CN105302859A - Intelligent interaction system based on Internet - Google Patents
Intelligent interaction system based on Internet Download PDFInfo
- Publication number
- CN105302859A CN105302859A CN201510603622.8A CN201510603622A CN105302859A CN 105302859 A CN105302859 A CN 105302859A CN 201510603622 A CN201510603622 A CN 201510603622A CN 105302859 A CN105302859 A CN 105302859A
- Authority
- CN
- China
- Prior art keywords
- word
- user
- information
- phrase
- steps
- 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
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
- G06F16/36—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
- G06F16/33—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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
Abstract
An intelligent interaction system based on Internet is provided. The system processes user information according to the following steps of (A) separating words for information sent by a user, (B) identifying whether characters, words and phrases separated in the step (A) belong to entities, (C) conducting semantic annotation analysis on the characters, the words and the phrases separated in the step (A), (D) conducting text correction to the the characters, the words and the phrases separated in the step (A), (E) analyzing syntax on information sent by the user, (F) conducting weight correction to information sent by the user and the characters, the words and the phrases separated in the step (A), (G) conducting context process to information sent by the user, (H) conducting similarity calculation to the information sent by the user according to results of step B to G, and (I) checking a preset knowledge base according to a threshold value result and returning the results to the user.
Description
Technical field
The present invention relates to a kind of intelligent interactive method, relate to a kind of intelligent answer method based on internet in particular.
Background technology
In traditional intelligent interaction, the general employing template way of intelligent interaction deals with complicated dialogue, and accuracy is lower, or analyzes after carrying out various participle to information, but general word segmentation result kind is many, and accuracy is lower.
Summary of the invention
The invention discloses a kind of intelligent interactive system based on internet, comprise the following steps:
A, participle is carried out to the information that user sends;
Whether B, word, word and phrase to after participle described in steps A belong to entity identifies;
C, word, word and phrase to after participle described in steps A carry out semantic tagger analysis;
D, word, word and phrase to after participle described in steps A carry out text error correction;
E, syntactic analysis is carried out to the information that user sends;
Word, word and phrase after participle described in F, the information sent user and steps A carry out weight correction;
G, context process is carried out to the information that user sends;
H, result according to described step B-G, carry out Similarity Measure to the information that user sends, obtain threshold value;
I, preset knowledge base according to threshold value result queries, return results to user.
Semantic tagger analysis in described step C comprises field, importance degree, similar word, synonym, cyberspeak.
Text error correction in described step D is included in the service class word in field and phrase carries out phonetic error correction;
Syntactic analysis in described step F adopts rule and mask method.
Accompanying drawing explanation
The example of Fig. 1-body and instantiation, succession
Fig. 2-part of speech management
Fig. 3-synonym, weight corrects
Embodiment
The invention discloses a kind of intelligent interactive system based on internet, comprise the following steps:
A, participle is carried out to the information that user sends;
Participle is the common technology means of Computational Linguistics or artificial intelligence field, general employing " maximum coupling divides morphology " or " most probable number method participle ",
Whether B, word, word and phrase to after participle described in steps A belong to entity identifies;
For entity, be the instantiation of body,
So-called body, being clear and definite to the one of concept and detailed description, is a kind of describing method to real world.In other words, in fact body is exactly the Formal Representation to certain cover concept and relation each other thereof among specific area.Generally comprise:
---concrete instances of ontology (object Object)
---the attribute of body
---affiliated Ontological classifications.
After instances of ontology, just can inherit the attribute of body, be semantic tagger ready for analysis thereafter;
Specifically, as accompanying drawing 1, there is a lot of basic business for banking, all basic businesses are exactly a kind of body, for a certain concrete body, such as handle rule, marketing activity is exactly a kind of succession to basic business, and its all attribute just can be inherited.
C, word, word and phrase to after participle described in steps A carry out semantic tagger analysis;
For semantic tagger analysis, comprise part-of-speech tagging and word sense tagging two parts:
For part-of-speech tagging: the general magnetic mask method adopting Hidden Markov Model (HMM) or drive based on the mistake of conversion;
For word sense tagging: generally adopt the word sense disambiguation method based on mutual information or the row's discrimination method based on dictionary;
For this step, when user inputs a problem in robot front end, first this problem can carry out word segmentation processing, then mates according to the result of participle, and therefore the construction of part of speech is good and bad, is closely connected with the degree of intelligence of robot.All can realize in [part of speech management] with amendment the additions and deletions of part of speech.
