CN112632260A - Intelligent question and answer method and device, electronic equipment and computer readable storage medium - Google Patents
Intelligent question and answer method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112632260A CN112632260A CN202011625530.7A CN202011625530A CN112632260A CN 112632260 A CN112632260 A CN 112632260A CN 202011625530 A CN202011625530 A CN 202011625530A CN 112632260 A CN112632260 A CN 112632260A
- Authority
- CN
- China
- Prior art keywords
- text
- answer
- answer text
- query
- question
- 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 30
- 230000011218 segmentation Effects 0.000 claims abstract description 73
- 238000004458 analytical method Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims description 88
- 238000012216 screening Methods 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 9
- 230000006870 function Effects 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—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
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3335—Syntactic pre-processing, e.g. stopword elimination, stemming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to big data technology, and discloses an intelligent question answering method, which comprises the following steps: receiving a query text, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity; performing semantic analysis on the query text to obtain problem intention characteristics; inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets; calculating and analyzing the relevance of the answer texts in the answer text set to obtain an answer text set to be selected; and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user. The invention also relates to a blockchain technology, and the answer knowledge base can be deployed in a blockchain. The invention also provides an intelligent question answering device, electronic equipment and a computer readable storage medium. The invention can improve the accuracy of intelligent question answering.
Description
Technical Field
The invention relates to the field of big data, in particular to an intelligent question answering method, an intelligent question answering device, electronic equipment and a computer readable storage medium.
Background
With machine learning and deep learning, and the rapid advance of natural language, intelligent question answering has become the most popular research and application direction of artificial intelligence today, such as: siri of apple inc, Tencent robot platform, Amazon's Echo, Microsoft's Luis.
Disclosure of Invention
The invention provides an intelligent question and answer method, an intelligent question and answer device, electronic equipment and a computer readable storage medium, and mainly aims to improve the accuracy of intelligent question and answer.
In order to achieve the above object, the present invention provides an intelligent question answering method, which comprises:
receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
performing semantic analysis on the query text based on a question semantic analysis model to obtain question intention characteristics;
inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets;
calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected;
and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
Optionally, the performing a word segmentation process on the query text includes:
field presetting: performing word segmentation operation on the query text by using a pre-constructed word segmentation dictionary, wherein the number of characters contained in the maximum entry in the pre-constructed word segmentation dictionary is n, if the number of all characters of the query text is less than n, the query text is used as a matching field, and if the number of all characters of the query text is equal to or more than n, the first n characters of the query text are used as the matching field;
word segmentation matching step: traversing and matching in the word segmentation dictionary by utilizing the matching field; if the word segmentation dictionary contains the same words as the matching fields, determining that the matching is successful, separating the matching fields from the query text, and executing the following sequential matching steps; if the word segmentation dictionary does not contain the same words as the matching fields, executing the following field updating step;
field updating step: if the number of characters contained in the matching field is equal to 1, separating the matching field from the query text, and executing the following sequential matching steps; if the number of the characters contained in the matching field is more than 1, removing the last character of the matching field, replacing and updating the matching field by the field after removal, and returning to the word segmentation matching step;
and (3) sequence matching: if the number of the characters after the matched field in the query text is less than n, replacing and updating the matched field with all the characters after the matched field in the query text, and simultaneously returning to the word segmentation matching step; if the number of the characters after the fields are matched in the query text is not less than n, replacing and updating the matched fields by n characters in the sequence after the fields are matched in the query text, and simultaneously returning to the word segmentation matching step; and if the number of the characters after the query text is matched with the fields is equal to 0, stopping word segmentation processing.
Optionally, the calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain the answer text set to be selected includes:
converting answer texts in the answer text set into answer text vectors;
converting the query text into a question text vector;
calculating the relevance values of the answer text vectors and the question text vectors, and summarizing all the relevance values to obtain a relevance text set;
sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value;
selecting an answer text vector corresponding to the maximum correlation value in the answer text set, and taking an answer text corresponding to the selected answer text vector as an answer text to be selected corresponding to the answer text set;
summarizing the answer texts to be selected to obtain the answer text set to be selected.
Optionally, the performing weighted calculation and analysis on the text of the answer to be selected in the text set of the answer to be selected by using the question intention characteristics to obtain a final answer text includes:
converting the problem intention features into problem intention feature vectors;
calculating the relevance value of the question intention characteristic vector and an answer text vector corresponding to each answer text to be selected to obtain the relevance value of the answer text to be selected;
calculating a total number of answer texts in the at least one set of answer text sets;
calculating the ratio of the number of answer texts in each group of answer text sets in the at least one group of answer text sets to the total number of the answer texts to obtain the weight of each group of answer text sets;
multiplying the answer text set weight corresponding to the answer text set in which the answer text to be selected is located by the answer text set relevancy corresponding to the answer text to be selected to obtain an answer text weight value to be selected;
summarizing the text weight values of the answers to be selected to obtain a text weight value set of the answers to be selected;
and selecting the to-be-selected answer text corresponding to the maximum to-be-selected answer text weight value in the to-be-selected answer text weight value set as the final answer text.
Optionally, the converting the query text into a question text vector includes:
obtaining a dimension window with a preset size;
inputting the query text into the dimension window to generate a dimension query text;
and coding the dimension query text by using a preset coding algorithm to generate the problem text vector.
Optionally, the converting the answer text in the answer text set into an answer text vector includes:
acquiring a word vector of each character contained in each answer text in the answer text set by using a pre-trained word vector dictionary;
and calculating the arithmetic mean value of the word vectors of all the characters in each answer text as the answer text vector corresponding to each answer text.
In order to solve the above problems, the present invention also provides an intelligent question answering device, including:
the entity extraction module is used for receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
the semantic analysis module is used for carrying out semantic analysis on the query text based on a pre-constructed question semantic analysis model to obtain question intention characteristics;
the answer screening module is used for inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets; calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected; and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
Optionally, the answer screening module performs relevancy calculation and analysis on answer texts in the at least one group of answer text sets to obtain an answer text set to be selected, including:
answer text vector module: converting answer texts in the answer text set into answer text vectors;
the question text vector module: converting the query text into a question text vector;
the relevance text set module: calculating the relevance values of the answer text vectors and the question text vectors, and summarizing all the relevance values to obtain a relevance text set;
a maximum correlation value module: sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value;
a to-be-selected answer text module: selecting an answer text vector corresponding to the maximum correlation value in the answer text set, and taking an answer text corresponding to the selected answer text vector as an answer text to be selected corresponding to the answer text set;
the answer to be selected text set module: summarizing the answer texts to be selected to obtain the answer text set to be selected.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the intelligent question answering method.
In order to solve the above problem, the present invention also provides a computer-readable storage medium including a stored data area and a stored program area, the stored data area storing data created according to the use of blockchain nodes, the stored program area storing a computer program, the computer-readable storage medium having stored therein at least one instruction, the at least one instruction being executed by a processor in an electronic device to implement the intelligent question-answering method described above.
The embodiment of the invention carries out word segmentation processing and entity extraction processing on the query text, and eliminates the influence of irrelevant words in the query text on subsequent answer query; semantic analysis is carried out on the query text to obtain question intention characteristics, and answers can be more accurately screened by utilizing the question intention characteristics; the problem entity is inquired by utilizing at least one pre-constructed answer knowledge base, so that the problem inquiry is more comprehensive and more accurate; calculating and analyzing the relevancy of the answer texts in the at least one group of answer text sets, and performing weighted calculation and analysis on the answer texts to be selected in the answer text sets to be selected by using the question intention characteristics to obtain a final answer text, so that the accuracy of answer screening is improved; and inquiring the inquiry text in different service answer knowledge bases, and further screening answers by using the question intention characteristics, so that the accuracy of intelligent question answering is improved.
Drawings
Fig. 1 is a schematic flow chart of an intelligent question answering method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of word segmentation processing in the intelligent question answering method according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of an intelligent question answering device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an internal structure of an electronic device implementing an intelligent question answering method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides an intelligent question answering method. Fig. 1 is a schematic flow chart of an intelligent question answering method according to an embodiment of the present invention. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the intelligent question answering method includes:
s1, receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
the query text in the embodiment of the present invention is a question that a user inputs and wants to consult, for example: "how do the weather today? "," what is the interest rate of the three year user deposit? ", the query text may be obtained through a text input module of the web page.
