answering processing method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of another question answering processing method according to an embodiment of the present application;
fig. 3 is a schematic processing diagram of a network model according to an embodiment of the present application;
fig. 4 is a schematic flow chart of another question answering processing method according to an embodiment of the present application;
fig. 5 is a schematic diagram of obtaining a plurality of candidate questions according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a question answering processing apparatus according to an embodiment of the present application;
fig. 7 is a block diagram of an electronic device for implementing the question answering method according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those 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 application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
A question answering processing method, apparatus, electronic device, and storage medium according to embodiments of the present application are described below with reference to the accompanying drawings.
Artificial intelligence is the subject of research on the use of computers to simulate certain mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of humans, both in the hardware and software domain. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology comprises a computer vision technology, a voice recognition technology, a natural language processing technology, deep learning, a big data processing technology, a knowledge map technology and the like.
NLP (Natural Language Processing) is an important direction in the fields of computer science and artificial intelligence, and the content of NLP research includes but is not limited to the following branch fields: text classification, information extraction, automatic summarization, intelligent question answering, topic recommendation, machine translation, subject word recognition, knowledge base construction, deep text representation, named entity recognition, text generation, text analysis (lexical, syntactic, grammatical, etc.), speech recognition and synthesis, and the like.
Deep learning is a new research direction in the field of machine learning. Deep learning is the intrinsic law and expression level of the learning sample data, and the information obtained in the learning process is very helpful for the interpretation of data such as characters, images and sounds. The final aim of the method is to enable the machine to have the analysis and learning capability like a human, and to recognize data such as characters, images and sounds.
Fig. 1 is a schematic flow chart of a question and answer processing method according to an embodiment of the present application.
The question-answering processing method can be executed by the question-answering processing device, the device can be configured in electronic equipment, conversation history is fully considered when questions are recalled, key information which is possibly omitted by currently input query sentences is supplemented, and therefore the question-answering effect of a question-answering system is improved, and accuracy of returned answers is improved.
As shown in fig. 1, the question answering processing method includes:
The question-answering processing method can be applied to question-answering systems, such as FAQ (Frequently Asked Questions) systems. When a user inputs a query statement in the question-and-answer system, in order to distinguish the query statement as a first query statement, the question-and-answer system may obtain the first query statement currently input by the user. For example, a question and answer system provided by a user at an airport inputs the query statement "XX flight number departure".
In the method and the system, when the user inputs the first query statement, the first query statement can be input through characters or can be input through voice, and after the question answering system acquires the voice input by the user, the acquired voice can be identified through a voice identification function so as to acquire the first query statement.
In the practical application of the question-answering system, a user may omit some information according to the context, and based on the information, the question-answering system in the application can also obtain historical query sentences.
Generally, the closer the time interval between the historical query statement and the first query statement, the greater the relevance of the historical query statement to the first query statement. For example, the first query statement of the current round of dialog is more relevant to the historical query statement in the penultimate round of dialog than to the historical query statement in the penultimate round 5. Then, when obtaining the historical query statement, N historical query statements preceding the first query statement may be obtained, where N is a positive integer.
In the application, a question-answer set is preset in the question-answer system, wherein the question-answer set comprises a plurality of question-answer pairs, and each question-answer pair comprises a question and a corresponding answer.
Because the question-answer set comprises a plurality of question-answer pairs, in order to improve the processing efficiency, after a first query statement and a historical query statement which are currently input by a user are obtained, a plurality of candidate questions can be obtained from the question-answer set according to the first query statement and the historical query statement.
When multiple candidate questions are obtained, the similarity between the first query statement and each historical query statement can be calculated, and the historical query statement with higher similarity to the first query statement is determined according to the similarity. And then, calculating the similarity between the questions in each question-answer pair in the question set and the screened historical query sentences, and extracting a plurality of candidate questions from the question-answer pairs according to the first query sentence and the historical query sentences with higher similarity. Therefore, a plurality of candidate problems are extracted based on the historical query statement and the first query statement, the conversation history is considered, and the screening accuracy of the candidate problems is improved.
In the application, after a plurality of candidate questions are obtained, each candidate question, the first query statement and the historical query statement may be input into a network model generated by training, and the network model performs encoding and decoding processing to obtain the first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement.
The network model can be generated by deep learning training, and the higher the first matching degree obtained through the network model is, the higher the similarity between the candidate question and the first query statement is.
And if a plurality of acquired historical query sentences are acquired, inputting the plurality of historical query sentences into the network model when acquiring the first matching degree corresponding to each candidate question. Thus, information included in the query expression in the history dialogue can be sufficiently considered when a question is recalled.
After the first matching degree corresponding to each candidate question is obtained, the target question may be extracted from the plurality of candidate questions according to the first matching degree corresponding to each candidate question. The target problem may be one or more.
For example, a candidate question having the highest first matching degree may be extracted from a plurality of candidate questions as a target question. Alternatively, a candidate problem having a first matching degree greater than a threshold may be taken as the target problem.
Or, the candidate questions may be ranked according to the first matching degree, and a preset number of candidate questions may be used as the target question.
And 105, acquiring answers corresponding to the target questions from the question and answer sets.
Since the target question is a question in the question-answer set, after the target question is obtained, an answer corresponding to the target question can be obtained from the question-answer set. If the target question is one, the answer can be directly returned, and if the target questions are multiple, each target question and the corresponding answer can be returned for the user to select.
In the embodiment of the application, a plurality of candidate questions are acquired from a preset question and answer set according to a first query statement and a historical query statement input by a user, each candidate question, the first query statement and the historical query statement are input into a network model generated by training to acquire a first matching degree between each candidate question and the first query statement and the historical query statement, a target question is extracted from the candidate questions according to each first matching degree, and answers corresponding to the target question are acquired from the question and answer set. Therefore, when a plurality of candidate questions are obtained from the question and answer set and the matching degree is obtained by utilizing the network model, the historical query sentences are fully considered, the question recall effect is improved, and the accuracy of answers returned by the question and answer system is improved.
In an embodiment of the present application, a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement may be obtained through a network model in a manner described in fig. 2. Fig. 2 is a schematic flow chart of another question answering processing method according to an embodiment of the present application.
As shown in fig. 2, the inputting each candidate question, the first query statement, and the historical query statement into the network model generated by training to obtain the first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement includes:
In the application, when vector mapping is performed on each word, a one-bit effective coding mode can be adopted, and a word steering quantity model trained in advance can be adopted to obtain the word vector of each word.
In the present application, each word may be position-coded according to its position in the sentence to obtain the first position vector. For example, the first query statement "how to weather today" may be counted from 0, each word pair in the query statement corresponds to 0, 1, 2, 3, 4, and 5, respectively, and then each number may be converted into a binary system with the same number of bits, that is, the first position vector corresponding to each word is obtained.
Because a plurality of sentences such as candidate questions, first query sentences, historical query sentences and the like exist, the position information of each word comprises the sentence where the word is located and the position of the sentence where the word is located, and therefore in the application, the second position vector corresponding to each word can be obtained according to the sentence where the word is located. That is, the second location vector is used to characterize the statement in which the word is located, and the second location vectors of the words in the same statement are the same.
As an implementation manner, mapping relationships between different statement types and vectors may be predefined, for example, a candidate question corresponding vector a, a vector B corresponding to a currently input first query statement, and a historical query statement corresponding vector C may be predefined. And if the statement in which a word is located is a candidate problem, determining that the second position vector of the word is A, if the statement in which the word is located is the first query statement, determining that the second position vector of the word is B, and if the statement in which the word is located is the historical query statement, determining that the second position vector of the word is C.
If there are a plurality of historical query statements, the farther the distance between the historical query statement and the first query statement is, the smaller the correlation with the first query statement is. As another possible implementation manner, when a statement in which any word is located is a candidate problem, a second position vector corresponding to any word may be determined according to the candidate problem; under the condition that the statement where any word is located is the first query statement, the second position vector corresponding to any word can be determined according to the first query statement; when the statement in which any word is located is a historical query statement, the second position vector corresponding to any word may be determined according to the distance between the historical query statement and the first query statement. Wherein the separation distance may be a time interval length.
For example, the type value corresponding to the candidate question is 0, the type value corresponding to the first query statement is 1, the type value corresponding to the historical query statement of the last round of dialog is 2, and the rest of the operations are analogized in sequence, so that the type value corresponding to the statement in which each word is located can be converted into a binary system with the same number of bits, and the binary system is used as the second position vector corresponding to each word. It will be appreciated that the larger the type value, the more distant the historical query statement is from the first query statement, and the less relevant it is to the first query statement.
When the second position vector corresponding to each word is determined, the second position vector corresponding to the word is determined according to the interval distance between the historical query statement and the first query statement under the condition that the statement where the word is located is the historical query statement, so that the influence of the distance between the historical query statement and the first query statement on the first matching degree is considered.
In the application, the word vector, the first position vector and the second position vector of each word can be spliced to obtain the vector representation corresponding to each word. That is, the vector representation corresponding to each word includes the word vector, the first position vector, and the second position vector of each word.
Since the word vector width of each word is the same, the first position vector width of each word is the same, and the second position vector width of each word is the same, the vector representation width of each word is the same.
For example, the width of the word vector, the first position vector, and the second position vector is l1, l2, and l3, respectively, and the vector of each word represents a width of k ═ l1+ l2+ l3, that is, the vector of each word represents a matrix of 1 × k.
Step 205, inputting the vector representation corresponding to each word into the network model generated by training, so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement.
In the application, the vector representations corresponding to the words can be input into a network model generated by training, the network model can encode the vector representations corresponding to the words to obtain a first feature vector, and the feature vector can represent the interaction relationship between each candidate problem and a first query statement and a historical query statement. And then, performing average pooling on the first feature vector to obtain a second feature vector, and converting the second feature vector into a first matching degree through a full connection layer.
Fig. 3 is a schematic processing diagram of a network model according to an embodiment of the present disclosure. In fig. 3, candidate questions ci (i ═ 1, 2, 3, …, m), a first query expression q0, a historical query expression q1, q2, …, qn are input to an embedding layer, the embedding layer outputs a vector representation corresponding to each word, and the vector representation of each word is input to a conversion network (for example, a two-layer transform network), the network processes the vector representation of each word, outputs a first feature vector, the first feature vector is input to an average pooling layer to be subjected to average pooling processing, obtains a second feature vector, and converts the second feature vector through one full connection layer to obtain a first degree of matching between ci and q0, q1, q2, …, qn.
For example, the vector corresponding to each word is represented as a matrix of 1 × k, the ci, q0, q1, q2, … and qn have h words in total, the first eigenvector is a matrix of h × k, the elements on the same column are added and averaged, that is, the average pooling is performed to obtain a matrix of 1 × k in the second eigenvector, thereby encoding all the information of ci, q0, q1, q2, … and qn into one vector of 1 × k, and the current matching state is represented by a single vector.
In the embodiment of the application, word coding and position coding are performed on each word in each candidate problem, the first query statement and the historical query statement, vector representation corresponding to each word is determined, the vector representation corresponding to each word is input into a network model, so that a first matching degree between each candidate problem and the first query statement and between each candidate problem and the historical query statement is obtained, therefore, a target problem can be selected from a plurality of candidate problems by using the first matching degree corresponding to each candidate problem, and an answer corresponding to the target problem is obtained.
In one embodiment of the present application, when obtaining a plurality of candidate questions, the plurality of candidate questions may also be extracted from the plurality of question-answer pairs by segmenting words in the first query sentence and the historical query sentences. Fig. 4 is a schematic flow chart of another question answering processing method provided in the embodiment of the present application.
As shown in fig. 4, the obtaining a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement may include:
In the application, the first query statement and the historical query statement may be subjected to word segmentation processing respectively to obtain each word segmentation included in the first query statement and each word segmentation included in the historical query statement, the obtained words may be subjected to duplicate removal processing, and the obtained words may constitute a word set.
For each first word in the word segmentation set, calculating a second matching degree between each first word and the question in each question-answer pair, for example, taking a distance between a vector corresponding to the first word and a vector corresponding to the question as the second matching degree, calculating an average value of the second matching degrees between each question and each first word, sorting the questions in the question-answer set according to the average value of the second matching degrees corresponding to each question, and extracting a plurality of candidate questions from the plurality of question-answer sets. For example, a preset number of questions with a higher second matching degree average may be extracted as candidate questions.
For example, there are 100 question-answer pairs in the question-answer set, each of which contains one question, that is, there are 100 questions in the question-answer set, and the top 20 questions with the highest average second matching degree may be extracted from the 100 questions as candidate questions.
Because the importance of each participle in the query sentence is different, when a plurality of candidate questions are extracted from a plurality of question-answer pairs according to the second matching degree between each participle and the question in each question-answer pair, the weight of each first participle set in the participle set can be determined, the participle with higher weight is extracted from the participle set as the target participle according to the weight of each first participle, and a plurality of candidate questions are extracted from the plurality of question-answer pairs based on the second matching degree between the question in each question-answer pair and the target participle. Therefore, the target participles are screened out according to the weight of the first participles, and a plurality of candidate problems are obtained by utilizing the target participles to carry out coarse-ranking retrieval, so that the processing efficiency can be improved.
In determining the weight of each first segmentation, the weight of each first segmentation may be obtained by using a model generated by training. Alternatively, the weight of each first participle may be determined according to the number of times that each first participle appears in each question in the question-and-answer set, wherein the weight is larger the more times that each first participle appears.
After the target participles are obtained, a third matching degree between each second participle contained in the question in each question-answer pair and each target participle can be calculated, and the number of the target participles contained in each question is determined according to the third matching degree between each second participle contained in each question and each target participle. For example, if the third matching degree between the target participle and the second participle exceeds the set threshold, it may be considered that the target participle is included in the question.
After the number of the target participles included in the questions in each question-answer pair is determined, the questions in the question-answer pairs can be ranked according to the number of the target participles included in the questions in each question-answer pair and the weight of the included target participles, and a plurality of candidate questions can be extracted from the questions.
For example, a plurality of questions may be ranked from large to small according to the number of target participles included in each question, and if the number of the included target participles is the same, the sum of the weights of the included target participles is compared, and the larger the sum of the weights, the higher the ranking is. And then, selecting the problems with the preset number from the sequence as candidate problems.
According to the method and the device, when a plurality of questions are extracted from a plurality of question-answer pairs, a plurality of candidate questions can be extracted according to the number of the target participles and the weight of the target participles contained in each question-answer pair, and the operation is simple.
In the embodiment of the application, when a plurality of candidate questions are obtained from a preset question and answer set, the word segmentation processing can be respectively carried out on the first query statement and the historical query statement to obtain a word segmentation set corresponding to the first query statement, and the candidate questions are extracted from the question and answer sets according to the second matching degree between each first word segmentation in the word segmentation set and the question in each question and answer pair. Therefore, by utilizing the first query statement and the participles in the historical query statement, a plurality of candidate problems can be efficiently acquired, the query statements in the dialogue history are considered, and the accuracy of the acquired candidate problems is improved.
After obtaining a plurality of candidate questions by using the method, each candidate question, the first query statement, and the historical query statement may be input into a network model generated by training to obtain a first matching degree between each candidate question and the first query statement as well as between each candidate question and the historical query statement. After the first matching degree corresponding to each candidate question is obtained, the target question can be selected from the candidate questions, and the answer of the target question obtained from the question and answer set is obtained and returned to the user.
Fig. 5 is a schematic diagram of obtaining multiple candidate questions according to an embodiment of the present application. In fig. 5, word segmentation is performed on the current first query statement q0 and the n historical query statements q1, q2, …, qn to obtain a plurality of words, and coarse search is performed by using the words to obtain coarse candidate results c1, c2, …, cm, that is, m questions are extracted from the plurality of question-answer pairs. Here, the rough search using the word segmentation means that a plurality of questions are extracted from a plurality of question-answer pairs using the word segmentation.
In order to implement the foregoing embodiments, an apparatus for processing a question and answer is also provided in the embodiments of the present application. Fig. 6 is a schematic structural diagram of a question answering processing device according to an embodiment of the present application.
As shown in fig. 6, the question answering processing apparatus 600 includes:
a first obtaining module 610, configured to obtain a first query statement and a historical query statement currently input by a user;
a second obtaining module 620, configured to obtain a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement, where the question and answer set includes a plurality of question and answer pairs, and each question and answer pair includes a question and a corresponding answer;
a third obtaining module 630, configured to input each candidate question, the first query statement, and the historical query statement into a network model generated by training, so as to obtain a first matching degree between each candidate question and the first query statement and the historical query statement;
an extraction module 640, configured to extract a target question from the candidate questions according to each of the first matching degrees;
a fourth obtaining module 650, configured to obtain answers corresponding to the target questions from the question and answer set.
In a possible implementation manner of this embodiment of the present application, the third obtaining module 630 includes:
the vector mapping unit is used for performing vector mapping on each word in each candidate problem, the first query statement and the historical query statement to acquire a word vector corresponding to each word;
the first acquisition unit is used for encoding the position of each word in the sentence so as to acquire a first position vector corresponding to each word;
the second obtaining unit is used for obtaining a second position vector corresponding to each word according to the statement where each word is located;
the determining unit is used for determining the vector representation corresponding to each word according to the word vector, the first position vector and the second position vector;
and the third acquisition unit is used for inputting the vector representation corresponding to each word into the network model generated by training so as to acquire the first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement.
In a possible implementation manner of the embodiment of the present application, the determining unit is configured to:
under the condition that a statement where any word is located is the candidate problem, determining a second position vector corresponding to the word according to the candidate problem;
under the condition that the statement where any word is located is the first query statement, determining a second position vector corresponding to the any word according to the first query statement;
and under the condition that the statement where any word is located is the historical query statement, determining a second position vector corresponding to the word according to the interval distance between the historical query statement and the first query statement.
In a possible implementation manner of this embodiment of the application, the second obtaining module 620 includes:
the word segmentation processing unit is used for performing word segmentation processing on the first query statement and the historical query statement respectively to acquire a word segmentation set corresponding to the first query statement;
and the extracting unit is used for extracting a plurality of candidate questions from the question-answer pairs according to a second matching degree between each first participle in the participle set and the question in each question-answer pair.
In a possible implementation manner of the embodiment of the present application, the extraction unit is configured to:
determining a weight of each first participle in the participle set;
extracting target participles from the participle set according to each weight;
and extracting the plurality of candidate questions from the plurality of question-answer pairs according to a second matching degree between the question in each question-answer pair and each target word segmentation.
In a possible implementation manner of the embodiment of the present application, the extracting unit is further configured to:
determining the number of target participles contained in the question in each question-answer pair according to a third matching degree between each second participle contained in the question in each question-answer pair and each target participle;
and extracting the candidate questions from the question-answer pairs according to the number of the target word segmentation contained in the question in each question-answer pair and the corresponding weight.
It should be noted that the explanation of the aforementioned embodiment of the question-answering method is also applicable to the question-answering device of this embodiment, and therefore is not repeated herein.
In the embodiment of the application, a plurality of candidate questions are acquired from a preset question and answer set according to a first query statement and a historical query statement input by a user, each candidate question, the first query statement and the historical query statement are input into a network model generated by training to acquire a first matching degree between each candidate question and the first query statement and the historical query statement, a target question is extracted from the candidate questions according to each first matching degree, and answers corresponding to the target question are acquired from the question and answer set. Therefore, when a plurality of candidate questions are obtained from the question and answer set and the matching degree is obtained by utilizing the network model, the historical query sentences are fully considered, the question recall effect is improved, and the accuracy of answers returned by the question and answer system is improved.
There is also provided, in accordance with an embodiment of the present application, an electronic device, a readable storage medium, and a computer program product.
FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present application. 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 phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 7, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes in accordance with a computer program stored in a ROM (Read-Only Memory) 702 or a computer program loaded from a storage unit 708 into a RAM (Random Access Memory) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An I/O (Input/Output) interface 705 is also connected to the bus 704.
Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be realized in digital electronic circuitry, Integrated circuitry, FPGAs (Field Programmable Gate arrays), ASICs (Application-Specific Integrated circuits), ASSPs (Application Specific Standard products), SOCs (System On Chip, System On a Chip), CPLDs (Complex Programmable Logic devices), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes 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 codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. 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 application, 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. A 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 RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or flash Memory, an optical fiber, a CD-ROM (Compact Disc Read-Only-Memory), 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 a pointing device (e.g., a mouse or a 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 can 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, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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: LAN (Local Area Network), WAN (Wide Area Network), internet, and blockchain Network.
The computer system may include clients and servers. A client and server are generally 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, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in a conventional physical host and a VPS (Virtual Private Server). The server may also be a server of a distributed system, or a server incorporating a blockchain.
According to an embodiment of the present application, there is also provided a computer program product, which when executed by an instruction processor in the computer program product, executes the question-answering processing method provided in the above-mentioned embodiment of the present application.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (15)
1. A question-answer processing method comprising:
acquiring a first query statement and a historical query statement currently input by a user;
acquiring a plurality of candidate questions from a preset question-answer set according to the first query statement and the historical query statement, wherein the question-answer set comprises a plurality of question-answer pairs, and each question-answer pair comprises a question and a corresponding answer;
inputting each candidate question, the first query statement and the historical query statement into a network model generated by training so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement;
extracting a target question from the plurality of candidate questions according to each first matching degree;
and obtaining answers corresponding to the target questions from the question and answer set.
2. The method of claim 1, wherein said inputting each of the candidate questions, the first query statement, and the historical query statement into a trained network model to obtain a first degree of match between each of the candidate questions and the first query statement and the historical query statement comprises:
performing vector mapping on each word in each candidate question, the first query statement and the historical query statement to obtain a word vector corresponding to each word;
coding the position of each word in the sentence to obtain a first position vector corresponding to each word;
acquiring a second position vector corresponding to each word according to the statement of each word;
determining a vector representation corresponding to each word according to the word vector, the first position vector and the second position vector;
and inputting the vector representation corresponding to each word into the network model generated by training so as to obtain a first matching degree between each candidate problem and the first query statement and the historical query statement.
3. The method of claim 2, wherein the obtaining the second position vector corresponding to each word according to the sentence in which each word is located comprises:
under the condition that a statement where any word is located is the candidate problem, determining a second position vector corresponding to the word according to the candidate problem;
under the condition that the statement where any word is located is the first query statement, determining a second position vector corresponding to the any word according to the first query statement;
and under the condition that the statement where any word is located is the historical query statement, determining a second position vector corresponding to the word according to the interval distance between the historical query statement and the first query statement.
4. The method according to any one of claims 1-3, wherein the obtaining a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement comprises:
performing word segmentation processing on the first query statement and the historical query statement respectively to obtain a word segmentation set corresponding to the first query statement;
and extracting a plurality of candidate questions from the plurality of question-answer pairs according to a second matching degree between each first participle in the participle set and the question in each question-answer pair.
5. The method of claim 4, wherein the extracting a plurality of candidate questions from the plurality of question-answer pairs according to a second degree of matching between each of the participles and the question in each of the question-answer pairs comprises:
determining a weight of each first participle in the participle set;
extracting target participles from the participle set according to each weight;
and extracting the plurality of candidate questions from the plurality of question-answer pairs according to a second matching degree between the question in each question-answer pair and each target word segmentation.
6. The method of claim 5, wherein after said extracting target participles from said set of participles according to each said weight, further comprising:
determining the number of target participles contained in the question in each question-answer pair according to a third matching degree between each second participle contained in the question in each question-answer pair and each target participle;
and extracting the candidate questions from the question-answer pairs according to the number of the target word segmentation contained in the question in each question-answer pair and the corresponding weight.
7. A question-answering processing device comprising:
the first acquisition module is used for acquiring a first query statement and a historical query statement currently input by a user;
a second obtaining module, configured to obtain a plurality of candidate questions from a preset question and answer set according to the first query statement and the historical query statement, where the question and answer set includes a plurality of question and answer pairs, and each question and answer pair includes a question and a corresponding answer;
a third obtaining module, configured to input each candidate question, the first query statement, and the historical query statement into a network model generated by training, so as to obtain a first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement;
an extraction module, configured to extract a target question from the multiple candidate questions according to each of the first matching degrees;
and the fourth acquisition module is used for acquiring answers corresponding to the target questions from the question and answer set.
8. The apparatus of claim 7, wherein the third obtaining means comprises:
the vector mapping unit is used for performing vector mapping on each word in each candidate problem, the first query statement and the historical query statement to acquire a word vector corresponding to each word;
the first acquisition unit is used for encoding the position of each word in the sentence so as to acquire a first position vector corresponding to each word;
the second obtaining unit is used for obtaining a second position vector corresponding to each word according to the statement where each word is located;
the determining unit is used for determining the vector representation corresponding to each word according to the word vector, the first position vector and the second position vector;
and the third acquisition unit is used for inputting the vector representation corresponding to each word into the network model generated by training so as to acquire the first matching degree between each candidate question and the first query statement and between each candidate question and the historical query statement.
9. The apparatus of claim 8, wherein the determining unit is to:
under the condition that a statement where any word is located is the candidate problem, determining a second position vector corresponding to the word according to the candidate problem;
under the condition that the statement where any word is located is the first query statement, determining a second position vector corresponding to the any word according to the first query statement;
and under the condition that the statement where any word is located is the historical query statement, determining a second position vector corresponding to the word according to the interval distance between the historical query statement and the first query statement.
10. The apparatus of any of claims 7-9, wherein the second obtaining means comprises:
the word segmentation processing unit is used for performing word segmentation processing on the first query statement and the historical query statement respectively to acquire a word segmentation set corresponding to the first query statement;
and the extracting unit is used for extracting a plurality of candidate questions from the question-answer pairs according to a second matching degree between each first participle in the participle set and the question in each question-answer pair.
11. The apparatus of claim 10, wherein the extraction unit is to:
determining a weight of each first participle in the participle set;
extracting target participles from the participle set according to each weight;
and extracting the plurality of candidate questions from the plurality of question-answer pairs according to a second matching degree between the question in each question-answer pair and each target word segmentation.
12. The apparatus of claim 11, wherein the extraction unit is further configured to:
determining the number of target participles contained in the question in each question-answer pair according to a third matching degree between each second participle contained in the question in each question-answer pair and each target participle;
and extracting the candidate questions from the question-answer pairs according to the number of the target word segmentation contained in the question in each question-answer pair and the corresponding weight.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
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 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738564.5A CN113553412B (en) | 2021-06-30 | 2021-06-30 | Question-answering processing method, question-answering processing device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738564.5A CN113553412B (en) | 2021-06-30 | 2021-06-30 | Question-answering processing method, question-answering processing device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113553412A true CN113553412A (en) | 2021-10-26 |
| CN113553412B CN113553412B (en) | 2023-07-25 |
Family
ID=78131163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110738564.5A Active CN113553412B (en) | 2021-06-30 | 2021-06-30 | Question-answering processing method, question-answering processing device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553412B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114461749A (en) * | 2022-02-15 | 2022-05-10 | 北京百度网讯科技有限公司 | Data processing method and device for conversation content, electronic equipment and medium |
| CN115952274A (en) * | 2023-03-10 | 2023-04-11 | 北京百度网讯科技有限公司 | Data generation method, training method and device based on deep learning model |
| CN115964471A (en) * | 2023-03-16 | 2023-04-14 | 成都安哲斯生物医药科技有限公司 | Approximate query method for medical data |
| CN116795953A (en) * | 2022-03-08 | 2023-09-22 | 腾讯科技（深圳）有限公司 | Question-answer matching method and device, computer readable storage medium and computer equipment |
| CN116992001A (en) * | 2023-08-07 | 2023-11-03 | 北京百度网讯科技有限公司 | Knowledge question-answering method, device, equipment, sound box and storage medium |
| CN117312530A (en) * | 2023-11-10 | 2023-12-29 | 北京百度网讯科技有限公司 | Questionnaire and model training method, device, equipment, medium and product |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180239811A1 (en) * | 2017-02-21 | 2018-08-23 | International Business Machines Corporation | Question-answer pair generation |
| CN110096580A (en) * | 2019-04-24 | 2019-08-06 | 北京百度网讯科技有限公司 | A kind of FAQ dialogue method, device and electronic equipment |
| CN110309283A (en) * | 2019-06-28 | 2019-10-08 | 阿里巴巴集团控股有限公司 | A kind of answer of intelligent answer determines method and device |
| CN110597966A (en) * | 2018-05-23 | 2019-12-20 | 北京国双科技有限公司 | Automatic question answering method and device |
| CN111046159A (en) * | 2019-12-13 | 2020-04-21 | 杭州翼兔网络科技有限公司 | Man-machine interaction method, device, equipment and medium |
| CN111241237A (en) * | 2019-12-31 | 2020-06-05 | 中国建设银行股份有限公司 | Intelligent question and answer data processing method and device based on operation and maintenance service |
| CN111428010A (en) * | 2019-01-10 | 2020-07-17 | 北京京东尚科信息技术有限公司 | Man-machine intelligent question and answer method and device |
| US20200243082A1 (en) * | 2019-01-30 | 2020-07-30 | Kabushiki Kaisha Toshiba | Dialog system and dialog method |
| CN111858859A (en) * | 2019-04-01 | 2020-10-30 | 北京百度网讯科技有限公司 | Automatic question-answering processing method, device, computer equipment and storage medium |
| CN111898643A (en) * | 2020-07-01 | 2020-11-06 | 上海依图信息技术有限公司 | Semantic matching method and device |
| WO2021068615A1 (en) * | 2019-10-12 | 2021-04-15 | 深圳壹账通智能科技有限公司 | Method and device for acquiring question and answer data in document, computer device, and storage medium |
-
2021
- 2021-06-30 CN CN202110738564.5A patent/CN113553412B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180239811A1 (en) * | 2017-02-21 | 2018-08-23 | International Business Machines Corporation | Question-answer pair generation |
| CN110597966A (en) * | 2018-05-23 | 2019-12-20 | 北京国双科技有限公司 | Automatic question answering method and device |
| CN111428010A (en) * | 2019-01-10 | 2020-07-17 | 北京京东尚科信息技术有限公司 | Man-machine intelligent question and answer method and device |
| US20200243082A1 (en) * | 2019-01-30 | 2020-07-30 | Kabushiki Kaisha Toshiba | Dialog system and dialog method |
| CN111858859A (en) * | 2019-04-01 | 2020-10-30 | 北京百度网讯科技有限公司 | Automatic question-answering processing method, device, computer equipment and storage medium |
| CN110096580A (en) * | 2019-04-24 | 2019-08-06 | 北京百度网讯科技有限公司 | A kind of FAQ dialogue method, device and electronic equipment |
| CN110309283A (en) * | 2019-06-28 | 2019-10-08 | 阿里巴巴集团控股有限公司 | A kind of answer of intelligent answer determines method and device |
| WO2021068615A1 (en) * | 2019-10-12 | 2021-04-15 | 深圳壹账通智能科技有限公司 | Method and device for acquiring question and answer data in document, computer device, and storage medium |
| CN111046159A (en) * | 2019-12-13 | 2020-04-21 | 杭州翼兔网络科技有限公司 | Man-machine interaction method, device, equipment and medium |
| CN111241237A (en) * | 2019-12-31 | 2020-06-05 | 中国建设银行股份有限公司 | Intelligent question and answer data processing method and device based on operation and maintenance service |
| CN111898643A (en) * | 2020-07-01 | 2020-11-06 | 上海依图信息技术有限公司 | Semantic matching method and device |
Non-Patent Citations (4)
| Title |
|---|
| SHUAI LIU等: "A Chinese Question Answering System based on GPT", IEEE XPLORE * |
| 刘汉兴;刘财兴;林旭东;: "基于问句相似度的本体问答系统", 广西师范大学学报(自然科学版), no. 01 * |
| 杨海天;王健;林鸿飞;: "基于特征融合的社区问答问句相似度计算", 江西师范大学学报(自然科学版), no. 02 * |
| 陈志豪;余翔;刘子辰;邱大伟;顾本刚;: "基于注意力和字嵌入的中文医疗问答匹配方法", 计算机应用, no. 06 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114461749A (en) * | 2022-02-15 | 2022-05-10 | 北京百度网讯科技有限公司 | Data processing method and device for conversation content, electronic equipment and medium |
| CN116795953A (en) * | 2022-03-08 | 2023-09-22 | 腾讯科技（深圳）有限公司 | Question-answer matching method and device, computer readable storage medium and computer equipment |
| CN115952274A (en) * | 2023-03-10 | 2023-04-11 | 北京百度网讯科技有限公司 | Data generation method, training method and device based on deep learning model |
| CN115952274B (en) * | 2023-03-10 | 2023-06-27 | 北京百度网讯科技有限公司 | Data generation method, training method and device based on deep learning model |
| CN115964471A (en) * | 2023-03-16 | 2023-04-14 | 成都安哲斯生物医药科技有限公司 | Approximate query method for medical data |
| CN116992001A (en) * | 2023-08-07 | 2023-11-03 | 北京百度网讯科技有限公司 | Knowledge question-answering method, device, equipment, sound box and storage medium |
| CN117312530A (en) * | 2023-11-10 | 2023-12-29 | 北京百度网讯科技有限公司 | Questionnaire and model training method, device, equipment, medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113553412B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113553412B (en) | Question-answering processing method, question-answering processing device, electronic equipment and storage medium | |
| CN112560496A (en) | Training method and device of semantic analysis model, electronic equipment and storage medium | |
| EP4064277A1 (en) | Method and apparatus for training speech recognition model, device and storage medium | |
| CN113392209B (en) | Text clustering method based on artificial intelligence, related equipment and storage medium | |
| EP4113357A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
| CN114416943B (en) | Training method and device for dialogue model, electronic equipment and storage medium | |
| CN116152833B (en) | Training method of form restoration model based on image and form restoration method | |
| CN115309877A (en) | Dialog generation method, dialog model training method and device | |
| CN115062718A (en) | Language model training method and device, electronic equipment and storage medium | |
| CN113763937A (en) | Method, device and equipment for generating voice processing model and storage medium | |
| CN112632227A (en) | Resume matching method, resume matching device, electronic equipment, storage medium and program product | |
| CN112232089B (en) | Pre-training method, device and storage medium of semantic representation model | |
| CN112507705A (en) | Position code generation method and device and electronic equipment | |
| CN114758649B (en) | Voice recognition method, device, equipment and medium | |
| CN113792230B (en) | Service linking method, device, electronic equipment and storage medium | |
| CN114841172A (en) | Knowledge distillation method, apparatus and program product for text matching double tower model | |
| CN114398482A (en) | Dictionary construction method and device, electronic equipment and storage medium | |
| CN114416941A (en) | Generation method and device of dialogue knowledge point determination model fusing knowledge graph | |
| CN114970666A (en) | Spoken language processing method and device, electronic equipment and storage medium | |
| CN114201953A (en) | Keyword extraction and model training method, device, equipment and storage medium | |
| CN114490965A (en) | Question processing method and device, electronic equipment and storage medium | |
| CN113886543A (en) | Method, apparatus, medium, and program product for generating an intent recognition model | |
| CN113806541A (en) | Emotion classification method and emotion classification model training method and device | |
| CN113221566A (en) | Entity relationship extraction method and device, electronic equipment and storage medium | |
| CN112784599A (en) | Poetry sentence generation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |