CN105677822A - Enrollment automatic question-answering method and system based on conversation robot - Google Patents
Enrollment automatic question-answering method and system based on conversation robot Download PDFInfo
- Publication number
- CN105677822A CN105677822A CN201610001347.7A CN201610001347A CN105677822A CN 105677822 A CN105677822 A CN 105677822A CN 201610001347 A CN201610001347 A CN 201610001347A CN 105677822 A CN105677822 A CN 105677822A
- Authority
- CN
- China
- Prior art keywords
- word
- user
- question
- answer
- enrollment
- 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 43
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000007246 mechanism Effects 0.000 claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007630 basic procedure Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009223 counseling Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
- G06Q50/2053—Education institution selection, admissions, or financial aid
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an enrollment automatic question-answering method and system based on a conversation robot. The method comprises the following steps that 1, characters input by a user are obtained; 2, character processing is conducted on the characters input by the user; 3, a best answer is selected from a knowledge base by means of a fuzzy matching method and an internal reasoning mechanism according to the characters subjected to character processing; 4, the best answer is sent to the user. According to the enrollment automatic question-answering method and system based on the conversation robot, the ALICE open-source conversation robot is improved, a domain ontology base serves as an additional knowledge base of a question-answering system, a hypernym-hyponym relation of a constructed domain ontology is utilized for conducting user intention excavation on a problem put forward by the user, a related content recommendation is given to the user by means of hypernym-hyponym information of the domain ontology on the basis of achieving basic question answering, therefore, an examinee can also obtain some recommended results with associated content when the examinee does not obtain an answer of the relevant question, and the satisfaction degree of the question-answering system is improved.
Description
Technical field
The invention belongs to Chinese natural language technical field of information processing, be specifically related to a kind of enrollment automatic question-answering method based on dialogue robot and system.
Background technology
The research history of existing more than 50 year of automatically request-answering system, and become an important branch and the study hotspot of natural language processing and information retrieval, automatically request-answering system is widely used in every field. Such as, along with being continuously increased of colleges and universities' source of students, examinee generally utilizes the enrolment consultation platform of colleges and universities more fully to understand the resource distribution of school, enrollment plan, enters oneself for the examination the information such as requirement. Colleges and universities omnibearing can also show school's strength and level, allows examinee, the head of a family and society more understand school, thus winning more better source of students. But traditional enrolment consultation work is faced with many problems, for instance the problem of major part examinee or parent counseling is all similar, and contact staff's repetitive work wastes many manpowers, financial resources and time resource. Along with deep development and the research of natural language processing technique, the automatic question answering robot in enrollment question and answer field arises at the historic moment.
Being currently used for the dialogue robot of enrollment question and answer, its basic procedure processing problem is: obtains customer problem, customer problem be analyzed and obtained user view, select corresponding problem answers from corpus. But the pattern of current question and answer robot is question-response, structure is single; And it is typically due to the restriction of language material scale and to the problem such as the supposition of user's query intention is inaccurate, all of problem can not be provided answer result, also without providing the content recommendation being associated.
ALICE (ArtificialLinguisticInternetComputerEntity) is by an artificial intelligence's chat robots based on experience of doctor's RichardS.Wallace exploitation of Pennsylvania, United States Lehigh university. The ALICE of initial release supports the language such as English, German, French, does not but support Chinese. Finding when ALICE source code is analyzed, Filtering system during its pretreatment forecloses Chinese character.
Summary of the invention
For above-mentioned problems of the prior art, it is an object of the invention to provide a kind of enrollment automatic question-answering method based on dialogue robot avoiding the occurrence of above-mentioned technological deficiency and system.
In order to realize foregoing invention purpose, technical scheme provided by the invention is as follows:
A kind of enrollment automatic question-answering method based on dialogue robot, comprises the following steps:
Step 1) obtain the word that user inputs;
Step 2) word that described user is inputted carries out word processing;
Step 3) according to carrying out the word after word processing, utilize Method of Fuzzy Matching and internal reasoning mechanism to select optimum answer from knowledge base;
Step 4) described optimum answer is sent to user.