Further, the embodiment of the present invention performs word segmentation processing and entity extraction processing on the query text to obtain a problem entity, where the word segmentation processing includes:
s10: performing word segmentation operation on the query text by using a pre-constructed word segmentation dictionary, wherein the number of characters contained in the maximum entry in the pre-constructed word segmentation dictionary is n;
s11: judging whether the number of all characters of the query text is less than n;
s12: if the number of all characters of the query text is less than n, the query text is used as a matching field,
s13: if the number of all characters of the query text is equal to or larger than n, taking the first n characters of the query text as the matching field;
s20: traversing and matching in the word segmentation dictionary by utilizing the matching field;
s21: judging whether the word segmentation dictionary contains the same words as the matching fields;
s22: if the word segmentation dictionary contains the same words as the matching fields, determining that matching is successful, separating the matching fields from the query text, and executing S40;
s23: if the word segmentation dictionary does not contain the same words as the matching fields, executing S30;
s30: judging whether the number of characters contained in the matching field is more than 1;
s31: if the number of characters contained in the matching field is equal to 1, separating the matching field from the query text, and executing S40;
s32: if the number of characters contained in the matching field is greater than 1, removing the last character of the matching field, replacing and updating the matching field by the field after removal, and returning to S20;
s40: judging whether the number of characters after the fields are matched in the query text is equal to 0;
s41: if the number of characters after the matched field of the query text is not equal to 0, judging whether the number of characters after the matched field in the query text is less than n;
s411: if the number of the characters after the matching field in the query text is less than n, replacing and updating the matching field with all the characters after the matching field in the query text, and simultaneously returning to S20;
s412: if the number of the characters after the matching field in the query text is not less than n, replacing and updating the matching field with n characters in the sequence after the field is matched by the query text, and simultaneously returning to S20;
s42: and if the number of the characters after the query text is matched with the fields is equal to 0, stopping word segmentation processing.
Through the implementation mode, the word segmentation is carried out in the forward segmentation mode, the word segmentation effect is more accurate, and the word segmentation speed is higher.
Preferably, the entity extraction process in the embodiment of the present invention includes: and identifying the query text after word segmentation by using a Named Entity identification technology (NER for short) to obtain a problem Entity. The named entity recognition technology can be used for recognizing entities (such as personal names, place names, organization names, proper nouns and the like) with specific meanings in the query text. For example: the query text after word segmentation processing is 'American president', 'who' and 'who', and a problem entity can be obtained by identifying the query text by the named entity identification technology.
The meaningless words in the query text can be removed through the word segmentation processing and the entity extraction processing, and the influence of the meaningless words on subsequent answer query is avoided.
S2, performing semantic analysis on the query text based on a pre-constructed question semantic analysis model to obtain question intention characteristics;
in the embodiment of the invention, the query text is subjected to semantic analysis by utilizing a pre-constructed semantic analysis model to obtain the problem intention characteristics. For example: the query text is "what is the interest rate of the three-year-old user deposit? ", the question intention feature of the query text is" deposit intention "; the query text is 'which fund has the highest annual interest rate', and the question intention characteristic for obtaining the query text is 'fund purchase intention'.
Preferably, the semantic analysis model may be constructed by using a BERT (Bidirectional Encoder) algorithm, and the training of the semantic analysis model is completed by using a historical user query text set as a training set and using a marked historical user query text set as a tag set. The historical user query text set is a set formed by a plurality of historical user query texts.
The question intention characteristics are obtained by performing semantic analysis on the query text, and answers can be more accurately screened by using the question intention characteristics.
S3, inquiring the question entity by using at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets;
in the embodiment of the invention, in order to ensure the accuracy of the answers, different answer knowledge bases, such as a business answer knowledge base, are pre-constructed, wherein the business answer knowledge base is a database consisting of business knowledge for limiting business categories. For example: the financial industry covers a number of traffic classes including: the embodiment of the invention collects and stores the knowledge related to the fund service into a database to obtain a fund service answer knowledge base, collects and stores the knowledge related to the deposit into the database to obtain a deposit service answer knowledge base, and collects and stores the knowledge related to the investment into the database to obtain an investment service answer knowledge base.
In another embodiment of the invention, the answer knowledge base is composed of limited domain knowledge and can be deployed on a regional chain.
Further, the question entity is inquired by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets; taking a service answer knowledge base as an example, three pre-constructed service answer knowledge bases, namely a fund service answer knowledge base, a deposit service answer knowledge base and an investment service answer knowledge base, are shared, the problem entity is inquired in the three service knowledge bases respectively to obtain a plurality of groups of service answer text sets, the fund service answer knowledge base is inquired to obtain a fund service answer text set, the deposit service answer knowledge base is inquired to obtain a deposit service answer text set, the investment service answer knowledge base is inquired to obtain an investment service answer text set, and 3 groups of service answer text sets are shared.
S4, calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected;
in the embodiment of the invention, in order to screen more accurate answers, answer texts in the answer text set are converted into answer text vectors, and the query texts are converted into question text vectors.
Preferably, a word vector of each character contained in each answer text in the answer text set is obtained by using a pre-trained word vector dictionary; and calculating the arithmetic mean value of the word vectors of all the characters in each answer text as the answer text vector corresponding to each answer text.
Further, the arithmetic mean is calculated as follows:
wherein, a1To anA word vector representing each character in each answer text, n represents the number of characters in the answer text, and W represents an answer text vector of the answer text.
Further, acquiring a dimension window with a preset size; inputting the query text into the dimension window to generate a dimension query text; and coding the dimension query text by using a preset coding algorithm to generate a problem text vector.
For example, a dimensional window is a dimensional window of k × k, where k is a positive integer greater than or equal to 1.
Preferably, in this embodiment, the predetermined coding algorithm may be a huffman coding algorithm.
Further, calculating the relevance values of the answer text vector and the question text vector, and summarizing all the relevance values to obtain a relevance text set; sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value; and selecting the answer text vector corresponding to the maximum correlation value in the answer text set, and taking the answer text corresponding to the selected answer text vector as the to-be-selected answer text corresponding to the answer text set.
In detail, the correlation value calculation may be represented by the following formula:
wherein x isiFor the answer text vector, i is a positive integer, y is the question text vector, sim (x)iAnd) is the relevance value of the answer text vector and the question text vector.
Further, summarizing the answer texts to be selected to obtain the answer text set to be selected.
S5, performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain final answer texts, and pushing the final answer texts to the user.
In detail, in order to further screen answers and ensure the accuracy of the answers, the embodiment of the present invention performs weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics, including:
s51, converting the question intention features into question intention feature vectors;
s52, calculating the relevance value of the question intention characteristic vector and an answer text vector corresponding to each answer text to be selected to obtain the relevance value of the answer text to be selected;
s53, calculating the total number of answer texts in the at least one group of answer text sets;
s54, calculating the ratio of the number of answer texts in each answer text set in the at least one answer text set to the total number of the answer texts to obtain the weight of each answer text set;
s55, multiplying the answer text set weight corresponding to the answer text set where the to-be-selected answer text is located by the to-be-selected answer text relevancy corresponding to the to-be-selected answer text to obtain a to-be-selected answer text weight value, and summarizing the to-be-selected answer text weight value to obtain a to-be-selected answer text weight value set;
and S56, selecting the to-be-selected answer text corresponding to the maximum to-be-selected answer text weight value in the to-be-selected answer text weight value set as the final answer text.
Further, the embodiment of the invention pushes the final answer text to the user, simultaneously obtains feedback information whether the user approves the final answer text, and correspondingly updates data in the knowledge base based on the feedback information, thereby realizing the error correction processing of the knowledge base.
The embodiment of the invention carries out word segmentation processing and entity extraction processing on the query text, and eliminates the influence of irrelevant words in the query text on subsequent answer query; semantic analysis is carried out on the query text to obtain question intention characteristics, and answers can be more accurately screened by utilizing the question intention characteristics; the problem entity is inquired by utilizing at least one pre-constructed answer knowledge base, so that the problem inquiry is more comprehensive and more accurate; calculating and analyzing the relevancy of the answer texts in the at least one group of answer text sets, and performing weighted calculation and analysis on the answer texts to be selected in the answer text sets to be selected by using the question intention characteristics to obtain a final answer text, so that the accuracy of answer screening is improved; and inquiring the inquiry text in different service answer knowledge bases, and further screening answers by using the question intention characteristics, so that the accuracy of intelligent question answering is improved.
Fig. 2 is a functional block diagram of the intelligent question answering device according to the present invention.
The intelligent question answering device 100 of the present invention can be installed in an electronic device. According to the realized functions, the intelligent question answering device can comprise an entity extraction module 101, a semantic analysis module 102 and an answer screening module 103. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the entity extraction module 101 is configured to receive a query text input by a user, perform word segmentation processing and entity extraction processing on the query text, and obtain a problem entity.
The query text in the embodiment of the present invention is a question that a user inputs and wants to consult, for example: "how do the weather today? "," what is the interest rate of the three year user deposit? ", the query text may be obtained through a text input module of the web page.
