CN106484801B - A kind of dialogue method and its knowledge base management system of intelligent customer service robot - Google Patents

A kind of dialogue method and its knowledge base management system of intelligent customer service robot Download PDF

Info

Publication number
CN106484801B
CN106484801B CN201610842401.0A CN201610842401A CN106484801B CN 106484801 B CN106484801 B CN 106484801B CN 201610842401 A CN201610842401 A CN 201610842401A CN 106484801 B CN106484801 B CN 106484801B
Authority
CN
China
Prior art keywords
question
answer
association
visitor
degree
Prior art date
Application number
CN201610842401.0A
Other languages
Chinese (zh)
Other versions
CN106484801A (en
Inventor
刘楚
李稀敏
蔡振华
刘晓葳
肖龙源
朱敬华
王宇
Original Assignee
厦门快商通科技股份有限公司
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 厦门快商通科技股份有限公司 filed Critical 厦门快商通科技股份有限公司
Priority to CN201610842401.0A priority Critical patent/CN106484801B/en
Publication of CN106484801A publication Critical patent/CN106484801A/en
Application granted granted Critical
Publication of CN106484801B publication Critical patent/CN106484801B/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2458Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462Approximate or statistical queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/242Query formulation
    • G06F16/2423Interactive query statement specification based on a database schema

Abstract

The invention discloses the dialogue methods and its knowledge base management system of a kind of intelligent customer service robot, it passes through preset one group or more in knowledge base of question and answer pair, and count the degree of association between each group question and answer pair, then the problem of being proposed according to visitor carries out corresponding question and answer pair in lookup knowledge base, the answer of the question and answer centering is provided to visitor, and further the question and answer to as basic question and answer pair, according to the degree of association between each group question and answer pair counted, the basic question and answer are provided to the related question of corresponding association question and answer centering to visitor;To greatly improve communication efficiency, using the big data and algorithm management of knowledge base, user is assisted to obtain faster desired as a result, user experience is more preferable.

Description

A kind of dialogue method and its knowledge base management system of intelligent customer service robot
Technical field
The present invention relates to field of communication technology, the dialogue method of especially a kind of intelligent customer service robot and its knowledge depositary management Reason system.
Background technique
As internet and the popularization and application of e-commerce, intelligent customer service are also more and more.Intelligent customer service is extensive The Industry-oriented application to grow up on the basis of knowledge processing, it is related to extensive Knowledge Processing Technology, natural language reason Solution technology, Knowledge Management Technology, automatically request-answering system, inference technology etc. have industry universal, and only enterprise does not provide Fine granularity Knowledge Management Technology, the communication also between enterprise and mass users establish a kind of fast having based on natural language The technological means of effect;Statistical analysis information needed for fine-grained management can also being provided for enterprise simultaneously.
Major part intelligent customer service is all based on the application of big data Knowledge Processing Technology at present, i.e., in advance by required data It is stored in knowledge base, in intelligent customer service work, goes to read the knowledge stored in knowledge base at any time, after reading existing knowledge Visitor is fed back to, the dialogue mode of question-response formula is taken.Current this mode has the following deficiencies:
1. user experience effect is general, dialogue mode is fixed, more stiff;
2. inefficient, intelligent customer service requires visitor every time and initiates problem dialogue just activation, then retrieval knowledge library into Row is corresponding to answer, and when visitor, which suspends, to be putd question to, intelligent customer service is then constantly in wait state;
3. when visitor is to the logic of oneself or is not intended to be apparent, entire consultation process by the very inefficient of change, Long period.
Summary of the invention
The present invention is to solve the above problems, provide the dialogue method and its knowledge base management of a kind of intelligent customer service robot The problem of system can not only be visitor furnish an answer, additionally it is possible to according to carrying out offer related question, pole the problem of visitor Big improves communication efficiency, has saved a large amount of time, and user experience is more preferable.
To achieve the above object, the technical solution adopted by the present invention are as follows:
A kind of dialogue method of intelligent customer service robot comprising following steps:
10) preset one group or more of the question and answer pair in knowledge base, every group of question and answer are to by least one problem and corresponding one A answer is constituted;
20) degree of association between each group question and answer pair is counted, two groups of associated question and answer are to including: by least one basic problem The basic question and answer pair constituted with corresponding one basic answer, are associated with answer structure with corresponding one by least one related question At association question and answer pair;And every group of basic question and answer are to the association question and answer pair including one group or more;
30) the problem of being proposed according to visitor carries out corresponding question and answer pair in lookup knowledge base, and provides the question and answer to visitor The answer of centering;
40) by the question and answer in the step 30) to each as basic question and answer pair, and according to what is counted in the step 20) The degree of association between group question and answer pair provides the basic question and answer found in the step 30) to visitor and asks corresponding association Related question in answering questions, return step 30).
Preferably, in the step 10), every group of question and answer are to including more than one Similar Problems, each Similar Problems It has the same meaning and corresponds to identical answer.
Preferably, it in the step 30), is asked the problem of visitor receives provided answer, and visitor proposes with this When the problems in answering questions not identical, then the problem of proposing visitor, is stored as one of the Similar Problems of the question and answer centering.
Preferably, in the step 20), the degree of association between each group question and answer pair is counted, is referred to each complete right Words process is as a statistical unit, by the related question and answer interacted between visitor and customer service robot to progress statistical correlation Degree.
Preferably, statistical correlation degree further includes steps of
21) for every group of associated basic question and answer to be associated with question and answer to one initial association value of imparting;
22) the initial association value is updated according to the clicking rate of related question:
When visitor clicks related question provided by customer service robot, then carry out enhancing association corresponding to the related question The degree of association between question and answer pair and basic question and answer pair increases the initial association value;
For other related questions not clicked, then carry out reducing association question and answer pair corresponding to the related question with The degree of association between basic question and answer pair, reduces the initial association value.
Preferably, in the step 30), the problem of being proposed according to visitor, carries out corresponding question and answer in lookup knowledge base Right, the problem of being by proposing to visitor, extracts key message, and is searched and matched knowledge according to the key message In library corresponding question and answer to the problems in.
Preferably, in the step 40), when providing related question to visitor, yet further still according to each related question Degree of association size between corresponding association question and answer pair and basic question and answer pair is ranked up, the bigger related question row of the degree of association In more front, the smaller related question of the degree of association is come more below.
In addition, the present invention also provides a kind of knowledge base management systems of intelligent customer service robot comprising:
Knowledge base, preset one group or more of question and answer pair in the knowledge base, every group of question and answer are to by least one problem and right The answer answered is constituted;
Degree of association statistical module, for counting the degree of association between each group question and answer pair, two groups of associated question and answer to include: by The basic question and answer pair that at least one basic problem and a corresponding basic answer are constituted, by least one related question and correspondence One association answer constitute association question and answer pair;And every group of basic question and answer are to the association question and answer pair including one group or more;
Visitor's session module, the problem of being proposed according to visitor, carry out corresponding question and answer pair in lookup knowledge base, and to visit Visitor provides the answer of the question and answer centering;
Related question recommending module, by the question and answer in visitor's session module to as basic question and answer pair, and according to The degree of association between each group question and answer pair counted in the degree of association statistical module provides in visitor's session module to visitor Related question of the basic question and answer found to corresponding association question and answer centering.
Preferably, the degree of association statistical module carries out the degree of association between statistics each group question and answer pair, refers to each Full dialog process is as a statistical unit, by the related question and answer interacted between visitor and customer service robot to uniting Count the degree of association.
Preferably, when the related question recommending module provides related question to visitor, yet further still according to each association Degree of association size between association question and answer pair and basic question and answer pair corresponding to problem is ranked up, and the bigger association of the degree of association is asked Topic comes more front, and the smaller related question of the degree of association comes more below.
The beneficial effects of the present invention are:
1. the present invention not only provides the answer of proposed problem to visitor, yet further still according to proposition problem provided Related question improves communication efficiency, using the big data and algorithm management of knowledge base, user is assisted to obtain desired knot faster Fruit;
2. knowledge base of the invention carries out data management in the form of question and answer pair, and is associated between every group of question and answer pair Processing, so that the management of knowledge base is more intelligent;
3. the same answer of every group of question and answer pair of the invention can correspond to multiple Similar Problems, so that data management is more square Just, and make data call more flexible;
4. the present invention is associated using each full dialog process as a statistical unit between each group question and answer pair The statistics of degree can greatly simplify algorithm, improve computational efficiency;
5. the present invention is constantly updated and is optimized degree of association information also according to the clicking rate of related question, so that knowledge base Association structure be continuously available optimization, and make recommended related question more accurate, user experience is more preferable.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of general flow chart of the dialogue method of intelligent customer service robot of the present invention;
Fig. 2 is a kind of structural schematic diagram figure of the knowledge base of intelligent customer service robot of the present invention;
Fig. 3 is a kind of structural schematic diagram of the knowledge base management system of intelligent customer service robot of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below Closing accompanying drawings and embodiments, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used To explain the present invention, it is not intended to limit the present invention.
As depicted in figs. 1 and 2, a kind of dialogue method of intelligent customer service robot of the invention comprising following steps:
10) preset one group or more of the question and answer pair in knowledge base, every group of question and answer are to by least one problem and corresponding one A answer is constituted;
20) degree of association between each group question and answer pair is counted, two groups of associated question and answer are to including: by least one basic problem The basic question and answer pair constituted with corresponding one basic answer, are associated with answer structure with corresponding one by least one related question At association question and answer pair;And every group of basic question and answer are to the association question and answer pair including one group or more;
30) the problem of being proposed according to visitor carries out corresponding question and answer pair in lookup knowledge base, and provides the question and answer to visitor The answer of centering;
40) by the question and answer in the step 30) to each as basic question and answer pair, and according to what is counted in the step 20) The degree of association between group question and answer pair provides the basic question and answer found in the step 30) to visitor and asks corresponding association Related question in answering questions, return step 30).
Such as:
What symptom does visitor: being pregnant have?
Customer service robot: pregnancy initial stage has fatigue, dizziness, without symptoms such as appetite, emotional labilities.
(while robot recommends following related question to visitor after the extraction of problem, calculating automatically)
Whether you also want to ask following problems:
1, how to determine that oneself is pregnant?
2, what if is unwanted pregnancy?
Which points for attention does 3, pregnant woman have?
4, the women and children hospital which nearby has well-known?
5、……
If having the problem of visitor wants to know about in the related question recommended, visitor can click directly on problem, thus quickly Obtain the answer of customer service robot, meanwhile, intelligent customer service robot continues to provide related question according to the selection of visitor, one It is solved until the problem of visitor.
In the step 10), to including more than one Similar Problems, each Similar Problems have identical every group of question and answer Meaning and corresponding identical answer.
Due to the extensive knowledge and profound scholarship and personal habits of Chinese, same a word can there are many expression ways, such as:
Similar Problems 1, how old are you?
Similar Problems 2, your at much ages in this year?
Similar Problems 3, you how old?
Similar Problems 4, you be which year birth?
Similar Problems 5, your your honourable age in this year?
Similar Problems 6, you be 20 years old?
The above Similar Problems can be answered with a common answer, such as: my in 25 years old this year.
Above-mentioned Similar Problems 1 to Similar Problems 6 and corresponding common answer constitute one group of question and answer pair.
In the step 20), the degree of association between each group question and answer pair is counted, is referred to each full dialog process work For a statistical unit, by the related question and answer interacted between visitor and customer service robot to carrying out statistical correlation degree.
For example, visitor is as follows the problem of asked in primary complete conversation procedure:
What symptom does related question 1, being pregnant have?
How does related question 2 determine that oneself is pregnant?
What if are related question 3, unwanted pregnancy?
Related question 4, the women and children hospital which nearby has well-known?
Related question 5, which archiater of the hospital?
Will does related question 6 go to this hospital be how to get to?
Customer service robot is using the above dialog procedure as a statistical unit, by what is interacted between visitor and customer service robot The above related question 1 to 6 is associated processing to statistical correlation degree is carried out by related question and answer.
Meanwhile associated related question further also is generated to each, relating value is marked, such as:
Visitor has asked " what symptom has been pregnant has " then asks " how determining that oneself is pregnant ", then between both of these problems The degree of association increase a numerical value.
In the present embodiment, statistical correlation degree is further included steps of
21) for every group of associated basic question and answer to be associated with question and answer to one initial association value of imparting;
22) the initial association value is updated according to the clicking rate of related question:
When visitor clicks related question provided by customer service robot, then carry out enhancing association corresponding to the related question The degree of association between question and answer pair and basic question and answer pair increases the initial association value;
For other related questions not clicked, then carry out reducing association question and answer pair corresponding to the related question with The degree of association between basic question and answer pair, reduces the initial association value.
In the present embodiment, the relating value is additionally provided with boundary, when the relating value of association question and answer pair is greater than or equal to the boundary In limited time, then recommend the association question and answer to corresponding related question to visitor;When the relating value of association question and answer pair is less than the boundary In limited time, then do not recommend the association question and answer to corresponding related question to visitor.
Such as:
What symptom does visitor: being pregnant have?
Customer service robot recommends following related question (assuming that the parameter of default while answering a question, to visitor Boundary for relating value is 30, then the related question by relating value more than or equal to 30 recommends visitor, while pressing numerical values recited It is ranked up, or is arranged and recommends 3 related questions as follows since being associated with angle value highest:
Related question a, how to determine that oneself is pregnant? (association angle value 50)
What if are related question b, unwanted pregnancy? (association angle value 40)
Related question c, the women and children hospital which nearby has well-known? (association angle value 30)
After visitor clicks the related question of system recommendation, illustrate that the related question of this recommendation meets the consulting meaning of visitor Relating value between the upper problem of the related question and visitor is continued to reinforce by figure, simultaneity factor.So long-term circulation, so that The accuracy of recommendation problem is higher and higher.Similarly, the lower related question of visitor's clicking rate, also can be with the association of other problems Angle value increases, and gradually reduces sequence, until being no longer present in related question list.
In the step 30), it is to pass through that the problem of being proposed according to visitor, which carries out corresponding question and answer pair in lookup knowledge base, The problem of proposing to visitor extracts key message, and according to the key message is searched and matched and is corresponding in knowledge base Question and answer to the problems in.Also, when visitor receive provided by answer, and visitor propose the problem of with the question and answer to the problems in When not identical, then the problem of proposing visitor, is stored as one of the Similar Problems of the question and answer centering.
In the step 40), when providing related question to visitor, yet further still according to corresponding to each related question Degree of association size between association question and answer pair and basic question and answer pair is ranked up, before the bigger related question of the degree of association comes more Face, the smaller related question of the degree of association come more below.
As shown in figure 3, the present invention also provides a kind of knowledge base management systems of intelligent customer service robot comprising:
Knowledge base, preset one group or more of question and answer pair in the knowledge base, every group of question and answer are to by least one problem and right The answer answered is constituted;
Degree of association statistical module, for counting the degree of association between each group question and answer pair, two groups of associated question and answer to include: by The basic question and answer pair that at least one basic problem and a corresponding basic answer are constituted, by least one related question and correspondence One association answer constitute association question and answer pair;And every group of basic question and answer are to the association question and answer pair including one group or more;
Visitor's session module, the problem of being proposed according to visitor, carry out corresponding question and answer pair in lookup knowledge base, and to visit Visitor provides the answer of the question and answer centering;
Related question recommending module, by the question and answer in visitor's session module to as basic question and answer pair, and according to The degree of association between each group question and answer pair counted in the degree of association statistical module provides in visitor's session module to visitor Related question of the basic question and answer found to corresponding association question and answer centering.
The degree of association statistical module carries out the degree of association between statistics each group question and answer pair, refers to each full dialog Process is as a statistical unit, by the related question and answer interacted between visitor and customer service robot to progress statistical correlation Degree.
It is right yet further still according to each related question institute when the related question recommending module provides related question to visitor The degree of association size between association question and answer pair and basic question and answer pair answered is ranked up, and the bigger related question of the degree of association comes more Front, the smaller related question of the degree of association come more below.
Using dialogue method and knowledge base management system of the invention, when visitor and intelligent customer service robot are in dialogue When, visitor proposes problem, and then intelligent customer service robot reads problem, and pre- in knowledge base after extraction, analysis, calculating The problem of setting is compared, and extracts the corresponding answer of the problem, then answers the problem of visitor is proposed.Meanwhile it will be after calculating Visitor's problem be compared with the data in knowledge base, find data problem in knowledge base and visitor mentioned when comparing When problem is related question, the related question in knowledge base is recommended into visitor automatically, visitor can click directly on the pass of recommendation Connection problem greatly improves communication efficiency to faster obtain the problem of wanting consulting answer.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since it is basically similar to the method embodiment, so being described relatively simple, related place referring to The explanation of embodiment of the method.Also, herein, the terms "include", "comprise" or its any other variant are intended to contain Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or equipment including the element.In addition, the common skill in this field Art personnel are understood that all or part of the steps of realization above-described embodiment may be implemented by hardware, and can also pass through program The relevant hardware is instructed to complete, the program can store in a kind of computer readable storage medium, mentioned above Storage medium can be read-only memory, disk or CD etc..
The preferred embodiment of the present invention has shown and described in above description, it should be understood that the present invention is not limited to this paper institute The form of disclosure, should not be regarded as an exclusion of other examples, and can be used for other combinations, modifications, and environments, and energy Enough in this paper invented the scope of the idea, modifications can be made through the above teachings or related fields of technology or knowledge.And people from this field The modifications and changes that member is carried out do not depart from the spirit and scope of the present invention, then all should be in the protection of appended claims of the present invention In range.

Claims (7)

1. a kind of dialogue method of intelligent customer service robot, which comprises the following steps:
10) preset one group or more of the question and answer pair in knowledge base, every group of question and answer are answered by least one problem and corresponding one Case is constituted;
20) degree of association between each group question and answer pair is counted, two groups of associated question and answer are to including: by least one basic problem and right The basic question and answer pair that the basic answer of one answered is constituted, are associated with what answer was constituted by least one related question with corresponding one It is associated with question and answer pair;And every group of basic question and answer are to the association question and answer pair including one group or more;
30) the problem of being proposed according to visitor carries out corresponding question and answer pair in lookup knowledge base, and provides the question and answer centering to visitor Answer;
40) question and answer in the step 30) are asked as basic question and answer pair, and according to each group counted in the step 20) The degree of association between answering questions provides the basic question and answer found in the step 30) to corresponding association question and answer pair to visitor In related question, return step 30);
In the step 20), the degree of association between each group question and answer pair is counted, is referred to using each full dialog process as one A statistical unit, by the related question and answer interacted between visitor and customer service robot to progress statistical correlation degree;
Statistical correlation degree further includes steps of
21) for every group of associated basic question and answer to be associated with question and answer to one initial association value of imparting;
22) the initial association value is updated according to the clicking rate of related question:
When visitor clicks related question provided by customer service robot, then carry out enhancing association question and answer corresponding to the related question To the degree of association between basic question and answer pair, increase the initial association value;
For other related questions not clicked, then carry out reducing association question and answer pair corresponding to the related question and basic The degree of association between question and answer pair reduces the initial association value.
2. a kind of dialogue method of intelligent customer service robot according to claim 1, it is characterised in that: the step 10) in, to including more than one Similar Problems, each Similar Problems have the same meaning and correspond to identical every group of question and answer Answer.
3. a kind of dialogue method of intelligent customer service robot according to claim 2, it is characterised in that: the step 30) in, when visitor receive provided by answer, and visitor propose the problem of with the question and answer to the problems in it is not identical when, then will The problem of visitor proposes is stored as one of the Similar Problems of the question and answer centering.
4. a kind of dialogue method of intelligent customer service robot according to claim 1, it is characterised in that: the step 30) in, the problem of the problem of being proposed according to visitor carries out corresponding question and answer pair in lookup knowledge base, is by proposing to visitor into Row extracts key message, and according to the key message searched and matched in knowledge base corresponding question and answer to the problems in.
5. a kind of dialogue method of intelligent customer service robot according to claim 1, it is characterised in that: the step 40) in, to visitor provide related question when, yet further still according to association question and answer pair corresponding to each related question with ask substantially Degree of association size between answering questions is ranked up, and the bigger related question of the degree of association comes more front, the smaller association of the degree of association Problem comes more below.
6. a kind of knowledge base management system of intelligent customer service robot characterized by comprising
Knowledge base, preset one group or more of question and answer pair in the knowledge base, every group of question and answer are to by least one problem and corresponding One answer is constituted;
Degree of association statistical module, for counting the degree of association between each group question and answer pair, two groups of associated question and answer are to including: by least The basic question and answer pair that one basic problem and a corresponding basic answer are constituted, by least one related question and corresponding one The association question and answer pair that a association answer is constituted;And every group of basic question and answer are to the association question and answer pair including one group or more;
Visitor's session module, the problem of being proposed according to visitor, carry out corresponding question and answer pair in lookup knowledge base, and mention to visitor For the answer of the question and answer centering;
Related question recommending module, by the question and answer in visitor's session module to as basic question and answer pair, and according to described The degree of association between each group question and answer pair counted in degree of association statistical module is provided in visitor's session module to visitor and is searched Related question of the basic question and answer arrived to corresponding association question and answer centering;
The degree of association statistical module carries out the degree of association between statistics each group question and answer pair, refers to each full dialog process As a statistical unit, by the related question and answer interacted between visitor and customer service robot to progress statistical correlation degree;
Statistical correlation degree further includes steps of
21) for every group of associated basic question and answer to be associated with question and answer to one initial association value of imparting;
22) the initial association value is updated according to the clicking rate of related question:
When visitor clicks related question provided by customer service robot, then carry out enhancing association question and answer corresponding to the related question To the degree of association between basic question and answer pair, increase the initial association value;
For other related questions not clicked, then carry out reducing association question and answer pair corresponding to the related question and basic The degree of association between question and answer pair reduces the initial association value.
7. a kind of knowledge base management system of intelligent customer service robot according to claim 6, it is characterised in that: the pass When connection question recommending module provides related question to visitor, yet further still according to association question and answer pair corresponding to each related question Degree of association size between basic question and answer pair is ranked up, and the bigger related question of the degree of association comes more front, the degree of association and gets over Small related question comes more below.
CN201610842401.0A 2016-09-23 2016-09-23 A kind of dialogue method and its knowledge base management system of intelligent customer service robot CN106484801B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610842401.0A CN106484801B (en) 2016-09-23 2016-09-23 A kind of dialogue method and its knowledge base management system of intelligent customer service robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610842401.0A CN106484801B (en) 2016-09-23 2016-09-23 A kind of dialogue method and its knowledge base management system of intelligent customer service robot

Publications (2)

Publication Number Publication Date
CN106484801A CN106484801A (en) 2017-03-08
CN106484801B true CN106484801B (en) 2019-10-11

Family

ID=58268769

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610842401.0A CN106484801B (en) 2016-09-23 2016-09-23 A kind of dialogue method and its knowledge base management system of intelligent customer service robot

Country Status (1)

Country Link
CN (1) CN106484801B (en)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107247726B (en) * 2017-04-28 2018-06-08 北京神州泰岳软件股份有限公司 Suitable for the implementation method and device of the intelligent robot of multi-service scene
CN107133349B (en) * 2017-05-24 2018-02-23 北京无忧创新科技有限公司 One kind dialogue robot system
CN107688667A (en) * 2017-09-30 2018-02-13 平安科技(深圳)有限公司 Intelligent robot client service method, electronic installation and computer-readable recording medium
US10691764B2 (en) * 2017-10-23 2020-06-23 International Business Machines Corporation Search engine optimization techniques
CN107832291B (en) * 2017-10-26 2020-03-31 平安科技(深圳)有限公司 Man-machine cooperation customer service method, electronic device and storage medium
CN108363759A (en) * 2018-02-01 2018-08-03 厦门快商通信息技术有限公司 Subject tree generation method and system based on structural data and Intelligent dialogue method
CN108509617A (en) * 2018-04-04 2018-09-07 上海智臻智能网络科技股份有限公司 Construction of knowledge base, intelligent answer method and device, storage medium, the terminal in knowledge based library
CN109002475A (en) * 2018-06-15 2018-12-14 联想(北京)有限公司 Content outputting method and system, computer system and computer readable storage medium
CN109461039A (en) * 2018-08-28 2019-03-12 厦门快商通信息技术有限公司 A kind of text handling method and intelligent customer service method
WO2020151220A1 (en) * 2019-01-22 2020-07-30 深圳追一科技有限公司 Auxiliary customer service device, method, system, robot, and storage medium
CN110049134B (en) * 2019-04-22 2020-04-14 苏州紫焰网络科技有限公司 Customer service chat method, customer service chat device, customer service end, server and storage medium
CN110070370A (en) * 2019-04-29 2019-07-30 上海智臻智能网络科技股份有限公司 Pay a return visit providing method, device, computer equipment and the storage medium of service
WO2021035578A1 (en) * 2019-08-28 2021-03-04 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for question recommendation

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1335574A (en) * 2001-09-05 2002-02-13 罗笑南 Intelligent semantic searching method
JP2004138990A (en) * 2002-10-17 2004-05-13 Kiyoshi Yoshida Rote exercise type correspondence learning system by means of portable phone
CN103853842A (en) * 2014-03-20 2014-06-11 百度在线网络技术(北京)有限公司 Automatic question and answer method and system
CN105786875A (en) * 2014-12-23 2016-07-20 北京奇虎科技有限公司 Method and device for providing question and answer pair data search results

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1335574A (en) * 2001-09-05 2002-02-13 罗笑南 Intelligent semantic searching method
JP2004138990A (en) * 2002-10-17 2004-05-13 Kiyoshi Yoshida Rote exercise type correspondence learning system by means of portable phone
CN103853842A (en) * 2014-03-20 2014-06-11 百度在线网络技术(北京)有限公司 Automatic question and answer method and system
CN105786875A (en) * 2014-12-23 2016-07-20 北京奇虎科技有限公司 Method and device for providing question and answer pair data search results

Also Published As

Publication number Publication date
CN106484801A (en) 2017-03-08

Similar Documents

Publication Publication Date Title
US10445351B2 (en) Customer support solution recommendation system
Chen et al. Learning to rank features for recommendation over multiple categories
Hansen et al. Transparency and deliberation within the FOMC: a computational linguistics approach
Tsai et al. Refining the linkage between perceived capability and entrepreneurial intention: Roles of perceived opportunity, fear of failure, and gender
Brinton et al. Learning about social learning in MOOCs: From statistical analysis to generative model
Sarkisian et al. Does singlehood isolate or integrate? Examining the link between marital status and ties to kin, friends, and neighbors
Geiger et al. Personalized task recommendation in crowdsourcing information systems—Current state of the art
Kiseleva et al. Understanding user satisfaction with intelligent assistants
Kontopoulos et al. Ontology-based sentiment analysis of twitter posts
Riffe et al. Analyzing media messages: Using quantitative content analysis in research
Smolak et al. Sexualizing the self: What college women and men think about and do to be “sexy”
Yuen et al. Taskrec: A task recommendation framework in crowdsourcing systems
Mentes et al. Assessing the usability of university websites: An empirical study on Namik Kemal University.
Gordon et al. Balancing caregiving and work: Role conflict and role strain dynamics
Hayes et al. Stimulating the quasi-statistical organ: Fear of social isolation motivates the quest for knowledge of the opinion climate
CN106095833B (en) Human-computer dialogue content processing method
US10171666B2 (en) Predictive routing
Lally et al. Experiences of habit formation: a qualitative study
Browne et al. Patterns of practice: a reflection on the development of quantitative/mixed methodologies capturing everyday life related to water consumption in the UK
Shin et al. Smart TV: are they really smart in interacting with people? Understanding the interactivity of Korean Smart TV
Heeks et al. New models of inclusive innovation for development
Al-Daihani et al. A text mining analysis of academic libraries' tweets
Terveen et al. Social matching: A framework and research agenda
Nunkoo et al. Applying the means-end chain theory and the laddering technique to the study of host attitudes to tourism
Gao et al. Developing an instrument to measure the adoption of mobile services

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant