CN111291156A - Question-answer intention identification method based on knowledge graph - Google Patents
Question-answer intention identification method based on knowledge graph Download PDFInfo
- Publication number
- CN111291156A CN111291156A CN202010068158.8A CN202010068158A CN111291156A CN 111291156 A CN111291156 A CN 111291156A CN 202010068158 A CN202010068158 A CN 202010068158A CN 111291156 A CN111291156 A CN 111291156A
- Authority
- CN
- China
- Prior art keywords
- question
- graph
- word
- knowledge
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000013598 vector Substances 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 2
- 108020001568 subdomains Proteins 0.000 claims description 2
- 241001347978 Major minor Species 0.000 claims 1
- 230000008569 process Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a question-answer intention identification method based on a knowledge graph, which comprises the following steps: constructing a domain topic dictionary; constructing a template; performing part-of-speech analysis and syntactic dependency analysis on the retrieval statement; calculating the similarity between the search text and the template sample by using a word vector and an LDA algorithm; based on the known word vectors, a more extensive intent recognition is made based on TextCNN as a result of the open information; and extracting key words from the domain map. The invention integrates various methods to realize intention identification, and combines the knowledge graph of the field to achieve the comprehensive retrieval of accurate answers and related information, thereby meeting the various requirements of users.
Description
Technical Field
The invention relates to the technical field of natural language processing and deep learning, in particular to a question-answering intention identification method based on a knowledge graph.
Background
With the explosive growth of information and the rapid development of scientific technology in the present generation, people no longer satisfy the traditional mode that a large number of webpages or links containing related keywords are returned after the keywords of a search engine are input for the functions of the search engine, and in the mode, a user also needs to manually distinguish and browse in returned results, redundant results often need to waste a large amount of time for the user to remove, and the accuracy is not high. The easier search engine allows the user to obtain answers or related knowledge with higher directionality after inputting the spoken description information, which requires the program to analyze the user's intention more accurately and efficiently. Therefore, more and more intelligent question-answering systems are being developed and used in recent years.
The traditional method for recognizing intent mainly applies syntactic semantic analysis, syntactic dependency analysis and template matching, needs a large number of rules for support, has high recognition accuracy in a specified range, but has poor expansibility, needs to be reconfigured once the rules are changed, and consumes a large amount of labor.
After the large-scale development of machine learning, algorithms for classifying problems, such as SVM, bayesian algorithm, KNN and the like, are also widely applied to the field of intention recognition, but the method still faces the problem that manual classification labeling requires a large amount of manual work, and in many application scenarios, text input by a user is not a single intention, and one sentence may contain two or more intentions. With the intensive research on machine learning, many scholars at home and abroad propose a plurality of multi-label classification methods to solve the problems.
After the concept of deep learning is introduced, deep learning algorithms such as CNN, RNN, LSTM, attention mechanism, etc. are also beginning to be widely applied to the field of text classification, and many field recognition systems also increasingly apply such algorithms to practical applications and make corresponding adjustments and improvements in combination with practical requirements.
According to the characteristics of the traffic field, the method integrates various methods to realize intention identification, and combines the knowledge map of the field to achieve comprehensive retrieval of accurate answers and related information, so that various requirements of users are met.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a question-answering intention identification method based on a knowledge graph.
The purpose of the invention is realized by the following technical scheme:
a question-answer intention identification method based on a knowledge graph comprises the following steps:
a, constructing a domain topic dictionary;
b, constructing a template;
c, performing part-of-speech analysis and syntactic dependency analysis on the retrieval statement;
d, calculating the similarity between the search text and the template sample by using a word vector and an LDA algorithm;
e based on the known word vectors, making a more extensive intent recognition based on TextCNN as a result of the open information;
and F, extracting keywords from the domain map.
One or more embodiments of the present invention may have the following advantages over the prior art:
and the intention recognition is realized by integrating various methods, and the comprehensive retrieval of accurate answers and related information is realized by combining the knowledge graph of the field, so that various requirements of users are met.
Drawings
FIG. 1 is a flow chart of a knowledge-graph-based question-answering intention identification method.
