CN106202301A - A kind of intelligent response system based on degree of depth study - Google Patents

A kind of intelligent response system based on degree of depth study Download PDF

Info

Publication number
CN106202301A
CN106202301A CN201610510464.6A CN201610510464A CN106202301A CN 106202301 A CN106202301 A CN 106202301A CN 201610510464 A CN201610510464 A CN 201610510464A CN 106202301 A CN106202301 A CN 106202301A
Authority
CN
China
Prior art keywords
response
answer
information
degree
unit
Prior art date
Application number
CN201610510464.6A
Other languages
Chinese (zh)
Other versions
CN106202301B (en
Inventor
李成华
刘丽君
Original Assignee
武汉泰迪智慧科技有限公司
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 武汉泰迪智慧科技有限公司 filed Critical 武汉泰迪智慧科技有限公司
Priority to CN201610510464.6A priority Critical patent/CN106202301B/en
Publication of CN106202301A publication Critical patent/CN106202301A/en
Application granted granted Critical
Publication of CN106202301B publication Critical patent/CN106202301B/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3349Reuse of stored results of previous queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri

Abstract

A kind of intelligent response system based on degree of depth study, it includes such as lower unit: information acquisition unit, for being obtained voice or the Word message of user's input by user terminal, when for voice messaging, it is identified voice messaging being converted to Word message and jumping to semantic acquiring unit, when for Word message, jumps directly to semantic acquiring unit;Semantic acquiring unit, for obtaining voice or the semanteme of Word message of user's input by degree of depth learning algorithm;Response matches unit, for utilizing Method of Fuzzy Matching and internal reasoning mechanism to select optimum answer from the knowledge base pre-set;Response display unit, shows user for described optimum answer.

Description

A kind of intelligent response system based on degree of depth study

Technical field

The present invention relates to big data field of cloud computer technology, particularly to a kind of intelligent response system based on degree of depth study System.

Background technology

Customer service system is as the effective promoting service of one and customer service model, increasingly by the weight of numerous enterprises and institutions Depending on and use.In the pattern of common telephone customer system, user dials customer service hotline, and customer service system connects this hot line After, it is supplied to, by voice, the service option that user is different, when user have selected corresponding service entry according to prompting, customer service system This user is linked into corresponding service group by system, related personnel answer this hot line.In customer service system, IVR (InteractiveVoiceResponse, interactive voice response) system is used widely, and it is with prerecording or TTS literary composition This voice turning voice technology synthesis carries out automatic-answering back device, it is provided that a kind of function carrying out menu navigation for client.

CTI technology is to send out from traditional computer telephone integration (ComputerTelephony Integration) technology Exhibition and come, be initially that computer technology is applied in telephone system, it is possible to automatically the signaling information in phone is carried out Identifying processing, and connect by setting up relevant speech channel, and transmit predetermined recording file, calling etc. of transferring to user.And arrive Now, CTI technology has developed into " computer telecommunication is integrated " technology (ComputerTelecommunication Integration).More existing call center uses CTI technology, makes full use of internet, telecommunication path net and computer The multiple function of net is integrated, and the complete integrated information service system being connected as a single entity with enterprise.It utilize existing respectively Plant advanced Information Technology Methods, effectively provide high-quality, high efficiency, comprehensive service for client.

Specifically, CTI system generally comprise business application system, CTI telephone system and equipment of attending a banquet (as traffic equipment, Traffic headset, computer of attending a banquet), cti server, CTI call center middleware (provide general call center system platform feature And interface, linking CTI hardware and application software) etc..CTI telephone system includes multiple identical or different phone system of manufacturer System.Business application system is different according to industry, is divided into different application management software, is such as order processing system or sends work Repair reporting system.

In the specific implementation, business application system needs to provide business datum to CTI telephone system, in order to phone system of manufacturer System can support its service application, and business application system cannot directly obtain business datum from manufacturer's telephone system.Right In some period and some specific service entry, always can have many consumers and wait in line.These data are present in CTI phone In system, but owing to business application system can not obtain these data, thus also cannot be supplied to user, cause the user cannot Knowing and currently have how many people waiting in line, how long general needs waits.Not only waste time and the communication expense of user With, waste and use the communication cost of producer that this customer service system is provided, and, if the waiting time long will result in The most bad customer experience, causes customer churn.

Summary of the invention

Therefore, it is necessary to provide one can reduce period of reservation of number, it is not necessary to too much contact staff participates in, Yong Huneng Enough intelligent response systems based on degree of depth study understanding information needed easily.

A kind of intelligent response system based on degree of depth study, it includes such as lower unit:

Information acquisition unit, for being obtained voice or the Word message of user's input by user terminal, is being believed for voice During breath, it is identified voice messaging being converted to Word message and jumping to semantic acquiring unit, direct when for Word message Jump to semantic acquiring unit;

Semantic acquiring unit, for obtaining voice or the semanteme of Word message of user's input by degree of depth learning algorithm;

Response matches unit, for utilizing Method of Fuzzy Matching and internal reasoning mechanism to select from the knowledge base pre-set Select optimum answer;

Response display unit, shows user for described optimum answer.

In intelligent response system based on degree of depth study of the present invention, described semantic acquiring unit includes:

Server is set up the compound mode weights of each lemma in Word message beyond the clouds, and weights are saved in weights In data base;

Server is set up based on big data translation word stocks beyond the clouds;

Cloud server receives the Word message sent, and extracts language sight from Word message, and to Word message Carry out participle and obtain each lemma;

Cloud server is according to carrying out each lemma after translation translated by the translation word stocks of degree of depth learning algorithm Lemma, and according to the language sight extracted, the lemma after translation is engaged in the dialogue restructuring;

Cloud server is sent to user terminal to the dialogue after restructuring;

Judge user terminal cognition and correction whether to the dialogue after restructuring, if any, then cloud server obtains user By user terminal, recombinant forms is entered by the cognition of dialogue after restructuring and correction, cognition and amendment operation according to user Row is revised, and according to the weights revised in power of amendment Value Data storehouse and jump to response matches unit;Otherwise jump to response Join unit.

In intelligent response system based on degree of depth study of the present invention,

Described response matches unit includes:

The knowledge base knowledge content of answering system organized and build according to the specification of AIML language;Knowledge base is used In carrying out Ontology Query, therefrom obtaining the field ontology library of the upper the next information of described effective word;For utilizing fuzzy matching Method and internal reasoning mechanism select optimum answer from knowledge base.

In intelligent response system based on degree of depth study of the present invention, to response system in described response matches unit The knowledge base that the knowledge content of system carries out organizing and building according to the specification of AIML language includes:

Obtain dialog history initiate information and the answer of history response and for response answer satisfaction value of feedback, Feedback to response answer;

Information of initiating dialog history is analyzed obtaining dialog history and initiates the emotional status of information, the length degree of dialogue And the order arrangement preference of each statement composition in information;

Answer according to history response and for the satisfaction value of feedback of response answer, feedback to response answer, will The answer of history response carries out satisfaction and is arranged in order from high to low, retains ranking history response before default ranking value Answer;

It is analyzed the answer of the ranking of reservation history response before default ranking value obtaining answering of history response The order arrangement preference of each statement composition in case emotional status, the length degree of dialogue and information;

Set up the suitable of each statement composition in emotional status in dialog history initiation information, the length degree of dialogue and information Answer emotional status, the length of dialogue in the answer of the ranking of sequence arrangement preference and reservation history response before default ranking value The multi-to-multi mapping relations of the order arrangement preference of each statement composition in short degree and information, and multi-to-multi mapping relations are set Mapping relations weights;

And dialog history is initiated information and the answer of history response and for response answer satisfaction value of feedback, The feedback information of response answer is organized and according to AIML (Artificial Intelligence Markup Language;Artificial intelligence markup language) language specification build knowledge base.

In intelligent response system based on degree of depth study of the present invention, described semantic acquiring unit passes through the degree of depth The semanteme of voice or Word message that learning algorithm obtains user's input also includes:

Whether the semanteme judging voice that user inputs or Word message is to obtain answer information;As for obtaining answer letter Breath, then the model answer that pre-sets in extracting directly knowledge base also jumps to response display unit, as chat message, Then jump to response matches unit.

In intelligent response system based on degree of depth study of the present invention,

Described semantic acquiring unit obtains answer information, after the model answer pre-set in extracting directly knowledge base Also include according to the order of each statement composition in emotional status, the length degree of dialogue and information in dialog history initiation information Answer emotional status, the length of dialogue in the answer of the ranking of arrangement preference and reservation history response before default ranking value The multi-to-multi mapping relations of the order arrangement preference of each statement composition in degree and information, and multi-to-multi mapping relations are set Mapping relations weights, carry out expression way restructuring, and jump to response display unit model answer information.

The intelligent response system based on degree of depth study that implementing the present invention provides compared with prior art has following useful Effect: obtained voice or the semanteme of Word message of user's input by degree of depth learning algorithm;And utilize response matches unit to use Method of Fuzzy Matching and internal reasoning mechanism select optimum answer from the knowledge base pre-set, it is possible to make answering system pair Higher in the matching degree of user's response.By judging user terminal cognition and correction whether to the dialogue after restructuring, if any, then Cloud server obtains user by user terminal for the cognition of dialogue after restructuring and correction, according to the cognition of user with repair Change operation recombinant forms is modified, and according to the weights revised in power of amendment Value Data storehouse and jump to response matches list Unit so that the dialogue after restructuring more can meet the language performance feature of each user self.Send out by setting up dialog history In the information of rising, in emotional status, the length degree of dialogue and information, the order of each statement composition arranges the ranking of preference and reservation Each statement in answer emotional status, the length degree of dialogue and information in the answer of the history response before default ranking value The multi-to-multi mapping relations of the order arrangement preference of composition, and the mapping relations weights of multi-to-multi mapping relations are set, it is possible to make The optimum answer that must reply not only semantically can meet the demand of user, and expression-form, emotional status, the length of dialogue Short degree can meet the individual demand of user.

Accompanying drawing explanation

Fig. 1 is the intelligent response system architecture diagram based on degree of depth study of the embodiment of the present invention.

Detailed description of the invention

As it is shown in figure 1, a kind of intelligent response system based on degree of depth study, it includes such as lower unit:

Information acquisition unit, for being obtained voice or the Word message of user's input by user terminal, is being believed for voice During breath, it is identified voice messaging being converted to Word message and jumping to semantic acquiring unit, direct when for Word message Jump to semantic acquiring unit.

Semantic acquiring unit, for obtaining voice or the semanteme of Word message of user's input by degree of depth learning algorithm;

Response matches unit, for utilizing Method of Fuzzy Matching and internal reasoning mechanism to select from the knowledge base pre-set Select optimum answer;

Response display unit, shows user for described optimum answer.

Alternatively, in the intelligent response system based on degree of depth study described in the embodiment of the present invention, described semantic acquisition Unit includes:

Server is set up the compound mode weights of each lemma in Word message beyond the clouds, and weights are saved in weights In data base;

Server is set up based on big data translation word stocks beyond the clouds;.

Cloud server receives the Word message sent, and extracts language sight from Word message, and to Word message Carry out participle and obtain each lemma;

Cloud server is according to carrying out each lemma after translation translated by the translation word stocks of degree of depth learning algorithm Lemma, and according to the language sight extracted, the lemma after translation is engaged in the dialogue restructuring;

Cloud server is sent to user terminal to the dialogue after restructuring;

Judge user terminal cognition and correction whether to the dialogue after restructuring, if any, then cloud server obtains user By user terminal, recombinant forms is entered by the cognition of dialogue after restructuring and correction, cognition and amendment operation according to user Row is revised, and according to the weights revised in power of amendment Value Data storehouse and jump to response matches unit;Otherwise jump to response Join unit.

Alternatively, in the intelligent response system based on degree of depth study described in the embodiment of the present invention,

Described response matches unit includes:

The knowledge base knowledge content of answering system organized and build according to the specification of AIML language;Knowledge base is used In carrying out Ontology Query, therefrom obtaining the field ontology library of the upper the next information of described effective word;For utilizing fuzzy matching Method and internal reasoning mechanism select optimum answer from knowledge base.

Alternatively, in the intelligent response system based on degree of depth study described in the embodiment of the present invention, described response matches The knowledge base that in unit, the knowledge content to answering system is organized and built according to the specification of AIML language includes:

Obtain dialog history initiate information and the answer of history response and for response answer satisfaction value of feedback, Feedback to response answer;

Information of initiating dialog history is analyzed obtaining dialog history and initiates the emotional status of information, the length degree of dialogue And the order arrangement preference of each statement composition in information;

Answer according to history response and for the satisfaction value of feedback of response answer, feedback to response answer, will The answer of history response carries out satisfaction and is arranged in order from high to low, retains ranking history response before default ranking value Answer;

It is analyzed the answer of the ranking of reservation history response before default ranking value obtaining answering of history response The order arrangement preference of each statement composition in case emotional status, the length degree of dialogue and information;

Set up the suitable of each statement composition in emotional status in dialog history initiation information, the length degree of dialogue and information Answer emotional status, the length of dialogue in the answer of the ranking of sequence arrangement preference and reservation history response before default ranking value The multi-to-multi mapping relations of the order arrangement preference of each statement composition in short degree and information, and multi-to-multi mapping relations are set Mapping relations weights;

And dialog history is initiated information and the answer of history response and for response answer satisfaction value of feedback, The feedback information of response answer is organized and builds knowledge base according to the specification of AIML language.

Alternatively, in the intelligent response system based on degree of depth study described in the embodiment of the present invention, described semantic acquisition The semanteme of the voice or Word message that obtain user's input by degree of depth learning algorithm in unit also includes:

Whether the semanteme judging voice that user inputs or Word message is to obtain answer information;As for obtaining answer letter Breath, then the model answer that pre-sets in extracting directly knowledge base also jumps to response display unit, as chat message, Then jump to response matches unit.

Alternatively, in the intelligent response system based on degree of depth study described in the embodiment of the present invention,

Described semantic acquiring unit obtains answer information, after the model answer pre-set in extracting directly knowledge base Also include according to the order of each statement composition in emotional status, the length degree of dialogue and information in dialog history initiation information Answer emotional status, the length of dialogue in the answer of the ranking of arrangement preference and reservation history response before default ranking value The multi-to-multi mapping relations of the order arrangement preference of each statement composition in degree and information, and multi-to-multi mapping relations are set Mapping relations weights, carry out expression way restructuring, and jump to response display unit model answer information.

Implement the embodiment of the present invention provide based on the degree of depth study intelligent response system compared with prior art have with Lower beneficial effect: obtained voice or the semanteme of Word message of user's input by degree of depth learning algorithm;And utilize response matches Unit Method of Fuzzy Matching and internal reasoning mechanism select optimum answer from the knowledge base pre-set, it is possible to make response System is higher for the matching degree of user's response.By judging user terminal cognition and correction whether to the dialogue after restructuring, If any, then cloud server obtains user by user terminal for the cognition of dialogue after restructuring and correction, according to user's Recombinant forms is modified by cognitive and amendment operation, and according to the weights revised in power of amendment Value Data storehouse and jump to response Matching unit so that the dialogue after restructuring more can meet the language performance feature of each user self.By setting up history In dialogue initiation information, in emotional status, the length degree of dialogue and information, the order of each statement composition arranges preference and reservation Ranking history response before default ranking value answer in each in answer emotional status, the length degree of dialogue and information The multi-to-multi mapping relations of the order arrangement preference of individual statement composition, and the mapping relations weights of multi-to-multi mapping relations are set, Enable to the optimum answer of response and not only semantically can meet the demand of user, and expression-form, emotional status, right The length degree of words can meet the individual demand of user.

It is understood that for the person of ordinary skill of the art, can conceive according to the technology of the present invention and do Go out other various corresponding changes and deformation, and all these change all should belong to the protection model of the claims in the present invention with deformation Enclose.

Claims (6)

1. an intelligent response system based on degree of depth study, it is characterised in that it includes such as lower unit:
Information acquisition unit, for being obtained voice or the Word message of user's input by user terminal, when for voice messaging, It is identified voice messaging being converted to Word message and jumping to semantic acquiring unit, jumps directly to when for Word message Semantic acquiring unit;
Semantic acquiring unit, for obtaining voice or the semanteme of Word message of user's input by degree of depth learning algorithm;
Response matches unit, for utilizing Method of Fuzzy Matching and internal reasoning mechanism to select from the knowledge base pre-set Good answer;
Response display unit, shows user for described optimum answer.
2. the intelligent response system learnt based on the degree of depth as claimed in claim 1, it is characterised in that described semantic acquiring unit Including:
Server is set up the compound mode weights of each lemma in Word message beyond the clouds, and weights are saved in weight data In storehouse;
Server is set up based on big data translation word stocks beyond the clouds;
Cloud server receives the Word message sent, and extracts language sight from Word message, and carries out Word message Participle obtains each lemma;
Cloud server is according to the word after being translated each lemma by the translation word stocks of degree of depth learning algorithm Unit, and according to the language sight extracted, the lemma after translation is engaged in the dialogue restructuring;
Cloud server is sent to user terminal to the dialogue after restructuring;
Judge user terminal cognition and correction whether to the dialogue after restructuring, if any, then cloud server obtains user and passes through Recombinant forms is repaiied by user terminal for the cognition of dialogue after restructuring and correction, cognition and amendment operation according to user Just, and according to the weights revised in power of amendment Value Data storehouse and jump to response matches unit;Otherwise jump to response matches list Unit.
3. the intelligent response system learnt based on the degree of depth as claimed in claim 2, it is characterised in that
Described response matches unit includes:
The knowledge base knowledge content of answering system organized and build according to the specification of AIML language;Knowledge base be used for into Row Ontology Query, therefrom obtain the field ontology library of the upper the next information of described effective word;For the method utilizing fuzzy matching And internal reasoning mechanism selects optimum answer from knowledge base.
4. the intelligent response system learnt based on the degree of depth as claimed in claim 3, it is characterised in that described response matches unit In the knowledge base the knowledge content of answering system being organized and builds according to the specification of AIML language include:
Obtain dialog history and initiate information and the answer of history response and for the satisfaction value of feedback of response answer, correspondence The feedback of answer;
To dialog history initiate information be analyzed obtain dialog history initiate the emotional status of information, the length degree of dialogue and The order arrangement preference of each statement composition in information;
Answer according to history response and for the satisfaction value of feedback of response answer, feedback to response answer, by history The answer of response carries out satisfaction and is arranged in order from high to low, retains answering of ranking history response before default ranking value Case;
The answer of the ranking of reservation history response before default ranking value is analyzed obtaining the answer feelings of history response The order arrangement preference of each statement composition in thread situation, the length degree of dialogue and information;
Set up the order row of each statement composition in emotional status in dialog history initiation information, the length degree of dialogue and information Answer emotional status, the length degree of dialogue in the answer of the ranking of row preference and reservation history response before default ranking value And the multi-to-multi mapping relations of the order arrangement preference of each statement composition in information, and reflecting of multi-to-multi mapping relations is set Penetrate relation weights;
And dialog history is initiated information and the answer of history response and for the satisfaction value of feedback of response answer, correspondence The feedback information of answer carries out organizing and building knowledge base according to the specification of AIML language.
5. the intelligent response system learnt based on the degree of depth as claimed in claim 4, it is characterised in that described semantic acquiring unit In obtain the voice of user's input by degree of depth learning algorithm or the semanteme of Word message also includes:
Whether the semanteme judging voice that user inputs or Word message is to obtain answer information;As for obtaining answer information, then The model answer that pre-sets in extracting directly knowledge base also jumps to response display unit, as chat message, then jump Forward response matches unit to.
6. the intelligent response system learnt based on the degree of depth as claimed in claim 5, it is characterised in that
Described semantic acquiring unit obtains answer information, also wraps after the model answer pre-set in extracting directly knowledge base Include according to the order arrangement of each statement composition in emotional status, the length degree of dialogue and information in dialog history initiation information Answer emotional status in the answer of the ranking of preference and reservation history response before default ranking value, dialogue length degree with And the multi-to-multi mapping relations of the order arrangement preference of each statement composition in information, and the mapping of multi-to-multi mapping relations is set Relation weights, carry out expression way restructuring, and jump to response display unit model answer information.
CN201610510464.6A 2016-07-01 2016-07-01 A kind of intelligent response system based on deep learning CN106202301B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610510464.6A CN106202301B (en) 2016-07-01 2016-07-01 A kind of intelligent response system based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610510464.6A CN106202301B (en) 2016-07-01 2016-07-01 A kind of intelligent response system based on deep learning

Publications (2)

Publication Number Publication Date
CN106202301A true CN106202301A (en) 2016-12-07
CN106202301B CN106202301B (en) 2019-10-08

Family

ID=57462912

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610510464.6A CN106202301B (en) 2016-07-01 2016-07-01 A kind of intelligent response system based on deep learning

Country Status (1)

Country Link
CN (1) CN106202301B (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106550156A (en) * 2017-01-23 2017-03-29 苏州咖啦魔哆信息技术有限公司 A kind of artificial intelligence's customer service system and its implementation based on speech recognition
CN106649786A (en) * 2016-12-28 2017-05-10 北京百度网讯科技有限公司 Deep question answer-based answer retrieval method and device
CN106815321A (en) * 2016-12-27 2017-06-09 深圳前海勇艺达机器人有限公司 Chat method and device based on intelligent chat robots
CN106951558A (en) * 2017-03-31 2017-07-14 广东睿盟计算机科技有限公司 A kind of data processing method of the tax intelligent consulting platform based on deep search
CN107068145A (en) * 2016-12-30 2017-08-18 中南大学 Speech evaluating method and system
CN107135247A (en) * 2017-02-16 2017-09-05 江苏南大电子信息技术股份有限公司 A kind of service system and method for the intelligent coordinated work of person to person's work
CN107403619A (en) * 2017-06-30 2017-11-28 武汉泰迪智慧科技有限公司 A kind of sound control method and system applied to bicycle environment
CN107562856A (en) * 2017-08-28 2018-01-09 深圳追科技有限公司 A kind of self-service customer service system and method
CN107579910A (en) * 2017-10-16 2018-01-12 人物互联网(北京)有限公司 Automatic answering system and method in a kind of instant messaging scene
CN107657949A (en) * 2017-04-14 2018-02-02 深圳市人马互动科技有限公司 The acquisition methods and device of game data
CN108255956A (en) * 2017-12-21 2018-07-06 北京声智科技有限公司 The method and system of dictionary are adaptively obtained based on historical data and machine learning
CN108418744A (en) * 2018-02-06 2018-08-17 国网浙江省电力有限公司信息通信分公司 A kind of electronics seat system for promoting electrical power services quality
WO2018195875A1 (en) * 2017-04-27 2018-11-01 Microsoft Technology Licensing, Llc Generating question-answer pairs for automated chatting
CN108806671A (en) * 2018-05-29 2018-11-13 杭州认识科技有限公司 Semantic analysis, device and electronic equipment
CN109299237A (en) * 2018-09-26 2019-02-01 苏州大学 Recirculating network interactive method based on actor reviewer's nitrification enhancement
CN109726002A (en) * 2018-12-30 2019-05-07 联想(北京)有限公司 A kind of process flow method of adjustment and device
CN109788367A (en) * 2018-11-30 2019-05-21 北京达佳互联信息技术有限公司 A kind of information cuing method, device, electronic equipment and storage medium
CN109935342A (en) * 2017-12-15 2019-06-25 北京医联蓝卡在线科技有限公司 A kind of family doctor assistant's help system and method
CN110085316A (en) * 2019-05-11 2019-08-02 北京康健数字化健康管理研究院 A kind of hypertension question answering system and its system method for building up based on deep learning
CN110351441A (en) * 2018-04-03 2019-10-18 北京智合大方科技有限公司 The assistant that attends a banquet is sold based on the smart phone of Real-time speech recognition and natural language processing technique
CN110931009A (en) * 2019-12-12 2020-03-27 贵州电力交易中心有限责任公司 System for rapidly improving conversation capacity of reception robot in electric power transaction hall
CN111200684A (en) * 2018-10-31 2020-05-26 永德利硅橡胶科技(深圳)有限公司 Language translation terminal and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968409A (en) * 2012-11-23 2013-03-13 海信集团有限公司 Intelligent human-machine interaction semantic analysis method and interaction system
CN103268313A (en) * 2013-05-21 2013-08-28 北京云知声信息技术有限公司 Method and device for semantic analysis of natural language
CN104462064A (en) * 2014-12-15 2015-03-25 陈包容 Method and system for prompting content input in information communication of mobile terminals
CN105630917A (en) * 2015-12-22 2016-06-01 成都小多科技有限公司 Intelligent answering method and intelligent answering device
CN105677913A (en) * 2016-02-29 2016-06-15 哈尔滨工业大学 Machine translation-based construction method for Chinese semantic knowledge base
CN105678324A (en) * 2015-12-31 2016-06-15 上海智臻智能网络科技股份有限公司 Similarity calculation-based questions and answers knowledge base establishing method, device and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968409A (en) * 2012-11-23 2013-03-13 海信集团有限公司 Intelligent human-machine interaction semantic analysis method and interaction system
CN103268313A (en) * 2013-05-21 2013-08-28 北京云知声信息技术有限公司 Method and device for semantic analysis of natural language
CN104462064A (en) * 2014-12-15 2015-03-25 陈包容 Method and system for prompting content input in information communication of mobile terminals
CN105630917A (en) * 2015-12-22 2016-06-01 成都小多科技有限公司 Intelligent answering method and intelligent answering device
CN105678324A (en) * 2015-12-31 2016-06-15 上海智臻智能网络科技股份有限公司 Similarity calculation-based questions and answers knowledge base establishing method, device and system
CN105677913A (en) * 2016-02-29 2016-06-15 哈尔滨工业大学 Machine translation-based construction method for Chinese semantic knowledge base

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815321A (en) * 2016-12-27 2017-06-09 深圳前海勇艺达机器人有限公司 Chat method and device based on intelligent chat robots
CN106649786A (en) * 2016-12-28 2017-05-10 北京百度网讯科技有限公司 Deep question answer-based answer retrieval method and device
US10606915B2 (en) 2016-12-28 2020-03-31 Beijing Baidu Netcom Science And Technology Co., Ltd. Answer searching method and device based on deep question and answer
CN106649786B (en) * 2016-12-28 2020-04-07 北京百度网讯科技有限公司 Answer retrieval method and device based on deep question answering
CN107068145A (en) * 2016-12-30 2017-08-18 中南大学 Speech evaluating method and system
CN106550156A (en) * 2017-01-23 2017-03-29 苏州咖啦魔哆信息技术有限公司 A kind of artificial intelligence's customer service system and its implementation based on speech recognition
CN107135247A (en) * 2017-02-16 2017-09-05 江苏南大电子信息技术股份有限公司 A kind of service system and method for the intelligent coordinated work of person to person's work
CN107135247B (en) * 2017-02-16 2019-11-29 江苏南大电子信息技术股份有限公司 A kind of service system and method for the intelligent coordinated work of person to person's work
CN106951558A (en) * 2017-03-31 2017-07-14 广东睿盟计算机科技有限公司 A kind of data processing method of the tax intelligent consulting platform based on deep search
CN106951558B (en) * 2017-03-31 2020-06-12 广东睿盟计算机科技有限公司 Data processing method of tax intelligent consultation platform based on deep search
CN107657949A (en) * 2017-04-14 2018-02-02 深圳市人马互动科技有限公司 The acquisition methods and device of game data
WO2018195875A1 (en) * 2017-04-27 2018-11-01 Microsoft Technology Licensing, Llc Generating question-answer pairs for automated chatting
CN107403619A (en) * 2017-06-30 2017-11-28 武汉泰迪智慧科技有限公司 A kind of sound control method and system applied to bicycle environment
CN107562856A (en) * 2017-08-28 2018-01-09 深圳追科技有限公司 A kind of self-service customer service system and method
CN107579910A (en) * 2017-10-16 2018-01-12 人物互联网(北京)有限公司 Automatic answering system and method in a kind of instant messaging scene
CN109935342A (en) * 2017-12-15 2019-06-25 北京医联蓝卡在线科技有限公司 A kind of family doctor assistant's help system and method
CN108255956A (en) * 2017-12-21 2018-07-06 北京声智科技有限公司 The method and system of dictionary are adaptively obtained based on historical data and machine learning
CN108418744A (en) * 2018-02-06 2018-08-17 国网浙江省电力有限公司信息通信分公司 A kind of electronics seat system for promoting electrical power services quality
CN110351441A (en) * 2018-04-03 2019-10-18 北京智合大方科技有限公司 The assistant that attends a banquet is sold based on the smart phone of Real-time speech recognition and natural language processing technique
CN108806671A (en) * 2018-05-29 2018-11-13 杭州认识科技有限公司 Semantic analysis, device and electronic equipment
CN108806671B (en) * 2018-05-29 2019-06-28 杭州认识科技有限公司 Semantic analysis, device and electronic equipment
CN109299237A (en) * 2018-09-26 2019-02-01 苏州大学 Recirculating network interactive method based on actor reviewer's nitrification enhancement
CN109299237B (en) * 2018-09-26 2020-06-16 苏州大学 Cyclic network man-machine conversation method based on actor critic reinforcement learning algorithm
CN111200684A (en) * 2018-10-31 2020-05-26 永德利硅橡胶科技(深圳)有限公司 Language translation terminal and method
CN109788367A (en) * 2018-11-30 2019-05-21 北京达佳互联信息技术有限公司 A kind of information cuing method, device, electronic equipment and storage medium
CN109726002A (en) * 2018-12-30 2019-05-07 联想(北京)有限公司 A kind of process flow method of adjustment and device
CN110085316A (en) * 2019-05-11 2019-08-02 北京康健数字化健康管理研究院 A kind of hypertension question answering system and its system method for building up based on deep learning
CN110931009A (en) * 2019-12-12 2020-03-27 贵州电力交易中心有限责任公司 System for rapidly improving conversation capacity of reception robot in electric power transaction hall

Also Published As

Publication number Publication date
CN106202301B (en) 2019-10-08

Similar Documents

Publication Publication Date Title
US20200204505A1 (en) Predictive messaging for computer-implemented devices
KR102050334B1 (en) Automatic suggestion responses to images received in messages, using the language model
US10262195B2 (en) Predictive and responsive video analytics system and methods
US10134391B2 (en) System and method for dynamic ASR based on social media
CN105591882B (en) A kind of intelligence machine person to person mixes the method and system of customer service
US9077804B2 (en) Interaction management
US9253320B2 (en) Implementing a network of intelligent virtual service agents to provide personalized automated responses
CN106133825B (en) Broad sense phrase in automatic speech recognition system
US9760565B2 (en) Natural expression processing method, processing and response method, device, and system
JP2017091535A (en) Electronic conference system
US10096316B2 (en) Sharing intents to provide virtual assistance in a multi-person dialog
KR20200129182A (en) Automated assistant invocation of appropriate agent
US20160378854A1 (en) System and method for supporting natural language queries and requests against a user's personal data cloud
US8411841B2 (en) Real-time agent assistance
US7487095B2 (en) Method and apparatus for managing user conversations
CN103080927B (en) Automatic route using Search Results
US7933399B2 (en) System and method for utilizing virtual agents in an interactive voice response application
DE102013212215A1 (en) System and method for determining expertise through speech analysis
US9148394B2 (en) Systems and methods for user interface presentation of virtual agent
US6346952B1 (en) Method and apparatus for summarizing previous threads in a communication-center chat session
JP2018063699A (en) Management of electronic meetings using artificial intelligence and meeting rules templates
US9426289B2 (en) Techniques for topical customer service menu reconfiguration based on social media
US9866693B2 (en) System and method for monitoring progress of automated chat conversations
US10038787B2 (en) System and method for managing and transitioning automated chat conversations
CN105261362B (en) A kind of call voice monitoring method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20200428

Address after: 430000 Room 302, building 42, No. 349, Guanshan Avenue, Hongshan District, Wuhan City, Hubei Province

Patentee after: Liu Lijun

Address before: 430000 A5, North 999, hi tech Avenue, East Lake New Technology Development Zone, Wuhan, Hubei 2-509, China

Patentee before: WUHAN TIPDM INTELLIGENT TECHNOLOGY Co.,Ltd.