[go: up one dir, main page]

CN106357942A - Intelligent response method and system based on context dialogue semantic recognition - Google Patents

Intelligent response method and system based on context dialogue semantic recognition Download PDF

Info

Publication number
CN106357942A
CN106357942A CN201610950298.1A CN201610950298A CN106357942A CN 106357942 A CN106357942 A CN 106357942A CN 201610950298 A CN201610950298 A CN 201610950298A CN 106357942 A CN106357942 A CN 106357942A
Authority
CN
China
Prior art keywords
counseling problem
context
counseling
result
intelligent response
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
CN201610950298.1A
Other languages
Chinese (zh)
Inventor
赖招展
姜磊
沈广盈
朱振航
杨辰
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.)
Guangzhou Bailing Data Co Ltd
Original Assignee
Guangzhou Bailing Data Co Ltd
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 Guangzhou Bailing Data Co Ltd filed Critical Guangzhou Bailing Data Co Ltd
Priority to CN201610950298.1A priority Critical patent/CN106357942A/en
Publication of CN106357942A publication Critical patent/CN106357942A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • Marketing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an intelligent response method and system based on context dialogue semantic recognition. The method comprises the following steps of: performing formatting and natural language processing on a consulting question to obtain a semantic type of the question, determine a question intention of a user, and extract out keywords; performing answer matching by using a recommend matching algorithm, and outputting hit knowledge points in the form of retrieved results; if no knowledge point with a corresponding matching degree exists, performing structural analysis on the consulting question, and performing semantic recognition on the consulting question in combination with context contents to recompose the consulting question; performing retrieving on the recomposed consulting question; and extracting a suitable answer from retrieval results. According to the method disclosed by the invention, a traditional intelligent response system is improved by virtue of a natural language processing technology, dialogue semantic recognition based on context is added, a user colloquial consulting mode can be effectively processed, the response matching degree of the intelligent response system is promoted, the user experience is greatly improved, and the customer service cost is effectively reduced.