Fig. 2, 3 and 4 are illustrations of specific embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings.
As shown in fig. 1, a process of a knowledge-graph-based question-answer intention identification method includes the following steps:
since there are many specialized vocabularies, entity names and acronyms in different specialized fields, a topic dictionary in the related vocabulary construction field needs to be arranged in advance to assist in the intention recognition. In many researches on intention recognition, topic dictionary construction in the professional field is lacked, and the method is considered to lack flexibility and need to be maintained manually, but in an application scenario that a user needs to accurately and quickly search within a specified range, the topic dictionary in the professional field is one of effective means for improving accuracy and recall rate.
at present, a common view covers information atmosphere information, navigation information, affairs information and the like contained in user search behaviors, and input of a question and answer system is divided into deterministic information, namely, a user hopes to obtain a definite answer through a certain question; open information, i.e. the user needs to get information in a wide or deeper direction.
Templates mainly help the system to solve deterministic information intention identification, and a plurality of specific items associated with intentions may be contained in the existing data, if not distinguished, the results of the search are still multi-directional and may be different. To help discern such intentions, a portion of ambiguous results need to be specified to help accurately identify the user's intent.
whether the Chinese retrieval or the foreign retrieval is carried out, certain grammatical rules are followed among all the words of the input sentence, and the understanding of the rules helps a program to understand the relation among all the words.
Limited to the length of the search sentence, the general search text is a short sentence with a short length and containing a large number of key words. The syntactic relations mainly concerned mainly include a main and subordinate relation (SBV), a moving object relation (VOB), a centering relation (ATT), an in-shape relation (ADV), a parallel relation (COO), and the like. The roles played by the words with different parts of speech in the sentence are generally fixed, the components of the sentence can be further divided on the basis of syntactic dependency analysis by knowing the parts of speech of the words, the relation among the words is known, and possible intentions and limiting conditions for the intentions are obtained.
In the traditional method, both part of speech and syntactic dependency are independently used, but in practical application, some verbs or adverbs can also be keywords, key information can be omitted simply by identifying entities or dividing sentence components, and in addition, the dividing accuracy of the conventional syntactic dependency analyzer on a plurality of sentence patterns cannot meet the requirements, so that the dependency relationship and part of speech of the words need to be specifically analyzed on the basis of obtaining the dependency relationship and part of speech, and a constructed domain topic dictionary is combined to better match more topics.
If (time, place, name, etc. of part of speech of word):
fill in the corresponding slot position
If (there is a relationship of principal and predicate guest)
If (subject, object and subject dictionary matching)
Judging the specific searching operation according to the predicates, and generating a conditional statement together with the subject object
Else
Performing openness matching in a map as a keyword
Elif (existence of a relationship in the middle, a relationship in the shape)
If (matching subject dictionary with fixed language and number-of-word)
Performing search operation with fixed language and shape language as limiting conditions
Elif (fixed language, number of words is possible aggregation operation)
Making condition limitation for key words modified by fixed language and number-like language
Else
Performing openness matching in a map as a keyword
Through the steps, the program can obtain more possible question-answer type accurate search intentions of the user, and does not simply carry out combined search matching on the keywords in the sentence.
and calculating the similarity between the search text and the template sample by using the word vector and an LDA algorithm.
And generating word vectors by using professional data and general data of the field and text which works through word segmentation, word stop and the like. Words are converted into dense vectors, and the similarity of the words is judged according to the distance between the word vectors, but in many cases, the two sentences have no obvious connection in terms of composition, so that implicit Dirichlet distribution (LDA) needs to be introduced to help a program to better understand the possible association between the sentences.
LDA is based on a Bayesian model, and the probability is gradually updated according to the obtained posterior distribution in the training process on the premise of prior probability. In the LDA model, a possible number of topics also needs to be preset for the first page, and after the number of topics is assumed, it is assumed that the prior distribution of texts conforms to Dirichlet distribution, that is, for any text, there is a text distribution
θm＝Dirichlet(α→)
Let words in the text also conform to a Dirichlet distribution, i.e. for any one topic, the word distribution satisfies
βm＝Dirichlet(η→)
Both text-topic and topic-term satisfy a polynomial distribution.
The posterior probability of the topic is satisfied
The posterior probability of the word-topic satisfies:
the joint probability is both:
under general conditions, a Gibbs sampling algorithm is adopted to solve the LDA
The key for solving the Gibbs Sampling algorithm is to solve the condition distribution corresponding to the ith word in the corpus
If the word wi is t, then
Because only conjugated structure is involved in the above formula
Thus is provided with
Thus the formula for Gibbs Samplin for LDA is
In fact, the flow of the LDA Gibbs sampling algorithm is as follows:
and randomly assigning a theme topici to each word of the text, recalculating the theme of each word according to a Gibbs sampling algorithm, updating, repeating the process until the model converges, and obtaining the theme of the word, which is the theme distribution result of the text.
Through template matching, the program can identify more spoken retrieval texts or ambiguous texts, accurately hit the most concerned problems of the user, and avoid the process of manually screening results by the user.
TextCNN is a deep learning algorithm for text classification proposed on the basis of CNN (convolutional neural network), and compared with CNN, TextCNN takes a word vector array as input, simplifies the original structure, only retains one convolutional layer and pooling layer, and finally realizes classification through softmax. The TextCNN has the advantages of simple structure, less parameters, higher training speed and lower maintenance cost by using the TextCNN under the condition of more data updating iterations. According to behavior statistics of the user, such as browsing records, operation logs and the like, the search preference of the user is obtained as a classification standard, and the obtained result can be closer to the actual use requirement of the user.
Through the steps, the program extracts the topics possibly contained in the text, but in the actual data, the description of the topics can be in various methods, namely one topic can correspond to a plurality of entities, or the subject is contained in an entity, so in order to more accurately obtain the user intention, the user needs to match possible related words of upper and lower level words in a domain map constructed in advance, mine the intention of the user in a deeper layer, explore sub-domains related to the keywords in the search sentence, for example, the user inputs the word "Beijing expressway", in the map, "Daguang high speed", "Jing bearing high speed", "Jing Shen high speed", "Jing Zang high speed", etc. can be returned to the user as the associated result through the Beijing expressway, or when the user searches "Jing Zang high speed", the information of 'length', 'speed limit', 'road grade', 'highway entrance' and the like are potential intentions of the user.
For the result of the accuracy, for example, "project with design speed greater than 80" is input to obtain an accurate answer as shown in fig. 2: the terms such as six lines, roadbed width and the like can be seen to be accurately positioned to the names of data storage in the database through the action of the domain map, and the answers of user retrieval sentences are accurately provided.
For the recognition of multiple intentions, input such as "what are items with a design speed of more than 80 and an investment amount of more than 100 ten thousand" as shown in fig. 3, it is clear from the figure that information containing a retrieval intention is accurately retrieved.
The following is a description of spoken content, such as "how many items there are in total in Guizhou. "it can be seen as shown in fig. 4 that the road specific information in all the Guizhou provinces below and the result of satisfying the question-answer are displayed on the page.
The embodiment integrates the advantages of the traditional syntactic dependency analysis and the part of speech analysis, combines the domain topic word list, quickly matches the domain professional words, analyzes the sentence structure, forms question-answer type retrieval conditions on the basis of obtaining the retrieval text topics, and accurately hits the question answers concerned by the user.
By combining the traditional method (syntactic dependency and part-of-speech analysis) and the deep learning algorithm (introducing similarity with templates to calculate possible topics for sentence division and combining the TextCNN algorithm to classify search sentences), the results of the traditional method and the deep learning algorithm are combined and preferentially used, so that the hit rate of the precision problem is higher, and the hit result of the openness problem is closer to the potential intention of a user.
Although the embodiments of the present invention have been described above, the above descriptions are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A question-answer intention identification method based on a knowledge graph is characterized by comprising the following steps:
a, constructing a domain topic dictionary;
b, constructing a template;
c, performing part-of-speech analysis and syntactic dependency analysis on the retrieval statement;
d, calculating the similarity between the search text and the template sample by using a word vector and an LDA algorithm;
e based on the known word vectors, making a more extensive intent recognition based on TextCNN as a result of the open information;
and F, extracting keywords from the domain map.