Further, described knowledge base is the knowledge base that the knowledge content to question and answer field is organized and built according to the specification of AIML language.
Further, described step 2) particularly as follows: utilize the word that user is inputted by Chinese word segmentation resolver to carry out Chinese word segmentation process, and utilize Harbin Institute of Technology to disable the stop words in the word of vocabulary removal user's input, then the word after processing is carried out effective word extraction, obtain effective word list.
Further, described Chinese word segmentation resolver is ICTCLAS segmenter.
Further, described step 3) replace with: according to the word after carrying out Chinese word segmentation process and removing stop words, the method and the internal reasoning mechanism that utilize fuzzy matching select optimum answer from described knowledge base, carry out Ontology Query simultaneously, the upper the next information of described effective word is obtained from additional knowledge storehouse, wherein, described additional knowledge storehouse is the field ontology library utilizing domain body to build.
Further, described step 4) replace with: described optimum answer and described the next information are sent to user.
Further, carrying out Ontology Query, obtain the upper the next information of described effective word from described field ontology library, this step is particularly as follows: arrange effective word from big to small according to weighted value, as the candidate word of Ontology Query, from described field ontology library, obtain the upper the next information of described effective word; Wherein, the computing formula of the described weighted value of described effective word is
In formula, n represents the noun in the word that user inputs, and v represents the verb in the word that user inputs, and o represents other words in the word that user inputs, and i represents the number of word, factor alpha=0.5, β=0.3, γ=0.2 in the word that user inputs.
A kind of enrollment automatically request-answering system based on dialogue robot, including:
Word for user is inputted carries out the Chinese word segmentation processing module of participle;
The knowledge base knowledge content in question and answer field organized and build according to the specification of AIML language;
For carrying out Ontology Query, therefrom obtaining the field ontology library of the upper the next information of described effective word;
Method and internal reasoning mechanism for utilizing fuzzy matching selects the answer acquisition module of optimum answer from knowledge base;
For obtaining the word of user's input and described optimum answer being sent to the user interactive module of user.
Enrollment automatic question-answering method based on dialogue robot provided by the invention and system, chat robots of being increased income by ALICE carries out secondary development, using the field ontology library additional knowledge storehouse as question answering system, user is asked a question and is carried out user intention mining by the hyponymy utilizing the domain body built, realizing on the basis of basic question and answer, user is provided related content and recommends by the upper the next information utilizing domain body, make examinee also can obtain the recommendation results of some associate content when not getting relevant issues answer, thus improve the satisfaction of question answering system, the needs of practical application can be met well.
Accompanying drawing explanation
Fig. 1 utilizes the Prot é g é certain fields body schematic diagram built;
Fig. 2 is the flow chart of the enrollment automatic question-answering method based on dialogue robot of the present invention.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearly understand, below in conjunction with the drawings and specific embodiments, the present invention will be further described. Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
The present invention utilizes the ALICE intelligence chat robots (being also dialogue robot) increased income, and modifies to adapt to the application in enrollment field to it. Original ALICE chat robots has been carried out further exploitation by the present invention, ALICE source code adds the code that Chinese text is supported, Chinese character processes to make it support, and adds Chinese word segmentation module and AIML construction of knowledge base module, finally achieves the automatic question answering of Chinese. ALICE is also dialogue robot in the present invention.
Comprise reasoning and pattern match mechanism inside ALICE, adopt AIML (ArtificialIntelligenceMarkupLanguage) to describe language as knowledge base. Knowledge base content is organized by it currently with the label type linguistic structure of a kind of XML of being similar to.
1) AIML Grammatical composition key element:
AIML is a kind of language-specific serving artificial intelligence field needs utilizing XML standard to define, and it describes the one group of data object being referred to as AIML object, and describes the behavior of the program processing these data objects. In AIML, basic blocks of knowledge is made up of classification (category), and the answer that the problem that each classification is inputted by user, ALICE export and optional context environmental (OptionalContext) are formed. One be simply classified as follows shown in:
<category>
<pattern>WHATISYOURNAME</pattern>
<template></template>
</category>
Wherein, pattern<pattern>part represents the question of user's input, template<template>part then represents after user inputs this question sentence, the answer that system should provide.
