CN109460452A - Intelligent customer service system based on ontology - Google Patents

Intelligent customer service system based on ontology Download PDF

Info

Publication number
CN109460452A
CN109460452A CN201811179093.3A CN201811179093A CN109460452A CN 109460452 A CN109460452 A CN 109460452A CN 201811179093 A CN201811179093 A CN 201811179093A CN 109460452 A CN109460452 A CN 109460452A
Authority
CN
China
Prior art keywords
knowledge
ontology
intelligent
customer service
service system
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
CN201811179093.3A
Other languages
Chinese (zh)
Inventor
陈耀东
彭蝶飞
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.)
Changsha Normal University
Original Assignee
Changsha Normal University
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 Changsha Normal University filed Critical Changsha Normal University
Priority to CN201811179093.3A priority Critical patent/CN109460452A/en
Publication of CN109460452A publication Critical patent/CN109460452A/en
Pending legal-status Critical Current

Links

Landscapes

  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The intelligent customer service system based on ontology that the invention discloses a kind of, including interactive terminal, business logic modules and data management platform, problem is inputted by the interactive terminal and receives answer, the problem of business logic modules are inputted according to interactive terminal carries out intelligent processing to it, obtains the knowledge for answering a question;The business logic modules include intelligent response engine and ontology model, the intelligent response engine is interacted with interactive terminal, and multiple analysis is carried out to the input of interactive terminal, problem after analyzing enters ontology model, the knowledge network formed by ontology model realizes the screening, recombination and building to knowledge, to obtain answer, the data management platform is realized to the management of the knowledge in ontology model, user management and priority assignation.The present invention can intelligently " understand " the problem of user, and establish knowledge base using knowledge network, convenient for safeguarding.