2. The knowledge-graph-based question-answering intention identifying method according to claim 1, wherein the syntactic relations in the step C comprise a major-minor relation, a motile-guest relation, a fixed relation, a middle-shape relation and a parallel relation.
3. The knowledge-graph-based question-answering intention identifying method according to claim 1, wherein in the step D: the method comprises the steps of generating word vectors by means of professional data and general data in the field and text of word stop work through word segmentation, converting words into dense vectors and judging similarity of the words according to distances between the word vectors.
4. The knowledge-graph-based question-answering intention identifying method according to claim 1, wherein the TextCNN is a deep learning algorithm for text classification proposed on the basis of a convolutional neural network CNN.
5. The knowledge-graph-based question-answering intention identifying method according to claim 1, wherein topics contained in the text are extracted in the step F, one topic in the topics corresponds to a plurality of entities, or the topic is contained in one entity.
6. The knowledge-graph-based question-answering intention identification method according to claim 1, wherein in the step F, possible upper-level and lower-level word associated words need to be matched in a domain graph constructed in advance, deeper intentions of the user are mined, and sub-domains associated with keywords in the search sentences are explored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010068158.8A CN111291156B (en) | 2020-01-21 | 2020-01-21 | Knowledge graph-based question and answer intention recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010068158.8A CN111291156B (en) | 2020-01-21 | 2020-01-21 | Knowledge graph-based question and answer intention recognition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291156A true CN111291156A (en) | 2020-06-16 |
| CN111291156B CN111291156B (en) | 2024-01-12 |
Family
ID=71021315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010068158.8A Active CN111291156B (en) | 2020-01-21 | 2020-01-21 | Knowledge graph-based question and answer intention recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291156B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782769A (en) * | 2020-07-01 | 2020-10-16 | 重庆邮电大学 | Intelligent knowledge graph question-answering method based on relation prediction |
| CN112100405A (en) * | 2020-09-23 | 2020-12-18 | 中国农业大学 | Veterinary drug residue knowledge graph construction method based on weighted LDA |
| CN112270166A (en) * | 2020-10-26 | 2021-01-26 | 摩森特(北京)科技有限公司 | Method for quickly making and creating 5G message |
| CN112905774A (en) * | 2021-02-22 | 2021-06-04 | 武汉市聚联科软件有限公司 | Human-computer conversation deep intention understanding method based on affair map |
| CN113051374A (en) * | 2021-06-02 | 2021-06-29 | 北京沃丰时代数据科技有限公司 | Text matching optimization method and device |
| CN113127627A (en) * | 2021-04-23 | 2021-07-16 | 中国石油大学(华东) | Poetry recommendation method based on LDA topic model and poetry knowledge map |
| CN113239163A (en) * | 2021-05-12 | 2021-08-10 | 同方知网数字出版技术股份有限公司 | Intelligent question-answering method and system based on traffic big data |
| CN113420130A (en) * | 2021-05-12 | 2021-09-21 | 同方知网数字出版技术股份有限公司 | Intention recognition algorithm based on government affair question-answering system |
| CN113590797A (en) * | 2021-08-05 | 2021-11-02 | 云上贵州大数据产业发展有限公司 | Intelligent operation and maintenance customer service system and implementation method |
| CN113792116A (en) * | 2021-08-25 | 2021-12-14 | 北京库睿科技有限公司 | Search term semantic-based multi-vertical domain multi-intention hierarchical judgment method and system |
| CN115809321A (en) * | 2022-10-09 | 2023-03-17 | 中原工学院 | Retrieval system and method based on knowledge graph |
| WO2023227030A1 (en) * | 2022-05-24 | 2023-11-30 | 中国电信股份有限公司 | Intention recognition method and apparatus, storage medium and electronic device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823848A (en) * | 2014-02-11 | 2014-05-28 | 浙江大学 | LDA (latent dirichlet allocation) and VSM (vector space model) based similar Chinese herb literature recommendation method |
| CN107562831A (en) * | 2017-08-23 | 2018-01-09 | 中国软件与技术服务股份有限公司 | A kind of accurate lookup method based on full-text search |
| CN109213999A (en) * | 2018-08-20 | 2019-01-15 | 成都佳发安泰教育科技股份有限公司 | A kind of subjective item methods of marking |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN109635117A (en) * | 2018-12-26 | 2019-04-16 | 零犀(北京)科技有限公司 | A kind of knowledge based spectrum recognition user intention method and device |
| CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
| WO2019144926A1 (en) * | 2018-01-26 | 2019-08-01 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and apparatus, computer device and computer-readable storage medium |
| CN110377911A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | Intension recognizing method and device under dialogue frame |
| CN110399457A (en) * | 2019-07-01 | 2019-11-01 | 吉林大学 | A kind of intelligent answer method and system |
| CN110633724A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Intention recognition model dynamic training method, device, equipment and storage medium |
-
2020
- 2020-01-21 CN CN202010068158.8A patent/CN111291156B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823848A (en) * | 2014-02-11 | 2014-05-28 | 浙江大学 | LDA (latent dirichlet allocation) and VSM (vector space model) based similar Chinese herb literature recommendation method |
| CN107562831A (en) * | 2017-08-23 | 2018-01-09 | 中国软件与技术服务股份有限公司 | A kind of accurate lookup method based on full-text search |
| WO2019144926A1 (en) * | 2018-01-26 | 2019-08-01 | 上海智臻智能网络科技股份有限公司 | Intelligent interaction method and apparatus, computer device and computer-readable storage medium |
| CN110633724A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Intention recognition model dynamic training method, device, equipment and storage medium |
| CN109213999A (en) * | 2018-08-20 | 2019-01-15 | 成都佳发安泰教育科技股份有限公司 | A kind of subjective item methods of marking |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN109635117A (en) * | 2018-12-26 | 2019-04-16 | 零犀(北京)科技有限公司 | A kind of knowledge based spectrum recognition user intention method and device |
| CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
| CN110399457A (en) * | 2019-07-01 | 2019-11-01 | 吉林大学 | A kind of intelligent answer method and system |
| CN110377911A (en) * | 2019-07-23 | 2019-10-25 | 中国工商银行股份有限公司 | Intension recognizing method and device under dialogue frame |
Non-Patent Citations (6)
| Title |
|---|
| NILESH CHAKRABORTY ET AL.: "Introduction of Neural Network based Approaches for Question Answering over Knowledge Graphs", ARXIV * |
| XIAOHAN ZOU: "A Survey on Application of Knowledge Series", JOURNAL OF PHYSICS * |
| 孙昌年: ""基于主题模型的文本相似度计算研究与实现"", 《中国优秀硕士学位论文全文数据库》 * |
| 孙昌年: ""基于主题模型的文本相似度计算研究与实现"", 《中国优秀硕士学位论文全文数据库》, 31 October 2012 (2012-10-31) * |
| 牛雪莹: ""结合主题模型词向量的CNN文本分类"", 《计算机与现代化》 * |
| 牛雪莹: ""结合主题模型词向量的CNN文本分类"", 《计算机与现代化》, 29 October 2019 (2019-10-29) * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782769A (en) * | 2020-07-01 | 2020-10-16 | 重庆邮电大学 | Intelligent knowledge graph question-answering method based on relation prediction |
| CN111782769B (en) * | 2020-07-01 | 2022-07-08 | 重庆邮电大学 | Intelligent knowledge graph question-answering method based on relation prediction |
| CN112100405A (en) * | 2020-09-23 | 2020-12-18 | 中国农业大学 | Veterinary drug residue knowledge graph construction method based on weighted LDA |
| CN112100405B (en) * | 2020-09-23 | 2024-01-30 | 中国农业大学 | Veterinary drug residue knowledge graph construction method based on weighted LDA |
| CN112270166A (en) * | 2020-10-26 | 2021-01-26 | 摩森特(北京)科技有限公司 | Method for quickly making and creating 5G message |
| CN112905774A (en) * | 2021-02-22 | 2021-06-04 | 武汉市聚联科软件有限公司 | Human-computer conversation deep intention understanding method based on affair map |
| CN113127627A (en) * | 2021-04-23 | 2021-07-16 | 中国石油大学(华东) | Poetry recommendation method based on LDA topic model and poetry knowledge map |
| CN113127627B (en) * | 2021-04-23 | 2023-01-17 | 中国石油大学(华东) | Poetry recommendation method based on LDA theme model and poetry knowledge map |
| CN113420130A (en) * | 2021-05-12 | 2021-09-21 | 同方知网数字出版技术股份有限公司 | Intention recognition algorithm based on government affair question-answering system |
| CN113239163A (en) * | 2021-05-12 | 2021-08-10 | 同方知网数字出版技术股份有限公司 | Intelligent question-answering method and system based on traffic big data |
| CN113051374B (en) * | 2021-06-02 | 2021-08-31 | 北京沃丰时代数据科技有限公司 | Text matching optimization method and device |
| CN113051374A (en) * | 2021-06-02 | 2021-06-29 | 北京沃丰时代数据科技有限公司 | Text matching optimization method and device |
| CN113590797A (en) * | 2021-08-05 | 2021-11-02 | 云上贵州大数据产业发展有限公司 | Intelligent operation and maintenance customer service system and implementation method |
| CN113792116A (en) * | 2021-08-25 | 2021-12-14 | 北京库睿科技有限公司 | Search term semantic-based multi-vertical domain multi-intention hierarchical judgment method and system |
| CN113792116B (en) * | 2021-08-25 | 2024-03-29 | 北京库睿科技有限公司 | Multi-vertical-domain multi-intention hierarchical judgment method and system based on search word semantics |
| WO2023227030A1 (en) * | 2022-05-24 | 2023-11-30 | 中国电信股份有限公司 | Intention recognition method and apparatus, storage medium and electronic device |
| CN115809321A (en) * | 2022-10-09 | 2023-03-17 | 中原工学院 | Retrieval system and method based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291156B (en) | 2024-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291156B (en) | Knowledge graph-based question and answer intention recognition method | |
| CN110399457B (en) | Intelligent question answering method and system | |
| CN108304375B (en) | Information identification method and equipment, storage medium and terminal thereof | |
| CN109271529B (en) | Method for constructing bilingual knowledge graph of Xilier Mongolian and traditional Mongolian | |
| CN108897857B (en) | Chinese text subject sentence generating method facing field | |
| CN112115238B (en) | Question-answering method and system based on BERT and knowledge base | |
| CN106997382B (en) | Innovative creative tag automatic labeling method and system based on big data | |
| CN111931506B (en) | Entity relationship extraction method based on graph information enhancement | |
| CN110309268B (en) | Cross-language information retrieval method based on concept graph | |
| CN109960786A (en) | Chinese Measurement of word similarity based on convergence strategy | |
| Suleiman et al. | The use of hidden Markov model in natural ARABIC language processing: a survey | |
| CN113535917A (en) | Intelligent question-answering method and system based on travel knowledge map | |
| CN110674252A (en) | High-precision semantic search system for judicial domain | |
| CN108874896B (en) | Humor identification method based on neural network and humor characteristics | |
| CN113505209A (en) | Intelligent question-answering system for automobile field | |
| CN111597328B (en) | New event theme extraction method | |
| CN113196277A (en) | System for retrieving natural language documents | |
| CN110888991A (en) | Sectional semantic annotation method in weak annotation environment | |
| CN110717045A (en) | Letter element automatic extraction method based on letter overview | |
| CN113282711B (en) | Internet of vehicles text matching method and device, electronic equipment and storage medium | |
| CN112434164B (en) | Network public opinion analysis method and system taking topic discovery and emotion analysis into consideration | |
| Shen et al. | SsciBERT: A pre-trained language model for social science texts | |
| CN112328800A (en) | System and method for automatically generating programming specification question answers | |
| CN114064901B (en) | Book comment text classification method based on knowledge graph word meaning disambiguation | |
| CN111159405B (en) | Irony detection method based on background knowledge |
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 |