As Fig. 2, having " public part of speech ", " proprietary part of speech " under [part of speech management] label, is wherein the part of speech that body generic attribute is corresponding under " public part of speech ", is the self-defining peculiar part of speech of project under " proprietary part of speech ".
D, word, word and phrase to after participle described in steps A carry out text error correction;
E, syntactic analysis is carried out to the information that user sends;
Word, word and phrase after participle described in F, the information sent user and steps A carry out weight correction;
As Fig. 3, select the classification right click needing to be linked into, select [newly-built subclassification] in a menu, in pop-up box, insert typonym preserved.
In native system, " * " " # " of item name side mark is used for distinguishing the importance degree of part of speech and similarity respectively, and " * " represents important, and weight is higher; " # " represents dissmilarity, and similarity is very low; " " word represented under this classification has phonetic error correction.Subclassification inherits " * " " # " " " setting of parent classification automatically.
Native system also can adjust weight according to user data daily record.Such as: " no " word Corpus--based Method is inessential, but through statistical study, " no " word occur and sentence tail ratio higher, its implication is completely different, so when " no " word appears at tail, such as " I can open CRBT not " adjustment " no " word weight.
G, context process is carried out to the information that user sends;
H, result according to described step B-G, carry out Similarity Measure to the information that user sends, obtain threshold value;
In addition, native system can also realize " hybrid operation of semantic formula and common question sentence ",
Such as: standard ask for: " cosmetics mark exaggerate effect, falsely represent how to investigate and prosecute? "
To should the standard semantic formula of asking can be analyzed to: [cosmetics | cosmetic brand] [falseness] [mark] [punishment] [method? ]
To should the standard a certain expansion of asking ask as " what method is the information that cosmetics mark mark is false take punish for this behavior industrial and commercial bureau "
Suppose to comprise above-mentioned knowledge in knowledge base, the information that system of users provides can carry out hybrid processing.Namely judge that the problem of user is asked can directly answer as being close to standard; As being decomposed into semantic formula, then answer according to semantic formula; Be close to expansion as can not semantic formula be resolved into ask, then ask answer according to expansion; And non-individual adopts above-mentioned any one party formula, to obtain max-thresholds.The i.e. answer of the most identical user's request.
I, preset knowledge base according to threshold value result queries, return results to user.
Semantic tagger analysis in described step C comprises field, importance degree, similar word, synonym, cyberspeak.
Specifically, after carrying out semantic tagger analysis according to above-mentioned aspect, the semanteme of the word divided is accurate, and ambiguity is eliminated substantially.
Text error correction in described step D is included in the service class word in field and phrase carries out phonetic error correction;
Syntactic analysis in described step e adopts rule and mask method.
Claims (4)
1., based on an intelligent interactive system for internet, described system adopts following steps to process user profile:
A, participle is carried out to the information that user sends;
Whether B, word, word and phrase to after participle described in steps A belong to entity identifies;
C, word, word and phrase to after participle described in steps A carry out semantic tagger analysis;
D, word, word and phrase to after participle described in steps A carry out text error correction;
E, syntactic analysis is carried out to the information that user sends;
Word, word and phrase after participle described in F, the information sent user and steps A carry out weight correction;
G, context process is carried out to the information that user sends;
H, result according to described step B-G, carry out Similarity Measure to the information that user sends, obtain threshold value;
I, preset knowledge base according to threshold value result queries, return results to user.
2. a kind of intelligent interactive system based on internet according to claim 1, is characterized in that:
Semantic tagger analysis in described step C comprises field, importance degree, similar word, synonym, cyberspeak.
3. a kind of intelligent interactive system based on internet according to claim 1, is characterized in that:
Text error correction in described step D is included in the service class word in field and phrase carries out phonetic error correction.
