CN103593412A - Tree-structure-based question answering system and method - Google Patents
Tree-structure-based question answering system and method Download PDFInfo
- Publication number
- CN103593412A CN103593412A CN201310506948.XA CN201310506948A CN103593412A CN 103593412 A CN103593412 A CN 103593412A CN 201310506948 A CN201310506948 A CN 201310506948A CN 103593412 A CN103593412 A CN 103593412A
- Authority
- CN
- China
- Prior art keywords
- node
- client
- response message
- tree structure
- query
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
- G06F16/986—Document structures and storage, e.g. HTML extensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
The invention discloses a tree-structure-based question answering system and method. A tree structure is built according to correlation of all question service attributes and different levels of all questions under services that the questions belong to; each node of the tree structure stores the questions and corresponding answers; each node of the tree structure is provided with a node identifier. The node questions and node identifiers in the tree structure are displayed to a client; after the node identifiers transmitted by the client over internet are received, the questions stored in the nodes corresponding to the node identifiers and the corresponding answers are supplied to the client. The tree-structure-based question answering system and method provides questions of the client with more accurate answers, so that user experience of the client is improved.
Description
Technical field
The present invention relates to e-commerce field, particularly a kind of answer method and system based on tree structure problem.
Background technology
Ecommerce is mainly to utilize internet to be engaged in commercial affairs or activity, in carrying out ecommerce process, e-commerce venture need to arrange online customer service at network side, the online answer that provides various commercial affairs to be correlated with query for client by internet, the relevant query of commercial affairs relates to association attributes consulting, e-commerce venture's correlated activation consulting and the after sale service consulting etc. to commercial product.Along with the continuous increase of client consulting amount, limited online customer service can not be satisfied the demand, and in order to meet the ever-increasing consulting amount of client, at network side, answering system is set, and automatically replies the relevant query of various business that client proposes.
When the answering system of network side setting automatically replies the relevant query of various business of client proposition, first, in consulting amount, can reply the relevant query of commercial affairs that up to ten thousand clients propose simultaneously; Secondly, in time, can whole day within 24 hours, reply the relevant query of commercial affairs that client proposes.
At present, the relevant query of commercial affairs that answering system adopts matching way acknowledged client end to propose conventionally, mainly adopts two kinds of implementation methods:
The first implementation method adopts the answering system based on way of search to reply
Answering system based on way of search receives after the query of client transmission, after mainly utilizing searched key technology to query coupling, finds corresponding response message to send to client.
Searched key technology is mainly utilized reverse indexing mode, and reverse indexing is again inverted index, and this data structure storage information and information are from the mapping relations of position in one or more documents, namely full-text search.When answering system receives after the query of client transmission, using query information as text, set up query index, adopt reverse indexing mode to match corresponding problem, then the response message of this set correspondence problem is sent to client.In this process, query information can be a plurality of phrases, by combination method of calling, is aided with the accuracy rate that Secondary Ordering Algorithm improves coupling when index.
Answering system based on way of search has the answering system based on full-text index engine lucene, can also carry out the models such as solr of secondary encapsulation on based on full-text index engine lucene.
Fig. 1 is that the answering system based on way of search of the prior art is realized the method flow diagram of replying, and its concrete steps are:
Because query information can be a plurality of, so be also to comprise a plurality of problems and corresponding response message in the problem of index coupling;
The second implementation method adopts the answering system based on artificial intelligence markup language to reply
Artificial intelligence markup language (AIML, Artificial Intelligence Markup Language) is a kind of XML voice that create natural language ageng.AIML is comprised of theme, classification and indexing unit liking, the data that form AIML object can be formatted data or nonformatted data, formatted data is comprised of character, comprising symbol data and form the coherent element of AIML, AIML can be encapsulated in response message in the template of definition, in template, may partly by label, form when replying and need to resolve acquisition response message.
Fig. 2 is the method flow diagram that the answering system based on artificial intelligence markup language of the prior art is replied, and its concrete steps are:
No matter adopting above-mentioned which kind of scheme to realize replying of answering system, be all that answering system is first analyzed and obtained after query information the query of client proposition, then coupling obtains corresponding response message.But, on the one hand, when query adopts Chinese statement, its semantic identification difficulty, the meaning that a same phrase is expressed under different pragmatics and linguistic context is diverse, identify the expressed meaning of Chinese, just need to form being in short divided into several words, because Chinese has very powerful ambiguousness, so existing analytical technology all can not be effectively by short cutting.On the other hand, above-mentioned two schemes is when realizing the replying of answering system, be adopt inverted index and one by one the mode of coupling carry out matching problem and corresponding response message, this matching way is not considered the correlativity between problem, but directly query information is mated with problem, so the problem of mating is not likely the problem of client needs, the response message that corresponding response message neither client needs, causes matching degree to reduce.
Therefore, when realizing the replying of answering system, how for client provides accurate response message, improving client application and experience, is a problem demanding prompt solution.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of answer method based on tree structure problem, and the method can provide accurate response message by client is asked a question.
The embodiment of the present invention also provides a kind of answering system based on tree structure problem, and this system can provide accurate response message by client is asked a question.
For achieving the above object, be of the invention processly specifically achieved in that
An answer method based on tree structure problem, the method comprises:
According to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
Node query and node identification in tree structure are showed to client;
Receive the node identification that client sends by internet;
Problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.
The method also comprises:
Provide the problem of the associated nodes storage of this node to select for client, problem and the corresponding response message of the associated nodes storage that client is selected offer client.
Before receiving the node identification that client sends by internet, the method also comprises:
Determine whether the query that client sends comprises node identification, if so, carry out the problem of node storage of institute's corresponding node sign and the step that the response message of correspondence offers client; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.
Before the method, also comprise:
Business datum is arranged, carry out business datum correlation analysis, and extract problem by modes such as correlation rule and contexts, problem service attribute is set.
An answering system based on tree structure problem, this system comprises: associate management module, data retrieval module and associated display module, wherein,
Associate management module, for according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
Data retrieval module, the node identification sending by internet for receiving client, inquires about problem and the corresponding response message of the node storage of corresponding node identification from associate management module;
Associated display module, for the query of tree structure node and node identification are showed to client, by problem and the corresponding response message of the node storage of the corresponding node identification of inquiry.
Data retrieval module, also, for providing the problem of the associated nodes storage of this node to select for client, obtains problem and the corresponding response message of the associated nodes storage of client selection from the inquiry of associate management module;
Associated display module, also shows client for inquiry being obtained to problem and the corresponding response message of the associated nodes storage of client selection.
Described data retrieval module, also for determining whether that the query that can send from client gets node identification; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, from associate management module, inquire about problem and the corresponding response message of the node storage of corresponding node identification.
Also comprise data preparation module, for business datum is arranged, carry out business datum correlation analysis, and extract problem by modes such as correlation rule and contexts, problem service attribute is set.
As can be seen from the above scheme, the present invention according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure.Node query and node identification in tree structure are showed to client, after receiving the node identification that client sends by internet, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.Also comprise: further provide the problem of the associated nodes storage of this node to select for client, problem and the corresponding response message of the associated nodes storage that client is selected offer client.Further, if cannot get node identification from the query of client, can carry out obtaining after query information after grammatical analysis to this query, determine the node identification of query information matches, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.Because system and method provided by the invention is by unique node identification problem identificatioin and relevant issues, guiding client completes the consulting of relevant all problems in the affiliated business of query, avoided of the prior art to the query analytic process of client and query information matches problem process, avoided because accuracy of analysis is not high and the not high or not problem of final response message degree of accuracy that affects of coupling degree of accuracy, thereby more accurate response message can be provided for the query of client, improve the user experience of client.
Accompanying drawing explanation
Fig. 1 is that the answering system based on way of search of the prior art is realized the method flow diagram of replying;
Fig. 2 is the method flow diagram that the answering system based on artificial intelligence markup language of the prior art is replied;
The answer method process flow diagram based on tree structure problem that Fig. 3 provides for the embodiment of the present invention;
The answering system structural representation based on tree structure problem that Fig. 4 provides for the embodiment of the present invention;
The structural representation of the tree structure problem that Fig. 5 provides for the embodiment of the present invention.
