CN101118554A - Intelligent interactive request-answering system and processing method thereof - Google Patents

Intelligent interactive request-answering system and processing method thereof Download PDF

Info

Publication number
CN101118554A
CN101118554A CNA2007100771269A CN200710077126A CN101118554A CN 101118554 A CN101118554 A CN 101118554A CN A2007100771269 A CNA2007100771269 A CN A2007100771269A CN 200710077126 A CN200710077126 A CN 200710077126A CN 101118554 A CN101118554 A CN 101118554A
Authority
CN
China
Prior art keywords
information
answer
user
module
expert
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
Application number
CNA2007100771269A
Other languages
Chinese (zh)
Inventor
刘丽丽
游波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZTE Corp filed Critical ZTE Corp
Priority to CNA2007100771269A priority Critical patent/CN101118554A/en
Priority to PCT/CN2007/003558 priority patent/WO2009033339A1/en
Publication of CN101118554A publication Critical patent/CN101118554A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2452Query translation
    • G06F16/24522Translation of natural language queries to structured queries

Abstract

The present invention discloses an intelligent interactive question-answering system, which includes a knowledge module used to provide information for the user to query; an interactive module used for information interaction between the system and the user; and a processing module used for searching the answering information in knowledge module according to the question of the user; the knowledge module includes a question classification base used to store the question information and a knowledge base used to store the answering information; the processing module includes a semantic analysis module used to analyze the natural language for the problem of the user to generate query conditions; an information searching module used to search in the knowledge base according to the query condition; and a result generation module used to generate answers according to the searching results. The present invention discloses a question-answering processing method of an intelligent interactive question-answering system simultaneously. The present invention provides a rapid and simple system and method for obtaining the demanded information, so as to improve the processing ability for problems and the processing accuracy.

Description

Intelligent interactive request-answering system and disposal route thereof
[technical field]
The present invention relates to the searching engine field of internet, particularly relate to a kind of intelligent interactive request-answering system.
[background technology]
Along with Internet development, online information is explosive increase.In order from these mass datas, to obtain the related data that we need, can utilize search engine system.Mode by input keyword in the search box in search engine system just can be searched relevant information.But because the diversity of the information source in the search engine, sometimes the user may obtain up to ten thousand the results that do not meet actual requirement, needs oneself to carry out secondary filtration.This just requires the user when searching for, and the selection of keyword needs certain skill.Keyword is too short, and possible return results is too many, and really the result who needs is submerged in the hundreds of thousands bar garbage on the contrary.If keyword is oversize, may can not get the information that needs again.People often wish and can obtain the accurate result oneself wanted by quick, simple mode.
Having occurred a kind of question answering system now makes the user that a kind of new searching method arranged.Utilize this method, the user can obtain needed information by RELEASE PROBLEM, referring to a kind of knowledge question-and-answer quick processing system based on artificial intelligence that adopts among the patent documentation CN200510023955.In this system, the user asks a question, and classify after the server reception problem, and whether the search system built-in system has similar other problems.If do not have, then on the website, issue this problem with the form of webpage, if having answer is distributed to the user.But this system has relatively high expectations to user's enquirement level, and for the problem lack of standardization or inaccurate that the user proposes, system can't in time handle, and can only issue, thereby make the user can't in time obtain information.Even and if customer problem is accurate, also might can't handle, so that the user can't in time obtain answer because of no similar problem in the knowledge base of this system.
[summary of the invention]
Technical matters to be solved by this invention is to overcome the above-mentioned defective of prior art, provide a kind of can enlarge the issue handling scope and improve the issue handling accuracy, intelligent interactive request-answering system timely and effectively.
For achieving the above object, the present invention adopts following technical scheme:
A kind of intelligent interactive request-answering system comprises:
The knowledge module is used to provide the information for user inquiring;
Interactive module is used for the information interaction between system and the user;
Processing module is used for searching for answer information according to customer problem in described knowledge module; It is characterized in that:
Described knowledge module comprises the knowledge base that is used to preserve the problem class library of problem information and is used to preserve answer information; The knowledge module can also comprise problem maintenance module and knowledge acquisition module, is used for maintenance issues class library and knowledge base information.
Described processing module comprises:
Semantic meaning analysis module is used for that customer problem is carried out natural language and resolves the generated query condition;
Information searching module is used for searching in described knowledge base according to described querying condition;
Result-generation module is used for generating answer according to Search Results.
Preferably, described semantic meaning analysis module comprises:
Taxon is used for extracting the classified information of customer problem, searches described customer problem corresponding problem category in described problem class library according to described classified information, and extracts the key condition information of described problem category after the location;
The condition judgment unit is used to judge whether described customer problem has comprised described key condition information;
The query string generation unit is used in the judged result of described condition judgment unit generating described querying condition according to described key condition information when being.
Described semantic meaning analysis module also comprises non-conformance report unit, is used in the judged result of described condition judgment unit sending the information that lacks key condition information to the user by described interactive module for not the time.
Described result-generation module comprises:
Setup unit is used to set minimum matching precision and extracts precision or extraction quantity;
Sequencing unit, to the Search Results that satisfies described minimum matching precision according to the precision rank order;
The abstract extraction unit carries out abstract extraction to the Search Results that satisfies described extraction precision or to the forward Search Results of precision ordering of described extraction quantity;
Answer forms the unit, forms answer according to the summary that extracts.
Further, also comprise expert's processing module, be used for when when described problem class library does not search the problem category of described customer problem correspondence, perhaps, when in described knowledge base, not searching the answer information of user's needs, described customer problem is offered the expert, and expert's answer is sent to the user by described interactive module.
Described expert's processing module comprises renewal of knowledge unit, the answer that the content that is used for handling according to the expert is added new problem category and added the expert to knowledge base to described problem class library.
For achieving the above object, the present invention provides a kind of intelligent interactive question and answer disposal route simultaneously, it is characterized in that comprising the steps:
1) receives customer problem;
2) customer problem is carried out natural language and resolve the generated query condition;
3) search for according to above-mentioned querying condition;
4) on the basis of Search Results, generate answer.
Preferably, above-mentioned steps 2) comprise following substep again:
21) classified information in the extraction customer problem is determined the pairing problem category of customer problem according to classified information, and extract its key condition information after the orientation problem classification;
22) judge whether customer problem has comprised above-mentioned key condition information;
23) when judged result when being, generate described querying condition according to above-mentioned key condition information.
Above-mentioned steps 23) further comprising the steps of: when judged result for not the time, send to the user and to lack the information of key condition information, and change above-mentioned steps 22 over to).
Also be included in above-mentioned steps 4) before to the minimum matching precision of Search Results and the setting step of extraction precision or extraction quantity; Above-mentioned steps 4) comprise following substep again:
To the Search Results that satisfies minimum matching precision according to the precision rank order;
Extract the Search Results of precision or carry out abstract extraction satisfied setting the forward Search Results of precision ordering that extracts quantity; And
Form answer according to the summary that extracts.
Further, in step 2) in, when can't the pairing problem category of consumer positioning problem, customer problem be offered the answer that the expert handles and the expert is handled send to the user.In step 3), when not searching the answer information that the user needs, customer problem is offered the answer that the expert handles and the expert is handled send to the user.
Further, also comprise the step of adding new problem category and adding expert's answer to knowledge base to the problem class library.
The present invention's beneficial effect compared with prior art is:
The present invention is by being provided with semantic meaning analysis module earlier to the processing that performs an analysis of the customer problem from interactive module, semantic meaning analysis module is carried out natural language understanding with natural language understanding technology to the customer problem content, and can judge whether to carry out the answer extraction according to the information of problem class library.Extract if can carry out answer, then the generated query condition is searched in knowledge base according to querying condition by information searching module; And generate answer according to this Search Results by result-generation module.If need further positioning problems, then form user prompt information, give the user by non-conformance report unit with information feedback.
Under the preferred mode, increase expert's processing module, when semantic meaning analysis module judge this problem be system can't handle problem the time, perhaps, when in knowledge base, not searching the answer information of user's needs, then hand over expert's processing module to handle, and expert's answer is returned to interactive module.
Intelligent interactive request-answering system of the present invention can improve the ability of system handles customer problem effectively, problem lack of standardization or inaccurate for user's proposition, system can in time handle, and the scope that has enlarged accessible problem has to a great extent also improved the accuracy of issue handling simultaneously.
[description of drawings]
Accompanying drawing described herein is used to provide further understanding of the present invention, constitutes the application's a part, and illustrative examples of the present invention and explanation thereof are used to explain the present invention, do not constitute improper qualification of the present invention.In the accompanying drawings:
Fig. 1 is the system architecture diagram of the embodiment of the invention one;
Fig. 2 is the system handles process flow diagram of the embodiment of the invention one;
Fig. 3 is the system architecture diagram of the embodiment of the invention two;
Fig. 4 A and Fig. 4 B are the system handles process flow diagram of the embodiment of the invention two.
[embodiment]
Feature of the present invention and advantage will be elaborated in conjunction with the accompanying drawings by embodiment.
Embodiment one:
Please refer to Fig. 1, the intelligent interactive request-answering system of present embodiment comprises knowledge module, interactive module and processing module.
Interactive module provides the interface between user and the system, receives the problem that the user submits to, and the answer that system is obtained returns to the user, the transmission of realization question and answer information.
The knowledge module comprises problem class library and knowledge base again, and the problem class library has been preserved the classified information of relevant issues, and knowledge base has been preserved the information of relevant all kinds of problem answers.The classified information of problem comprises variety of issue type information and the key condition information corresponding with the variety of issue type.The problem that the user submitted to is come the partition problem type according to the issue type information in the problem class library, and key condition information is the conditional information that user institute must provide when answering the type problem, and it is used to judge user's the whether satisfied requirement that can search for of problem.
The knowledge module can further include problem maintenance module and knowledge acquisition module.The system manager can safeguard the problem class library by the problem maintenance module, by the knowledge acquisition module knowledge base be upgraded.The knowledge acquisition module is responsible for each information source is collected integration, and in integration process to the extraction of classifying of these information, and add information to knowledge base, make information updating.The problem maintenance module to the management of problem base, safeguard operational administratives such as the increase that comprises the problem classified information, deletion, modification.
Processing module is searched for answer information according to user's problem in the knowledge module, it comprises semantic meaning analysis module, information searching module and result-generation module again.
Semantic meaning analysis module is carried out natural language understanding with the generated query condition to the content of customer problem.Semantic meaning analysis module comprises taxon, condition judgment unit, non-conformance report unit and query string generation unit again.Wherein, taxon is used for extracting the classified information of customer problem, searches customer problem pairing problem category in the problem class library according to this classified information, and extracts the key condition information of this problem category after the location.The condition judgment unit is used to judge whether user's problem has comprised key condition information.Non-conformance report unit is used in the judged result of condition judgment unit sending the information that lacks key condition information to the user by interactive module for not the time.The query string generation unit is used in the judged result of condition judgment unit generating described querying condition according to this key condition information when being.
Information searching module is searched in knowledge base according to the querying condition that semantic meaning analysis module produces, and returns the result of search.
Result-generation module is further handled the result of search, generates user oriented answer, and sends to the user by interactive module.Result-generation module comprises that again setup unit, sequencing unit, abstract extraction unit and answer form the unit.Wherein, setup unit is used to set minimum matching precision and extracts precision or extract quantity; Sequencing unit to the Search Results that satisfies described minimum matching precision according to the precision rank order; The Search Results that extracts precision is set to satisfying in the abstract extraction unit, perhaps carries out abstract extraction to setting the forward Search Results of precision ordering that extracts quantity; Answer forms the unit and forms final answer according to the summary that extracts.
Please refer to Fig. 2, the system handles flow process of present embodiment is carried out according to following steps:
Step S1 receives the problem that the user submits to;
Step S2 extracts user related information, search, orientation problem type;
Step S3 for the customer problem of having located type, has judged whether to provide the key condition information of this problem types, if do not satisfy, then points out the user to replenish;
Step S4 if user's problem satisfies key condition information, then extracts pairing key condition information and forms querying condition;
Step S5 inquires about in knowledge base according to querying condition;
Step S6 handles the result, generates final result;
Step S7 sends to the user with answer.
In above-mentioned steps 1 and the step 7, the user can be undertaken by the interactive module of external network and system alternately.External network comprises multiple network such as IP network, WAP network, by agreement access interaction formula question answering systems such as HTTP, TCP/IP.The interactive module of system is finished the input that receives the user, the information that transmitting system generates is given the user, extracts the also relevant information of recording user.In the step 1, interactive module with the user carry out mutual in, relevant information, user's relevant information that need to extract the user is relevant with interactive mode, may be user's information such as phone number, IP address or user name.
Among the above-mentioned steps S2, system at first needs the problem of user's input is classified, and extracts the type that the classified information in the customer problem will be handled problems with the location by semantic meaning analysis module.The problem classifying rules of taking can be defined by the keeper.The location of type in the problem class library under the customer problem can be taked but be not limited to the mode of pattern match.For the mode of pattern match, can customize better user's enquirement pattern in advance.The problem of each type all is provided with the key condition of the type problem, after the type of problem has been located by system, next obtains the key condition information of the type problem from the problem class library, and can do further to judge and handle to customer problem in view of the above.For example, the keeper has defined the problem of following several types, comprising stock, weather, medical treatment etc.As for weather classification problem, mode with pattern match, regulation adopts enquirement patterns such as " how many degree of xx ", " may I ask how many degree of xx ", " weather xx ", when user's problem adopts a certain proposition in above several modes, user's positioning problems is arrived " weather " class by the search in the problem class library.Perhaps can take the mode of according to keyword classifying, pre-define the sort key speech of problem types,, extract " weather " in the customer problem this moment earlier, in the problem class library, carry out classification and matching according to this keyword again as keyword as " weather " etc.
Among the above-mentioned steps S3, after having located corresponding problem types, semantic meaning analysis module is extracted the key condition information of this problem types, and the key word that the user is imported carries out record, and judges further whether customer problem provides whole key condition information.For example, be " area " to the set key condition information of the problem of " weather " type, if the user provides this information, then with " area " and " weather " as querying condition, next step can form the target query string and be sent to the information search module.If the user only imports weather, do not import location information, system can judge that the user lacks necessary condition, then points out the user to replenish this key condition information so that can form querying condition.Information is putd question to according to user's history by system, has judged whether to provide enough key conditions when the user imports next time.For example, the information of pointing out the user to import this area first, if the user has imported " Chongqing " for the second time, then according to the information " weather " of twice input of user and the information in " Chongqing ", next step forms the target query string.
Among the above-mentioned steps S4, semantic meaning analysis module produces querying condition according to the key message condition, forms the query string that meets the information searching module grammer in the above-mentioned steps 5, searches for for information searching module.
Among the above-mentioned steps S5, carry out search mission by the information search module in knowledge base, the information search module can be taked various search engine techniques, to search for according to the querying condition of Different Logic array mode.
Among the above-mentioned steps S6,, handle according to keyword, key condition and matching precision by the Search Results of result-generation module reception information search module.Result-generation module preestablishes minimum matching precision, and can set the result and extract quantity.Result-generation module is discarded in the Search Results under the setting accuracy, and according to matching precision principle from high to low Search Results is carried out two minor sorts, and the Query Result that sorts setting bar number higher is handled successively.These Search Results that meet the demands are carried out information extraction, autoabstract generation, make it to form the information of the search problem that meets the user, form the needed answer of user.
Certainly, the running of above-mentioned each module, each unit, information transmission each other all can be worked in coordination with under the control action of systematic unity and be finished, and realize overall control and scheduling.
Embodiment two:
As shown in Figure 3, compare with the intelligent interactive request-answering system of embodiment one, the key distinction of present embodiment is to have set up expert's processing module.Comprise renewal of knowledge unit in expert's processing module, the answer that the content that this renewal of knowledge unit is handled according to the expert is added new problem category and added the expert to knowledge base to the problem class library.The purpose of setting up expert's processing module is the customer problem that can't handle automatically in the receiving system, and it is directly mutual to utilize artificial mode that expert and user are carried out, and finishes question and answer.And renewal of knowledge unit carries out classified finishing with this this type of problem and problem answers automatically, adds in problem class library and the knowledge base content of the module of further enriching one's knowledge thus, the ability that enhanced system is handled problems automatically respectively.
The knowledge module comprises problem class library, knowledge base, knowledge acquisition module and problem maintenance module in the present embodiment.The knowledge acquisition module is responsible for each information source is integrated, and in integration process to extractions of classifying of these information, generate the knowledge base information of continual renovation.The problem maintenance module is responsible for management, the maintenance of problem base, and it provides the operational administratives such as increase, deletion, modification of problem base, and forms the problem search index.The problem base management of information comprises the classified information of this problem and the management of information such as key condition of the type problem.
Please refer to Fig. 4 A and Fig. 4 B, the system handles flow process of present embodiment is as follows:
Step S1 receives the problem that the user submits to;
Step S2 extracts user related information, search, orientation problem type;
Step S2 ', successfully whether the decision problem type location; When fail in the problem types location, change step S8 over to;
Step S3 for the customer problem of having located type, has judged whether to provide the key condition information of this problem types, if do not satisfy, then points out the user to replenish;
Step S4 if user's problem satisfies key condition information, then extracts pairing key condition information and forms querying condition;
Step S5 inquires about in knowledge base according to querying condition;
Step S5 ' judges whether to inquire effective result; Fail to obtain effective step S8 that changes over to as a result the time;
Step S6 handles the result, generates final result;
Step S7 ' sends to the user with answer;
In above-mentioned steps S2 ', if in the problem class library, do not search the pairing problem types of customer problem, then directly mark and return, next customer problem is given to the expert and handles by expert's processing module;
In above-mentioned steps S5 ', if judging, system in knowledge base, do not search the answer information that the user needs, also customer problem is given to the expert and handles by expert's processing module;
In step S8, to failure of problem types location and the situation that can not inquire effective result, the mode that adopts the expert to handle.Shown in Fig. 4 B, step S8 comprises following substep again:
Step S8-1, it is mutual that expert's processing module prompting on-line expert and user carry out question and answer;
Step S8-2, expert carry out the question and answer answer, generate answer;
Step S8-3, expert's processing module is carried out taxonomic revision with this problem, add in the problem base, and with this finish message in knowledge base;
Step S8-4, expert's processing module is delivered to interactive module with answer.
During expert's processing demands that the system that receives in expert's processing module sends, can by but the modes such as mail, note that are not limited to are carried out the issue handling prompting to on-line expert.
Among the above-mentioned steps S7 ', answer is sent to the user through interactive module by result-generation module or expert's processing module, and will be through question and answer content augmentation that the expert handles in the knowledge module.
In addition, also comprise generating and the step of maintenance issues class library information, in this step, receive, integrate automatically the data message of various separate sources, and form information searching module and inquire about required knowledge base by the knowledge acquisition module; And the step of generation and maintenance knowledge library information, in this step, provide the maintenance of problem base by the problem maintenance module, the system maintenance personnel can utilize this problem maintenance module that problem base is safeguarded, comprise the operation such as increase, deletion, renewal of problem base.
Present embodiment is in conjunction with natural language understanding technology, Computer Automatic Search technology and manual search technology, for the user a kind of method and system that fast, simply obtains information needed is provided.The employing of natural language understanding technology makes the user not need more to search for skill, can be described problem by natural language.The employing of search engine technique can realize the integration to multiple information source, and in integration process to the extraction of classifying of the information source of various piece, form the knowledge base resource of system.Utilize search engine technique also can retrieve the location to information quickly and easily.On the other hand, system also provides a cover manual coordination mechanism, utilize the pattern of human expert system to solve the problem that can't solve automatically in the system in the past, and the problem that automatically this class has been solved adds in the knowledge base and problem class library of system, realize the autolearn feature of system.
Can see that the present invention has very significant advantage:
1, provide a kind of new information search mode, what system can be by with the user is repeatedly mutual, understand the user be essential really ask after, for the user provides information service more accurately;
2, promote user experience, make the user feel carrying out aspectant communication and consulting with this domain expert;
3, have the automatic question answering function, can save human resources, improve the automatism of information processing;
4, possess autolearn feature, continue to optimize the functional module of intelligent search.
Above content be in conjunction with concrete preferred implementation to further describing that the present invention did, can not assert that concrete enforcement of the present invention is confined to these explanations.For the general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, can also make some simple deduction or replace, all should be considered as belonging to protection scope of the present invention.

Claims (13)

1. intelligent interactive request-answering system comprises:
The knowledge module is used to provide the information for user inquiring;
Interactive module is used for the information interaction between system and the user;
Processing module is used for searching for answer information according to customer problem in described knowledge module; It is characterized in that:
Described knowledge module comprises the knowledge base that is used to preserve the problem class library of problem information and is used to preserve answer information;
Described processing module comprises:
Semantic meaning analysis module is used for that customer problem is carried out natural language and resolves the generated query condition;
Information searching module is used for searching in described knowledge base according to described querying condition;
Result-generation module is used for generating answer according to Search Results.
2. a kind of intelligent interactive request-answering system as claimed in claim 1 is characterized in that, described semantic meaning analysis module comprises:
Taxon is used for extracting the classified information of customer problem, searches described customer problem corresponding problem category in described problem class library according to described classified information, and extracts the key condition information of described problem category after the location;
The condition judgment unit is used to judge whether described customer problem has comprised described key condition information;
The query string generation unit is used in the judged result of described condition judgment unit generating described querying condition according to described key condition information when being.
3. a kind of intelligent interactive request-answering system as claimed in claim 2, it is characterized in that, described semantic meaning analysis module also comprises non-conformance report unit, be used in the judged result of described condition judgment unit sending the information that lacks key condition information to the user by described interactive module for not the time.
4. a kind of intelligent interactive request-answering system as claimed in claim 1 is characterized in that, described result-generation module comprises:
Setup unit is used to set minimum matching precision and extracts precision or extraction quantity;
Sequencing unit, to the Search Results that satisfies described minimum matching precision according to the precision rank order;
The abstract extraction unit carries out abstract extraction to the Search Results that satisfies described extraction precision or to the forward Search Results of precision ordering of described extraction quantity;
Answer forms the unit, forms answer according to the summary that extracts.
5. as any described intelligent interactive request-answering system among the claim 1-4, it is characterized in that, also comprise expert's processing module, be used for when when described problem class library does not search the problem category of described customer problem correspondence, perhaps, when in described knowledge base, not searching the answer information that the user needs, described customer problem is offered the expert, and expert's answer is sent to the user by described interactive module.
6. intelligent interactive request-answering system as claimed in claim 5, it is characterized in that, described expert's processing module comprises renewal of knowledge unit, the answer that the content that is used for handling according to the expert is added new problem category and added the expert to knowledge base to described problem class library.
7. an intelligent interactive question and answer disposal route is characterized in that comprising the steps:
1) receives customer problem;
2) customer problem is carried out natural language and resolve the generated query condition;
3) search for according to above-mentioned querying condition;
4) on the basis of Search Results, generate answer.
8. intelligent interactive question and answer disposal route as claimed in claim 7 is characterized in that above-mentioned steps 2) comprise following substep again:
21) classified information in the extraction customer problem is determined the pairing problem category of customer problem according to classified information, and extract its key condition information after the orientation problem classification;
22) judge whether customer problem has comprised above-mentioned key condition information;
23) when judged result when being, generate described querying condition according to above-mentioned key condition information.
9. intelligent interactive question and answer disposal route as claimed in claim 8 is characterized in that above-mentioned steps 23) further comprising the steps of: when judged result for not the time, send to the user and to lack the information of key condition information, and change above-mentioned steps 22 over to).
10. intelligent interactive question and answer disposal route as claimed in claim 9 is characterized in that, also is included in above-mentioned steps 4) before to the minimum matching precision of Search Results and the setting step of extraction precision or extraction quantity; Above-mentioned steps 4) comprise following substep again:
To the Search Results that satisfies minimum matching precision according to the precision rank order;
Extract the Search Results of precision or carry out abstract extraction satisfied setting the forward Search Results of precision ordering that extracts quantity; And
Form answer according to the summary that extracts.
11. as any described intelligent interactive question and answer disposal route of claim 8-10, it is characterized in that, in above-mentioned steps 2) in, when can't the pairing problem category of consumer positioning problem, customer problem be offered the answer that the expert handles and the expert is handled send to the user.
12., it is characterized in that: in above-mentioned steps 3 as the described intelligent interactive question and answer of claim 7-10 disposal route) in, when not searching the answer information that the user needs, customer problem is offered the answer that the expert handles and the expert is handled send to the user.
13. intelligent interactive question and answer disposal route as claimed in claim 11 is characterized in that, also comprises the step of adding new problem category and adding expert's answer to knowledge base to the problem class library.
CNA2007100771269A 2007-09-14 2007-09-14 Intelligent interactive request-answering system and processing method thereof Pending CN101118554A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CNA2007100771269A CN101118554A (en) 2007-09-14 2007-09-14 Intelligent interactive request-answering system and processing method thereof
PCT/CN2007/003558 WO2009033339A1 (en) 2007-09-14 2007-12-12 Intelligently interactive question answer system and processing method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNA2007100771269A CN101118554A (en) 2007-09-14 2007-09-14 Intelligent interactive request-answering system and processing method thereof

Publications (1)

Publication Number Publication Date
CN101118554A true CN101118554A (en) 2008-02-06

Family

ID=39054670

Family Applications (1)

Application Number Title Priority Date Filing Date
CNA2007100771269A Pending CN101118554A (en) 2007-09-14 2007-09-14 Intelligent interactive request-answering system and processing method thereof

Country Status (2)

Country Link
CN (1) CN101118554A (en)
WO (1) WO2009033339A1 (en)

Cited By (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009033339A1 (en) * 2007-09-14 2009-03-19 Zte Corporation Intelligently interactive question answer system and processing method
CN101986293A (en) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 Method and equipment for displaying search answer information on search interface
CN102004794A (en) * 2010-12-09 2011-04-06 百度在线网络技术(北京)有限公司 Search engine system and implementation method thereof
CN102073736A (en) * 2011-01-20 2011-05-25 百度在线网络技术(北京)有限公司 Method and system for searching difficult word
CN102456060A (en) * 2010-10-28 2012-05-16 株式会社日立制作所 Information processing device and information processing method
CN102662570A (en) * 2012-03-26 2012-09-12 腾讯科技(深圳)有限公司 Method and device for processing information
CN102681992A (en) * 2011-03-07 2012-09-19 腾讯科技(深圳)有限公司 Method and system for data hierarchy
CN101799736B (en) * 2009-04-30 2013-03-20 广东国笔科技股份有限公司 Function real-time associative interactive system and method
CN103198155A (en) * 2013-04-27 2013-07-10 俞志晨 Mobile terminal based smart question answering interaction system and method
CN103279528A (en) * 2013-05-31 2013-09-04 俞志晨 Question-answering system and question-answering method based on man-machine integration
CN103309846A (en) * 2013-06-26 2013-09-18 北京云知声信息技术有限公司 Method and device for processing natural language information
CN103377224A (en) * 2012-04-24 2013-10-30 北京百度网讯科技有限公司 Method and device for recognizing problem types and method and device for establishing recognition models
CN103488858A (en) * 2012-06-15 2014-01-01 国家人口计生委科学技术研究所 Contraception method selection expert evaluation system and method
CN103488859A (en) * 2012-06-15 2014-01-01 国家人口计生委科学技术研究所 Intelligent expert consulting system
CN103544219A (en) * 2013-09-24 2014-01-29 北京光年无限科技有限公司 Question-answering system with intelligent recommendation
CN103593054A (en) * 2013-11-25 2014-02-19 北京光年无限科技有限公司 Question-answering system combining emotion recognition and output
CN103810218A (en) * 2012-11-14 2014-05-21 北京百度网讯科技有限公司 Problem cluster-based automatic asking and answering method and device
CN103870440A (en) * 2012-12-12 2014-06-18 中国移动通信集团广西有限公司 Text data processing method and device
CN103995870A (en) * 2014-05-21 2014-08-20 百度在线网络技术(北京)有限公司 Interactive searching method and device
CN104063521A (en) * 2014-07-17 2014-09-24 百度在线网络技术(北京)有限公司 Method and device for achieving searching service
CN104090907A (en) * 2014-05-28 2014-10-08 北京百度网讯科技有限公司 Method and device for providing information for user in specific application field
CN104123351A (en) * 2014-07-09 2014-10-29 百度在线网络技术(北京)有限公司 Interactive search method and device
CN104636908A (en) * 2015-01-30 2015-05-20 北京完美和声信息技术有限公司 Information interaction platform and information interaction method
CN104679815A (en) * 2014-12-08 2015-06-03 北京云知声信息技术有限公司 Method and system for screening question and answer pairs and updating question and answer database in real time
CN104735132A (en) * 2015-02-13 2015-06-24 腾讯科技(深圳)有限公司 Information inquiry method, servers and terminal
CN104834651A (en) * 2014-02-12 2015-08-12 北京京东尚科信息技术有限公司 Method and apparatus for providing answers to frequently asked questions
CN105005564A (en) * 2014-04-17 2015-10-28 北京搜狗科技发展有限公司 Data processing method and apparatus based on question-and-answer platform
CN105096138A (en) * 2015-06-30 2015-11-25 百度在线网络技术(北京)有限公司 Method and device for realizing O2O dialogue interaction
CN105144205A (en) * 2013-04-29 2015-12-09 西门子公司 Device and method for answering a natural language question using a number of selected knowledge bases
CN105161097A (en) * 2015-07-23 2015-12-16 百度在线网络技术(北京)有限公司 Voice interaction method and apparatus
CN105183850A (en) * 2015-09-07 2015-12-23 百度在线网络技术(北京)有限公司 Information querying method and device based on artificial intelligence
CN105450781A (en) * 2016-01-12 2016-03-30 李劲杰 Interactive question and answer method, platform, client and server
CN105468648A (en) * 2014-09-11 2016-04-06 北大方正集团有限公司 Method and apparatus for establishing specialized knowledge question/answer system
WO2016050066A1 (en) * 2014-09-29 2016-04-07 华为技术有限公司 Method and device for parsing interrogative sentence in knowledge base
CN105653671A (en) * 2015-12-29 2016-06-08 畅捷通信息技术股份有限公司 Similar information recommendation method and system
CN105786798A (en) * 2016-02-25 2016-07-20 上海交通大学 Natural language intention understanding method in man-machine interaction
CN105929964A (en) * 2016-05-10 2016-09-07 海信集团有限公司 Method and device for human-computer interaction
CN103870440B (en) * 2012-12-12 2016-11-30 中国移动通信集团广西有限公司 A kind of text data processing method and device
CN106326353A (en) * 2016-08-09 2017-01-11 百度在线网络技术(北京)有限公司 Method and equipment for providing representation information
CN106339602A (en) * 2016-08-26 2017-01-18 丁腊春 Intelligent consulting robot
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
CN106503123A (en) * 2016-10-20 2017-03-15 宁波江东大金佰汇信息技术有限公司 A kind of deep learning intelligent response system based on computer cloud data
WO2017054758A1 (en) * 2015-09-30 2017-04-06 北京奇虎科技有限公司 Information search method and device
CN106649706A (en) * 2016-12-20 2017-05-10 北京云知声信息技术有限公司 Natural language knowledge learning method and apparatus
CN106682194A (en) * 2016-12-29 2017-05-17 北京百度网讯科技有限公司 Answer positioning method and device based on deep questions and answers
CN106774852A (en) * 2016-11-25 2017-05-31 宇龙计算机通信科技(深圳)有限公司 A kind of message treatment method and device based on virtual reality
WO2017097061A1 (en) * 2015-12-07 2017-06-15 中兴通讯股份有限公司 Smart response method and apparatus
CN107220389A (en) * 2017-07-12 2017-09-29 广州市昊链信息科技股份有限公司 A kind of Logistics Knowledge intelligent Answer System and method
CN107315787A (en) * 2017-06-13 2017-11-03 北京品智能量科技有限公司 Data processing method and device for vehicle trouble question answering system
CN107329995A (en) * 2017-06-08 2017-11-07 北京神州泰岳软件股份有限公司 A kind of controlled answer generation method of semanteme, apparatus and system
CN107729410A (en) * 2017-09-26 2018-02-23 广西电网有限责任公司电力科学研究院 A kind of database engine suitable for power equipment big data
CN107832342A (en) * 2017-10-13 2018-03-23 北京康夫子科技有限公司 Robot chat method and system
CN107908717A (en) * 2017-11-13 2018-04-13 北京百度网讯科技有限公司 method and device for interactive information
CN107958001A (en) * 2016-10-14 2018-04-24 阿里巴巴集团控股有限公司 The implementation method and device of a kind of intelligent answer
CN107977236A (en) * 2017-12-21 2018-05-01 上海智臻智能网络科技股份有限公司 Generation method, terminal device, storage medium and the question answering system of question answering system
CN108073628A (en) * 2016-11-16 2018-05-25 中兴通讯股份有限公司 A kind of interactive system and method based on intelligent answer
CN108984778A (en) * 2018-07-25 2018-12-11 南京瓦尔基里网络科技有限公司 A kind of intelligent interaction automatically request-answering system and self-teaching method
CN109271500A (en) * 2018-09-18 2019-01-25 广州神马移动信息科技有限公司 A kind of intelligent prompt method, device and the terminal device of question and answer input
CN109308357A (en) * 2015-05-04 2019-02-05 上海智臻智能网络科技股份有限公司 It is a kind of for obtaining the method, apparatus and equipment of answer information
CN109492081A (en) * 2018-10-30 2019-03-19 上海智臻智能网络科技股份有限公司 Text information search and information interacting method, device, equipment and storage medium
CN109858976A (en) * 2019-02-22 2019-06-07 北京智乐瑟维科技有限公司 Business method for early warning, device, storage medium and the equipment of product
CN110019736A (en) * 2017-12-29 2019-07-16 北京京东尚科信息技术有限公司 Question and answer matching process, system, equipment and storage medium based on language model
CN111149107A (en) * 2017-09-28 2020-05-12 甲骨文国际公司 Enabling autonomous agents to distinguish between problems and requests
CN111862971A (en) * 2020-06-15 2020-10-30 南京林业大学 Forestry science popularization voice interaction method and control terminal system thereof
CN112925915A (en) * 2019-12-06 2021-06-08 株式会社日立制作所 Data generation method and device in database
CN113140299A (en) * 2020-12-31 2021-07-20 上海明品医学数据科技有限公司 Medical expert training auxiliary system and auxiliary method
US20210287563A1 (en) * 2018-05-25 2021-09-16 Nec Corporation Scoring device, scoring method, and recording medium
CN113449117A (en) * 2021-06-24 2021-09-28 武汉工程大学 Bi-LSTM and Chinese knowledge graph-based composite question-answering method
US11238111B2 (en) 2016-10-24 2022-02-01 International Business Machines Corporation Response generation
CN117076651A (en) * 2023-10-16 2023-11-17 彩讯科技股份有限公司 Method, device, equipment and computer readable storage medium for processing interaction information

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110019724A (en) * 2017-12-21 2019-07-16 上海智臻智能网络科技股份有限公司 Modify the device of question answering system
CN110795540A (en) * 2018-07-17 2020-02-14 上海智臻智能网络科技股份有限公司 Attachment preview method and device of question-answering system, storage medium and terminal
CN110517019A (en) * 2019-08-26 2019-11-29 西安文理学院 Semantic-based registration information Security Officer authentication capability assessment method and system
CN111200737A (en) * 2019-12-29 2020-05-26 航天信息股份有限公司企业服务分公司 Intelligent robot-assisted question answering system and method for live video platform
CN111198969A (en) * 2019-12-31 2020-05-26 应东明 Economic information consultation system and method based on network big data
CN111275536A (en) * 2020-01-13 2020-06-12 山东浪潮商用系统有限公司 Tax intelligent consultation method and system integrating manual intervention
CN112527965A (en) * 2020-12-18 2021-03-19 国家电网有限公司客户服务中心 Automatic question answering implementation method and device based on combination of professional library and chatting library
CN114152444B (en) * 2021-10-20 2023-09-15 中国航发四川燃气涡轮研究院 Portable auxiliary system for mounting and troubleshooting engine bench and use method thereof
CN115658852B (en) * 2022-12-28 2023-10-24 北京百车宝科技有限公司 Automobile intelligent question-answering system based on knowledge base

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050108200A1 (en) * 2001-07-04 2005-05-19 Frank Meik Category based, extensible and interactive system for document retrieval
CN100416570C (en) * 2006-09-22 2008-09-03 浙江大学 FAQ based Chinese natural language ask and answer method
CN101118554A (en) * 2007-09-14 2008-02-06 中兴通讯股份有限公司 Intelligent interactive request-answering system and processing method thereof

Cited By (97)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009033339A1 (en) * 2007-09-14 2009-03-19 Zte Corporation Intelligently interactive question answer system and processing method
CN101799736B (en) * 2009-04-30 2013-03-20 广东国笔科技股份有限公司 Function real-time associative interactive system and method
CN101986293A (en) * 2010-09-03 2011-03-16 百度在线网络技术(北京)有限公司 Method and equipment for displaying search answer information on search interface
CN101986293B (en) * 2010-09-03 2016-08-24 百度在线网络技术(北京)有限公司 For presenting the method and apparatus of search answer information in search interface
CN102456060A (en) * 2010-10-28 2012-05-16 株式会社日立制作所 Information processing device and information processing method
CN102004794A (en) * 2010-12-09 2011-04-06 百度在线网络技术(北京)有限公司 Search engine system and implementation method thereof
CN102004794B (en) * 2010-12-09 2013-05-08 百度在线网络技术(北京)有限公司 Search engine system and implementation method thereof
CN102073736A (en) * 2011-01-20 2011-05-25 百度在线网络技术(北京)有限公司 Method and system for searching difficult word
CN102681992A (en) * 2011-03-07 2012-09-19 腾讯科技(深圳)有限公司 Method and system for data hierarchy
CN102662570A (en) * 2012-03-26 2012-09-12 腾讯科技(深圳)有限公司 Method and device for processing information
CN102662570B (en) * 2012-03-26 2015-11-18 腾讯科技(深圳)有限公司 Information processing method and device
CN103377224B (en) * 2012-04-24 2016-08-17 北京百度网讯科技有限公司 Identify the method and device of problem types, set up the method and device identifying model
CN103377224A (en) * 2012-04-24 2013-10-30 北京百度网讯科技有限公司 Method and device for recognizing problem types and method and device for establishing recognition models
CN103488858A (en) * 2012-06-15 2014-01-01 国家人口计生委科学技术研究所 Contraception method selection expert evaluation system and method
CN103488858B (en) * 2012-06-15 2017-03-22 国家卫生计生委科学技术研究所 Contraception method selection expert evaluation method
CN103488859A (en) * 2012-06-15 2014-01-01 国家人口计生委科学技术研究所 Intelligent expert consulting system
CN103810218B (en) * 2012-11-14 2018-06-08 北京百度网讯科技有限公司 A kind of automatic question-answering method and device based on problem cluster
CN103810218A (en) * 2012-11-14 2014-05-21 北京百度网讯科技有限公司 Problem cluster-based automatic asking and answering method and device
CN103870440A (en) * 2012-12-12 2014-06-18 中国移动通信集团广西有限公司 Text data processing method and device
CN103870440B (en) * 2012-12-12 2016-11-30 中国移动通信集团广西有限公司 A kind of text data processing method and device
CN103198155A (en) * 2013-04-27 2013-07-10 俞志晨 Mobile terminal based smart question answering interaction system and method
CN103198155B (en) * 2013-04-27 2017-09-22 北京光年无限科技有限公司 A kind of intelligent answer interactive system and method based on mobile terminal
CN105144205B (en) * 2013-04-29 2018-05-08 西门子公司 The apparatus and method of natural language problem are answered using multiple selected knowledge bases
CN105144205A (en) * 2013-04-29 2015-12-09 西门子公司 Device and method for answering a natural language question using a number of selected knowledge bases
CN103279528A (en) * 2013-05-31 2013-09-04 俞志晨 Question-answering system and question-answering method based on man-machine integration
CN103309846A (en) * 2013-06-26 2013-09-18 北京云知声信息技术有限公司 Method and device for processing natural language information
CN103309846B (en) * 2013-06-26 2016-05-25 北京云知声信息技术有限公司 A kind of processing method of natural language information and device
CN103544219A (en) * 2013-09-24 2014-01-29 北京光年无限科技有限公司 Question-answering system with intelligent recommendation
CN103593054A (en) * 2013-11-25 2014-02-19 北京光年无限科技有限公司 Question-answering system combining emotion recognition and output
CN104834651A (en) * 2014-02-12 2015-08-12 北京京东尚科信息技术有限公司 Method and apparatus for providing answers to frequently asked questions
CN105005564B (en) * 2014-04-17 2019-09-03 北京搜狗科技发展有限公司 A kind of data processing method and device based on answer platform
CN105005564A (en) * 2014-04-17 2015-10-28 北京搜狗科技发展有限公司 Data processing method and apparatus based on question-and-answer platform
CN103995870A (en) * 2014-05-21 2014-08-20 百度在线网络技术(北京)有限公司 Interactive searching method and device
CN104090907B (en) * 2014-05-28 2017-06-09 北京百度网讯科技有限公司 A kind of method and apparatus for providing a user with information
CN104090907A (en) * 2014-05-28 2014-10-08 北京百度网讯科技有限公司 Method and device for providing information for user in specific application field
CN104123351A (en) * 2014-07-09 2014-10-29 百度在线网络技术(北京)有限公司 Interactive search method and device
CN104123351B (en) * 2014-07-09 2017-08-25 百度在线网络技术(北京)有限公司 Interactive method and device
US10055453B2 (en) 2014-07-09 2018-08-21 Baidu Online Network Technology (Beijing) Co., Ltd. Interactive searching method and apparatus
CN104063521A (en) * 2014-07-17 2014-09-24 百度在线网络技术(北京)有限公司 Method and device for achieving searching service
CN105468648A (en) * 2014-09-11 2016-04-06 北大方正集团有限公司 Method and apparatus for establishing specialized knowledge question/answer system
WO2016050066A1 (en) * 2014-09-29 2016-04-07 华为技术有限公司 Method and device for parsing interrogative sentence in knowledge base
US10706084B2 (en) 2014-09-29 2020-07-07 Huawei Technologies Co., Ltd. Method and device for parsing question in knowledge base
CN104679815A (en) * 2014-12-08 2015-06-03 北京云知声信息技术有限公司 Method and system for screening question and answer pairs and updating question and answer database in real time
CN104679815B (en) * 2014-12-08 2018-02-23 北京云知声信息技术有限公司 It is a kind of to screen question and answer pair and the method and system in real-time update question and answer storehouse
CN104636908A (en) * 2015-01-30 2015-05-20 北京完美和声信息技术有限公司 Information interaction platform and information interaction method
CN104735132A (en) * 2015-02-13 2015-06-24 腾讯科技(深圳)有限公司 Information inquiry method, servers and terminal
CN104735132B (en) * 2015-02-13 2017-05-24 腾讯科技(深圳)有限公司 Information inquiry method, servers and terminal
CN109308357A (en) * 2015-05-04 2019-02-05 上海智臻智能网络科技股份有限公司 It is a kind of for obtaining the method, apparatus and equipment of answer information
CN109308357B (en) * 2015-05-04 2023-07-18 上海智臻智能网络科技股份有限公司 Method, device and equipment for obtaining answer information
CN105096138A (en) * 2015-06-30 2015-11-25 百度在线网络技术(北京)有限公司 Method and device for realizing O2O dialogue interaction
CN105161097A (en) * 2015-07-23 2015-12-16 百度在线网络技术(北京)有限公司 Voice interaction method and apparatus
CN105183850A (en) * 2015-09-07 2015-12-23 百度在线网络技术(北京)有限公司 Information querying method and device based on artificial intelligence
WO2017054758A1 (en) * 2015-09-30 2017-04-06 北京奇虎科技有限公司 Information search method and device
WO2017097061A1 (en) * 2015-12-07 2017-06-15 中兴通讯股份有限公司 Smart response method and apparatus
CN105653671A (en) * 2015-12-29 2016-06-08 畅捷通信息技术股份有限公司 Similar information recommendation method and system
CN105450781A (en) * 2016-01-12 2016-03-30 李劲杰 Interactive question and answer method, platform, client and server
CN105786798A (en) * 2016-02-25 2016-07-20 上海交通大学 Natural language intention understanding method in man-machine interaction
CN105786798B (en) * 2016-02-25 2018-11-02 上海交通大学 Natural language is intended to understanding method in a kind of human-computer interaction
CN105929964A (en) * 2016-05-10 2016-09-07 海信集团有限公司 Method and device for human-computer interaction
CN106326353A (en) * 2016-08-09 2017-01-11 百度在线网络技术(北京)有限公司 Method and equipment for providing representation information
CN106339602B (en) * 2016-08-26 2019-02-26 丁腊春 A kind of intelligent consulting robot
CN106339602A (en) * 2016-08-26 2017-01-18 丁腊春 Intelligent consulting robot
CN107958001A (en) * 2016-10-14 2018-04-24 阿里巴巴集团控股有限公司 The implementation method and device of a kind of intelligent answer
CN106503123A (en) * 2016-10-20 2017-03-15 宁波江东大金佰汇信息技术有限公司 A kind of deep learning intelligent response system based on computer cloud data
US11238111B2 (en) 2016-10-24 2022-02-01 International Business Machines Corporation Response generation
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
CN108073628A (en) * 2016-11-16 2018-05-25 中兴通讯股份有限公司 A kind of interactive system and method based on intelligent answer
CN106774852B (en) * 2016-11-25 2020-01-10 宇龙计算机通信科技(深圳)有限公司 Message processing method and device based on virtual reality
CN106774852A (en) * 2016-11-25 2017-05-31 宇龙计算机通信科技(深圳)有限公司 A kind of message treatment method and device based on virtual reality
CN106649706A (en) * 2016-12-20 2017-05-10 北京云知声信息技术有限公司 Natural language knowledge learning method and apparatus
CN106682194A (en) * 2016-12-29 2017-05-17 北京百度网讯科技有限公司 Answer positioning method and device based on deep questions and answers
CN106682194B (en) * 2016-12-29 2020-05-22 北京百度网讯科技有限公司 Answer positioning method and device based on deep question answering
CN107329995B (en) * 2017-06-08 2018-03-23 北京神州泰岳软件股份有限公司 A kind of controlled answer generation method of semanteme, apparatus and system
CN107329995A (en) * 2017-06-08 2017-11-07 北京神州泰岳软件股份有限公司 A kind of controlled answer generation method of semanteme, apparatus and system
CN107315787A (en) * 2017-06-13 2017-11-03 北京品智能量科技有限公司 Data processing method and device for vehicle trouble question answering system
CN107220389A (en) * 2017-07-12 2017-09-29 广州市昊链信息科技股份有限公司 A kind of Logistics Knowledge intelligent Answer System and method
CN107729410A (en) * 2017-09-26 2018-02-23 广西电网有限责任公司电力科学研究院 A kind of database engine suitable for power equipment big data
CN111149107B (en) * 2017-09-28 2023-08-22 甲骨文国际公司 Enabling autonomous agents to differentiate between questions and requests
CN111149107A (en) * 2017-09-28 2020-05-12 甲骨文国际公司 Enabling autonomous agents to distinguish between problems and requests
CN107832342B (en) * 2017-10-13 2021-08-24 北京左医科技有限公司 Robot chatting method and system
CN107832342A (en) * 2017-10-13 2018-03-23 北京康夫子科技有限公司 Robot chat method and system
CN107908717A (en) * 2017-11-13 2018-04-13 北京百度网讯科技有限公司 method and device for interactive information
CN107977236B (en) * 2017-12-21 2020-11-13 上海智臻智能网络科技股份有限公司 Question-answering system generation method, terminal device, storage medium and question-answering system
CN107977236A (en) * 2017-12-21 2018-05-01 上海智臻智能网络科技股份有限公司 Generation method, terminal device, storage medium and the question answering system of question answering system
CN110019736B (en) * 2017-12-29 2021-10-01 北京京东尚科信息技术有限公司 Question-answer matching method, system, equipment and storage medium based on language model
CN110019736A (en) * 2017-12-29 2019-07-16 北京京东尚科信息技术有限公司 Question and answer matching process, system, equipment and storage medium based on language model
US20210287563A1 (en) * 2018-05-25 2021-09-16 Nec Corporation Scoring device, scoring method, and recording medium
CN108984778A (en) * 2018-07-25 2018-12-11 南京瓦尔基里网络科技有限公司 A kind of intelligent interaction automatically request-answering system and self-teaching method
CN109271500A (en) * 2018-09-18 2019-01-25 广州神马移动信息科技有限公司 A kind of intelligent prompt method, device and the terminal device of question and answer input
CN109492081A (en) * 2018-10-30 2019-03-19 上海智臻智能网络科技股份有限公司 Text information search and information interacting method, device, equipment and storage medium
CN109858976A (en) * 2019-02-22 2019-06-07 北京智乐瑟维科技有限公司 Business method for early warning, device, storage medium and the equipment of product
CN112925915A (en) * 2019-12-06 2021-06-08 株式会社日立制作所 Data generation method and device in database
CN111862971A (en) * 2020-06-15 2020-10-30 南京林业大学 Forestry science popularization voice interaction method and control terminal system thereof
CN113140299A (en) * 2020-12-31 2021-07-20 上海明品医学数据科技有限公司 Medical expert training auxiliary system and auxiliary method
CN113449117A (en) * 2021-06-24 2021-09-28 武汉工程大学 Bi-LSTM and Chinese knowledge graph-based composite question-answering method
CN113449117B (en) * 2021-06-24 2023-09-26 武汉工程大学 Bi-LSTM and Chinese knowledge graph based compound question-answering method
CN117076651A (en) * 2023-10-16 2023-11-17 彩讯科技股份有限公司 Method, device, equipment and computer readable storage medium for processing interaction information

Also Published As

Publication number Publication date
WO2009033339A1 (en) 2009-03-19

Similar Documents

Publication Publication Date Title
CN101118554A (en) Intelligent interactive request-answering system and processing method thereof
Faliagka et al. Application of machine learning algorithms to an online recruitment system
US8386482B2 (en) Method for personalizing information retrieval in a communication network
US20080147630A1 (en) Recommender and payment methods for recruitment
CN105144205B (en) The apparatus and method of natural language problem are answered using multiple selected knowledge bases
US20090089126A1 (en) Method and system for an automated corporate governance rating system
CN102546771A (en) Cloud mining network public opinion monitoring system based on characteristic model
CN110807085B (en) Fault information query method and device, storage medium and electronic device
CN103049440A (en) Recommendation processing method and processing system for related articles
CN101140588A (en) Method and apparatus for ordering incidence relation search result
Delen et al. A holistic framework for knowledge discovery and management
CN112036842B (en) Intelligent matching device for scientific and technological service
CN101101605A (en) Method, device and system for searching web page and device for establishing index database
CN112989761B (en) Text classification method and device
CN109145168A (en) A kind of expert service robot cloud platform
CN108027814A (en) Disable word recognition method and device
Birzniece Artificial intelligence in knowledge management: Overview and trends.
KR20100063289A (en) System and method for managing work for integrating
CN115757689A (en) Information query system, method and equipment
KR101365481B1 (en) System for generating and managing a portal for program management
CN115982429B (en) Knowledge management method and system based on flow control
Stollberg et al. H-Techsight—A next generation knowledge management platform
Kuhrmann et al. A mapping study on method engineering: first results
Croce et al. On the experimental usage of ontology-based data management for the italian integrated system of statistical registers: quality issues
CN110209804B (en) Target corpus determining method and device, storage medium and electronic device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C12 Rejection of a patent application after its publication
RJ01 Rejection of invention patent application after publication