4. a kind of intelligent interactive system based on internet according to claim 1, is characterized in that:
Syntactic analysis in described step e adopts rule and mask method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510603622.8A CN105302859B (en) | 2015-09-21 | 2015-09-21 | A kind of intelligent interactive system Internet-based |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510603622.8A CN105302859B (en) | 2015-09-21 | 2015-09-21 | A kind of intelligent interactive system Internet-based |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105302859A true CN105302859A (en) | 2016-02-03 |
CN105302859B CN105302859B (en) | 2018-11-30 |
Family
ID=55200131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510603622.8A Active CN105302859B (en) | 2015-09-21 | 2015-09-21 | A kind of intelligent interactive system Internet-based |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105302859B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106599163A (en) * | 2016-12-08 | 2017-04-26 | 上海云信留客信息科技有限公司 | Data mining method and device for big data |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
CN110175230A (en) * | 2019-05-29 | 2019-08-27 | 广州伟宏智能科技有限公司 | Intelligent robot interactive system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101174259A (en) * | 2007-09-17 | 2008-05-07 | 张琰亮 | Intelligent interactive request-answering system |
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
CN101510221A (en) * | 2009-02-17 | 2009-08-19 | 北京大学 | Enquiry statement analytical method and system for information retrieval |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
US20150261744A1 (en) * | 2014-03-12 | 2015-09-17 | Asuman Suenbuel | Systems and methods for natural language processing |
-
2015
- 2015-09-21 CN CN201510603622.8A patent/CN105302859B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101174259A (en) * | 2007-09-17 | 2008-05-07 | 张琰亮 | Intelligent interactive request-answering system |
CN101373532A (en) * | 2008-07-10 | 2009-02-25 | 昆明理工大学 | FAQ Chinese request-answering system implementing method in tourism field |
CN101510221A (en) * | 2009-02-17 | 2009-08-19 | 北京大学 | Enquiry statement analytical method and system for information retrieval |
US20150261744A1 (en) * | 2014-03-12 | 2015-09-17 | Asuman Suenbuel | Systems and methods for natural language processing |
CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
CN108073587B (en) * | 2016-11-09 | 2022-05-27 | 阿里巴巴集团控股有限公司 | Automatic question answering method and device and electronic equipment |
CN106599163A (en) * | 2016-12-08 | 2017-04-26 | 上海云信留客信息科技有限公司 | Data mining method and device for big data |
CN106599163B (en) * | 2016-12-08 | 2019-11-22 | 上海云信留客信息科技有限公司 | A kind of data digging method and device for big data |
CN110175230A (en) * | 2019-05-29 | 2019-08-27 | 广州伟宏智能科技有限公司 | Intelligent robot interactive system |
Also Published As
Publication number | Publication date |
---|---|
CN105302859B (en) | 2018-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112069298B (en) | Man-machine interaction method, device and medium based on semantic web and intention recognition | |
WO2020119075A1 (en) | General text information extraction method and apparatus, computer device and storage medium | |
CN105117388B (en) | A kind of intelligent robot interactive system | |
CN110717018A (en) | Industrial equipment fault maintenance question-answering system based on knowledge graph | |
Hawkins et al. | Criterial features in learner corpora: Theory and illustrations | |
CN110222045B (en) | Data report acquisition method and device, computer equipment and storage medium | |
CN111931506B (en) | Entity relationship extraction method based on graph information enhancement | |
CN103020230A (en) | Semantic fuzzy matching method | |
CN112052324A (en) | Intelligent question answering method and device and computer equipment | |
WO2020233386A1 (en) | Intelligent question-answering method and device employing aiml, computer apparatus, and storage medium | |
CN105302859A (en) | Intelligent interaction system based on Internet | |
CN112380848B (en) | Text generation method, device, equipment and storage medium | |
CN111143531A (en) | Question-answer pair construction method, system, device and computer readable storage medium | |
CN112445894A (en) | Business intelligent system based on artificial intelligence and analysis method thereof | |
CN108536673B (en) | News event extraction method and device | |
CN111368540A (en) | Keyword information extraction method based on semantic role analysis | |
CN114579709B (en) | Intelligent question-answering intention identification method based on knowledge graph | |
CN105183716B (en) | A kind of intelligent interactive method based on abstract semantics | |
CN109992651B (en) | Automatic identification and extraction method for problem target features | |
JP2013190985A (en) | Knowledge response system, method and computer program | |
CN105260178A (en) | Intelligent cloud service application development method and system | |
CN113792542A (en) | Intention understanding method fusing syntactic analysis and semantic role pruning | |
CN117272977A (en) | Character description sentence recognition method and device, electronic equipment and storage medium | |
CN117112767A (en) | Question and answer result generation method, commercial query big model training method and device | |
CN110188190B (en) | Dialogue analysis method, device, server and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |