CN103116577A - Method of intelligently processing user natural language order - Google Patents
Method of intelligently processing user natural language order Download PDFInfo
- Publication number
- CN103116577A CN103116577A CN2013100414411A CN201310041441A CN103116577A CN 103116577 A CN103116577 A CN 103116577A CN 2013100414411 A CN2013100414411 A CN 2013100414411A CN 201310041441 A CN201310041441 A CN 201310041441A CN 103116577 A CN103116577 A CN 103116577A
- Authority
- CN
- China
- Prior art keywords
- keyword
- answer
- natural language
- disposal route
- matching
- 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 17
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims 1
- 230000013011 mating Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method of quickly positioning an answer or a processing inlet corresponding to a user natural language order. The method of intelligently processing the user natural language order is characterized in that an answer set and a processing inlet set in the fixing field are limited. A natural language problem in the limited set is scanned with a key word, thus a characteristic key word set is obtained. The best answer or the best processing inlet can be obtained by the maximum matching of the answer set and the processing inlet set. Synonyms are permitted to be connected with one-level or multi-level in a matching way in the matching process.
Description
Technical field
The present invention is mainly used in specific area, and by setting up suitable computer model, the simulation human brain is processed the process of problem, the problem that the most of user of quick solution proposes with natural language.Because, most of user in the inquiry problem, for computer system or artificial customer service system, all be confined to certain field, i.e. so-called expert system.
Background technology
Along with the expanding day of users ' individualized requirement, the demand of two aspects is arranged in progressively enlarging.
The answer demand that the first generalizes, namely everyone inquires a problem under same situation, the optimum answer that obtains is unique; By searching frequently asked questions, can reply the user.
It two is, the treatment scheme of generalization, and the input and output of these flow processs are fixed up basically, and credit card user for example needs the current integration of inquiry oneself, and at this time, computer system can obtain correct result by fixedly calling of inside.
Above two kinds of situations occupy more than 80% of user's services consume, and these can achieve a solution by the present invention all.
Summary of the invention
When the user used the natural language query problem, the keyword sweep test by the scanning to problem, obtained the subset of keyword set;
Compatible portion, according to the above subset that obtains, check on one's answers collection and disposal route collection maximize coupling, obtain optimum matching conclusion or disposal route entrance; In matching process, near synonym can be used as bridge, play positive role in coupling.
If a plurality of maximum couplings are arranged, in conjunction with context (linguistic context), therefrom select the coupling an of the best;
If conclusion is best, conclusion is returned to the user; If what obtain is disposal route, calling processing method, and result is returned.
Description of drawings
User's natural language problem Q1 after the keyword scan program scanning, obtains the keyword subset in the field, and this set is { K1, K3, K4};
For above-mentioned subset, mate, obtain matching relationship: answer R1 matching result is { K1, K3, K4}; Answer R2 matching result is { K3, K4}; Method S1 matching result is { K1}.
It should be noted that and mate in the path, although keyword K3 is directly not related with answer R1, due to the existence of keyword K6, matching effect is identical, and like this, the near synonym problem has just solved.
So, maximizing the conclusion of mating is that answer R1 is optimum;
Because answer R1 is conclusion, directly returns to the user and get final product as answer.
Embodiment
One, data model is set up process
The foundation of frequently asked questions: for the problem in own field, set up the answer inventory, each concrete answer has clear correct keyword set corresponding; Certainly, keyword set that each is fixing has unique answer, even if fuzzy answer, neither a plurality of entries.
The foundation of disposal route collection: for computer system, the disposal route that can support is similar to the foundation of frequently asked questions, set up equally the corresponding relation of entrance sign and keyword set, unique requirement is by this sign, can conveniently call when recalling.
Annexation between keyword is set up: between near synonym, we also can set up many-to-many relationship, equivalent process in coupling.
In computer system, setting up above many-to-many relationship (another name) is easily to solve.We have obtained two set, and one is the set of FAQs or disposal route, and another one is the set of keyword.
Two, the keyword scanning process of natural language problem
When receiving user's natural language instructions, rapid scanning appears at the keyword set in this order, obtains the subset of keyword.
Three, the maximization matching process of keyword
According to the keyword subset, the set of FAQs or disposal route is mated, obtain the match condition of each entry; Carry out sorting by reversals to the coupling amount this moment, obtains one or more maximum couplings.In mating the path, we allow the existence of the relation of calling, and one or many can appear in the another name relation in the path.
In conjunction with context, filter out an optimum matching.
Four, reply user or executable operations
If optimum matching is a conclusion, directly reply to the user; Otherwise, call the processing procedure entrance, be for further processing, if result is arranged, result is returned to the user.
Claims (4)
1. in answer and the disposal route of association area inner question, carry out mark with suitable keyword set, the many-to-many relationship inventory of keyword set and answer set in the field, disposal route collection has so just been arranged.
2. between approximate keyword, connect, avoid repeatedly repeating label.
3. on the basis of right 1, the problem for natural language proposes in above-mentioned keyword set interscan, can obtain the subset of keyword.
4. the keyword subset that obtains according to right 3, check on one's answers the collection and the disposal route collection maximize coupling, in matching process, allow to carry out described one or more levels connection of right 2 between keyword, mostly be most principle with number of matches, obtain optimum matching, problem can optimization solve (return to correct answer or process with correct method).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100414411A CN103116577A (en) | 2013-02-04 | 2013-02-04 | Method of intelligently processing user natural language order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100414411A CN103116577A (en) | 2013-02-04 | 2013-02-04 | Method of intelligently processing user natural language order |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103116577A true CN103116577A (en) | 2013-05-22 |
Family
ID=48414954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013100414411A Pending CN103116577A (en) | 2013-02-04 | 2013-02-04 | Method of intelligently processing user natural language order |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103116577A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6038560A (en) * | 1997-05-21 | 2000-03-14 | Oracle Corporation | Concept knowledge base search and retrieval system |
| CN1928864A (en) * | 2006-09-22 | 2007-03-14 | 浙江大学 | FAQ based Chinese natural language ask and answer method |
| CN101030267A (en) * | 2006-02-28 | 2007-09-05 | 腾讯科技（深圳）有限公司 | Automatic question-answering method and system |
| CN101286161A (en) * | 2008-05-28 | 2008-10-15 | 华中科技大学 | Intelligent Chinese request-answering system based on concept |
| CN101593206A (en) * | 2009-06-25 | 2009-12-02 | 腾讯科技（深圳）有限公司 | Searching method and device based on answer in the question and answer interaction platform |
-
2013
- 2013-02-04 CN CN2013100414411A patent/CN103116577A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6038560A (en) * | 1997-05-21 | 2000-03-14 | Oracle Corporation | Concept knowledge base search and retrieval system |
| CN101030267A (en) * | 2006-02-28 | 2007-09-05 | 腾讯科技（深圳）有限公司 | Automatic question-answering method and system |
| CN1928864A (en) * | 2006-09-22 | 2007-03-14 | 浙江大学 | FAQ based Chinese natural language ask and answer method |
| CN101286161A (en) * | 2008-05-28 | 2008-10-15 | 华中科技大学 | Intelligent Chinese request-answering system based on concept |
| CN101593206A (en) * | 2009-06-25 | 2009-12-02 | 腾讯科技（深圳）有限公司 | Searching method and device based on answer in the question and answer interaction platform |
Non-Patent Citations (2)
| Title |
|---|
| 段建勇等: "《限定领域的自动问答系统研究》", 《北方工业大学学报》 * |
| 王波等: "《网上销售常问问答系统的构建》", 《软件导刊》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345690B (en) | Intelligent question and answer method and system | |
| CN108038234B (en) | Automatic question template generating method and device | |
| Euzenat et al. | Ontology alignment with OLA | |
| CN100472518C (en) | Category setting support method and apparatus | |
| CN100578539C (en) | Automatic question-answering method and system | |
| WO2002048824A3 (en) | System for completing forms on the internet | |
| CN103425741A (en) | Information exhibiting method and device | |
| DE60335472D1 (en) | SYSTEM AND METHOD FOR AUTOMATED IMAGING OF KEYWORDS AND KEYPHRASES ON DOCUMENTS | |
| CN110782318A (en) | Marketing method and device based on audio interaction and storage medium | |
| CN103389988A (en) | Method and device for guiding user to carry out information search | |
| CN105404619B (en) | A kind of Semantic Web Services cluster mask method based on similarity | |
| US10740401B2 (en) | System for the automated semantic analysis processing of query strings | |
| CN110110049A (en) | Service consultation method, apparatus, system, service robot and storage medium | |
| CN102117467A (en) | Question and answer mode online shopping guide method | |
| CN106547813A (en) | A kind of method of hoisting machine people voice response ability | |
| CN107515900A (en) | Intelligent robot and its event memorandum system and method | |
| CN105893427A (en) | Resource searching method and server | |
| CN104994105A (en) | Android intelligent terminal security authentication method | |
| KR20230079729A (en) | Method for converting natural language query to sql and device thereof | |
| CN103927339B (en) | Knowledge Reorganizing system and method for knowledge realignment | |
| CN111400453A (en) | Intelligent interaction system and method based on legal consultation | |
| CN110750559A (en) | Authority information processing method and device, storage medium and electronic device | |
| CN103116577A (en) | Method of intelligently processing user natural language order | |
| CN107547354A (en) | Business datum provides method and device | |
| CN107135269A (en) | A kind of method and system quickly numbered to cloud terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: QINGDAO SHUANGNIU INFORMATION TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: LIU DONGMIN Effective date: 20140522 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100036 HAIDIAN, BEIJING TO: 266000 QINGDAO, SHANDONG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20140522 Address after: 266000 Shandong Province, Qingdao high tech Zone Songyuan Road No. 17 Applicant after: Qingdao double cattle Information Technology Co., Ltd. Address before: 100036, Haidian District, Wanshou Road, No. four, 4-94, Beijing Applicant before: Liu Dongmin |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130522 |