Embodiment
For making object of the present invention, technical scheme and advantage clearer, referring to the accompanying drawing embodiment that develops simultaneously, the present invention is described in further detail.
In order to provide accurate response message for client institute statement into question, need to avoid of the prior art to the query analytic process of client and query information matches problem process, avoid because accuracy of analysis is not high and the not high or not problem of final response message degree of accuracy that affects of coupling degree of accuracy.Therefore, the present invention according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure.Node query and node identification in tree structure are showed to client, after receiving the node identification that client sends by internet, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.Also comprise: further provide the problem of the associated nodes storage of this node to select for client, problem and the corresponding response message of the associated nodes storage that client is selected offer client.
Further, if cannot get node identification in the query receiving, can carry out obtaining, after query information, determining the node identification of query information matches after grammatical analysis to this query, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.
The present invention is by unique node identification problem identificatioin and relevant issues, guiding client completes the consulting of relevant all problems in the affiliated business of query, the semantic ambiguity problem that can cause while avoiding analyzing query, thereby can provide accurate response message for client institute statement into question, improve the user experience of client.
The answer method process flow diagram based on tree structure problem that Fig. 3 provides for the embodiment of the present invention, its concrete steps are:
Step 301, according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
In this step, according to the service attribute of problem, adopt correlation rule, sorting technique or the mode that manually marks to divide the typical problem under business and relevant issues, structure tree structure;
After step 304, the method also comprises:
Before step 303, the method can also comprise:
This step need to be carried out grammatical analysis to this query, and adopts invert indexed search, obtains corresponding query information, at this moment, just need in database, set in advance the text that comprises query, obtains corresponding query information in text;
Specifically, the whole process of step 301 is carried out by data preparation module and associate management module, wherein,
Data preparation module, for business datum is arranged, carries out business datum correlation analysis, and extracts problem by modes such as correlation rule and contexts, and problem service attribute is set;
Associate management module, be used for constructing tree structure, according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, problem and corresponding response message are imported in tree structure respective nodes, when importing, can verify problem and corresponding response message, whether problem identificatioin there is repetition; Here, can also be to adding or deletion of node in constructed tree structure, for new problem being filled into or deleted existing problem.
Specifically, described in Fig. 3 302 completed by data retrieval module to the process of step 3033, comprise: first judgement receives the query that client sends, determine whether to get node identification from this query, if so, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, problem and the corresponding response message of the node storage of corresponding node identification are offered to client.
In the present invention, also there is associated display module, for tree structure is shown, show: problem and the corresponding response message of the node storage of the node identification that tree structure problem and corresponding response message, corresponding client send, and problem and the corresponding response message of the node storage of the node identification of the query coupling that sends of the problem of the associated nodes of this node storage and corresponding response message and client, and the problem of the associated nodes of this node storage and corresponding response message.
Fig. 4 is the answering system structural representation based on tree structure problem that the embodiment of the present invention provides, and as shown in the figure, comprising: associate management module, data retrieval module and associated display module, wherein,
Associate management module, for according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
Data retrieval module, the node identification sending by internet for receiving client, inquires about problem and the corresponding response message of the node storage of corresponding node identification from associate management module;
Associated display module, for the query of tree structure node and node identification are showed to client, by problem and the corresponding response message of the node storage of the corresponding node identification of inquiry.
In this system, also comprise data preparation module, for business datum is arranged, carry out business datum correlation analysis, and extract problem by modes such as correlation rule and contexts, problem service attribute is set.
In this system, data retrieval module, also, for providing the problem of the associated nodes storage of this node to select for client, obtains problem and the corresponding response message of the associated nodes storage of client selection from the inquiry of associate management module;
Associated display module, also shows client for inquiry being obtained to problem and the corresponding response message of the associated nodes storage of client selection.
In this system, described data retrieval module, also for determining whether that the query that can send from client gets node identification; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, from associate management module, inquire about problem and the corresponding response message of the node storage of corresponding node identification.