2) AIML knowledge tree:
AIML knowledge base is to be stored in calculator memory in the form of a tree, tree each node on behalf pattern in a phrase or asterisk wildcard, it is connected according to before and after the position that it occurs in a template, each leaf node comprises a template attributes, when returning the Template Information of leaf node after this pattern match success. Many AIML files comprising different field knowledge can be merged into a knowledge base, improves autgmentability and the compatibility of system.
3) AIML reasoning process:
The inference mechanism of AIML is the template content that coupling was inquired about and found to the content according to user's input from classification.
ALICE chat robots is not directly applicable enrollment question and answer, so that modified to adapt to enrollment question and answer field.
The enrollment automatically request-answering system based on ALICE of the present invention includes: Chinese word segmentation processing module, knowledge base, answer acquisition module, user interactive module, and wherein the effect of each several part and function are as follows:
(1) Chinese word segmentation processing module
Owing to ALICE original contents does not comprise Chinese language processing module, need to add Chinese word segmentation resolver, the present invention adopts Chinese Academy of Sciences's ICTCLAS segmenter, it has the advantages such as word segmentation accuracy height, speed is fast and can add Custom Dictionaries, such as " score line ", " retrial flow process of preparing for the postgraduate qualifying examination " etc. To sum up, enrollment automatically request-answering system, when getting the word of user's input, calls Chinese language processing module and carries out participle and remove the operation of unrelated word.Enrollment automatically request-answering system calls the word of ICTCLAS segmenter user's input to being obtained by user interactive module to carry out participle, remove stop words operation and the word after processing is submitted to answer acquisition module.
(2) knowledge base
ALICE needs AIML knowledge base to support, so that problem and answer to enrollment question and answer field are built into knowledge base, i.e. AIML knowledge base, in the present embodiment, the content of certain school enrollment website by obtaining in advance, is undertaken the content of enrollment organizing and building knowledge base according to the specification of AIML language.
Such as:
● does is your school enrollment in this year how many?
● may I ask computer major autonomous enrolment?
So the matching template of the structure of the two problem is respectively as follows:
●<pattern>* enrollment * number *</pattern>
●<pattern>* the autonomous * enrollment * of computer major *</pattern>
1000 relevant matching templates are organized and constructed to relevant enrollment content by the present embodiment.
(3) answer acquisition module
The word of user's input that enrollment automatically request-answering system is obtained by answer acquisition module processes, and answer acquisition module, according to the sentence carried out after processing, utilizes the method for fuzzy matching and internal reasoning mechanism to select optimum answer from AIML knowledge base.
(4) user interactive module
User interactive module primary responsibility user and dialogue robot between mutual, for talk with robot obtain user input word and dialogue robot answer information is sent to user. The word that user is inputted by Chinese information processing module carries out Chinese word segmentation and removes stop words process, answer acquisition module is given by the result after processing, after answer acquisition module is analyzed reasoning, from template, finds the optimum answer of coupling and eventually through user interactive module, optimum answer is presented to user.
Based on problems such as the enrollment question and answer robot restriction due to language material scale of ALICE and the supposition to user's query intention are inaccurate, all of problem can not be provided answer result so that the satisfaction of question answering system is declined by user. The present invention, further using the domain body additional knowledge storehouse as question and answer robot, the problem content according to user, provides related content and recommends, thus improving the satisfaction that question answering system is overall. The improvement further of question answering system is included the work of two aspects by the present invention: the structure of domain body is recommended with parsing, user content.
Domain body (DomainOntology) is professional body, what describe is the relation between the concept in specific area and concept, provide the relation between the vocabulary of concept in certain special disciplines field and concept, or in this field prevailing theory. Prot é g é is Stanford University is an instrument developing of knowledge acquisition, and first the present invention obtains some and set up field concept structures about the concept in enrollment field, and utilizes Prot é g é instrument to carry out the structure of body.
Ontology library used in the present embodiment is the field ontology library for enrollment field, and content relates to the content such as subject, mechanism. There are computer, economics, accounting in branch under such as concept " subject ", and computer has again individual software engineering, computer utility etc. below, and there are enrollment office, Educational Affairs Office, political affairs religion place etc. in the branch under concept mechanism for another example. Utilize Prot é g é this body display of certain fields built as shown in Figure 1.
Original ALICE source code does not have the parsing module to domain body, source code has been improved by the present invention, with the addition of the interface for resolving domain body, this interface includes the interface getSuperClass for obtaining superordination and for obtaining the interface getSubClass of the next relation.
After user inputs word, user's word is carried out participle, then adopt Harbin Institute of Technology to disable vocabulary and remove stop words therein. Generally in sentence, user asked a question in noun and verb in sentence, play important effect, and noun often carries more quantity of information than verb. When extracting effective word, suitably give noun and the certain weighted value of verb, it is possible to extract effective word. Effective word and weighted value definition are as follows:
Definition 1 effective word: can embody the word of sentence core word, mainly is become to be grouped into by noun, verb.
The weighted value of definition 2 effective words: the expression that quantizes to word effective in sentence.
The computing formula (1) of the weighted value of effective word is as follows:
In formula (1), n represents the noun in sentence, and v represents the verb in sentence, and o represents other word, and i represents the number of word, factor alpha=0.5, β=0.3, γ=0.2, represents the significance level of different part of speech.
After utilizing effective word to calculate, by obtained effective word according to weight from big to small order arrangement, candidate word as Ontology Query, the upper the next information of effective word is inquired about from ontology knowledge base, the content that the upper the next information of effective word is namely relevant to problem, sends jointly to user by the upper the next information of the effective word obtained and optimum answer. In body resolving, when namely obtaining the upper the next information of effective word, the present invention uses the Jena instrument incorporated in ALICE that the field ontology library built is resolved, and obtains the upper the next information of effective word.
ALICE has two handling processes: namely Article 1 is obtain the optimum answer of problem from knowledge base after getting the word of user's input; Article 2 is to extract effective word from the word of user's input, then according to effective word, utilizes the Jena instrument incorporated in ALICE to obtain the upper the next information of effective word from field ontology library; Finally the upper the next information of optimum answer and effective word is sent jointly to user.
Below with object lesson (question sentence) " how may I ask computer major? " verify for example.
Question sentence: how may I ask computer major?
Word segmentation result: how may I ask computer major?
After removing stop words, the key word of question sentence is: computer major how
Wherein, in AIML corpus, there is matching template<pattern>how * computer major * *</pattern>. Question answering system can provide the question and answer content in corresponding template, after adding domain body, the key word extracted from question sentence has computer major, admission, three key words of score line, Query Result after building the upper the next information obtaining these key words field ontology library is: soft project, Computer Science and Technology, the content such as computer utility. After inquiring PRELIMINARY RESULTS, to result according to different parts of speech according to weight sequencing, identical part of speech natural ordering returns to user.
In sum, as in figure 2 it is shown, the concrete steps based on the enrollment automatic question-answering method of dialogue robot of the present invention are summarized as follows:
Step 1) obtain the word that user inputs;
Step 2) word that described user is inputted carries out word processing: utilize the word that user is inputted by Chinese word segmentation resolver to carry out Chinese word segmentation process, and utilize Harbin Institute of Technology to disable the stop words in the word of vocabulary removal user's input, then the word after processing is carried out effective word extraction, obtain effective word list;
Step 3) according to the word after carrying out Chinese word segmentation process and removing stop words, the method and the internal reasoning mechanism that utilize fuzzy matching select optimum answer from described knowledge base, carry out Ontology Query simultaneously, the upper the next information of described effective word is obtained from additional knowledge storehouse, wherein, described additional knowledge storehouse is the field ontology library utilizing domain body to build;
Step 4) answer content (i.e. described optimum answer and described the next information) is sent to user.
A kind of system of the enrollment automatic question-answering method based on dialogue robot, including:
Word for user is inputted carries out the Chinese word segmentation processing module of participle;
The knowledge base knowledge content in question and answer field organized and build according to the specification of AIML language;
For carrying out Ontology Query, therefrom obtaining the field ontology library of the upper the next information of described effective word;
Method and internal reasoning mechanism for utilizing fuzzy matching selects the answer acquisition module of optimum answer from knowledge base;
For obtaining the word of user's input and described optimum answer being sent to the user interactive module of user.
By experiment the effect of the present invention is evaluated, from recommending the degree of association and two aspects of user satisfaction, experimental result has been carried out overall merit measurement. The definition recommending degree of association RC (recommendedcorrelation) and user satisfaction US (Usersatisfaction) is as follows respectively:
The definition 3 recommendation degrees of association: whether relevant refer to be asked a question to user in the result recommended tolerance. Its computing formula is as follows:
Recommendation number relevant to problem for RC=/all recommendation numbers (2)
Recommend incidence number purpose to calculate with user, the judgement recommending entry to be measured.
Define 4 user satisfaction: refer to the satisfaction of user's answer to question answering system and content recommendation thereof, be made up of the accuracy rate of system answer and the degree of association of recommendation respectively. Its computing formula is as follows:
In formula (3), N represents the number that user asks a question, n represent answer accurately and number of questions.
By means of the invention it is also possible to reduce the problem reducing user's user satisfaction to complicated question because question answering system can not get accurately answering, thus improving the effectiveness of question answering system.
Enrollment automatic question-answering method based on dialogue robot provided by the invention and system, chat robots of being increased income by ALICE carries out secondary development, using the field ontology library additional knowledge storehouse as question answering system, user is asked a question and is carried out user intention mining by the hyponymy utilizing the domain body built, realizing on the basis of basic question and answer, user is provided related content and recommends by the upper the next information utilizing domain body, make user after the problem (problem etc. in such as University Enrollment) that input to be inquired, also the recommendation results of some associate content can be obtained when not getting relevant issues answer, thus improve the satisfaction of question answering system, the needs of practical application can be met well.
Embodiment described above only have expressed embodiments of the present invention, and it describes comparatively concrete and detailed, but therefore can not be interpreted as the restriction to the scope of the claims of the present invention. It should be pointed out that, for the person of ordinary skill of the art, without departing from the inventive concept of the premise, it is also possible to making some deformation and improvement, these broadly fall into protection scope of the present invention. Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (8)
1. the enrollment automatic question-answering method based on dialogue robot, it is characterised in that comprise the following steps:
Step 1) obtain the word that user inputs.
Step 2) word that described user is inputted carries out word processing.
Step 3) according to carrying out the word after word processing, utilize Method of Fuzzy Matching and internal reasoning mechanism to select optimum answer from knowledge base.
Step 4) described optimum answer is sent to user.
2. the knowledge base in method according to claim 1, it is characterised in that described knowledge base is the knowledge base that the knowledge content to question and answer field is organized and built according to the specification of AIML language.
3. according to claim 1 based on the step 2 in the automatic question-answering method of dialogue robot), it is characterized in that, described step 2) particularly as follows: utilize the word that user is inputted by Chinese word segmentation resolver to carry out Chinese word segmentation process, and utilize Harbin Institute of Technology to disable the stop words in the word of vocabulary removal user's input. Then the word after processing is carried out effective word extraction, obtain effective word list.
4. Chinese word segmentation resolver according to claim 3, it is characterised in that described Chinese word segmentation resolver is ICTCLAS segmenter.
5. the answering method based on robot according to claim 3, it is characterized in that, described step 3) replace with: according to the word after carrying out Chinese word segmentation process and removing stop words, the method and the internal reasoning mechanism that utilize fuzzy matching know selection optimum answer storehouse from described, carry out Ontology Query simultaneously, from additional knowledge storehouse, obtain the upper the next information of described effective word. Wherein, described additional knowledge storehouse is the field ontology library utilizing domain body to build.
6. the answering method based on robot according to claim 5, it is characterised in that described step 4) replace with: described optimum answer and described the next information are sent to user.
7. the answering method based on robot according to claim 5, it is characterized in that, carry out Ontology Query, the upper the next information of described effective word is obtained from this storehouse, described field, this step is particularly as follows: arrange effective word from big to small according to weighted value, as the candidate word of Ontology Query, from described field ontology library, obtain the upper the next information of described effect word. Wherein, the computing formula of the described weighted value of described effective word is
In formula, n represents the noun in the word that user inputs, and v represents the verb in the word that user inputs, and o represents other words in the word that user inputs, and i represents the number of word, factor alpha=0.5, β=0.3, γ=0.2 in the word that user inputs.
8. the enrollment automatically request-answering system based on dialogue robot using the enrollment automatic question-answering method based on dialogue robot according to claim 6, it is characterised in that including:
Word for user is inputted carries out the Chinese word segmentation processing module of participle.
The knowledge base knowledge content in question and answer field organized and build according to the specification of AIML language.
For carrying out Ontology Query, therefrom obtaining the field ontology library of the upper the next information of described effective word.
Method and internal reasoning mechanism for utilizing fuzzy matching selects the answer acquisition module of optimum answer from knowledge base.
For obtaining the word of user's input and described optimum answer being sent to the user interactive module of user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610001347.7A CN105677822A (en) | 2016-01-05 | 2016-01-05 | Enrollment automatic question-answering method and system based on conversation robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610001347.7A CN105677822A (en) | 2016-01-05 | 2016-01-05 | Enrollment automatic question-answering method and system based on conversation robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105677822A true CN105677822A (en) | 2016-06-15 |
Family
ID=56190341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610001347.7A Pending CN105677822A (en) | 2016-01-05 | 2016-01-05 | Enrollment automatic question-answering method and system based on conversation robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105677822A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446162A (en) * | 2016-09-26 | 2017-02-22 | 浙江大学 | Orient field self body intelligence library article search method |
CN106471502A (en) * | 2016-06-29 | 2017-03-01 | 深圳狗尾草智能科技有限公司 | Intension recognizing method based on water conservancy diversion and system |
CN106484916A (en) * | 2016-11-04 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | A kind of enrollment answering method and device |
CN106485328A (en) * | 2016-10-31 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Information processing system and method |
CN106528759A (en) * | 2016-11-04 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
CN106844335A (en) * | 2016-12-21 | 2017-06-13 | 海航生态科技集团有限公司 | Natural language processing method and device |
CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技(上海)有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
WO2018000205A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Question answering method and system based on multiple intents and multiple skill packets, and robot |
CN107861951A (en) * | 2017-11-17 | 2018-03-30 | 康成投资(中国)有限公司 | Session subject identifying method in intelligent customer service |
CN107895193A (en) * | 2017-11-13 | 2018-04-10 | 北京神州泰岳软件股份有限公司 | A kind of construction of knowledge base method, parameter setting method and device based on dialogue |
CN108958247A (en) * | 2018-07-02 | 2018-12-07 | 深圳市益鑫智能科技有限公司 | A kind of guided robot |
WO2019000170A1 (en) * | 2017-06-26 | 2019-01-03 | Microsoft Technology Licensing, Llc | Generating responses in automated chatting |
CN109241258A (en) * | 2018-08-23 | 2019-01-18 | 江苏索迩软件技术有限公司 | A kind of deep learning intelligent Answer System using tax field |
CN109313638A (en) * | 2017-03-09 | 2019-02-05 | 微软技术许可有限责任公司 | Using recommendation |
CN109815324A (en) * | 2019-01-10 | 2019-05-28 | 平安科技(深圳)有限公司 | Querying method, device, computer equipment and the storage medium of campus information |
CN110059169A (en) * | 2019-01-25 | 2019-07-26 | 邵勃 | Intelligent robot chat context realization method and system based on corpus labeling |
CN110321416A (en) * | 2019-05-23 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium based on AIML |
TWI683272B (en) * | 2017-03-02 | 2020-01-21 | 大陸商騰訊科技(深圳)有限公司 | Information acquisition method, providing method, device, system, and storage medium |
CN110750632A (en) * | 2019-10-21 | 2020-02-04 | 闽江学院 | Improved Chinese ALICE intelligent question-answering method and system |
CN110941962A (en) * | 2019-11-26 | 2020-03-31 | 中国科学院自动化研究所 | Answer sentence selection method and device based on graph network |
WO2021028776A1 (en) * | 2019-08-09 | 2021-02-18 | International Business Machines Corporation | Query relaxation using external domain knowledge for query answering |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8719005B1 (en) * | 2006-02-10 | 2014-05-06 | Rusty Shawn Lee | Method and apparatus for using directed reasoning to respond to natural language queries |
CN105095195A (en) * | 2015-07-03 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Method and system for human-machine questioning and answering based on knowledge graph |
-
2016
- 2016-01-05 CN CN201610001347.7A patent/CN105677822A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8719005B1 (en) * | 2006-02-10 | 2014-05-06 | Rusty Shawn Lee | Method and apparatus for using directed reasoning to respond to natural language queries |
CN105095195A (en) * | 2015-07-03 | 2015-11-25 | 北京京东尚科信息技术有限公司 | Method and system for human-machine questioning and answering based on knowledge graph |
Non-Patent Citations (1)
Title |
---|
余昕聪等: ""本体上下位关系在招生问答机器人中的应用研究"", 《现代图书情报技术》 * |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018000205A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Question answering method and system based on multiple intents and multiple skill packets, and robot |
CN106471502A (en) * | 2016-06-29 | 2017-03-01 | 深圳狗尾草智能科技有限公司 | Intension recognizing method based on water conservancy diversion and system |
WO2018000279A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Diversion-based intention recognition method and system |
CN106446162A (en) * | 2016-09-26 | 2017-02-22 | 浙江大学 | Orient field self body intelligence library article search method |
CN106485328A (en) * | 2016-10-31 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Information processing system and method |
CN106484916A (en) * | 2016-11-04 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | A kind of enrollment answering method and device |
CN106528759A (en) * | 2016-11-04 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Information processing method and device for intelligent question-answering system |
CN106528759B (en) * | 2016-11-04 | 2019-04-02 | 上海智臻智能网络科技股份有限公司 | The information processing method and device of intelligent Answer System |
CN106844335A (en) * | 2016-12-21 | 2017-06-13 | 海航生态科技集团有限公司 | Natural language processing method and device |
CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技(上海)有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
TWI683272B (en) * | 2017-03-02 | 2020-01-21 | 大陸商騰訊科技(深圳)有限公司 | Information acquisition method, providing method, device, system, and storage medium |
CN109313638A (en) * | 2017-03-09 | 2019-02-05 | 微软技术许可有限责任公司 | Using recommendation |
CN109313638B (en) * | 2017-03-09 | 2023-09-01 | 微软技术许可有限责任公司 | Application recommendation |
WO2019000170A1 (en) * | 2017-06-26 | 2019-01-03 | Microsoft Technology Licensing, Llc | Generating responses in automated chatting |
US11586810B2 (en) | 2017-06-26 | 2023-02-21 | Microsoft Technology Licensing, Llc | Generating responses in automated chatting |
CN107895193A (en) * | 2017-11-13 | 2018-04-10 | 北京神州泰岳软件股份有限公司 | A kind of construction of knowledge base method, parameter setting method and device based on dialogue |
CN107895193B (en) * | 2017-11-13 | 2020-03-13 | 中科鼎富(北京)科技发展有限公司 | Knowledge base construction method, and parameter setting method and device based on conversation |
CN107861951A (en) * | 2017-11-17 | 2018-03-30 | 康成投资(中国)有限公司 | Session subject identifying method in intelligent customer service |
CN108958247A (en) * | 2018-07-02 | 2018-12-07 | 深圳市益鑫智能科技有限公司 | A kind of guided robot |
CN109241258A (en) * | 2018-08-23 | 2019-01-18 | 江苏索迩软件技术有限公司 | A kind of deep learning intelligent Answer System using tax field |
CN109241258B (en) * | 2018-08-23 | 2022-09-06 | 江苏索迩软件技术有限公司 | Deep learning intelligent question-answering system applied to tax field |
CN109815324A (en) * | 2019-01-10 | 2019-05-28 | 平安科技(深圳)有限公司 | Querying method, device, computer equipment and the storage medium of campus information |
CN110059169A (en) * | 2019-01-25 | 2019-07-26 | 邵勃 | Intelligent robot chat context realization method and system based on corpus labeling |
CN110059169B (en) * | 2019-01-25 | 2023-12-01 | 邵勃 | Intelligent robot chat context implementation method and system based on corpus labeling |
WO2020233386A1 (en) * | 2019-05-23 | 2020-11-26 | 深圳壹账通智能科技有限公司 | Intelligent question-answering method and device employing aiml, computer apparatus, and storage medium |
CN110321416A (en) * | 2019-05-23 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium based on AIML |
WO2021028776A1 (en) * | 2019-08-09 | 2021-02-18 | International Business Machines Corporation | Query relaxation using external domain knowledge for query answering |
GB2601936A (en) * | 2019-08-09 | 2022-06-15 | Ibm | Query relaxation using external domain knowledge for query answering |
US11841867B2 (en) | 2019-08-09 | 2023-12-12 | International Business Machines Corporation | Query relaxation using external domain knowledge for query answering |
CN110750632A (en) * | 2019-10-21 | 2020-02-04 | 闽江学院 | Improved Chinese ALICE intelligent question-answering method and system |
CN110750632B (en) * | 2019-10-21 | 2022-09-09 | 闽江学院 | Improved Chinese ALICE intelligent question-answering method and system |
CN110941962A (en) * | 2019-11-26 | 2020-03-31 | 中国科学院自动化研究所 | Answer sentence selection method and device based on graph network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105677822A (en) | Enrollment automatic question-answering method and system based on conversation robot | |
CN110147436B (en) | Education knowledge map and text-based hybrid automatic question-answering method | |
Al Emran et al. | A survey of intelligent language tutoring systems | |
US11409964B2 (en) | Method, apparatus, device and storage medium for evaluating quality of answer | |
WO2019118257A1 (en) | Assertion-based question answering | |
Gomaa et al. | Arabic short answer scoring with effective feedback for students | |
Jia et al. | Insta-Reviewer: A Data-Driven Approach for Generating Instant Feedback on Students' Project Reports. | |
Ohlsson et al. | Measuring an artificial intelligence system’s performance on a verbal IQ test for young children | |
Alhassan et al. | A novel framework for Arabic dialect chatbot using machine learning | |
Wijeratne et al. | Natural language processing for government: Problems and potential | |
CN116541493A (en) | Interactive response method, device, equipment and storage medium based on intention recognition | |
Wahde et al. | DAISY: an implementation of five core principles for transparent and accountable conversational AI | |
Sukkarieh et al. | Auto-marking 2: An update on the UCLES-Oxford University research into using computational linguistics to score short, free text responses | |
Flor et al. | Text mining and automated scoring | |
Yogish et al. | Survey on trends and methods of an intelligent answering system | |
Alshammari et al. | TAQS: an Arabic question similarity system using transfer learning of BERT with BILSTM | |
Aloqayli et al. | Intelligent Chatbot for Admission in Higher Education | |
Gardner et al. | Engineering registers in the 21st century: SFL perspectives on online publications | |
Wang et al. | Research and implementation of English grammar check and error correction based on Deep Learning | |
Alsheddi et al. | English and arabic chatbots: A systematic literature review | |
Riza et al. | Natural language processing and levenshtein distance for generating error identification typed questions on TOEFL | |
Almotairi et al. | Developing a Semantic Question Answering System for E-Learning Environments Using Linguistic Resources. | |
Shelke et al. | Database Creation for Marathi QA System | |
Lee | Natural Language Processing: A Textbook with Python Implementation | |
Khandait et al. | Automatic question generation through word vector synchronization using lamma |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160615 |
|
WD01 | Invention patent application deemed withdrawn after publication |