Description

Intelligent response method and system based on the identification of context dialog semantics
Technical field
The present invention relates to intelligent response technical field, specially the intelligent response method based on the identification of context dialog semantics And system.
Background technology
With developing rapidly of computerized information and Internet technology, customer service is progressively to networking, intelligent and individual The direction of property is developed, and enterprise needs to provide a large amount of contact staff to meet the information consultation demand of client.With speech recognition skill The intelligent customer service that artificial intelligence technology based on art, natural language understanding builds, by the online channels such as web, voice, note with Client realizes intelligent man-machine interaction, greatly improves the work efficiency of contact staff and the duplication of labour reducing customer service, effectively Reduce artificial customer service cost, lifting service quality.
Before this, domestic enterprise information system development relatively lag behind, human cost relatively low, therefore enterprise using intelligence The original power of customer service is not enough, but through some intelligent customer service manufacturers domestic continuous expansion commercially and intelligent customer service city The field growth of itself, has had a lot of families to new technique using relatively positive telecom operators, financial field, electricity at present Sub- business enterprise employs intelligent customer service.After siri issues, more people are aware of intelligent answer technology, have been also aware that intelligence The ability of question answering system, expands range of application in enterprise for the intelligent customer service further.Intelligent customer service covers channel bag at present Include the traditional channels such as phone, note, website, qq, also obtain on the novel electron channel such as wechat, microblogging, app simultaneously Practical application.
Intelligent customer service is not only enterprise and provides fine granularity Knowledge Management Technology, also for the ditch between enterprise and mass users Lead to and set up a kind of efficiently and effectively technological means based on natural language.Intelligent customer service be in the nature answering system, its process Flow process can overview be substantially 3 major parts: case study, information retrieval, answer extracting, and that is, client proposes to ask by online channel Topic, system is mated corresponding answer from the knowledge base of backstage and is returned to client or returned to knowledge point with Key for Reference form Contact staff supplies it to select.To rapidly and accurately answer the problem of client, the system of it is critical only that can correct understanding client carry The problem going out.Due to the language convention of the mankind, the problem of client's consulting assumes colloquial style phenomenon is serious, the default composition of sentence is many etc. Feature, existing answering system also cannot very well be processed, the intention of correct understanding client, thus intelligent response system Also has huge room for promotion.
Content of the invention
In order to solve in prior art client's consulting due to leading to system cannot correctly manage the default composition of colloquial style sentence more The technical problem that solution client is intended to, the present invention proposes the intelligent response method and system based on the identification of context dialog semantics, carries The high recommendation matching degree of intelligent response system, efficiently reduces artificial customer service cost, lifting service quality.
The intelligent response method that the present invention is identified based on context dialog semantics, employs the following technical solutions to realize: base In context dialog semantics identification intelligent response method it is characterised in that comprising the following steps:
S1, analysis, from the counseling problem of mobile device input, format to counseling problem and natural language processing, obtain Go out the semantic type of counseling problem, determine the intention that user puts question to, extract keyword；
S2, the analysis result according to step s1, recommend matching algorithm to carry out answer matches using corresponding, then basis The knowledge point hit is exported in the form of retrieval result by degree of joining, if the knowledge point of no corresponding matching degree, proceeds to step s3；
S3, counseling problem is carried out with structural analysis, and with reference to context, the semanteme of counseling problem is identified, root According to recognition result restructuring counseling problem；Counseling problem after restructuring is retrieved again, is exported retrieval result；
S4, extract suitable answer from retrieval result.
Preferably, the matching algorithm of recommending described in step s2 carries out the analysis of grammer and syntax to analysis result, further according to The keyword of query statement and syntactic structure, are ranked up according to matching degree size to the knowledge point in knowledge base, finally according to Result returns to matching degree highest knowledge point.
Preferably, step s3 adopts following steps:
S31, first structural analysis is carried out to counseling problem, obtain the composition of counseling problem by sentence constituent analysis model Composition, then judges that what the default composition of counseling problem is, obtain counseling problem one-tenth be grouped into default become member record；
S32, by being analyzed to the composition of context, and combine the sentence constituent of counseling problem, carry out semantics recognition, The basic constituent of sentence is supplemented complete；
S33, by the constituent of counseling problem as input, counseling problem is reconfigured, and is generated as system The sentence expression way that can explain；
S34, for the counseling problem after reconfiguring, re-start information retrieval, after the completion of retrieval result is exported.
The intelligent response system that the present invention is identified based on context dialog semantics, employs the following technical solutions to realize: base In context dialog semantics identification intelligent response system it is characterised in that include mobile device, phone route, voice turn literary composition This module, responder module and customer service are attended a banquet display, and wherein mobile device, phone route and speech to text module connect successively Connect, responder module is connected with mobile device, speech to text module, display of attending a banquet respectively；Described responder module is asked to consulting Topic formats and natural language processing, recommends matching algorithm to carry out answer matches using corresponding, then according to matching degree The knowledge point of hit is exported to display of attending a banquet in the form of retrieval result；If responder module pair when no accordingly mating knowledge point Counseling problem carries out structural analysis, and with reference to context, the semanteme of counseling problem is identified, according to recognition result weight Group counseling problem, and the counseling problem after restructuring is retrieved again, export retrieval result to display of attending a banquet.
Preferably, client passes through described mobile device input voice or Word message, described display output response of attending a banquet Result supplies contact staff to select, and is connected by phone of attending a banquet between described client and contact staff.
From above technical scheme, the present invention increased based on up and down in the processing mode of traditional intelligence answering system The dialog semantics identification function of literary composition, when, after case study, information retrieval, being not matched to corresponding answer, then proceed to Dialog semantics identification to based on context: first, by current problem is carried out with sentence constituent structural analysis, judge currently to ask Topic which composition default, carries out semantics recognition in conjunction with context, confirms the true intention of user, next problem is carried out Reconstruct, finally re-starts information retrieval, by answer extracting, corresponding answer is returned to user.Compared with prior art, The invention has the advantages that and beneficial effect:
1st, the present invention improves intelligent response system problem recommendation hit rate, and user is being seeked advice from colloquial mode And/or in the case of the default composition of sentence, default composition can be supplemented using the present invention complete, allow system to efficiently identify out User is accurately intended to, and returns the correct workload mated answer, reduce artificial customer service, increases customer satisfaction degree.
2nd, with the lifting of colony of entire society troxerutine tabtets, and the service experience of industry-by-industry is improved, intelligent customer service Theory is urgently lifted to " customer experience guiding " further from " customer demand orientation ", and the quality of customer service work directly represents Culture, overall image and the overall qualities of an enterprise.Intelligent customer service as Internet era under advanced client clothes Business represents, using high hit rate intelligent response system it is provided that one-to-many, efficient, convenient and stable 24 hours whole days Wait service, artificial customer service cost can be greatly reduced, its function expansibility is strong, represent formal intuition, various, mutual for expanding Networking service channel service ability, maintaining enterprise brand image important in inhibiting, thus improve the core competitiveness of enterprise.
Brief description
Fig. 1 is the structural representation of the present invention；
Fig. 2 is the answer recommended flowsheet of intelligent response system of the present invention.
Specific embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is done and more specifically describe, but embodiments of the present invention are not limited to This.
Embodiment:
Referring to Fig. 1, intelligent response system of the present invention includes mobile device, phone route, speech to text module, response mould Block and customer service are attended a banquet display, and wherein mobile device, phone route and speech to text module is sequentially connected, and responder module is respectively It is connected with mobile device, speech to text module, display of attending a banquet.
Client mainly has two ways to access intelligent response system, and one kind is to dial service calls by mobile device, leads to Cross phone route, speech to text module is converted into text input to responder module, another kind be by the app of mobile device, The modes such as the online response page directly enter text into responder module.Referring to Fig. 2, the present invention is in traditional intelligence answering system Dialog semantics identification function based on context be increased on processing mode, responder module after receiving text, first to visitor Family current problem carries out answer retrieval, if not retrieving suitable answer, being transferred to the dialog semantics based on context and knowing Not.Specifically, semantics recognition is by structural modeling that the context that current problem produces is engaged in the dialogue, by machine learning side Method analyzes the contextual information when proposing current problem for the user, by the sentence composition structural analyses to current problem, knows Do not go out the sentence composition that current problem is lacked, carry out subject analysis and semantic analysis in conjunction with context, to currently asking The semantic information of topic is extended and understands, then goes out to meet the semantic answer of current problem from system retrieval.Customer service is attended a banquet people After member views corresponding answer by display, client is replied by phone.
The intelligent response method that the present invention is identified based on context dialog semantics, flow process is specific as follows:
First, case study, inputs, to client, the question format come in and carries out natural language processing.
The purpose of case study is the semantic type of problem analysis, determines the intention that user puts question to, crucial step is to carry Take out keyword therein.Such as user to be putd question to be " I wants to ask the rate introduction that lower 4g flies to enjoy set meal ", first have to by Content formats, and such as English character unification is converted into capitalization 4g and becomes 4g, and wrong word is replaced etc., after completing to format, Proceed by text participle, after the completion of participle, just carry out keyword extraction, in such as current example, what client wanted to ask is that rate are situated between Continue, keyword therein is exactly " 4g flies to enjoy set meal ", " rate ", " introduction ", and such as " I thinks ", " asking down " these vocabulary is then made For secondary word or directly filtration, also the key word extracting to be done with part of speech analysis simultaneously, after the completion of then processing Result be transferred to next flow process and processed.
2nd, information retrieval, carries out knowledge point retrieval based on Company Knowledge Cooley with proposed algorithm.
Information retrieval is to recommend matching algorithm using corresponding according to the result that case study obtains from Company Knowledge storehouse, Carry out answer matches, then the knowledge point record of corresponding hit is transferred to by the 4th step according to matching degree, without matching degree Higher knowledge point then jumps to the 3rd step.
Recommend matching algorithm the result that case study input is come in can be carried out with the analysis of grammer and syntax, further according to inquiry The keyword of sentence and syntactic structure, are ranked up according to matching degree size to the knowledge point inside knowledge base, finally according to knot Fruit returns matching degree highest knowledge point record.
3rd, semantics recognition, is engaged in the dialogue semantics recognition based on context.
When only the higher knowledge point record of matching degree not being had according to the counseling problem content of current input, then start to current The problem of consulting carries out structural analysis and with reference to context, the semanteme of problem is identified, and is answered with accurately identifying to go wrong Case.
1) structural analysis
First structural analysis is carried out to current counseling problem, become by the composition that sentence constituent analysis model obtains problem Point, then what the default composition of decision problem is, obtain problem one-tenth be grouped into default become member record.
2) semantics recognition
By the spoken custom analysis of people, find that default problem composition usually there will be in the context of dialogue, then By being analyzed to the composition of context, and combine the sentence constituent of counseling problem, jointly carry out the semantics recognition of user, The basic constituent of sentence supplements completely at last.
3) problem reformulation
, problem is reconfigured, and is generated as system to enter as input by the constituent of counseling problem The sentence expression way that row is explained.
4) information retrieval
For the problem after reconfiguring, re-start information retrieval, after the completion of retrieval result is exported, for contact staff Select.
4th, answer extracting, the content of knowledge point is refined and colloquial mode returns.
Answer extracting is exactly to extract answer from the knowledge point that information retrieval result returns.Because the content-form of knowledge point Have length have short it is possible to an only word or in short, be also likely to be the text string grown very much or a paragraph.Institute , during answer extracting, answer can be carried out from the length of knowledge point contents using different strategies according to the intention of problem and to take out Take.When particularly answer is longer, be not suitable for directly as answer, using automatic Summarization Technique, by knowledge point contents Simplified, by the digest user after simplifying can Information faster, the expression-form of answer is changed simultaneously, Exported with colloquial mode as far as possible, improved the experience of user.
Above-described embodiment is one embodiment of the present invention, but embodiments of the present invention do not limit and this, are engaged in This skilled person without departing from the present invention spirit and principle under made any modification, replacement, improvement, be all contained in this In bright protection domain.

Claims (5)

1. the intelligent response method based on the identification of context dialog semantics is it is characterised in that comprise the following steps:
S1, analysis, from the counseling problem of mobile device input, format to counseling problem and natural language processing, draw official communication The semantic type of inquiry topic, determines the intention that user puts question to, extracts keyword；
S2, the analysis result according to step s1, recommend matching algorithm to carry out answer matches using corresponding, then according to matching degree The knowledge point of hit is exported in the form of retrieval result, if the knowledge point of no corresponding matching degree, proceeds to step s3；
S3, counseling problem is carried out with structural analysis, and with reference to context, the semanteme of counseling problem is identified, according to knowledge Other result restructuring counseling problem；Counseling problem after restructuring is retrieved again, is exported retrieval result；
S4, extract suitable answer from retrieval result.
2. the intelligent response method based on the identification of context dialog semantics according to claim 1 is it is characterised in that step Matching algorithm of recommending described in s2 carries out analysis, the keyword further according to query statement and the sentence of grammer and syntax to analysis result Method structure, is ranked up according to matching degree size to the knowledge point in knowledge base, returns matching degree highest finally according to result Knowledge point.
3. the intelligent response method based on the identification of context dialog semantics according to claim 1 is it is characterised in that step S3 adopts following steps:
S31, first structural analysis is carried out to counseling problem, become by the composition that sentence constituent analysis model obtains counseling problem Point, then judge that what the default composition of counseling problem is, obtain counseling problem one-tenth be grouped into default become member record；
S32, by being analyzed to the composition of context, and combine the sentence constituent of counseling problem, carry out semantics recognition, by sentence The basic constituent of son supplements complete；
S33, by the constituent of counseling problem as input, counseling problem is reconfigured, and is generated as system to enter The sentence expression way that row is explained；
S34, for the counseling problem after reconfiguring, re-start information retrieval, after the completion of retrieval result is exported.
4. based on context dialog semantics identification intelligent response system it is characterised in that include mobile device, phone route, Speech to text module, responder module and customer service are attended a banquet display, wherein mobile device, phone route and speech to text module It is sequentially connected, responder module is connected with mobile device, speech to text module, display of attending a banquet respectively；Described responder module pair Counseling problem formats and natural language processing, recommends matching algorithm to carry out answer matches using corresponding, then basis The knowledge point of hit is exported to display of attending a banquet in the form of retrieval result by matching degree；If response when no accordingly mating knowledge point Module carries out structural analysis to counseling problem, and with reference to context, the semanteme of counseling problem is identified, according to identification Result restructuring counseling problem, and the counseling problem after restructuring is retrieved again, export retrieval result to display of attending a banquet.
5. the intelligent response system based on the identification of context dialog semantics according to claim 4 is it is characterised in that client Voice or Word message are inputted by described mobile device, described display output response result of attending a banquet supplies contact staff to select, It is connected by phone of attending a banquet between described client and contact staff.
CN201610950298.1A 2016-10-26 2016-10-26 Intelligent response method and system based on context dialogue semantic recognition Pending CN106357942A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610950298.1A CN106357942A (en) 2016-10-26 2016-10-26 Intelligent response method and system based on context dialogue semantic recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610950298.1A CN106357942A (en) 2016-10-26 2016-10-26 Intelligent response method and system based on context dialogue semantic recognition

Publications (1)

Publication Number Publication Date
CN106357942A true CN106357942A (en) 2017-01-25

Family

ID=57863517

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610950298.1A Pending CN106357942A (en) 2016-10-26 2016-10-26 Intelligent response method and system based on context dialogue semantic recognition

Country Status (1)

Country Link
CN (1) CN106357942A (en)

Cited By (63)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153965A (en) * 2017-04-05 2017-09-12 芜湖恒天易开软件科技股份有限公司 A kind of intelligent customer service solution of multiple terminals
CN107918640A (en) * 2017-10-20 2018-04-17 阿里巴巴集团控股有限公司 Sample determines method and device
CN108320738A (en) * 2017-12-18 2018-07-24 上海科大讯飞信息科技有限公司 Voice data processing method and device, storage medium, electronic equipment
CN108446322A (en) * 2018-02-10 2018-08-24 灯塔财经信息有限公司 Method and device for realizing an intelligent question answering system
CN108664472A (en) * 2018-05-08 2018-10-16 腾讯科技（深圳）有限公司 Natural language processing method, apparatus and its equipment
WO2018205084A1 (en) * 2017-05-08 2018-11-15 Microsoft Technology Licensing, Llc Providing local service information in automated chatting
CN108897771A (en) * 2018-05-30 2018-11-27 东软集团股份有限公司 Automatic question-answering method, device, computer readable storage medium and electronic equipment
CN109104534A (en) * 2018-10-22 2018-12-28 北京智合大方科技有限公司 A kind of system for improving outgoing call robot and being intended to Detection accuracy, recall rate
CN109165274A (en) * 2018-07-16 2019-01-08 厦门快商通信息技术有限公司 A kind of on-line automatic client service method, system and electronic equipment
CN109325155A (en) * 2018-07-25 2019-02-12 南京瓦尔基里网络科技有限公司 A kind of novel dialogue state storage method and system
CN109376354A (en) * 2018-09-26 2019-02-22 出门问问信息科技有限公司 Fraud recognition methods, device, electronic equipment and readable storage medium storing program for executing
CN109471953A (en) * 2018-10-11 2019-03-15 平安科技（深圳）有限公司 A kind of voice data retrieval method and terminal device
CN109492126A (en) * 2018-11-02 2019-03-19 廊坊市森淼春食用菌有限公司 A kind of intelligent interactive method and device
CN109493186A (en) * 2018-11-20 2019-03-19 北京京东尚科信息技术有限公司 The method and apparatus for determining pushed information
CN109597994A (en) * 2018-12-04 2019-04-09 挖财网络技术有限公司 Short text problem semantic matching method and system
CN109685673A (en) * 2018-12-19 2019-04-26 前海企保科技（深圳）有限公司 A kind of insurance coupled customer service system and method based on artificial intelligence
CN109698886A (en) * 2017-10-24 2019-04-30 上海易谷网络科技股份有限公司 A method of allowing attend a banquet carrying out Information Mobile Service
CN109816423A (en) * 2018-12-14 2019-05-28 深圳壹账通智能科技有限公司 Product programming method and server based on speech recognition
CN109829744A (en) * 2018-12-15 2019-05-31 深圳壹账通智能科技有限公司 Consultation method, device, electronic equipment and medium based on natural language processing
CN109885823A (en) * 2017-12-01 2019-06-14 武汉楚鼎信息技术有限公司 A kind of distributed semantic recognition methods of financial industry and system and device
CN109933651A (en) * 2019-03-26 2019-06-25 联想(北京)有限公司 Information interacting method, device and server
CN110008308A (en) * 2019-01-24 2019-07-12 阿里巴巴集团控股有限公司 For the method and apparatus of user's question sentence supplemental information
CN110008322A (en) * 2019-03-25 2019-07-12 阿里巴巴集团控股有限公司 Art recommended method and device under more wheel session operational scenarios
CN110135879A (en) * 2018-11-17 2019-08-16 华南理工大学 Customer service quality automatic scoring method based on natural language processing
CN110138982A (en) * 2018-02-09 2019-08-16 埃森哲环球解决方案有限公司 Service based on artificial intelligence is realized
CN110245223A (en) * 2019-06-20 2019-09-17 济宁市众帮来袭信息科技有限公司 Parking service method, apparatus, equipment and storage medium
CN110266899A (en) * 2019-06-11 2019-09-20 平安科技（深圳）有限公司 The recognition methods and customer service system that client is intended to
CN110266900A (en) * 2019-06-11 2019-09-20 平安科技（深圳）有限公司 Recognition methods, device and the customer service system that client is intended to
CN110263135A (en) * 2019-05-20 2019-09-20 北京字节跳动网络技术有限公司 A kind of data exchange matching process, device, medium and electronic equipment
CN110597952A (en) * 2019-08-20 2019-12-20 深圳壹账通智能科技有限公司 Information processing method, server, and computer storage medium
CN110931016A (en) * 2019-11-15 2020-03-27 深圳供电局有限公司 Voice recognition method and system for offline quality inspection
CN110955762A (en) * 2019-11-01 2020-04-03 上海百事通信息技术股份有限公司 Intelligent question and answer platform
CN110970021A (en) * 2018-09-30 2020-04-07 航天信息股份有限公司 Question-answering control method, device and system
CN111048075A (en) * 2018-10-11 2020-04-21 上海智臻智能网络科技股份有限公司 Intelligent customer service system and intelligent customer service robot
CN111061855A (en) * 2018-10-17 2020-04-24 阿里巴巴集团控股有限公司 Method and device for generating reply content, method for processing online chat and electronic equipment
CN111062220A (en) * 2020-03-13 2020-04-24 成都晓多科技有限公司 End-to-end intention recognition system and method based on memory forgetting device
CN111094924A (en) * 2017-09-15 2020-05-01 宝马股份公司 Data processing apparatus and method for performing voice-based human-machine interaction
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
CN111309883A (en) * 2020-02-13 2020-06-19 腾讯科技（深圳）有限公司 Man-machine conversation method based on artificial intelligence, model training method and device
CN111324708A (en) * 2020-02-07 2020-06-23 普强时代(珠海横琴)信息技术有限公司 Natural language processing system based on human-computer interaction
CN111447331A (en) * 2020-03-26 2020-07-24 中国建设银行股份有限公司 Voice portal session management system and method
CN111508494A (en) * 2020-04-20 2020-08-07 广东工业大学 An intelligent tax payment voice consultation method and system
CN111738018A (en) * 2020-06-24 2020-10-02 深圳前海微众银行股份有限公司 An intent understanding method, apparatus, device and storage medium
CN111800550A (en) * 2020-07-06 2020-10-20 国泰新点软件股份有限公司 Telephone audio conversion apparatus, method and storage medium
TWI712975B (en) * 2017-06-29 2020-12-11 永豐商業銀行股份有限公司 A voice-activated system for financial information services
CN112347233A (en) * 2019-08-06 2021-02-09 现代自动车株式会社 Dialogue processing apparatus, vehicle including dialogue processing apparatus, and dialogue processing method
CN112422757A (en) * 2019-08-21 2021-02-26 阿瓦亚公司 Automatic message generation and presentation to communication nodes participating in a communication
CN112509575A (en) * 2020-11-26 2021-03-16 上海济邦投资咨询有限公司 Financial consultation intelligent guiding system based on big data
CN112527983A (en) * 2020-11-27 2021-03-19 长威信息科技发展股份有限公司 Man-machine natural interaction service system for personalized government affairs
CN112580371A (en) * 2020-12-25 2021-03-30 江苏鑫盛通讯科技有限公司 Man-machine coupling customer service system and method based on artificial intelligence
CN112633919A (en) * 2020-12-15 2021-04-09 航天信息股份有限公司 Method and system for realizing intelligent customer service
CN112818102A (en) * 2021-02-01 2021-05-18 杭州微洱网络科技有限公司 Context-based fast question answering method for FAQ (failure of expert knowledge) knowledge base
CN112948557A (en) * 2021-03-09 2021-06-11 哈尔滨工业大学 Iterative intelligent customer service system based on common problem set and assisted by description document
CN113076403A (en) * 2021-04-21 2021-07-06 深圳追一科技有限公司 User message processing method and related equipment
CN114138962A (en) * 2021-11-30 2022-03-04 昆明电力交易中心有限责任公司 Automatic response method based on electric power transaction, terminal and storage medium
CN114357126A (en) * 2020-10-13 2022-04-15 深圳前海微众银行股份有限公司 Intelligent question-answering system
CN114500747A (en) * 2022-01-28 2022-05-13 江苏号百信息服务有限公司 A method for building an intelligent traffic disaster recovery platform for emergency traffic switching
CN115510211A (en) * 2022-10-12 2022-12-23 重庆远见信息产业集团股份有限公司 Tax intelligent management system
CN115774795A (en) * 2022-02-24 2023-03-10 青岛海尔电冰箱有限公司 Food material management method, system and computer storage medium
CN116260909A (en) * 2023-03-08 2023-06-13 深圳方思鼎云科技有限公司 Voice application control method of calling system and calling system
CN116340475A (en) * 2022-12-27 2023-06-27 中国工商银行股份有限公司 Question and answer method and device based on financial business, electronic equipment and storage medium
CN118689976A (en) * 2024-06-06 2024-09-24 河南省种业发展中心 Dynamic multi-level retrieval enhanced knowledge base question answering method and device, medium, and equipment
CN119052379A (en) * 2024-10-30 2024-11-29 深圳星网信通科技股份有限公司 Control method and equipment for customer service system and computer readable storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101431573A (en) * 2007-11-08 2009-05-13 上海赢思软件技术有限公司 Method and equipment for implementing automatic customer service through human-machine interaction technology
CN104951456A (en) * 2014-03-26 2015-09-30 上海智臻网络科技有限公司 A method, device and equipment for obtaining answer information
CN105162977A (en) * 2015-08-26 2015-12-16 上海银天下科技有限公司 Excuse recommendation method and device
CN105589844A (en) * 2015-12-18 2016-05-18 北京中科汇联科技股份有限公司 Missing semantic supplementing method for multi-round question-answering system
US20160142546A1 (en) * 2013-04-09 2016-05-19 Avaya Inc. System and method for keyword-based notification and delivery of content
CN105744057A (en) * 2016-01-21 2016-07-06 平安科技（深圳）有限公司 Intelligent voice dialogue interaction method and intelligent voice dialogue interaction device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101431573A (en) * 2007-11-08 2009-05-13 上海赢思软件技术有限公司 Method and equipment for implementing automatic customer service through human-machine interaction technology
US20160142546A1 (en) * 2013-04-09 2016-05-19 Avaya Inc. System and method for keyword-based notification and delivery of content
CN104951456A (en) * 2014-03-26 2015-09-30 上海智臻网络科技有限公司 A method, device and equipment for obtaining answer information
CN105162977A (en) * 2015-08-26 2015-12-16 上海银天下科技有限公司 Excuse recommendation method and device
CN105589844A (en) * 2015-12-18 2016-05-18 北京中科汇联科技股份有限公司 Missing semantic supplementing method for multi-round question-answering system
CN105744057A (en) * 2016-01-21 2016-07-06 平安科技（深圳）有限公司 Intelligent voice dialogue interaction method and intelligent voice dialogue interaction device

Cited By (87)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153965A (en) * 2017-04-05 2017-09-12 芜湖恒天易开软件科技股份有限公司 A kind of intelligent customer service solution of multiple terminals
CN109416695B (en) * 2017-05-08 2022-05-27 微软技术许可有限责任公司 Providing local service information in automatic chat
WO2018205084A1 (en) * 2017-05-08 2018-11-15 Microsoft Technology Licensing, Llc Providing local service information in automated chatting
US10951555B2 (en) 2017-05-08 2021-03-16 Microsoft Technology Licensing, Llc Providing local service information in automated chatting
CN109416695A (en) * 2017-05-08 2019-03-01 微软技术许可有限责任公司 Local service information is provided in automatic chatting
TWI712975B (en) * 2017-06-29 2020-12-11 永豐商業銀行股份有限公司 A voice-activated system for financial information services
CN111094924A (en) * 2017-09-15 2020-05-01 宝马股份公司 Data processing apparatus and method for performing voice-based human-machine interaction
CN107918640A (en) * 2017-10-20 2018-04-17 阿里巴巴集团控股有限公司 Sample determines method and device
CN109698886A (en) * 2017-10-24 2019-04-30 上海易谷网络科技股份有限公司 A method of allowing attend a banquet carrying out Information Mobile Service
CN109885823A (en) * 2017-12-01 2019-06-14 武汉楚鼎信息技术有限公司 A kind of distributed semantic recognition methods of financial industry and system and device
CN108320738B (en) * 2017-12-18 2021-03-02 上海科大讯飞信息科技有限公司 Voice data processing method and device, storage medium and electronic equipment
CN108320738A (en) * 2017-12-18 2018-07-24 上海科大讯飞信息科技有限公司 Voice data processing method and device, storage medium, electronic equipment
CN110138982B (en) * 2018-02-09 2021-08-10 埃森哲环球解决方案有限公司 Service implementation based on artificial intelligence
CN110138982A (en) * 2018-02-09 2019-08-16 埃森哲环球解决方案有限公司 Service based on artificial intelligence is realized
CN108446322A (en) * 2018-02-10 2018-08-24 灯塔财经信息有限公司 Method and device for realizing an intelligent question answering system
CN108664472B (en) * 2018-05-08 2021-08-06 腾讯科技（深圳）有限公司 Natural language processing method, device and equipment
CN108664472A (en) * 2018-05-08 2018-10-16 腾讯科技（深圳）有限公司 Natural language processing method, apparatus and its equipment
CN108897771A (en) * 2018-05-30 2018-11-27 东软集团股份有限公司 Automatic question-answering method, device, computer readable storage medium and electronic equipment
CN109165274A (en) * 2018-07-16 2019-01-08 厦门快商通信息技术有限公司 A kind of on-line automatic client service method, system and electronic equipment
CN109325155A (en) * 2018-07-25 2019-02-12 南京瓦尔基里网络科技有限公司 A kind of novel dialogue state storage method and system
CN109376354A (en) * 2018-09-26 2019-02-22 出门问问信息科技有限公司 Fraud recognition methods, device, electronic equipment and readable storage medium storing program for executing
CN110970021A (en) * 2018-09-30 2020-04-07 航天信息股份有限公司 Question-answering control method, device and system
CN110970021B (en) * 2018-09-30 2022-03-08 航天信息股份有限公司 Question-answering control method, device and system
CN109471953A (en) * 2018-10-11 2019-03-15 平安科技（深圳）有限公司 A kind of voice data retrieval method and terminal device
CN111048075A (en) * 2018-10-11 2020-04-21 上海智臻智能网络科技股份有限公司 Intelligent customer service system and intelligent customer service robot
CN111061855A (en) * 2018-10-17 2020-04-24 阿里巴巴集团控股有限公司 Method and device for generating reply content, method for processing online chat and electronic equipment
CN111061855B (en) * 2018-10-17 2023-05-02 阿里巴巴集团控股有限公司 Reply content generation method and device, online chat processing method and electronic equipment
CN109104534A (en) * 2018-10-22 2018-12-28 北京智合大方科技有限公司 A kind of system for improving outgoing call robot and being intended to Detection accuracy, recall rate
CN109492126A (en) * 2018-11-02 2019-03-19 廊坊市森淼春食用菌有限公司 A kind of intelligent interactive method and device
CN109492126B (en) * 2018-11-02 2022-03-01 廊坊市森淼春食用菌有限公司 Intelligent interaction method and device
CN110135879B (en) * 2018-11-17 2024-01-16 华南理工大学 Automatic scoring method of customer service quality based on natural language processing
CN110135879A (en) * 2018-11-17 2019-08-16 华南理工大学 Customer service quality automatic scoring method based on natural language processing
CN109493186A (en) * 2018-11-20 2019-03-19 北京京东尚科信息技术有限公司 The method and apparatus for determining pushed information
CN109597994B (en) * 2018-12-04 2023-06-06 挖财网络技术有限公司 Short text problem semantic matching method and system
CN109597994A (en) * 2018-12-04 2019-04-09 挖财网络技术有限公司 Short text problem semantic matching method and system
CN109816423A (en) * 2018-12-14 2019-05-28 深圳壹账通智能科技有限公司 Product programming method and server based on speech recognition
CN109829744A (en) * 2018-12-15 2019-05-31 深圳壹账通智能科技有限公司 Consultation method, device, electronic equipment and medium based on natural language processing
CN109685673A (en) * 2018-12-19 2019-04-26 前海企保科技（深圳）有限公司 A kind of insurance coupled customer service system and method based on artificial intelligence
CN110008308B (en) * 2019-01-24 2023-06-02 创新先进技术有限公司 Method and device for supplementing information for user questions
CN110008308A (en) * 2019-01-24 2019-07-12 阿里巴巴集团控股有限公司 For the method and apparatus of user's question sentence supplemental information
CN110008322B (en) * 2019-03-25 2023-04-07 创新先进技术有限公司 Word recommendation method and device in multi-round dialogue scene
CN110008322A (en) * 2019-03-25 2019-07-12 阿里巴巴集团控股有限公司 Art recommended method and device under more wheel session operational scenarios
CN109933651A (en) * 2019-03-26 2019-06-25 联想(北京)有限公司 Information interacting method, device and server
CN110263135A (en) * 2019-05-20 2019-09-20 北京字节跳动网络技术有限公司 A kind of data exchange matching process, device, medium and electronic equipment
CN110266899B (en) * 2019-06-11 2023-03-03 平安科技（深圳）有限公司 Client intention identification method and customer service system
CN110266900B (en) * 2019-06-11 2023-04-07 平安科技（深圳）有限公司 Method and device for identifying customer intention and customer service system
CN110266900A (en) * 2019-06-11 2019-09-20 平安科技（深圳）有限公司 Recognition methods, device and the customer service system that client is intended to
CN110266899A (en) * 2019-06-11 2019-09-20 平安科技（深圳）有限公司 The recognition methods and customer service system that client is intended to
CN110245223A (en) * 2019-06-20 2019-09-17 济宁市众帮来袭信息科技有限公司 Parking service method, apparatus, equipment and storage medium
CN112347233A (en) * 2019-08-06 2021-02-09 现代自动车株式会社 Dialogue processing apparatus, vehicle including dialogue processing apparatus, and dialogue processing method
CN110597952A (en) * 2019-08-20 2019-12-20 深圳壹账通智能科技有限公司 Information processing method, server, and computer storage medium
US11715112B2 (en) 2019-08-21 2023-08-01 Avaya Inc. Automatic message generation and presentation to a communication node engaged in a communication
CN112422757A (en) * 2019-08-21 2021-02-26 阿瓦亚公司 Automatic message generation and presentation to communication nodes participating in a communication
CN110955762B (en) * 2019-11-01 2023-10-31 上海百事通信息技术股份有限公司 Intelligent question-answering platform
CN110955762A (en) * 2019-11-01 2020-04-03 上海百事通信息技术股份有限公司 Intelligent question and answer platform
CN110931016A (en) * 2019-11-15 2020-03-27 深圳供电局有限公司 Voice recognition method and system for offline quality inspection
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
CN111324708A (en) * 2020-02-07 2020-06-23 普强时代(珠海横琴)信息技术有限公司 Natural language processing system based on human-computer interaction
CN111309883B (en) * 2020-02-13 2023-08-08 腾讯科技（深圳）有限公司 Human-computer dialogue method, model training method and device based on artificial intelligence
CN111309883A (en) * 2020-02-13 2020-06-19 腾讯科技（深圳）有限公司 Man-machine conversation method based on artificial intelligence, model training method and device
CN111062220B (en) * 2020-03-13 2020-06-16 成都晓多科技有限公司 End-to-end intention recognition system and method based on memory forgetting device
CN111062220A (en) * 2020-03-13 2020-04-24 成都晓多科技有限公司 End-to-end intention recognition system and method based on memory forgetting device
CN111447331A (en) * 2020-03-26 2020-07-24 中国建设银行股份有限公司 Voice portal session management system and method
CN111508494A (en) * 2020-04-20 2020-08-07 广东工业大学 An intelligent tax payment voice consultation method and system
CN111508494B (en) * 2020-04-20 2023-03-07 广东工业大学 An intelligent tax payment voice consultation method and system
CN111738018A (en) * 2020-06-24 2020-10-02 深圳前海微众银行股份有限公司 An intent understanding method, apparatus, device and storage medium
CN111800550B (en) * 2020-07-06 2021-12-31 国泰新点软件股份有限公司 Telephone audio conversion apparatus, method and storage medium
CN111800550A (en) * 2020-07-06 2020-10-20 国泰新点软件股份有限公司 Telephone audio conversion apparatus, method and storage medium
CN114357126A (en) * 2020-10-13 2022-04-15 深圳前海微众银行股份有限公司 Intelligent question-answering system
CN112509575B (en) * 2020-11-26 2022-07-22 上海济邦投资咨询有限公司 Financial consultation intelligent guiding system based on big data
CN112509575A (en) * 2020-11-26 2021-03-16 上海济邦投资咨询有限公司 Financial consultation intelligent guiding system based on big data
CN112527983A (en) * 2020-11-27 2021-03-19 长威信息科技发展股份有限公司 Man-machine natural interaction service system for personalized government affairs
CN112633919A (en) * 2020-12-15 2021-04-09 航天信息股份有限公司 Method and system for realizing intelligent customer service
CN112580371A (en) * 2020-12-25 2021-03-30 江苏鑫盛通讯科技有限公司 Man-machine coupling customer service system and method based on artificial intelligence
CN112818102A (en) * 2021-02-01 2021-05-18 杭州微洱网络科技有限公司 Context-based fast question answering method for FAQ (failure of expert knowledge) knowledge base
CN112948557A (en) * 2021-03-09 2021-06-11 哈尔滨工业大学 Iterative intelligent customer service system based on common problem set and assisted by description document
CN113076403A (en) * 2021-04-21 2021-07-06 深圳追一科技有限公司 User message processing method and related equipment
CN114138962A (en) * 2021-11-30 2022-03-04 昆明电力交易中心有限责任公司 Automatic response method based on electric power transaction, terminal and storage medium
CN114500747B (en) * 2022-01-28 2024-10-29 江苏号百科技有限公司 Intelligent telephone traffic disaster recovery platform building method for emergency telephone traffic switching
CN114500747A (en) * 2022-01-28 2022-05-13 江苏号百信息服务有限公司 A method for building an intelligent traffic disaster recovery platform for emergency traffic switching
CN115774795A (en) * 2022-02-24 2023-03-10 青岛海尔电冰箱有限公司 Food material management method, system and computer storage medium
CN115510211A (en) * 2022-10-12 2022-12-23 重庆远见信息产业集团股份有限公司 Tax intelligent management system
CN116340475A (en) * 2022-12-27 2023-06-27 中国工商银行股份有限公司 Question and answer method and device based on financial business, electronic equipment and storage medium
CN116260909A (en) * 2023-03-08 2023-06-13 深圳方思鼎云科技有限公司 Voice application control method of calling system and calling system
CN116260909B (en) * 2023-03-08 2024-03-26 深圳方思鼎云科技有限公司 Voice application control method of calling system and calling system
CN118689976A (en) * 2024-06-06 2024-09-24 河南省种业发展中心 Dynamic multi-level retrieval enhanced knowledge base question answering method and device, medium, and equipment
CN119052379A (en) * 2024-10-30 2024-11-29 深圳星网信通科技股份有限公司 Control method and equipment for customer service system and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN106357942A (en) Intelligent response method and system based on context dialogue semantic recognition
CN106446045B (en) User portrait construction method and system based on dialogue interaction
CN110472017A (en) A kind of analysis of words art and topic point identify matched method and system
KR101605430B1 (en) System and method for constructing a questionnaire database, search system and method using the same
CN109446305A (en) The construction method and system of intelligent tour customer service system
CN107153965A (en) A kind of intelligent customer service solution of multiple terminals
CN117453895B (en) Intelligent customer service response method, device, equipment and readable storage medium
CN103593412B (en) A kind of answer method and system based on tree structure problem
CN108052605A (en) A kind of intelligent Answer System based on client feature library
CN117312521A (en) Processing method for intelligent customer service dialogue and related products
CN108491378A (en) Power information O＆M intelligent response system
CN109460459A (en) A kind of conversational system automatic optimization method based on log study
CN106022708A (en) Method for predicting employee resignation
CN110321414B (en) Artificial intelligence consultation service method and system based on deep learning
CN112417852B (en) Method and device for judging importance of code segment
CN106326307A (en) Language interaction method
CN116091045B (en) Knowledge-graph-based communication network operation and maintenance method and operation and maintenance device
CN114969297A (en) Method for analyzing power customer appeal relevancy
CN117709969B (en) Generative matching large model construction method, medium and equipment for customer service scenarios
CN118036724A (en) Intelligent customer service system for government service and service method thereof
CN119669923A (en) A hybrid interactive system based on AI large model
CN106127526A (en) Intelligent robot system and method for work thereof
CN116431806A (en) Natural language understanding method and refrigerator
CN115455156A (en) NL2SQL modeling method, device, electronic equipment and storage medium
CN115374765B (en) Computing power network 5G data analysis system and method based on natural language processing

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170125