Lifting an object lesson is elaborated to the embodiment of the present invention
The structural representation of the tree structure problem that Fig. 5 provides for the embodiment of the present invention: when the query sending by internet when client can be found corresponding node from tree structure, just inquire about this node self and the associated problem of all node storages and the response message of correspondence thereof, when showing client, can adopt tree structure to show this node self and the associated problem of all node storages and the response message of correspondence thereof.Client can be found node again according to showing, End-Customer end can obtain the root of tree structure, just can certain traffic issues of complete solution to each leaf node from the root of tree structure.By the mode based on tree structure query, the consulting of fine guiding client finishing service, is used the user of client to obtain good user experience like this.As shown in Figure 5, when query is determined to be the problem 1 of wanting inquiry business, by problem 1 with corresponding reply displaying, and prompting relevant issues 3,4 and 5 and corresponding replying whether show; When receiving query, be determined to be and want the problem 3 of inquiry business to be, showing problem 3 and corresponding replying, and point out replying of relevant query 8 and 9 whether to show; By that analogy until complete this business all problems and corresponding replying.By tree structure guidance mode, by client, carry out like this selection of node query, avoided client directly to input query, avoided Chinese ambiguity problem.
From such scheme provided by the invention, can find out, the present invention, by analyzing a large number of services search record, sums up the indicator problem of main type of service and this traffic aided and the relation between these typical problems, and problem is formed to tree structure.By tree structure problem guiding client, carry out business consultation, client is by click mode, just can determine selected node identification, by node identification, in tree structure, inquire about corresponding replying, avoided client that non-type query is provided and cause coupling time ambiguity problem.By tree-like guiding, obtain a preferably consulting experience, thereby be more ready to select automatic answering system to carry out business consultation, can reduce to greatest extent online customer service pressure like this.
By experiment, in one month, adopt the answering system the present invention is based on tree structure problem to carry out business consultation amount and can account for the more than 50% of total business consultation amount, raise the efficiency and user experience.
More than lift preferred embodiment; the object, technical solutions and advantages of the present invention are further described; institute is understood that; the foregoing is only preferred embodiment of the present invention; not in order to limit the present invention; within the spirit and principles in the present invention all, any modification of doing, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. the answer method based on tree structure problem, is characterized in that, the method comprises:
According to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
Node query and node identification in tree structure are showed to client;
Receive the node identification that client sends by internet;
Problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.
2. the method for claim 1, is characterized in that, the method also comprises:
Provide the problem of the associated nodes storage of this node to select for client, problem and the corresponding response message of the associated nodes storage that client is selected offer client.
3. method as claimed in claim 1 or 2, is characterized in that, before receiving the node identification that client sends by internet, the method also comprises:
Determine whether the query that client sends comprises node identification, if so, carry out the problem of node storage of institute's corresponding node sign and the step that the response message of correspondence offers client; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, problem and the corresponding response message of the node storage of institute's corresponding node sign are offered to client.
4. method as claimed in claim 3, is characterized in that, before the method, also comprises:
Business datum is arranged, carry out business datum correlation analysis, and extract problem by modes such as correlation rule and contexts, problem service attribute is set.
5. the answering system based on tree structure problem, is characterized in that, this system comprises: associate management module, data retrieval module and associated display module, wherein,
Associate management module, for according to the relevance between all problems service attribute and at all problems the different stage under affiliated business, structure tree structure, each node storage problem of tree structure and corresponding response message, and be each the Node configuration node identification in tree structure;
Data retrieval module, the node identification sending by internet for receiving client, inquires about problem and the corresponding response message of the node storage of corresponding node identification from associate management module;
Associated display module, for the query of tree structure node and node identification are showed to client, by problem and the corresponding response message of the node storage of the corresponding node identification of inquiry.
6. system as claimed in claim 5, it is characterized in that, data retrieval module, also, for providing the problem of the associated nodes storage of this node to select for client, obtains problem and the corresponding response message of the associated nodes storage of client selection from the inquiry of associate management module;
Associated display module, also shows client for inquiry being obtained to problem and the corresponding response message of the associated nodes storage of client selection.
7. the system as described in claim 5 or 6, is characterized in that, described data retrieval module, also for determining whether that the query that can send from client gets node identification; If not, this query is carried out to grammatical analysis and obtain query information, determine the node identification of query information matches, from associate management module, inquire about problem and the corresponding response message of the node storage of corresponding node identification.
8. system as claimed in claim 7, is characterized in that, also comprises data preparation module, for business datum is arranged, carries out business datum correlation analysis, and extracts problem by modes such as correlation rule and contexts, and problem service attribute is set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310506948.XA CN103593412B (en) | 2013-10-24 | 2013-10-24 | A kind of answer method and system based on tree structure problem |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310506948.XA CN103593412B (en) | 2013-10-24 | 2013-10-24 | A kind of answer method and system based on tree structure problem |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103593412A true CN103593412A (en) | 2014-02-19 |
| CN103593412B CN103593412B (en) | 2017-10-03 |
Family
ID=50083553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310506948.XA Active CN103593412B (en) | 2013-10-24 | 2013-10-24 | A kind of answer method and system based on tree structure problem |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103593412B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408639A (en) * | 2014-10-22 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Multi-round conversation interaction method and system |
| CN105354185A (en) * | 2015-10-30 | 2016-02-24 | 上海智臻智能网络科技股份有限公司 | Method and apparatus for question and answer system to mine relevant questions |
| CN105554139A (en) * | 2015-12-24 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Online customer service method, online customer service server and online customer service system |
| CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富（北京）科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
| CN106599604A (en) * | 2017-01-12 | 2017-04-26 | 上海博集医疗科技有限公司 | Smart medical information interaction system and method |
| CN106991112A (en) * | 2016-11-07 | 2017-07-28 | 阿里巴巴集团控股有限公司 | Information query method and device |
| CN107391551A (en) * | 2017-06-06 | 2017-11-24 | 广东广业开元科技有限公司 | A kind of web business datums analysis method and system based on data mining |
| WO2018001040A1 (en) * | 2016-06-27 | 2018-01-04 | 中兴通讯股份有限公司 | Method and device for providing service data, and computer storage medium |
| CN107992459A (en) * | 2017-10-12 | 2018-05-04 | 如是科技（大连）有限公司 | Resume generation method and device |
| CN108432190A (en) * | 2015-09-01 | 2018-08-21 | 三星电子株式会社 | Response message recommends method and its equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851700A (en) * | 2005-11-01 | 2006-10-25 | 华为技术有限公司 | Inquiry method and system, and inquiry switching device |
| CN101166212A (en) * | 2006-10-19 | 2008-04-23 | 华为技术有限公司 | A method and system for realizing graphic display of interactive voice response system |
| CN101635010A (en) * | 2009-08-21 | 2010-01-27 | 腾讯科技（深圳）有限公司 | Dialogue processing method and dialogue system in dialogue community |
| CN102375835A (en) * | 2010-08-17 | 2012-03-14 | 腾讯科技（深圳）有限公司 | Information searching system and method |
-
2013
- 2013-10-24 CN CN201310506948.XA patent/CN103593412B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851700A (en) * | 2005-11-01 | 2006-10-25 | 华为技术有限公司 | Inquiry method and system, and inquiry switching device |
| CN101166212A (en) * | 2006-10-19 | 2008-04-23 | 华为技术有限公司 | A method and system for realizing graphic display of interactive voice response system |
| CN101635010A (en) * | 2009-08-21 | 2010-01-27 | 腾讯科技（深圳）有限公司 | Dialogue processing method and dialogue system in dialogue community |
| CN102375835A (en) * | 2010-08-17 | 2012-03-14 | 腾讯科技（深圳）有限公司 | Information searching system and method |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10817786B2 (en) | 2014-10-22 | 2020-10-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Multi-round session interaction method and system, and computer device |
| CN104408639A (en) * | 2014-10-22 | 2015-03-11 | 百度在线网络技术（北京）有限公司 | Multi-round conversation interaction method and system |
| CN108432190B (en) * | 2015-09-01 | 2021-10-26 | 三星电子株式会社 | Response message recommendation method and equipment thereof |
| CN108432190A (en) * | 2015-09-01 | 2018-08-21 | 三星电子株式会社 | Response message recommends method and its equipment |
| CN105354185A (en) * | 2015-10-30 | 2016-02-24 | 上海智臻智能网络科技股份有限公司 | Method and apparatus for question and answer system to mine relevant questions |
| CN105554139A (en) * | 2015-12-24 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Online customer service method, online customer service server and online customer service system |
| CN105554139B (en) * | 2015-12-24 | 2018-09-21 | 上海智臻智能网络科技股份有限公司 | Online customer service method of servicing, online customer service server and online customer service system |
| CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富（北京）科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
| WO2018001040A1 (en) * | 2016-06-27 | 2018-01-04 | 中兴通讯股份有限公司 | Method and device for providing service data, and computer storage medium |
| CN107547354A (en) * | 2016-06-27 | 2018-01-05 | 南京中兴软件有限责任公司 | Business datum provides method and device |
| CN106991112A (en) * | 2016-11-07 | 2017-07-28 | 阿里巴巴集团控股有限公司 | Information query method and device |
| CN106991112B (en) * | 2016-11-07 | 2021-05-25 | 创新先进技术有限公司 | Information query method and device |
| CN106599604A (en) * | 2017-01-12 | 2017-04-26 | 上海博集医疗科技有限公司 | Smart medical information interaction system and method |
| CN106599604B (en) * | 2017-01-12 | 2019-10-08 | 上海博集医疗科技有限公司 | Medical information intelligent interactive system and method |
| CN107391551B (en) * | 2017-06-06 | 2020-04-14 | 广东广业开元科技有限公司 | Web service data analysis method and system based on data mining |
| CN107391551A (en) * | 2017-06-06 | 2017-11-24 | 广东广业开元科技有限公司 | A kind of web business datums analysis method and system based on data mining |
| CN107992459A (en) * | 2017-10-12 | 2018-05-04 | 如是科技（大连）有限公司 | Resume generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103593412B (en) | 2017-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103593412A (en) | Tree-structure-based question answering system and method | |
| RU2745632C1 (en) | Automated response server device, terminal device, response system, response method and program | |
| CN108345690B (en) | Intelligent question and answer method and system | |
| US10726446B2 (en) | Method and apparatus for pushing information | |
| CN109446341A (en) | The construction method and device of knowledge mapping | |
| GB2561660A (en) | Computer-implemented method of querying a dataset | |
| US10217049B2 (en) | Systems and methods for determining social perception | |
| CN106815356B (en) | Precision target user message method for pushing and system based on semantic analysis | |
| CN106934068A (en) | The method that robot is based on the semantic understanding of environmental context | |
| CN105630938A (en) | Intelligent question-answering system | |
| CN102866990A (en) | Thematic conversation method and device | |
| CN108664509B (en) | Method, device and server for ad hoc query | |
| KR20200137601A (en) | Apparatus and method for processing of question and answer using chatbot | |
| CN107992513B (en) | Information processing system and method for realizing information processing | |
| CN101330432A (en) | System and method for implementing on-line QA | |
| CN111813956A (en) | Knowledge graph construction method and device, and information penetration method and system | |
| KR101123697B1 (en) | Apparatus and method for searching user of common interest | |
| CN113127506A (en) | Target query statement construction method and device, storage medium and electronic device | |
| CN113626571A (en) | Answer sentence generating method and device, computer equipment and storage medium | |
| CN113326363A (en) | Searching method and device, prediction model training method and device, and electronic device | |
| CN103473243A (en) | Method and device for generating semantic network service document | |
| CN106462579A (en) | Construction of lexicon for selected context | |
| CN111125332A (en) | Method, device, equipment and storage medium for calculating TF-IDF value of word | |
| CN110704637B (en) | Method and device for constructing multi-modal knowledge base and computer readable medium | |
| CN113064982A (en) | Question-answer library generation method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |