CN108197167A - Human-computer dialogue processing method, equipment and readable storage medium storing program for executing - Google Patents
Human-computer dialogue processing method, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN108197167A CN108197167A CN201711363313.3A CN201711363313A CN108197167A CN 108197167 A CN108197167 A CN 108197167A CN 201711363313 A CN201711363313 A CN 201711363313A CN 108197167 A CN108197167 A CN 108197167A
- Authority
- CN
- China
- Prior art keywords
- task
- knowledge
- robot
- answer
- library
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention discloses a kind of human-computer dialogue processing method, includes the following steps:It receives robot and receives the problem of user proposes, and based on knowledge library, identify whether the problem is Task problem;If Task problem, then robot is received by the corresponding task of the problem, the handling machine people for possessing the Mission Capability is distributed to, task is performed so that handling machine people is based on knowledge library;If not Task problem, then robot is received by searching for knowledge library, returns to the answer of the problem.Invention additionally discloses a kind of man-machine dialogue equipment and computer readable storage mediums.The present invention realizes the conversion that task distribution processor is received from problem, not only improves the service ability and efficiency of dialogue robot, while also improves user service experience.
Description
Technical field
The present invention relates to interactive field more particularly to a kind of human-computer dialogue processing method, equipment and readable deposit
Storage media.
Background technology
It is more convenient, efficient to provide the user with the progress of science and technology and the rapid growth of business event amount
One-to-one service, more and more enterprises have introduced interactive to adapt to business and clothes on the basis of artificial customer service
Business requirement.
Knowledge base is the important component in interactive system, usually by pattern, keyword, problem and correspondence
Answer composition, during human-computer dialogue, the processing for the problem of being proposed for user, it is generally only in knowledge to talk with robot
Matched and searched is carried out in library and returns to corresponding answer, if dialogue machine accurately cannot quickly identify customer problem, then not only
It searches the inefficiency of answer or even it is also possible to the answer of return mistake, thereby reduces user and use man-machine dialog procedure
In usage experience.
Invention content
It is a primary object of the present invention to provide a kind of human-computer dialogue processing method, equipment and readable storage medium storing program for executing, it is intended to
Solve how during human-computer dialogue promoted dialogue robot service ability and efficiency of service the technical issues of.
To achieve the above object, the present invention provides a kind of human-computer dialogue processing method, and dialogue robot includes reception machine
People and handling machine people, the human-computer dialogue processing method include the following steps:
It receives robot and receives the problem of user proposes, and based on knowledge library, identify whether the problem is Task
Problem;
If Task problem, then robot is received by the corresponding task of the problem, is distributed to and possesses the tasks carrying energy
The handling machine people of power, so that handling machine people performs the task based on knowledge library;
If not Task problem, then robot is received by searching for knowledge library, returns to the answer of the problem.
Optionally, reception robot is described man-machine right before identifying whether the problem of user proposes is Task problem
Words processing method further includes:
Reception robot the problem of being proposed to user, cleans, for by word, and/or word invalid in problem, and/or
Phrase is removed;And
Initialism and/or colloquial style word in the problem of by after cleaning carry out completion.
Optionally, the human-computer dialogue processing method further includes:
It receives the problem of robot is to after cleaning and completion and carries out intention assessment, it is described for determining the type of the problem
Type includes at least:Explain type, cause type, time type.
Optionally, the knowledge base includes at least:Knowledge base, knowledge mapping library, professional knowledge library and task is chatted to know
Know library;
The chat knowledge base includes preset daily question and answer term set;The knowledge mapping library is used to push away including several
The knowledge of reason;The professional knowledge library includes the problem of preset and answer set;
The task knowledge library includes:
Problem instruction set, for identifying the mapping relations between Task problem and the instruction of corresponding execution;
Command status set, for identifying instruction and the mapping relations between corresponding task status sequence;
State operational set, for identifying the mapping relations between task status and the operation of corresponding execution;
Basic operation set includes a variety of basic operations.
Optionally, the human-computer dialogue processing method further includes:
After the receiving the distribution of reception robot of the task, handling machine people is based on the task knowledge in knowledge library
Library performs the task of reception robot distribution, and is returned task action result as answer.
Optionally, if not the Task problem, then robot is received by searching for knowledge library, returns to the problem
Answer the step of include:
If not Task problem, then robot is received based on the professional knowledge library in knowledge library, to the problem point
Not carry out question matching and retrieval ordering and based on the knowledge mapping library in knowledge library, knowledge is carried out to the problem and is pushed away
Reason, obtains result set;
Judge in the result set with the presence or absence of the answer for meeting preset requirement;
If in the presence of the answer for meeting the preset requirement, the answer is returned to, and other similar to the problem is recommended to ask
Topic.
Optionally, after in the judgement result set with the presence or absence of the step of answer for meeting preset requirement, institute
Human-computer dialogue processing method is stated to further include:
If there is no the answer for meeting the preset requirement, the chat knowledge in robot lookup knowledge library is received
Library;
If there is corresponding answer in the chat knowledge base, the answer is returned, otherwise returns to preset acquiescence answer.
Further, to achieve the above object, the present invention also provides a kind of man-machine dialogue equipment, the man-machine dialogue equipments
Including:Memory, processor and it is stored in the interactive program(me) that can be run on the memory and on the processor, institute
It states and is realized when interactive program(me) is performed by the processor such as the step of human-computer dialogue processing method described in any one of the above embodiments.
Optionally, the man-machine dialogue equipment further includes:The knowledge base optimization program being stored on the memory, it is described
It is any one or more in operations described below to perform that processor is configured to perform the knowledge base optimization program:
Template is expanded using problem automatically, the diversity that way to put questions is carried out to the problems in knowledge base expands, and by expansion
As a result it is associated with correspondence problem;
Classification model is understood using problem, is classified to the problems in knowledge base according to semantic understanding;
Conversation log between conversation log, and/or user between user and artificial customer service and dialogue robot into
Row analysis and arrange, for from the new knowledge point of conversation log learning and be saved in knowledge base or based on conversation log strengthen
The existing knowledge point preserved in knowledge base.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
Interactive program(me) is stored on readable storage medium storing program for executing, is realized when the interactive program(me) is executed by processor as any of the above-described
Described in human-computer dialogue processing method the step of.
In the present invention, dialogue robot is on the one hand divided into reception robot and task processor device according to work role
On the other hand people carries out the subdivision of knowledge base based on the work role of robot so that different robots possess it is respective
Knowledge base, reception robot are responsible for receiving the problem of proposing with identification user, and then realize the Preliminary division to customer problem, if
It is Task problem, then the corresponding task of problem is distributed to corresponding task processor device people performs, so as to real in processing
Now to the further subdivision of customer problem, and if not Task problem, then the problem is returned to by searching for knowledge library
Answer.By the division in terms of above-mentioned two, and customer problem is handled by the way of task distribution, this not only reduces right
The workload of robot matched and searched answer in knowledge base is talked about, improves working efficiency, but also improve dialogue robot
Professional service ability.
Description of the drawings
Fig. 1 is the structure diagram of device hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the function structure schematic diagram for talking with robot in man-machine one embodiment of dialog process method of the present invention;
Fig. 3 is the flow diagram of man-machine one embodiment of dialog process method of the present invention;
Fig. 4 is the composition of content schematic diagram of one embodiment of knowledge base used by the man-machine dialog process method of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that specific embodiment described herein is not intended to limit the present invention only to explain the present invention.
As shown in Figure 1, the structure diagram of device hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to.
Man-machine dialogue equipment of the embodiment of the present invention can be PC machine, server or smart mobile phone, tablet computer,
The equipment that pocket computer, intelligent toy etc. have the function of display or recording broadcasting, interactive process can be voice shape
Formula is talked with or written form is talked with or voice+written form dialogue.
As shown in Figure 1, the man-machine dialogue equipment can include:Processor 1001, such as CPU, communication bus 1002, user
Interface 1003, network interface 1004, memory 1005.Wherein, communication bus 1002 is used to implement the connection between these components
Communication.User interface 1003 can include display screen (Display), input unit such as keyboard (Keyboard), optional user
Interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 can optionally include having for standard
Line interface, wireless interface (such as WI-FI interfaces).Memory 1005 can be the storage of high-speed RAM memory or stabilization
Device (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processing
The storage device of device 1001.
Optionally, man-machine dialogue equipment can also include camera, RF (Radio Frequency, radio frequency) circuit, sensing
Device, voicefrequency circuit, WiFi module etc..
It will be understood by those skilled in the art that the hardware configuration of the man-machine dialogue equipment shown in Fig. 1 is not formed to people
The restriction of machine conversational device can include either combining certain components or different portions than illustrating more or fewer components
Part is arranged.
As shown in Figure 1, as operating system, net can be included in a kind of memory 1005 of computer readable storage medium
Network communication module, Subscriber Interface Module SIM and computer program, such as interactive program(me), knowledge base optimization program etc..Wherein,
Operating system is management and the program of control man-machine dialogue equipment and software resource, supports network communication module, user interface mould
Block, interactive program(me), knowledge base optimize the operation of program and other programs or software;Network communication module for manage and
Control network interface 1002;Subscriber Interface Module SIM is used to managing and controlling user interface 1003.
In man-machine dialogue equipment hardware configuration shown in Fig. 1, network interface 1004 is mainly used for connecting system background, with
System background is into row data communication;User interface 1003 is mainly used for connecting client (user terminal), and data are carried out with client
Communication;Man-machine dialogue equipment calls the interactive program(me) stored in memory 1005 by processor 1001, following to perform
Operation:
It receives robot and receives the problem of user proposes, and based on knowledge library, identify whether the problem is Task
Problem;
If Task problem, then robot is received by the corresponding task of the problem, is distributed to and possesses the tasks carrying energy
The handling machine people of power, so that handling machine people performs the task based on knowledge library;
If not Task problem, then robot is received by searching for knowledge library, returns to the answer of the problem.
Further, the man-machine dialogue equipment calls the human-computer dialogue stored in memory 1005 by processor 1001
Program, to perform following operate:
Reception robot the problem of being proposed to user, cleans, for by word, and/or word invalid in problem, and/or
Phrase is removed;And
Initialism and/or colloquial style word in the problem of by after cleaning carry out completion.
Further, the man-machine dialogue equipment calls the human-computer dialogue stored in memory 1005 by processor 1001
Program, to perform following operate:
It receives the problem of robot is to after cleaning and completion and carries out intention assessment, it is described for determining the type of the problem
Type includes at least:Explain type, cause type, time type.
Further, the man-machine dialogue equipment calls the human-computer dialogue stored in memory 1005 by processor 1001
Program, to perform following operate:
After the receiving the distribution of reception robot of the task, handling machine people is based on the task knowledge in knowledge library
Library performs the task of reception robot distribution, and is returned task action result as answer.
Further, the man-machine dialogue equipment calls the human-computer dialogue stored in memory 1005 by processor 1001
Program, to perform following operate:
If not Task problem, then robot is received based on the professional knowledge library in knowledge library, to the problem point
Not carry out question matching and retrieval ordering and based on the knowledge mapping library in knowledge library, knowledge is carried out to the problem and is pushed away
Reason, obtains result set;
Judge in the result set with the presence or absence of the answer for meeting preset requirement;
If in the presence of the answer for meeting the preset requirement, the answer is returned to, and other similar to the problem is recommended to ask
Topic.
Further, the man-machine dialogue equipment calls the human-computer dialogue stored in memory 1005 by processor 1001
Program, to perform following operate:
If there is no the answer for meeting the preset requirement, the chat knowledge in robot lookup knowledge library is received
Library;
If there is corresponding answer in the chat knowledge base, the answer is returned, otherwise returns to preset acquiescence answer.
Further, the man-machine dialogue equipment calls the knowledge base stored in memory 1005 excellent by processor 1001
Change program, it is any one or more in operations described below to perform:
Template is expanded using problem automatically, the diversity that way to put questions is carried out to the problems in knowledge base expands, and by expansion
As a result it is associated with correspondence problem;
Classification model is understood using problem, is classified to the problems in knowledge base according to semantic understanding;
Conversation log between conversation log, and/or user between user and artificial customer service and dialogue robot into
Row analysis and arrange, for from the new knowledge point of conversation log learning and be saved in knowledge base or based on conversation log strengthen
The existing knowledge point preserved in knowledge base.
Based on above-mentioned man-machine dialogue equipment hardware configuration, each embodiment of the man-machine dialog process method of the present invention is proposed.
With reference to Fig. 2, Fig. 2 is the function structure signal of dialogue robot in man-machine one embodiment of dialog process method of the present invention
Figure.
As shown in Fig. 2, the dialogue that human-computer dialogue is specifically referred between user and machine interacts.In the present embodiment, dialogue machine
Device people is specially the virtual objects fictionalized in interactive program(me) come for engaging in the dialogue with user, based on work role not
Together, dialogue robot can be divided into reception robot (being illustrated as receptionist) and handling machine people (being illustrated as processing person), reception
Robot and the work role of handling machine people are similar to artificial customer service and artificial technology person in reality, therefore do not do excessive superfluous
It states.
For example, the financing APP that user uses has the function of intelligent sound assistant, user can with intelligent sound assistant into
Row dialogue, if user is putd question to as general issue, is directly replied by reception robot, and if professional sex chromosome mosaicism,
For example open an account, borrow money, buying finance product etc., then it receives robot and the problem is given to the processor with corresponding professional ability
Device people is replied.
In the present embodiment, receive robot and handling machine people possesses respective knowledge base respectively, each robot is based on certainly
The knowledge base of body replies customer problem.It should be noted that reception robot and knowing of respectively using of handling machine people
Know library can be content and construct all identical or content be different from construction or can also be construct it is identical and
Content is different.
The knowledge base of other side can mutually be learnt between reception robot and handling machine people.Reception robot is mainly responsible for
Whether the enquirement for identifying user is Task problem, possesses the tasks carrying if so, the corresponding task of the problem is distributed to
The handling machine people of ability, the role for then taking over reception robot by handling machine people again continue to execute the task, and with
Family carries out subsequent interaction after the completion of task, then consigns to reception robot again and carry out at user's enquirement next time
Reason, such as the task of opening an account need user to input name, identification card number, cell-phone number, after handling machine people has performed the task of opening an account
User is returned result to, while current session is consigned to reception robot again.
In addition, it will be appreciated by persons skilled in the art that ensure interactive service quality and safety, in people
In machine dialog procedure, business Process Design for operator or individual subscriber need, can be on the backstage of dialogue robot
It introduces artificial customer service to participate in, needs to carry out manual examination and verification such as the business of opening an account.
With reference to Fig. 3, Fig. 3 is the flow diagram of the man-machine dialog process method first embodiment of the present invention.In the present embodiment,
Human-computer dialogue processing method includes the following steps:
Step S10, reception robot receives the problem of user proposes, and based on knowledge library, whether identifies the problem
For Task problem;
It needs to stress in the present invention, the problem of being not necessarily referring in absolute sense the problem of user proposes, such as " please
Ask today weather how", but referring to user needs to talk with a kind of form of communication that robot provides reply, the form of communication
Can be:Enquirement, request, order, explanation, consultation, compliment etc..For example, user can be that " you very may be used the problem of proposition
Love ", " how do you do ", " how to get to may I ask bus station ", " a first song please be sing ", " closing fund account to me " etc..
Meanwhile the present embodiment proposes that the form of problem is unlimited for user, for example, written form or speech form.If
The problem of user proposes then is received after robot receives the phonetic problem, needs first to carry out speech recognition for speech form, with
The problem of obtaining corresponding written form.
It is unlimited for the particular content of knowledge base and structural form used in reception robot in the present embodiment, but connect
It treats knowledge base of the robot based on itself, can identify whether the problem of user proposes is Task problem.
The problem of the present embodiment proposes user is divided into Task problem and two major class of non task type problem.Task is asked
Topic specifically refers to the problem of dialogue robot needs reply user by way of performing task.For example, user, which puts question to, " please give me
It is OK to open a family", the answer for receiving robot at this time cannot only " good ", because this reply and do not solve asking for user
Topic, therefore reception robot should also perform the task corresponding to the Task problem, could really solve asking for user's proposition
Topic.
For reception robot identification user propose the problem of whether be Task problem mode it is unlimited.For example, it can incite somebody to action
Identify whether to be converted to for Task problem and identify whether task to be performed, and for whether to perform the mode of task and can be used
Task question template is judged.For example, the problem of pre-setting all tasks that handling machine people is supported template, one
Question template can correspond to a variety of question formulations.For example, the corresponding question formulation of task question template for task of opening an account can be " please
Me is helped to open an account ", " I will open an account ", " open a family ", " open a family can with " etc..
For another example the identification of Task problem is triggered using keyword and pattern, such as pattern:" the predetermined * meetings of *
Room * " triggers the tasks carrying of predetermined conference room when the enquirement of user meets the pattern.For example " I will make a reservation for user's enquirement
Tomorrow morning 9 points to 10: 7 buildings of meeting room ", the words triggers the pattern of predetermined conference room above, then into meeting
The scheduled flow of task in room, which needs some necessary parameters such as time, floor etc., and is just wrapped in the words
Contained time and floor, then they are identified rear and filled in the task interface into predetermined conference room, then by
Manage the fundamental operation that robot initiates predetermined conference room.
Step S20 if Task problem, then receives robot by the corresponding task of the problem, is distributed to and possesses this
The handling machine people for executive capability of being engaged in, so that handling machine people performs the task based on knowledge library;
In the present embodiment, reception robot can not only identify whether problem is to appoint when identifying the problem of user proposes
Business type problem, while can also determine the task corresponding to Task problem.For example, the enquirement of user is " opening family can be with
", then it receives robot and identifies the problem as Task problem, and can determine that the corresponding task of the problem is " task of opening an account ".
The present embodiment is unlimited for the mode for determining Task problem.It is supported for example, handling machine people can be pre-set
All tasks, and the task key word corresponding to each task is set, if including task key word in Task problem,
It then can determine the task corresponding to the Task problem, it is as shown in table 1 below.
Table 1
Task type | Task key word |
It opens an account | It opens an account, register for a household residence card, account |
It borrows money | It borrows, borrow money, provide a loan, borrow money |
Purchase | It buys, buy |
If reception robot identifies that the problem of user proposes for Task problem, receives robot by the problem pair
Answering for task is distributed to the handling machine people for possessing the Mission Capability.In the present embodiment, different handling machine people corresponds to
It handles different tasks namely different handling machine people possesses different Mission Capabilities.
In the present embodiment, handling machine people is specifically based on knowledge library and performs task, and specific executive mode is unlimited.It needs
It further illustrates, handling machine people can also continue to engage in the dialogue with user during execution task, the dialogue shape
Formula can be dialogic operation of the user directly with handling machine people.
Step S30 if not Task problem, then receives robot by searching for knowledge library, returns to the problem
Answer.
If the problem of user proposes is not Task problem, which need not be distributed at handling machine people
Reason, but directly by reception robot by searching for knowledge library, to return to the answer of problem to user.Need what is illustrated
It is that the answer that reception robot returns is possible in its own knowledge base, it is also possible to not exist, but final reception robot is all
An answer can be returned and be given to user.
In the present embodiment, dialogue robot is on the one hand divided into reception robot and task processor according to work role
Device people, on the other hand carries out the subdivision of knowledge base based on the work role of robot, so that different robots possesses respectively
Knowledge base, reception robot is responsible for receiving the problem of proposing with identification user, and then realizes to the Preliminary division of customer problem,
If Task problem, then the corresponding task of problem is distributed to corresponding task processor device people and performed, so as in processing
Realize the further subdivision to customer problem, and if not Task problem, then ask by searching for knowledge library to return to this
The answer of topic.By the division in terms of above-mentioned two, and customer problem is handled by the way of task distribution, this not only reduces
Talk with the workload of robot matched and searched answer in knowledge base, improve working efficiency, but also improve dialogue machine
The professional service ability of people.
Further alternative, in the man-machine dialog process method second embodiment of the present invention, reception robot is used in identification
Before whether the problem of family proposes is Task problem, also pre-processed as follows:
(1) reception robot the problem of being proposed to user, cleans, for by word, and/or word invalid in problem,
And/or phrase is removed;
In the present embodiment, problem cleaning is primarily referred to as invalidation word unimportant, nonsensical in rejecting problem, word or word
Group.For example " I wants to ask ", " could you tell me ", not only these phrases are nonsensical to entire problem or even also robot can be answered
Multiple problem brings interference.
It is unlimited for the realization method of problem cleaning in the present embodiment.For example, pre-setting invalid character word stock, include
Invalid word, phrase, short sentence set and clause pattern have met invalid word under certain clause pattern and the pattern, short when question sentence
Language, short sentence will correspond to invalid part and weed out.Such as the colloquial style auxiliary word that user is commonly used:It " eh, ", " can be with
", " capable not " etc., in problem cleaning process, semantic division is carried out to problem, and based on invalid character word stock, it is semantic to carrying out
The problem of after division, content cleaned, so as to which word, and/or word invalid in problem, and/or phrase be removed.
(2) by after cleaning initialism and/or colloquial style word in the problem of carry out completion;
In the present embodiment, initialism or colloquial word that problem completion is primarily referred to as during user is putd question to are mended
Entirely, so as to make subject of question of greater clarity.Such as " money that I borrows should when also " should completion be the " money that I borrows
When refund ".
It is unlimited for the realization method of problem completion in the present embodiment.For example, problem completion character word stock is pre-set, by
Initialism is formed with complete words mapping relations set and clause pattern, when question sentence has met under certain clause pattern and the pattern
Initialism is replaced with complete words by initialism.For example, common colloquial style word can be pre-set, corresponding to initialism
Former problem can also be carried out the replacement on way to put questions, so as to fulfill the completion to former problem by completion mode.
(3) it receives the problem of robot is to after cleaning and completion and carries out intention assessment, for determining the type of the problem, institute
Type is stated to include at least:Explain type, cause type, time type.
In the present embodiment, it is intended that identification is primarily referred to as puing question to user the classification carried out in some intentions, for example be divided into
The enquirement of " explaining class ", the enquirement of " reason class ", the enquirement of " time class " etc..
The present embodiment is unlimited for the realization method of intention assessment.For example, first carrying out semantic division to problem, for example divide
It to perform subject, execution action, time adverbial, tone adverbial word etc., is then divided again based on semantic, determines the meaning that user puts question to
Figure, for example, " when I will refund " can be classified as " time class " problem, " how opening an account " can be classified as " explain class " problem,
" why not can provide a loan " can then be classified as " reason class ".
Certainly, the problem of can also being proposed in the present embodiment to user is further to be classified, for example " explaining class " can be with
It is further divided into the classifications such as " professional qualification explanation ", " business tine explanation ", " service processing result explanation ".
In the present embodiment, before receiving robot and judging whether the problem of user proposes is Task problem, first dock
The pretreatments such as the problem of receiving is cleaned, completion, intention assessment, so as to promote understanding energy of the dialogue robot to problem
Power, and then the search efficiency and accuracy rate of Upgrade Problem answer.
With reference to Fig. 4, Fig. 4 is that the composition of content of one embodiment of knowledge base used by the man-machine dialog process method of the present invention shows
It is intended to.
As shown in figure 4, in the present embodiment, knowledge base includes at least:Chat knowledge base, knowledge mapping library, professional knowledge library
And task knowledge library.
(1) knowledge base is chatted
It chats in knowledge base and mainly stores preset daily question and answer term set, for example " you are very lovely " correspondence " be thanks and be overstated
Prize ";" you can sing first song " correspondence " good, to may I ask you and want what song listened " etc. is mainly used for answer user some
Works and expressions for everyday use are talked with.
It is mainly the conventional data arranged by way of off-line learning to chat the daily question and answer term in knowledge base,
Therefore it does not need to knowledge base management person and carries out human-edited.
(2) knowledge mapping library
Several knowledge for reasoning, such as the knowledge mapping related with opening an account and loaning bill are stored in knowledge mapping library
Related knowledge mapping etc. or with the relevant knowledge mapping of user session theme, such as weather knowledge mapping, automobile knowledge figure
Spectrum, star's knowledge mapping etc. are mainly used for carrying out knowledge-based reasoning during replying.
Knowledge mapping is mainly the conventional data arranged by way of off-line learning, therefore does not need to knowledge depositary management
Reason person carries out human-edited.
(3) professional knowledge library
Professional knowledge stores the problem of preset and answer set in library, and the content of the knowledge base is mainly related to business, because
And it is mainly formed by knowledge base management person by human-edited.For example, problem is arranged for the work hours, then corresponding answer is week
One to Friday, at 9 points in the morning at 17 points in afternoon;Problem is the loan repayment time limit, then corresponding answer be 5 years, 10 years, 15 years, 20
Year, 30 years.
(4) task knowledge library
Task knowledge library is mainly used for providing support in the corresponding task of handling machine people processing Task problem.Task
Knowledge base mainly includes following aggregates content:
Problem instruction set, for identifying the mapping relations between Task problem and the instruction of corresponding execution;
Command status set, for identifying instruction and the mapping relations between corresponding task status sequence;
State operational set, for identifying the mapping relations between task status and the operation of corresponding execution;
Basic operation set, comprising a variety of basic operations, for example receive, obtain, uploading, issuing, inquiring, deleting, prompting,
Compression, display etc..
In the present embodiment, pending Task-decomposing is performed for multiple execution steps and sequentially.Specially:Problem->
Assignment instructions->Task status sequence, task status->Operation, the final completion for realizing task.
For example instruction is " predetermined conference room ", state includes " floor ", " initial time ", " end time ", " participant
Number " etc., operation include " inquiry meeting room where floor ", " inquiring all meeting room details ", " inquiring certain layer of meeting room details ",
" predetermined conference room ", " cancellation of meeting room " etc..
The structural form of knowledge base enhances the reason for the problem of dialogue robot proposes user used by the present embodiment
Solution ability, so that user can be interacted using more natural question formulation with robot.
Optionally, the composition of content based on the knowledge base in a upper embodiment, in the man-machine dialog process method of the present invention the
In three embodiments, handling machine people is known after the receiving the distribution of reception robot of the task based on the task in knowledge library
Know library, perform the task of reception robot distribution, and return task action result as answer.
For example, Task problem is " me please be helped to open an account ", corresponding task is " task of opening an account ", and handling machine people performs should
The flow of task is as follows:
1st, by problem " me please be help to open an account ", determine corresponding instruction for " execution open an account task ";
2nd, by instruction " execution open an account task ", determine that corresponding task status sequence is:User basic information, information are tested
It demonstrate,proves, account information of opening an account;
2.1 user basic information respective operations are as follows:User is prompted to input essential information, information package is uploaded into backstage;
2.2 Information Authentication respective operations are as follows:Submit information, obtain auditing rule, based on auditing rule verification information, return
Return verification result;
2.3 account information respective operations of opening an account are as follows:Generate account information, extraction account information in relevant information, under
Send out the relevant information.
Still optionally further, in one embodiment of man-machine dialogue equipment of the present invention, to advanced optimize and being promoted dialogue machine
The answer ability of device people, in the present embodiment, man-machine dialogue equipment further includes:The knowledge base optimization journey being stored on memory 1005
Sequence, it is any one or more in operations described below to perform that processor 1001 is configured to execution knowledge base optimization program:
Operation one:Template is expanded using problem automatically, the diversity that way to put questions is carried out to the problems in knowledge base expands, and will
The result of expansion is associated with correspondence problem;The problem of operation mainly edits knowledge base management person is expanded automatically
It fills, and then the question sentence set for expressing equivalent is expanded automatically and is come out.
For example, opening an account in this problem, some users may ask " how applying for card ", " what flow of applying for card is ", " do
What the condition requirement of card is " etc..For example after user edits " what is that particle is borrowed ", then the problem expands between this operation will be automatic
It is charged to " particle, which is borrowed, to be introduced ", " particle borrows explanation " etc..
Operation two:Classification model is understood using problem, is classified to the problems in knowledge base according to semantic understanding;The behaviour
Make that processing speed and accuracy rate that robot replies can be improved.
For example, first carrying out semantic division to problem, for example it is divided into and performs subject, execution action, time adverbial, tone pair
Then word etc. is divided based on semantic again, determine the intention that user puts question to, for example, " when I will refund " can be classified as " when
Between class " problem, " how opening an account " can be classified as " explaining class " problem, " why not can provide a loan " can then be classified as " reason class ".
As long as by the sufficiently fine of the classification granularity point of customer problem, it is possible to greatly improve the accuracy rate of problem retrieval.
Operation three:The dialogue between conversation log, and/or user and dialogue robot between user and artificial customer service
Daily record is analyzed and is arranged, for from the new knowledge point of conversation log learning and be saved in knowledge base or based on dialogue day
Will strengthens the existing knowledge point preserved in knowledge base.
The operation realizes the automatic study of knowledge base, learns new knowledge point to expand knowledge base, while consolidate existing
Knowledge point is with hoisting machine people to the answer ability of problem.It is unlimited for the mode learnt automatically.For example, by using learning template, text
The machine learning methods such as this generation, seq2seq excavate new knowledge point (such as problem answers set) from the dialogue date.It needs
It is further noted that since reception robot and handling machine people use respective knowledge base respectively, for promotion pair
The answer ability of robot is talked about, therefore, the knowledge base of both sides can be carried out mutually learning, so that reception robot or place
Reason robot can possess the answer ability of other side, so as to realize the efficient, accurate of answer process on the whole.
It is further alternative, in the man-machine dialog process method fourth embodiment of the present invention, based on the method for the present invention first
Embodiment, the realization of the upper step S30 include the following steps:
Step S301 if not Task problem, then receives robot based on the professional knowledge library in knowledge library, right
The problem carries out question matching and retrieval ordering and respectively based on the knowledge mapping library in knowledge library, to the problem into
Row knowledge reasoning, obtains result set;
Step S302 is judged in the result set with the presence or absence of the answer for meeting preset requirement;
If step S303 in the presence of the answer for meeting the preset requirement, returns to the answer, and recommend similar to the problem
Other problems.
In the present embodiment, if user is not Task problem the problem of proposition, receives robot and be based respectively on itself
The correspondence answer of the problem is searched in professional knowledge library and knowledge mapping library in knowledge base.
(1) based on professional knowledge library, question matching and retrieval ordering are carried out;
In the present embodiment, the problems in reception robot the problem of proposing user and professional knowledge library, carry out one by one
Match, obtain corresponding matching result collection;Meanwhile carry out retrieval inverted index, and to searching after the problem of proposing user participle
To the problem of set be ranked up according to the weight of matching word, obtain corresponding retrieval set;
(2) knowledge based spectrum library carries out knowledge reasoning.
In the present embodiment, also by knowledge based spectrum library, the problem of being proposed to user, carries out knowledge reasoning for reception robot,
Obtain corresponding the reasoning results collection.
Above-mentioned matching result collection, retrieval set and the reasoning results collection constitute the answer result set of reception robot, so
Afterwards, reception robot needs further to judge with the presence or absence of the answer for meeting preset requirement in the answer result set, if it does,
The answer is then returned into user.
It should be noted that the present embodiment is unlimited for the setting of preset requirement, it is configured with specific reference to actual needs.
For example, preset requirement can be set as:If there is an answer, then answer of the answer as customer problem is directly returned to, and
If there are multiple answers, optimal answer in Optimum Matching result set, from matching result collection, retrieval set and the reasoning results
Collection chooses optimal result.
In addition, to promote service ability, when replying customer problem, further by similar its problem of proposition to user
His question recommending is to user.
It is further alternative, in man-machine the 5th embodiment of dialog process method of the present invention, based on the method for the present invention the 4th
Embodiment, in the present embodiment, human-computer dialogue processing method further includes:
If step S304 there is no the answer for meeting the preset requirement, receives robot and searches in knowledge library
Chat knowledge base;
Step S305 if there is corresponding answer in the chat knowledge base, returns to the answer, otherwise returns to preset acquiescence
Answer.
In the present embodiment, if reception robot can not obtain answer from business knowledge base, knowledge mapping library, further
Answer is searched in knowledge base is chatted, mode of searching can be the modes such as question matching, retrieval ordering.If chatting knowledge base
In find it is corresponding chat as a result, then return to user as answer, otherwise select preset silent of man-machine dialogue equipment
Recognize answer and return to user, such as " sorry not find satisfactory answer, we understand continuous learning ... ", such as
It is such.
The present invention also provides a kind of computer readable storage mediums.
Interactive program(me) is stored on the computer readable storage medium of the present invention, the interactive program(me) is by processor
The step in above-mentioned human-computer dialogue processing method any embodiment is realized during execution.
Further, knowledge base optimization program can also be stored on computer readable storage medium of the invention, this is known
Know any one or more in execution operations described below when library optimization program is executed by processor:
Template is expanded using problem automatically, the diversity that way to put questions is carried out to the problems in knowledge base expands, and by expansion
As a result it is associated with correspondence problem;
Classification model is understood using problem, is classified to the problems in knowledge base according to semantic understanding;
Conversation log between conversation log, and/or user between user and artificial customer service and dialogue robot into
Row analysis and arrange, for from the new knowledge point of conversation log learning and be saved in knowledge base or based on conversation log strengthen
The existing knowledge point preserved in knowledge base.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements not only include those elements, and
And it further includes other elements that are not explicitly listed or further includes intrinsic for this process, method, article or device institute
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical elements in the process of element, method, article or device.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), used including some instructions so that a station terminal (can be mobile phone, computer services
Device, air conditioner or network equipment etc.) perform method described in each embodiment of the present invention.
The embodiment of the present invention is described above in conjunction with attached drawing, but the invention is not limited in above-mentioned specific
Embodiment, above-mentioned specific embodiment is only schematical rather than restricted, those of ordinary skill in the art
Under the enlightenment of the present invention, present inventive concept and scope of the claimed protection are not being departed from, can also made very much
Form, every equivalent structure or equivalent flow shift made using description of the invention and accompanying drawing content, directly or indirectly
Other related technical areas are used in, these are belonged within the protection of the present invention.
Claims (10)
1. a kind of human-computer dialogue processing method, which is characterized in that dialogue robot includes reception robot and handling machine people, institute
Human-computer dialogue processing method is stated to include the following steps:
It receives robot and receives the problem of user proposes, and based on knowledge library, identify whether the problem is Task problem;
If Task problem, then robot is received by the corresponding task of the problem, is distributed to and possesses the Mission Capability
Handling machine people, so that handling machine people performs the task based on knowledge library;
If not Task problem, then robot is received by searching for knowledge library, returns to the answer of the problem.
2. human-computer dialogue processing method as described in claim 1, which is characterized in that reception robot is proposed in identification user
Before whether problem is Task problem, the human-computer dialogue processing method further includes:
Reception robot the problem of being proposed to user, cleans, for by word, and/or word invalid in problem, and/or phrase
It removes;And
Initialism and/or colloquial style word in the problem of by after cleaning carry out completion.
3. human-computer dialogue processing method as claimed in claim 2, which is characterized in that the human-computer dialogue processing method is also wrapped
It includes:
It receives the problem of robot is to after cleaning and completion and carries out intention assessment, for determining the type of the problem, the type
It includes at least:Explain type, cause type, time type.
4. human-computer dialogue processing method as described in claim 1, which is characterized in that the knowledge base includes at least:Chat is known
Know library, knowledge mapping library, professional knowledge library and task knowledge library;
The chat knowledge base includes preset daily question and answer term set;The knowledge mapping library includes several for reasoning
Knowledge;The professional knowledge library includes the problem of preset and answer set;
The task knowledge library includes:
Problem instruction set, for identifying the mapping relations between Task problem and the instruction of corresponding execution;
Command status set, for identifying instruction and the mapping relations between corresponding task status sequence;
State operational set, for identifying the mapping relations between task status and the operation of corresponding execution;
Basic operation set includes a variety of basic operations.
5. human-computer dialogue processing method as claimed in claim 4, which is characterized in that the human-computer dialogue processing method is also wrapped
It includes:
After the receiving the distribution of reception robot of the task, handling machine people is held based on the task knowledge library in knowledge library
The task of row reception robot distribution, and returned task action result as answer.
6. human-computer dialogue processing method as claimed in claim 4, which is characterized in that if not the Task problem, then connect
Robot is treated by searching for knowledge library, the step of answer for returning to the problem includes:
If not Task problem, then receive robot based on the professional knowledge library in knowledge library, to the problem respectively into
Row question matching and retrieval ordering and based on the knowledge mapping library in knowledge library, carry out knowledge reasoning to the problem, obtain
To result set;
Judge in the result set with the presence or absence of the answer for meeting preset requirement;
If in the presence of the answer for meeting the preset requirement, the answer is returned to, and recommend the other problems similar to the problem.
7. human-computer dialogue processing method as claimed in claim 6, which is characterized in that it is described judge in the result set whether
After the step of answer for meeting preset requirement, the human-computer dialogue processing method further includes:
If there is no the answer for meeting the preset requirement, the chat knowledge base in robot lookup knowledge library is received;
If there is corresponding answer in the chat knowledge base, the answer is returned, otherwise returns to preset acquiescence answer.
8. a kind of man-machine dialogue equipment, which is characterized in that the man-machine dialogue equipment includes:It memory, processor and is stored in
On the memory and the interactive program(me) that can run on the processor, the interactive program(me) is by the processor
The step of human-computer dialogue processing method as described in any one of claim 1 to 7 is realized during execution.
9. man-machine dialogue equipment as claimed in claim 8, which is characterized in that the man-machine dialogue equipment further includes:It is stored in
Knowledge base optimization program on the memory, it is following to perform that the processor is configured to perform the knowledge base optimization program
It is any one or more in operation:
Template is expanded using problem automatically, the diversity that way to put questions is carried out to the problems in knowledge base expands, and by the result of expansion
It is associated with correspondence problem;
Classification model is understood using problem, is classified to the problems in knowledge base according to semantic understanding;
The conversation log between conversation log, and/or user and dialogue robot between user and artificial customer service is divided
Analysis and arrange, for from the new knowledge point of conversation log learning and be saved in knowledge base or based on conversation log strengthen knowledge
The existing knowledge point preserved in library.
10. a kind of computer readable storage medium, which is characterized in that it is man-machine right to be stored on the computer readable storage medium
Program is talked about, the human-computer dialogue as described in any one of claim 1 to 7 is realized when the interactive program(me) is executed by processor
The step of processing method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711363313.3A CN108197167A (en) | 2017-12-18 | 2017-12-18 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711363313.3A CN108197167A (en) | 2017-12-18 | 2017-12-18 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108197167A true CN108197167A (en) | 2018-06-22 |
Family
ID=62576955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711363313.3A Pending CN108197167A (en) | 2017-12-18 | 2017-12-18 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108197167A (en) |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846125A (en) * | 2018-06-29 | 2018-11-20 | 北京百度网讯科技有限公司 | Talk with generation method, device, terminal and computer readable storage medium |
CN108900726A (en) * | 2018-06-28 | 2018-11-27 | 北京首汽智行科技有限公司 | Artificial customer service forwarding method based on speech robot people |
CN109033223A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | For method, apparatus, equipment and computer readable storage medium across type session |
CN109145100A (en) * | 2018-08-24 | 2019-01-04 | 深圳追科技有限公司 | A kind of the Task customer service robot system and its working method of customizable process |
CN109376228A (en) * | 2018-11-30 | 2019-02-22 | 北京猎户星空科技有限公司 | A kind of information recommendation method, device, equipment and medium |
CN109446305A (en) * | 2018-10-10 | 2019-03-08 | 长沙师范学院 | The construction method and system of intelligent tour customer service system |
CN109597993A (en) * | 2018-11-30 | 2019-04-09 | 深圳前海微众银行股份有限公司 | Sentence analysis processing method, device, equipment and computer readable storage medium |
CN109597607A (en) * | 2018-10-31 | 2019-04-09 | 拓科(武汉)智能技术股份有限公司 | Task interactive system and its implementation, device and electronic equipment |
CN109660678A (en) * | 2018-12-07 | 2019-04-19 | 深圳前海微众银行股份有限公司 | Electric core network system realization, system and readable storage medium storing program for executing |
CN110019755A (en) * | 2019-02-27 | 2019-07-16 | 杭州简简科技有限公司 | Digital people's livelihood system and construction method based on artificial intelligence big data |
CN110175240A (en) * | 2019-05-16 | 2019-08-27 | 五竹科技(天津)有限公司 | Construction method, device and the storage medium of knowledge mapping relevant to outgoing call process |
CN110263144A (en) * | 2019-06-27 | 2019-09-20 | 深圳前海微众银行股份有限公司 | A kind of answer acquisition methods and device |
CN110334347A (en) * | 2019-06-27 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Information processing method, relevant device and storage medium based on natural language recognition |
CN110472024A (en) * | 2019-07-11 | 2019-11-19 | 北京云迹科技有限公司 | For the configuration of the customized question and answer of robot, processing method and device, robot |
CN110516035A (en) * | 2019-07-05 | 2019-11-29 | 同济大学 | A kind of man-machine interaction method and system of mixing module |
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 |
CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
CN111080259A (en) * | 2019-12-19 | 2020-04-28 | 中国工商银行股份有限公司 | Multi-robot cooperation system and method based on bank application scene |
CN111104504A (en) * | 2019-12-25 | 2020-05-05 | 天津中科智能识别产业技术研究院有限公司 | Natural language processing and knowledge graph based dialogue method |
CN111274372A (en) * | 2020-01-15 | 2020-06-12 | 上海浦东发展银行股份有限公司 | Method, electronic device, and computer-readable storage medium for human-computer interaction |
CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
CN111816173A (en) * | 2020-06-01 | 2020-10-23 | 珠海格力电器股份有限公司 | Dialogue data processing method, device, storage medium and computer equipment |
CN111897942A (en) * | 2020-06-30 | 2020-11-06 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
CN111966808A (en) * | 2019-12-31 | 2020-11-20 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
CN111966716A (en) * | 2020-08-20 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Data processing method and device |
CN111966788A (en) * | 2019-12-31 | 2020-11-20 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
CN112000786A (en) * | 2020-06-30 | 2020-11-27 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
CN112035640A (en) * | 2020-08-31 | 2020-12-04 | 重庆长安汽车股份有限公司 | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment |
CN112148853A (en) * | 2020-09-15 | 2020-12-29 | 上海风秩科技有限公司 | Query result determination method and device, storage medium and electronic device |
CN112381642A (en) * | 2020-11-30 | 2021-02-19 | 中国银行股份有限公司 | Network management system and method based on network robot |
CN112487186A (en) * | 2020-11-27 | 2021-03-12 | 上海浦东发展银行股份有限公司 | Human-human conversation log analysis method, system, equipment and storage medium |
CN112559701A (en) * | 2020-11-10 | 2021-03-26 | 联想(北京)有限公司 | Man-machine interaction method, device and storage medium |
CN112632239A (en) * | 2020-12-11 | 2021-04-09 | 南京三眼精灵信息技术有限公司 | Brain-like question-answering system based on artificial intelligence technology |
CN112800204A (en) * | 2021-02-24 | 2021-05-14 | 浪潮云信息技术股份公司 | Construction method of intelligent dialogue system |
CN112800188A (en) * | 2019-11-13 | 2021-05-14 | 阿里巴巴集团控股有限公司 | Conversation processing method and device |
CN113076413A (en) * | 2021-04-30 | 2021-07-06 | 平安国际智慧城市科技股份有限公司 | Parameter association service method, system, device and storage medium |
WO2022142019A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技(深圳)有限公司 | Question distribution method and apparatus based on intelligent robot, and electronic device and storage medium |
CN111816173B (en) * | 2020-06-01 | 2024-06-07 | 珠海格力电器股份有限公司 | Dialogue data processing method and device, storage medium and computer equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101741759A (en) * | 2008-11-24 | 2010-06-16 | 中国电信股份有限公司 | Instant communication-based intelligent interactive system and interactive method |
CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
CN105892320A (en) * | 2016-04-26 | 2016-08-24 | 京东方科技集团股份有限公司 | Self-service robot, service method, control device and service system |
CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
CN106952646A (en) * | 2017-02-27 | 2017-07-14 | 深圳市朗空亿科科技有限公司 | A kind of robot interactive method and system based on natural language |
CN107133305A (en) * | 2017-04-28 | 2017-09-05 | 上海斐讯数据通信技术有限公司 | A kind of automatic construction device of chat robots knowledge base and its method |
-
2017
- 2017-12-18 CN CN201711363313.3A patent/CN108197167A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101741759A (en) * | 2008-11-24 | 2010-06-16 | 中国电信股份有限公司 | Instant communication-based intelligent interactive system and interactive method |
CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
CN105892320A (en) * | 2016-04-26 | 2016-08-24 | 京东方科技集团股份有限公司 | Self-service robot, service method, control device and service system |
CN106952646A (en) * | 2017-02-27 | 2017-07-14 | 深圳市朗空亿科科技有限公司 | A kind of robot interactive method and system based on natural language |
CN106934068A (en) * | 2017-04-10 | 2017-07-07 | 江苏东方金钰智能机器人有限公司 | The method that robot is based on the semantic understanding of environmental context |
CN107133305A (en) * | 2017-04-28 | 2017-09-05 | 上海斐讯数据通信技术有限公司 | A kind of automatic construction device of chat robots knowledge base and its method |
Cited By (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108900726A (en) * | 2018-06-28 | 2018-11-27 | 北京首汽智行科技有限公司 | Artificial customer service forwarding method based on speech robot people |
CN109033223A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | For method, apparatus, equipment and computer readable storage medium across type session |
CN108846125A (en) * | 2018-06-29 | 2018-11-20 | 北京百度网讯科技有限公司 | Talk with generation method, device, terminal and computer readable storage medium |
CN109033223B (en) * | 2018-06-29 | 2021-09-07 | 北京百度网讯科技有限公司 | Method, apparatus, device and computer-readable storage medium for cross-type conversation |
CN109145100A (en) * | 2018-08-24 | 2019-01-04 | 深圳追科技有限公司 | A kind of the Task customer service robot system and its working method of customizable process |
CN109446305A (en) * | 2018-10-10 | 2019-03-08 | 长沙师范学院 | The construction method and system of intelligent tour customer service system |
CN109597607A (en) * | 2018-10-31 | 2019-04-09 | 拓科(武汉)智能技术股份有限公司 | Task interactive system and its implementation, device and electronic equipment |
CN109376228B (en) * | 2018-11-30 | 2021-04-16 | 北京猎户星空科技有限公司 | Information recommendation method, device, equipment and medium |
CN109376228A (en) * | 2018-11-30 | 2019-02-22 | 北京猎户星空科技有限公司 | A kind of information recommendation method, device, equipment and medium |
CN109597993A (en) * | 2018-11-30 | 2019-04-09 | 深圳前海微众银行股份有限公司 | Sentence analysis processing method, device, equipment and computer readable storage medium |
CN109660678A (en) * | 2018-12-07 | 2019-04-19 | 深圳前海微众银行股份有限公司 | Electric core network system realization, system and readable storage medium storing program for executing |
CN110019755A (en) * | 2019-02-27 | 2019-07-16 | 杭州简简科技有限公司 | Digital people's livelihood system and construction method based on artificial intelligence big data |
CN110175240A (en) * | 2019-05-16 | 2019-08-27 | 五竹科技(天津)有限公司 | Construction method, device and the storage medium of knowledge mapping relevant to outgoing call process |
CN110175240B (en) * | 2019-05-16 | 2022-12-09 | 五竹科技(北京)有限公司 | Method and device for constructing knowledge graph related to virtual robot outbound flow |
CN110334347A (en) * | 2019-06-27 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Information processing method, relevant device and storage medium based on natural language recognition |
CN110263144A (en) * | 2019-06-27 | 2019-09-20 | 深圳前海微众银行股份有限公司 | A kind of answer acquisition methods and device |
WO2020258654A1 (en) * | 2019-06-27 | 2020-12-30 | 深圳前海微众银行股份有限公司 | Answer acquisition method and device |
CN110516035A (en) * | 2019-07-05 | 2019-11-29 | 同济大学 | A kind of man-machine interaction method and system of mixing module |
CN110472024A (en) * | 2019-07-11 | 2019-11-19 | 北京云迹科技有限公司 | For the configuration of the customized question and answer of robot, processing method and device, robot |
CN112800188A (en) * | 2019-11-13 | 2021-05-14 | 阿里巴巴集团控股有限公司 | Conversation processing method and device |
CN112800188B (en) * | 2019-11-13 | 2024-02-27 | 阿里巴巴集团控股有限公司 | Dialogue processing method and device |
CN111026855A (en) * | 2019-12-06 | 2020-04-17 | 易小博(武汉)科技有限公司 | Intelligent customer service response method, system, controller and medium |
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 |
CN111080259A (en) * | 2019-12-19 | 2020-04-28 | 中国工商银行股份有限公司 | Multi-robot cooperation system and method based on bank application scene |
CN111104504A (en) * | 2019-12-25 | 2020-05-05 | 天津中科智能识别产业技术研究院有限公司 | Natural language processing and knowledge graph based dialogue method |
CN111966808A (en) * | 2019-12-31 | 2020-11-20 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
CN111966788A (en) * | 2019-12-31 | 2020-11-20 | 北京来也网络科技有限公司 | Dialogue question-answering method, device, equipment and storage medium combining RPA and AI |
CN111274372A (en) * | 2020-01-15 | 2020-06-12 | 上海浦东发展银行股份有限公司 | Method, electronic device, and computer-readable storage medium for human-computer interaction |
CN111309889A (en) * | 2020-02-27 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
CN111309889B (en) * | 2020-02-27 | 2023-04-14 | 支付宝(杭州)信息技术有限公司 | Method and device for text processing |
CN111816173A (en) * | 2020-06-01 | 2020-10-23 | 珠海格力电器股份有限公司 | Dialogue data processing method, device, storage medium and computer equipment |
CN111816173B (en) * | 2020-06-01 | 2024-06-07 | 珠海格力电器股份有限公司 | Dialogue data processing method and device, storage medium and computer equipment |
CN111897942A (en) * | 2020-06-30 | 2020-11-06 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
CN112000786A (en) * | 2020-06-30 | 2020-11-27 | 北京来也网络科技有限公司 | Dialogue robot problem processing method, device and equipment combining RPA and AI |
CN111966716A (en) * | 2020-08-20 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Data processing method and device |
CN111966716B (en) * | 2020-08-20 | 2024-05-28 | 支付宝(杭州)信息技术有限公司 | Data processing method and device |
CN112035640A (en) * | 2020-08-31 | 2020-12-04 | 重庆长安汽车股份有限公司 | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment |
CN112148853A (en) * | 2020-09-15 | 2020-12-29 | 上海风秩科技有限公司 | Query result determination method and device, storage medium and electronic device |
CN112559701A (en) * | 2020-11-10 | 2021-03-26 | 联想(北京)有限公司 | Man-machine interaction method, device and storage medium |
CN112487186A (en) * | 2020-11-27 | 2021-03-12 | 上海浦东发展银行股份有限公司 | Human-human conversation log analysis method, system, equipment and storage medium |
CN112381642B (en) * | 2020-11-30 | 2023-08-22 | 中国银行股份有限公司 | Dot management system and method based on dot robot |
CN112381642A (en) * | 2020-11-30 | 2021-02-19 | 中国银行股份有限公司 | Network management system and method based on network robot |
CN112632239A (en) * | 2020-12-11 | 2021-04-09 | 南京三眼精灵信息技术有限公司 | Brain-like question-answering system based on artificial intelligence technology |
WO2022142019A1 (en) * | 2020-12-30 | 2022-07-07 | 平安科技(深圳)有限公司 | Question distribution method and apparatus based on intelligent robot, and electronic device and storage medium |
CN112800204A (en) * | 2021-02-24 | 2021-05-14 | 浪潮云信息技术股份公司 | Construction method of intelligent dialogue system |
CN113076413B (en) * | 2021-04-30 | 2023-12-26 | 平安国际智慧城市科技股份有限公司 | Parameter association service method, system, device and storage medium |
CN113076413A (en) * | 2021-04-30 | 2021-07-06 | 平安国际智慧城市科技股份有限公司 | Parameter association service method, system, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108197167A (en) | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing | |
CN110096191B (en) | Man-machine conversation method and device and electronic equipment | |
US11315560B2 (en) | Method for conducting dialog between human and computer | |
CN105592237B (en) | A kind of method, apparatus and intelligent customer service robot of session switching | |
CN110138982A (en) | Service based on artificial intelligence is realized | |
WO2018213300A1 (en) | Method and system for developing, training, and deploying effective intelligent virtual agent | |
CN110472023A (en) | Customer service switching method, device, computer equipment and storage medium | |
KR20180071312A (en) | Routing interactions with optimized contact center agents based on machine learning | |
CN108763495B (en) | Interactive method, system, electronic equipment and storage medium | |
CN104813311A (en) | System and methods for virtual agent recommendation for multiple persons | |
CN107451274A (en) | Aid in method for pushing, device, equipment and the storage medium of customer service information | |
CN109460451A (en) | Actively obtain method, the intelligent customer service method and system of user information | |
US20210398150A1 (en) | Method and computer network for gathering evaluation information from users | |
CN109635271A (en) | A kind of user's intension recognizing method, customer service system, device and electronic equipment | |
CN111402071B (en) | Intelligent customer service robot system and equipment for insurance industry | |
CN112925888A (en) | Method and device for training question-answer response and small sample text matching model | |
CN108628908A (en) | The method, apparatus and electronic equipment of sorted users challenge-response boundary | |
Tamrakar et al. | Scientific study of technological chatbot adoption in customer service | |
Jesemann et al. | Migration of the Lean-Startup approach from High-Tech startups towards product design in large manufacturing companies | |
CN112784024B (en) | Man-machine conversation method, device, equipment and storage medium | |
Natt och Dag et al. | An experiment on linguistic tool support for consolidation of requirements from multiple sources in market-driven product development | |
CN116757855A (en) | Intelligent insurance service method, device, equipment and storage medium | |
CN116521832A (en) | Dialogue interaction method, device and system, electronic equipment and storage medium | |
CN109118151B (en) | Work order transaction processing method and work order transaction processing system | |
Stepanov et al. | Estimation of contact center performance measures in case of overload and chatbot implementation |
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: 20180622 |
|
RJ01 | Rejection of invention patent application after publication |