Description

Intelligent customer service system based on ontology
Technical field
The present invention relates to internet intelligent field, specifically a kind of intelligent customer service system based on ontology.
Background technique
In internet area, it usually needs manually answer online and solve the problems, such as consultant or potential consumer etc., It but is all greatly among these problems, FAQs, browsing explanation by these crowds itself can be solved, and can show It is all to click directly on and link artificial customer service that reality, which is most people,.Due to internet, audient is very wide, and large-scale Internet company needs Will a large amount of artificial online customer service, in order to mitigate customer service pressure, internet platform, which all starts to introduce machine intelligence, is answered, according to official communication Inquiry person inputs the keyword and type of problem, the answer that pop-up consultant needs.However, computer is often difficult to real " understanding " Question and answer, therefore the application of intelligent customer service is restricted.
Ontology (Ontology) is a philosophical concept, is meant that " to the System describe of world's objective reality object ".? It introduces before " ontology ", computer field is difficult adequately to describe the field of objective world or some reality.The field mould of early stage Type mainly uses the technologies such as automatic reasoner, template engine, lacks to knowledge base and unifies the understanding, thus these domain models have Semantic inconsistent, many disadvantages such as knowledge maintenance is difficult, is difficult to be multiplexed.The most of intelligent customer service system or similar in current China Ground chat auxiliary tool still uses these technologies as the Question-Answering Model of its core, thus these products are mainly asked there are two Topic: one, can not real " understanding " question and answer;Two, the foundation and maintenance of knowledge base need to expend a large amount of manpower and material resources.These problems Seriously constrain the validity and practicability of customer service system.
Summary of the invention
In view of this, the present invention for it is above-mentioned it is of the existing technology can not really " understanding " question and answer and knowledge base be built The problem of vertical, maintenance has difficulties, provides a kind of above problem for solving to restrict customer service system application, union knowledge acquisition, Tissue and analysis are in the intelligent customer service system based on ontology of one.
The technical solution of the invention is as follows, provides a kind of intelligent customer service system based on ontology with flowering structure, including Interactive terminal, business logic modules and data management platform input problem by the interactive terminal and receive answer, described Business logic modules the problem of being inputted according to interactive terminal intelligent processing is carried out to it, obtain knowing for what is answered a question Know;
The business logic modules include intelligent response engine and ontology model, the intelligent response engine and interaction Terminal interacts, and carries out multiple analysis to the input of interactive terminal, and the problem after analyzing enters ontology model, by ontology The knowledge network that model is formed realizes the screening, recombination and building to knowledge, to obtain answer, the data management platform is real Now to the management of the knowledge in ontology model, user management and priority assignation.
Using the above structure, compared with prior art, the present invention having the advantage that using the present invention, ontology is introduced Model, when user inputs problem or keyword from interactive terminal, the intelligent response engine is played to problem or keyword The intelligent effect understood, after being incorrectly understood, the knowledge network that ontology model is set up can be answered according to from intelligence Information obtained in engine is answered, realizes screening, recombination and building to knowledge, so that answer is obtained, by data management platform reality Now to the management of the knowledge in ontology model, user management and priority assignation;The present invention constructs field using Ontology engineering theory Knowledge model reaches field concept and service logic global coherency, unambiguity with the shared of knowledge, reuse for target, and Convenient for the foundation and maintenance of knowledge base.
Preferably, the ontology model includes conceptual network, knowledge base and service logic rule, the concept net Network characterizes between concept and concept possessed multirelation and retrieves phase from knowledge base according to constructed conceptual network The knowledge data answered, using the answer as answer, the logic of the input of service logic rule problem of implementation and knowledge output Interaction.Based on the design, every knowledge is no longer the text template based on keyword, but express one group it is expansible Knowledge Set keeps customer service system more intelligent convenient for being accurately positioned corresponding knowledge.
Preferably, possessed multirelation refers between the concept and concept, hierarchical relationship and logical relation; Conceptual network is set to set up basic knowledge semantic.The design can make conceptual network express richer semanteme, more conducively after The continuous precise positioning to knowledge in knowledge base.
Preferably, the intelligent response engine includes syntactic analysis, semantic analysis, semantic retrieval and scene interactivity mould Block, the inherent noun and user hand that the syntax Analysis Module occurs in customer problem for identification are accidentally or carelessness bring Input error;The semantic module uses superficial layer analyzing algorithm, converts sequence labelling problem for graph model problem;Institute The semantic retrieval module stated uses the strategy that grading search is combined with comprehensive marking;The scene interactivity module is based on pre- If scene carries out intelligent guidance, interaction and recommendation to user.
Preferably, the data management platform includes dictionary management module, ontology knowledge database management module and log pipe Module is managed, the dictionary management module filters the improper demand of user according to vocabulary, while supporting for the user to be added to Subscriber blacklist column, the ontology knowledge database management module are realized the acquisition of knowledge in knowledge base in ontology model, editor, are examined Core, update, backup and statistics, the data of log management module the record user uplink and system descending.
Preferably, the business logic modules further include study engine modules, the study engine modules according to The data that historical record, artificial addition are edited, to create knowledge new in ontology model knowledge base, or to already existing knowledge It is updated.
Preferably, it is described when encountering unanswerable problem, then learn engine modules according to default rule to specified Knowledge open platform on corresponding knowledge automatically grabbed, with creation and more new knowledge.
Preferably, the interactive terminal is webpage client, cell phone and instant communication software.To different friendships The user of mutual terminal, using different user information verification modes, to meet the needs of more users.
Detailed description of the invention
Fig. 1 is that the present invention is based on the structural schematic diagrams of the intelligent customer service system of ontology.
Fig. 2 is the structural block diagram of business logic modules.
Fig. 3 is a kind of schematic diagram of conceptual network.
Specific embodiment
With regard to specific embodiment, the invention will be further described below, but the present invention is not restricted to these embodiments.
The present invention covers any substitution made on the essence and scope of the present invention, modification, equivalent method and scheme.For So that the public is had thorough understanding to the present invention, is described in detail concrete details in the following preferred embodiment of the present invention, and The present invention can also be understood completely in description without these details for a person skilled in the art.In addition, the attached drawing of the present invention In be explained herein not being drawn to scale accurately completely for the needs of signal.
As shown in Figure 1, a kind of intelligent customer service system based on ontology of the invention, including interactive terminal, service logic mould Block and data management platform input problem by the interactive terminal and receive answer, the business logic modules according to The problem of interactive terminal inputs carries out intelligent processing to it, obtains the knowledge for answering a question;In order to more clearly show Logical relation out, interactive terminal are named and are presented with " presentation layer " in Fig. 1, and the two is looked like unanimously in this application, and business is patrolled Module is collected in Fig. 1 with " Business Logic ", to embody the hierarchical relationship between modules.
The business logic modules include intelligent response engine and ontology model, the intelligent response engine and interaction Terminal interacts, and carries out multiple analysis to the input of interactive terminal, and the problem after analyzing enters ontology model, by ontology The knowledge network that model is formed realizes the screening, recombination and building to knowledge, to obtain answer, the data management platform is real Now to the management of the knowledge in ontology model, user management and priority assignation.
As shown in Figure 1,2 and 3, Ontology Modeling essence is a semantic abstraction process to intelligent answer.The ontology Model includes conceptual network, knowledge base and service logic rule, and the conceptual network, which characterizes between concept and concept, to be had Some multirelations retrieve corresponding knowledge data according to constructed conceptual network from knowledge base, using answering as answer Case, the logic that the service logic rule problem of implementation input is exported with knowledge interact.Institute between the concept and concept The multirelation having refers to, hierarchical relationship and logical relation;Conceptual network is set to set up basic knowledge semantic.
In order to for example, expressing the part conceptual network figure of communication body in Fig. 3.Have between concept and concept more Kind relationship, for example, hierarchical relationship: " set meal " is a kind of " product ";Relation on attributes: " set meal " has " brand " and " price " attribute Deng.The conceptual network expressed in a manner of scheming has automation inferential capability, such as " set meal " has (Has a) attribute " brand ", " 100 set meal of walk in the Divine Land " is the one kind (Is a) of " set meal ", then can show that " 100 set meal of walk in the Divine Land " also has with automated reasoning " brand " attribute.There is similar inference function by the knowledge base that conceptual network constructs, thus only need a small amount of knowledge " kind Son " can effectively solve a large amount of similar problems (there is further explained in following " project main contents " column).With work as The preceding customer service system by accumulating a large amount of templates is compared, and the intelligent customer service system based on ontology has more efficient Knowledge Management Capability More intelligent question and answer ability.Based on the design, every knowledge is no longer the text template based on keyword, but is expressed One group of expansible Knowledge Set keeps customer service system more intelligent convenient for being accurately positioned corresponding knowledge.The present invention is used Intelligent answer technology establish on domain body model.Difference and traditional text based text handling method, product are logical That crosses that domain body contained enriches one's knowledge, and by fast word segmentation, Shallow Semantic Parsing and is intended to the series of algorithms such as analysis, " understanding " user is intended to, and then by semantic search, feeds back most suitable answer, thus provides good user experience.
The intelligent response engine includes syntactic analysis, semantic analysis, semantic retrieval and scene interactivity module, described The inherent noun and user hand that syntax Analysis Module occurs in customer problem for identification are accidentally or carelessness bring input error; The semantic module uses superficial layer analyzing algorithm, converts sequence labelling problem for graph model problem;The semanteme Retrieval module uses the strategy that grading search is combined with comprehensive marking;The scene interactivity module be based on default scene to User carries out intelligent guidance, interaction and recommendation.
The data management platform includes dictionary management module, ontology knowledge database management module and log management module, institute The dictionary management module stated filters the improper demand of user according to vocabulary, while supporting the user being added to subscriber blacklist Column, the ontology knowledge database management module realize the acquisition of knowledge in knowledge base in ontology model, editor, audit, update, standby Part and statistics, the data of log management module the record user uplink and system descending.
The business logic modules further include study engine modules, the study engine modules according to historical record, The data of artificial addition editor, to create knowledge new in ontology model knowledge base, or are updated already existing knowledge. Self study engine is intelligent customer service system significant components.In order to guarantee the quality and efficiency of study, the data source that system is learnt From three aspects, the historical record and real-time logs of 1. customer service systems;2. by Edition Contains personnel according to engine settings Rule or the data information of template addition;3. being grabbed automatically by certain presetting rule to specified knowledge open platform It takes.By the way that data source is obtained non-structural or structural data transfers to data mart modeling module to carry out structuring or semi-structured Processing, such as classified using hierarchical clustering (hierarchical clustering) to data.
It is described when encountering unanswerable problem, then it is open to specified knowledge according to default rule to learn engine modules Corresponding knowledge on platform is automatically grabbed, with creation and more new knowledge.
The interactive terminal is webpage client, cell phone and instant communication software.To distinct interaction terminal User, using different user information verification modes, to meet the needs of more users.WEB customer service interface includes user's input Area, three, channel navigation area part are replied in area, customer service.After user's proposition problem, system gives the correct option to go wrong, simultaneously Other problems relevant to customer problem are also shown, in right side navigation area, by the relevant other movements of automatic Display customer problem Product effectively guides user.Cell phone is then to be sent to the command information of Short Message Service Gateway by user to pass through intelligence The server of note system is handled by server analysis and is interacted with user, is obtained after user is clearly intended to by system It sends stereotyped command and gives background business logic system, be user's transacting business.User does not need to remember complicated instruction code again, Related service directly can be handled by natural language.Instant communication software includes QQ, wechat, Ali Wang Wang, etc..
Only the preferred embodiment of the present invention has been described above, but is not to be construed as limiting the scope of the invention.This Invention is not only limited to above embodiments, and specific structure is allowed to vary.In short, all guarantors in independent claims of the present invention Made various change is within the scope of the invention in shield range.

Claims (8)

1. a kind of intelligent customer service system based on ontology, including interactive terminal, business logic modules and data management platform, pass through The problem of interactive terminal input problem and reception answer, the business logic modules are inputted according to interactive terminal, is to it Intelligent processing is carried out, the knowledge for answering a question is obtained;It is characterized by:
The business logic modules include intelligent response engine and ontology model, the intelligent response engine and interactive terminal It interacts, and multiple analysis is carried out to the input of interactive terminal, the problem after analyzing enters ontology model, by ontology model The knowledge network of formation realizes the screening, recombination and building to knowledge, so that answer is obtained, the data management platform realization pair Management, user management and the priority assignation of knowledge in ontology model.
2. the intelligent customer service system according to claim 1 based on ontology, it is characterised in that: the ontology model includes Conceptual network, knowledge base and service logic rule, the conceptual network characterizes possessed multiple between concept and concept Relationship retrieves corresponding knowledge data according to constructed conceptual network from knowledge base, described using the answer as answer The logic that is exported with knowledge of service logic rule problem of implementation input interact.
3. the intelligent customer service system according to claim 2 based on ontology, it is characterised in that: the concept and concept it Between possessed multirelation refer to, hierarchical relationship and logical relation;Conceptual network is set to set up basic knowledge semantic.
4. the intelligent customer service system according to claim 1 or 2 based on ontology, it is characterised in that: the intelligent response Engine includes syntactic analysis, semantic analysis, semantic retrieval and scene interactivity module, and the syntax Analysis Module is used for identification The inherent noun and user hand occurred in the problem of family misses or carelessness bring input error;The semantic module uses Graph model problem is converted sequence labelling problem by superficial layer analyzing algorithm;The semantic retrieval module uses grading search With the strategy that comprehensive marking combines;The scene interactivity module is based on default scene and carries out intelligent guidance, friendship to user Mutually with recommendation.
5. the intelligent customer service system according to claim 2 based on ontology, it is characterised in that: the data management platform packet Dictionary management module, ontology knowledge database management module and log management module are included, the dictionary management module is according to vocabulary mistake The improper demand of user is filtered, while supporting for the user to be added to subscriber blacklist column, the ontology knowledge base manages mould Block realizes acquisition, editor, audit, update, backup and the statistics of knowledge in knowledge base in ontology model, the log management mould The data of block record user uplink and system descending.
6. the intelligent customer service system according to claim 2 based on ontology, it is characterised in that: the business logic modules It further include study engine modules, the study engine modules are according to historical record, the data of artificial addition editor, to create this New knowledge in body Model knowledge base, or already existing knowledge is updated.
7. the intelligent customer service system according to claim 6 based on ontology, it is characterised in that: it is described encounter it is unanswerable When problem, then learns engine modules and the corresponding knowledge on specified knowledge open platform is grabbed automatically according to default rule It takes, with creation and more new knowledge.
8. the intelligent customer service system according to claim 1 or 2 based on ontology, it is characterised in that: the interactive terminal For webpage client, cell phone and instant communication software.
CN201811179093.3A 2018-10-10 2018-10-10 Intelligent customer service system based on ontology Pending CN109460452A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811179093.3A CN109460452A (en) 2018-10-10 2018-10-10 Intelligent customer service system based on ontology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811179093.3A CN109460452A (en) 2018-10-10 2018-10-10 Intelligent customer service system based on ontology

Publications (1)

Publication Number Publication Date
CN109460452A true CN109460452A (en) 2019-03-12

Family

ID=65607498

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811179093.3A Pending CN109460452A (en) 2018-10-10 2018-10-10 Intelligent customer service system based on ontology

Country Status (1)

Country Link
CN (1) CN109460452A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109992669A (en) * 2019-04-08 2019-07-09 浙江大学 A kind of keyword answering method based on language model and intensified learning

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101373532A (en) * 2008-07-10 2009-02-25 昆明理工大学 FAQ Chinese request-answering system implementing method in tourism field
US20130297553A1 (en) * 2012-05-04 2013-11-07 Pearl.com LLC Method and apparatus for predicting question answerability in an online consultation system
CN106649394A (en) * 2015-11-03 2017-05-10 中兴通讯股份有限公司 Fusion knowledge base processing method and device and knowledge base management system
CN107977415A (en) * 2017-11-22 2018-05-01 北京寻领科技有限公司 Automatic question-answering method and device
US20180239816A1 (en) * 2017-02-21 2018-08-23 International Business Machines Corporation Processing request documents

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101373532A (en) * 2008-07-10 2009-02-25 昆明理工大学 FAQ Chinese request-answering system implementing method in tourism field
US20130297553A1 (en) * 2012-05-04 2013-11-07 Pearl.com LLC Method and apparatus for predicting question answerability in an online consultation system
CN106649394A (en) * 2015-11-03 2017-05-10 中兴通讯股份有限公司 Fusion knowledge base processing method and device and knowledge base management system
US20180239816A1 (en) * 2017-02-21 2018-08-23 International Business Machines Corporation Processing request documents
CN107977415A (en) * 2017-11-22 2018-05-01 北京寻领科技有限公司 Automatic question-answering method and device

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
冯志伟: "《自然语言处理简明教程》", 30 September 2012 *
屠要峰: "基于电信业务场景的智能问答机器人关键技术", 《计算机科学与应用》 *
王博: "基于本体的智能化问答系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109992669A (en) * 2019-04-08 2019-07-09 浙江大学 A kind of keyword answering method based on language model and intensified learning

Similar Documents

Publication Publication Date Title
CN112579707B (en) Log data knowledge graph construction method
CN109446305A (en) The construction method and system of intelligent tour customer service system
WO2018072563A1 (en) Knowledge graph creation method, device, and system
CN112860872B (en) Power distribution network operation ticket semantic compliance verification method and system based on self-learning
CN106357942A (en) Intelligent response method and system based on context dialogue semantic recognition
CN107783973A (en) The methods, devices and systems being monitored based on domain knowledge spectrum data storehouse to the Internet media event
CN104281702B (en) Data retrieval method and device based on electric power critical word participle
CN106934068A (en) The method that robot is based on the semantic understanding of environmental context
CN104462064A (en) Method and system for prompting content input in information communication of mobile terminals
CN104978314A (en) Media content recommendation method and device
CN112632239A (en) Brain-like question-answering system based on artificial intelligence technology
CN106372118A (en) Large-scale media text data-oriented online semantic comprehension search system and method
CN107480270A (en) A kind of real time individual based on user feedback data stream recommends method and system
CN110175272A (en) One kind realizing the convergent control method of work order and control device based on feature modeling
CN116010581A (en) Knowledge graph question-answering method and system based on power grid hidden trouble shooting scene
CN113505233B (en) Extraction method of ecological civilized geographic knowledge based on open domain
CN114911893A (en) Method and system for automatically constructing knowledge base based on knowledge graph
CN109460452A (en) Intelligent customer service system based on ontology
CN113407726A (en) Emergency disposal plan method and system
CN106407271B (en) Intelligent customer service system and updating method of intelligent customer service knowledge base thereof
CN109062913B (en) Internationalization resource intelligent acquisition method and storage medium
CN106777124B (en) Semantic knowledge method, apparatus and system
Yijing Intelligent customer service system design based on natural language processing
CN115937881A (en) Method for automatically identifying content of knowledge graph construction standard form
CN115269862A (en) Electric power question-answering and visualization system based on knowledge graph

Legal Events

Date Code Title Description
PB01 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

Application publication date: 20190312

RJ01 Rejection of invention patent application after publication