Further, in the embodiment of the present invention, the entity extraction module 101 performs word segmentation and entity extraction on the query text to obtain a problem entity, where the entity extraction module 101 performs word segmentation by the following means:
field presetting: performing word segmentation operation on the query text by using a pre-constructed word segmentation dictionary, wherein the number of characters contained in the maximum entry in the pre-constructed word segmentation dictionary is n, if the number of all characters of the query text is less than n, the query text is used as a matching field, and if the number of all characters of the query text is equal to or more than n, the first n characters of the query text are used as the matching field;
word segmentation matching step: traversing and matching in the word segmentation dictionary by utilizing the matching field; if the word segmentation dictionary contains the same words as the matching fields, determining that the matching is successful, separating the matching fields from the query text, and executing the following sequential matching steps; if the word segmentation dictionary does not contain the same words as the matching fields, executing the following field updating step;
field updating step: if the number of characters contained in the matching field is equal to 1, separating the matching field from the query text, and executing the following sequential matching steps; if the number of the characters contained in the matching field is more than 1, removing the last character of the matching field, replacing and updating the matching field by the field after removal, and returning to the word segmentation matching step;
and (3) sequence matching: if the number of the characters after the matched field in the query text is less than n, replacing and updating the matched field with all the characters after the matched field in the query text, and simultaneously returning to the word segmentation matching step; if the number of the characters after the fields are matched in the query text is not less than n, replacing and updating the matched fields by n characters in the sequence after the fields are matched in the query text, and simultaneously returning to the word segmentation matching step; and if the number of the characters after the query text is matched with the fields is equal to 0, stopping word segmentation processing.
Through the embodiment, the entity extraction module 101 performs word segmentation in a forward segmentation mode, so that the word segmentation effect is more accurate and the word segmentation speed is higher.
Preferably, the entity extracting module 101 of the embodiment of the present invention performs entity extracting processing including: and identifying the query text after word segmentation by using a Named Entity identification technology (NER for short) to obtain a problem Entity. The named entity recognition technology can be used for recognizing entities (such as personal names, place names, organization names, proper nouns and the like) with specific meanings in the query text. For example: the query text after word segmentation processing is 'American president', 'who' and 'who', and a problem entity can be obtained by identifying the query text by the named entity identification technology.
The meaningless words in the query text can be removed through the word segmentation processing and the entity extraction processing, and the influence of the meaningless words on subsequent answer query is avoided.
The semantic analysis module 102 is configured to perform semantic analysis on the query text based on a pre-constructed question semantic analysis model to obtain question intention features.
In the embodiment of the present invention, the semantic analysis module 102 performs semantic analysis on the query text by using a pre-constructed semantic analysis model to obtain the problem intention characteristics. For example: the query text is "what is the interest rate of the three-year-old user deposit? ", the question intention feature of the query text is" deposit intention "; the query text is 'which fund has the highest annual interest rate', and the question intention characteristic for obtaining the query text is 'fund purchase intention'.
Preferably, the semantic analysis model may be constructed by using a BERT (Bidirectional Encoder) algorithm, and the training of the semantic analysis model is completed by using a historical user query text set as a training set and using a marked historical user query text set as a tag set. The historical user query text set is a set formed by a plurality of historical user query texts.
The question intention characteristics are obtained by performing semantic analysis on the query text, and answers can be more accurately screened by using the question intention characteristics.
The answer screening module 103 is configured to query the question entity by using at least one pre-constructed answer knowledge base to obtain at least one answer text set; calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected; and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
In the embodiment of the present invention, in order to ensure the accuracy of the answer, the answer screening module 103 pre-constructs different answer knowledge bases, such as a business answer knowledge base, where the business answer knowledge base is a database composed of business knowledge defining business categories. For example: the financial industry covers a number of traffic classes including: the embodiment of the invention collects and stores the knowledge related to the fund service into a database to obtain a fund service answer knowledge base, collects and stores the knowledge related to the deposit into the database to obtain a deposit service answer knowledge base, and collects and stores the knowledge related to the investment into the database to obtain an investment service answer knowledge base.
In another embodiment of the invention, the answer knowledge base is composed of limited domain knowledge and can be deployed on a regional chain.
Further, the answer screening module 103 queries the question entity by using at least one answer knowledge base which is pre-constructed, to obtain at least one group of answer text sets; taking a service answer knowledge base as an example, three pre-constructed service answer knowledge bases, namely a fund service answer knowledge base, a deposit service answer knowledge base and an investment service answer knowledge base, are shared, the problem entity is inquired in the three service knowledge bases respectively to obtain a plurality of groups of service answer text sets, the fund service answer knowledge base is inquired to obtain a fund service answer text set, the deposit service answer knowledge base is inquired to obtain a deposit service answer text set, the investment service answer knowledge base is inquired to obtain an investment service answer text set, and 3 groups of service answer text sets are shared.
In the embodiment of the present invention, in order to filter a more accurate answer, the answer filtering module 103 converts the answer texts in the answer text set into answer text vectors, and converts the query texts into question text vectors.
Preferably, the answer filtering module 103 obtains an answer text vector by:
acquiring a word vector of each character contained in each answer text in the answer text set by using a pre-trained word vector dictionary;
and calculating the arithmetic mean value of the word vectors of all the characters in each answer text as the answer text vector corresponding to each answer text.
Further, the arithmetic mean is calculated as follows:
wherein, a1To anA word vector representing each character in each answer text, n represents the number of characters in the answer text, and W represents an answer text vector of the answer text.
Further, the answer filtering module 103 obtains a question text vector by:
obtaining a dimension window with a preset size;
inputting the query text into the dimension window to generate a dimension query text;
and coding the dimension query text by using a preset coding algorithm to generate a problem text vector.
For example, a dimensional window is a dimensional window of k × k, where k is a positive integer greater than or equal to 1.
Preferably, in this embodiment, the predetermined coding algorithm may be a huffman coding algorithm.
Further, the answer screening module 103 obtains the text of the answer to be selected by the following means:
calculating the relevance values of the answer text vectors and the question text vectors, and summarizing all the relevance values to obtain a relevance text set;
sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value;
and selecting the answer text vector corresponding to the maximum correlation value in the answer text set, and taking the answer text corresponding to the selected answer text vector as the to-be-selected answer text corresponding to the answer text set.
In detail, the correlation value calculation may be represented by the following formula:
wherein x isiFor the answer text vector, i is a positive integer, y is the question text vector, sim (x)iAnd) is the relevance value of the answer text vector and the question text vector.
Further, the answer screening module 103 summarizes the answer texts to be selected to obtain the answer text set to be selected.
In detail, in order to further screen answers and ensure the accuracy of the answers, in the embodiment of the present invention, the answer screening module 103 performs weighted calculation and analysis on the candidate answer texts in the candidate answer text set by using the question intention characteristics through the following means, including:
converting the problem intention features into problem intention feature vectors;
calculating the relevance value of the question intention characteristic vector and an answer text vector corresponding to each answer text to be selected to obtain the relevance value of the answer text to be selected;
calculating a total number of answer texts in the at least one set of answer text sets;
calculating the ratio of the number of answer texts in each group of answer text sets in the at least one group of answer text sets to the total number of the answer texts to obtain the weight of each group of answer text sets;
multiplying the answer text set weight corresponding to the answer text set in which the answer text to be selected is located by the answer text set relevancy corresponding to the answer text to be selected to obtain an answer text weight value to be selected, and summarizing the answer text weight value to be selected to obtain an answer text weight value set to be selected;
and selecting the to-be-selected answer text corresponding to the maximum to-be-selected answer text weight value in the to-be-selected answer text weight value set as the final answer text.
Further, in the embodiment of the present invention, the answer screening module 103 pushes the final answer text to the user, and meanwhile, obtains feedback information whether the user approves the final answer text, and performs corresponding update on data in the knowledge base based on the feedback information, thereby implementing error correction processing on the knowledge base.
The entity extraction module 101 of the embodiment of the invention performs word segmentation processing and entity extraction processing on the query text, and eliminates the influence of irrelevant words in the query text on subsequent answer queries; the semantic analysis module 102 performs semantic analysis on the query text to obtain question intention features, and answers can be more accurately screened by using the question intention features; the answer screening module 103 queries the question entity by using at least one pre-constructed answer knowledge base, so that the question query is more comprehensive and more accurate; the answer screening module 103 calculates and analyzes the relevance of the answer texts in the at least one group of answer text sets, and the answer screening module 103 performs weighted calculation and analysis on the answer texts to be selected in the answer text sets to be selected by using the question intention characteristics to obtain the final answer texts, so that the accuracy of answer screening is improved; and inquiring the inquiry text in different service answer knowledge bases, and further screening answers by using the question intention characteristics, so that the accuracy of intelligent question answering is improved.
Fig. 3 is a schematic structural diagram of an electronic device implementing the intelligent question answering method according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a smart question and answer program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of a smart question answering program, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., smart question answering programs, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The smart question-answering program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, enable:
receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
semantic analysis is carried out on the query text based on a pre-constructed problem semantic analysis model to obtain problem intention characteristics;
inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets;
calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected;
and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
Further, the computer usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. An intelligent question-answering method, characterized in that the method comprises:
receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
semantic analysis is carried out on the query text based on a pre-constructed problem semantic analysis model to obtain problem intention characteristics;
inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets;
calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected;
and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
2. The intelligent question-answering method according to claim 1, wherein the performing word segmentation processing on the query text comprises:
field presetting: performing word segmentation operation on the query text by using a pre-constructed word segmentation dictionary, wherein the number of characters contained in the maximum entry in the pre-constructed word segmentation dictionary is n, if the number of all characters of the query text is less than n, the query text is used as a matching field, and if the number of all characters of the query text is equal to or more than n, the first n characters of the query text are used as the matching field;
word segmentation matching step: traversing and matching in the word segmentation dictionary by utilizing the matching field; if the word segmentation dictionary contains the same words as the matching fields, determining that the matching is successful, separating the matching fields from the query text, and executing the following sequential matching steps; if the word segmentation dictionary does not contain the same words as the matching fields, executing the following field updating step;
field updating step: if the number of characters contained in the matching field is equal to 1, separating the matching field from the query text, and executing the following sequential matching steps; if the number of the characters contained in the matching field is more than 1, removing the last character of the matching field, replacing and updating the matching field by the field after removal, and returning to the word segmentation matching step;
and (3) sequence matching: if the number of the characters after the matched field in the query text is less than n, replacing and updating the matched field with all the characters after the matched field in the query text, and simultaneously returning to the word segmentation matching step; if the number of the characters after the fields are matched in the query text is not less than n, replacing and updating the matched fields by n characters in the sequence after the fields are matched in the query text, and simultaneously returning to the word segmentation matching step; and if the number of the characters after the query text is matched with the fields is equal to 0, stopping word segmentation processing.
3. The intelligent question-answering method according to claim 1, wherein the calculating and analyzing the relevance of the answer texts in the at least one answer text set to obtain the answer text set to be selected comprises:
converting answer texts in the answer text set into answer text vectors;
converting the query text into a question text vector;
calculating the relevance values of the answer text vectors and the question text vectors, and summarizing all the relevance values to obtain a relevance text set;
sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value;
selecting an answer text vector corresponding to the maximum correlation value in the answer text set, and taking an answer text corresponding to the selected answer text vector as an answer text to be selected corresponding to the answer text set;
summarizing the answer texts to be selected to obtain the answer text set to be selected.
4. The intelligent question-answering method according to claim 3, wherein the obtaining of the final answer text by performing weighted calculation and analysis on the to-be-selected answer texts in the to-be-selected answer text set by using the question intention characteristics comprises:
converting the problem intention features into problem intention feature vectors;
calculating the relevance value of the question intention characteristic vector and an answer text vector corresponding to each answer text to be selected to obtain the relevance value of the answer text to be selected;
calculating a total number of answer texts in the at least one set of answer text sets;
calculating the ratio of the number of answer texts in each group of answer text sets in the at least one group of answer text sets to the total number of the answer texts to obtain the weight of each group of answer text sets;
multiplying the answer text set weight corresponding to the answer text set in which the answer text to be selected is located by the answer text set relevancy corresponding to the answer text to be selected to obtain an answer text weight value to be selected;
summarizing the text weight values of the answers to be selected to obtain a text weight value set of the answers to be selected;
and selecting the to-be-selected answer text corresponding to the maximum to-be-selected answer text weight value in the to-be-selected answer text weight value set as the final answer text.
5. The intelligent question-answering method according to claim 3, wherein said converting the query text into a question text vector comprises:
obtaining a dimension window with a preset size;
inputting the query text into the dimension window to generate a dimension query text;
and coding the dimension query text by using a preset coding algorithm to generate the problem text vector.
6. The intelligent question-answering method according to claim 3, wherein the converting the answer texts in the answer text set into answer text vectors comprises:
acquiring a word vector of each character contained in each answer text in the answer text set by using a pre-trained word vector dictionary;
and calculating the arithmetic mean value of the word vectors of all the characters in each answer text as the answer text vector corresponding to each answer text.
7. An intelligent question answering device, characterized in that the device comprises:
the entity extraction module is used for receiving a query text input by a user, and performing word segmentation processing and entity extraction processing on the query text to obtain a problem entity;
the semantic analysis module is used for carrying out semantic analysis on the query text based on a pre-constructed question semantic analysis model to obtain question intention characteristics;
the answer screening module is used for inquiring the question entity by utilizing at least one pre-constructed answer knowledge base to obtain at least one group of answer text sets; calculating and analyzing the relevance of the answer texts in the at least one group of answer text sets to obtain an answer text set to be selected; and performing weighted calculation and analysis on the texts of the answers to be selected in the text set of the answers to be selected by using the question intention characteristics to obtain a final answer text, and pushing the final answer text to the user.
8. The intelligent question answering device according to claim 7, wherein the answer screening module calculates and analyzes the relevance of the answer texts in the at least one answer text set to obtain a candidate answer text set by the following means, including:
converting answer texts in the answer text set into answer text vectors;
converting the query text into a question text vector;
calculating the relevance values of the answer text vectors and the question text vectors, and summarizing all the relevance values to obtain a relevance text set;
sorting the relevancy values in the relevancy text set to obtain a maximum relevancy value;
selecting an answer text vector corresponding to the maximum correlation value in the answer text set, and taking an answer text corresponding to the selected answer text vector as an answer text to be selected corresponding to the answer text set;
summarizing the answer texts to be selected to obtain the answer text set to be selected.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
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 question answering method according to any one of claims 1 to 6.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the intelligent question answering method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011625530.7A CN112632260A (en) | 2020-12-30 | 2020-12-30 | Intelligent question and answer method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011625530.7A CN112632260A (en) | 2020-12-30 | 2020-12-30 | Intelligent question and answer method and device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112632260A true CN112632260A (en) | 2021-04-09 |
Family
ID=75290352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011625530.7A Pending CN112632260A (en) | 2020-12-30 | 2020-12-30 | Intelligent question and answer method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632260A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114372122A (en) * | 2021-12-08 | 2022-04-19 | 阿里云计算有限公司 | Information acquisition method, computing device and storage medium |
| CN114461777A (en) * | 2022-02-14 | 2022-05-10 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
-
2020
- 2020-12-30 CN CN202011625530.7A patent/CN112632260A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114372122A (en) * | 2021-12-08 | 2022-04-19 | 阿里云计算有限公司 | Information acquisition method, computing device and storage medium |
| CN114461777A (en) * | 2022-02-14 | 2022-05-10 | 平安科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016304A (en) | Text error correction method and device, electronic equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN112988963A (en) | User intention prediction method, device, equipment and medium based on multi-process node | |
| CN113821622A (en) | Answer retrieval method and device based on artificial intelligence, electronic equipment and medium | |
| CN112559687A (en) | Question identification and query method and device, electronic equipment and storage medium | |
| CN113268615A (en) | Resource label generation method and device, electronic equipment and storage medium | |
| CN112667775A (en) | Keyword prompt-based retrieval method and device, electronic equipment and storage medium | |
| CN113360654A (en) | Text classification method and device, electronic equipment and readable storage medium | |
| CN112632264A (en) | Intelligent question and answer method and device, electronic equipment and storage medium | |
| CN112883730B (en) | Similar text matching method and device, electronic equipment and storage medium | |
| CN113869456A (en) | Sampling monitoring method and device, electronic equipment and storage medium | |
| CN114398557A (en) | Information recommendation method and device based on double portraits, electronic equipment and storage medium | |
| CN112733551A (en) | Text analysis method and device, electronic equipment and readable storage medium | |
| CN112632260A (en) | Intelligent question and answer method and device, electronic equipment and computer readable storage medium | |
| CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
| CN115238670A (en) | Information text extraction method, device, equipment and storage medium | |
| CN114677526A (en) | Image classification method, device, equipment and medium | |
| CN112347739A (en) | Application rule analysis method and device, electronic equipment and storage medium | |
| CN112560427A (en) | Problem expansion method, device, electronic equipment and medium | |
| CN112633988A (en) | User product recommendation method and device, electronic equipment and readable storage medium | |
| CN116521867A (en) | Text clustering method and device, electronic equipment and storage medium | |
| CN114943306A (en) | Intention classification method, device, equipment and storage medium | |
| CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
| CN115203364A (en) | Software fault feedback processing method, device, equipment and readable storage medium | |
| CN115346095A (en) | Visual question answering method, device, 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 |