CN107958059A - Intelligent answer method, apparatus, terminal and computer-readable recording medium - Google Patents
Intelligent answer method, apparatus, terminal and computer-readable recording medium Download PDFInfo
- Publication number
- CN107958059A CN107958059A CN201711249343.1A CN201711249343A CN107958059A CN 107958059 A CN107958059 A CN 107958059A CN 201711249343 A CN201711249343 A CN 201711249343A CN 107958059 A CN107958059 A CN 107958059A
- Authority
- CN
- China
- Prior art keywords
- answer
- question
- key
- key message
- storehouse
- 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.)
- Granted
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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of intelligent answer method, including:Extract the key message of problem when user puts question to;Problem trunk is established according to the key message of problem, and is engaged in the dialogue guiding according to problem trunk, obtains key problem retrieval type;The answer to match is inquired about in question and answer storehouse according to key problem retrieval type.Realize the combination of answer matches and dialogue understanding, user can be smoothly switched in both forms, avoid and a plurality of service logic and question and answer intention logic is established in question answering process, user easily can go to ask same problem from a variety of paths, each problem points are without establishing accurate be intended to, developer's workload is reduced, improves question and answer efficiency and question and answer accuracy rate.The present invention also proposes a kind of intelligent answer device, a kind of intelligent answer terminal and a kind of computer-readable recording medium.
Description
Technical field
The present invention relates to field of computer technology, relates generally to a kind of intelligent answer method, further relates to a kind of intelligent answer
Device, terminal and computer-readable recording medium.
Background technology
Since human cost, work efficiency and customer experience are valued very much by enterprise, in recent years, most enterprises are all
Or considering that the website at oneself, APP, business hall etc. introduce intelligent customer service or the intelligent answer production of human-computer interaction
Product, help artificial customer service to answer universal problem, so that the part duplication of labour of customer service link is substituted, due to intelligent answer product
Can help enterprise significantly reduces human cost, therefore question and answer class demand is always the firm of generally existing during enterprise operation
Need.At present, intelligent answer is had been widely used in industry-by-industry, finance especially larger to consulting amount, telecommunications, government affairs, electric business
Field.
At present, existing intelligent answer product mainly has two aspect functions:In Primary Speciation, i.e., first index question and answer money
Source, goes out the question and answer resource with user demand " approximate ", the intelligent answer method of Primary Speciation using Semantic Search " matching "
It can not be combined with dialogue management;In advanced form, NLU (natural language understanding Natural are understood by dialogue
Language Understanding) it is combined with dialogue management, language understanding is the form of " intention+word groove ", and pass through
Successor technologies carry out accurate answer generation.Developer is typically to the demand of intelligent answer product:First pass through above-mentioned primary shape
State, that is, answer matches meet primary demand, afterwards, part high frequency question and answer demand are picked out from answer matches, passes through advanced shape
State is to talk with the dialogue management in understanding to provide more good user experience.
However, during using Semantic Search, since user is when puing question to, there are a variety of enquirement thinkings, but final ask
Topic is consistent, and existing question answering system extracts key message point of the user when puing question to first, establishes a plurality of service logic, it
Afterwards, immediate question and answer resource is matched in question and answer resources bank, obtained question and answer resource can not also directly obtain accurate problem,
Afterwards, a plurality of question and answer are established according to key message point and immediate question and answer resource and is intended to logic, being intended to logic by question and answer examines
Rope obtains immediate question and answer and is intended to, and obtains accurate problem.In the above process, establish a plurality of service logic and question and answer and be intended to logic
It might have thousands of up to ten thousand, it is necessary to mass data is trained study, not only take, cost is also very high.
Therefore, how efficiently quickly to provide accurate question and answer is that those skilled in the art are badly in need of technical problems to be solved.
The content of the invention
The embodiment of the present invention provides a kind of intelligent answer method, intelligent answer device, intelligent answer terminal and computer
Readable storage medium storing program for executing, at least to solve above technical problem of the prior art.
In a first aspect, an embodiment of the present invention provides a kind of intelligent answer method, including:
Extract the key message of problem when user puts question to;
Problem trunk is established according to the key message of described problem, and is engaged in the dialogue guiding according to described problem trunk, is obtained
To key problem retrieval type;
The answer to match is inquired about in question and answer storehouse according to the key problem retrieval type.
With reference to first aspect, the present invention is described according to the key problem in the first embodiment of first aspect
Retrieval type is inquired about in question and answer storehouse before the answer to match, is further included:
Classify to the question and answer storehouse according to Question-Answering Model, obtain multiple function question and answer storehouses.
With reference to first aspect, the present invention is described according to the key problem in second of embodiment of first aspect
Retrieval type inquires about the answer to match in question and answer storehouse to be included:
The function question and answer storehouse to be matched according to key problem retrieval type inquiry, and in the function question and answer storehouse
Inquire about the answer to match.
With reference to first aspect, in the third embodiment of first aspect, the extraction user asks the present invention when puing question to
The key message of topic, including:
The problem of being selected for user class node is provided successively according to classified order, according to the institute selected every time
State Question Classification node to engage in the dialogue guiding, the key message of described problem is extracted in dialog procedure.
With reference to first aspect, in the 4th kind of embodiment of first aspect, the extraction user asks the present invention when puing question to
The key message of topic, including:
The problem of multiple and different species for being used for user selection are provided at the same time class node, according to one selected
Or the described problem class node of multiple species engages in the dialogue guiding, the key message of described problem is extracted in dialog procedure.
Second aspect, an embodiment of the present invention provides a kind of intelligent answer device, including:
Information extraction modules, for extracting the key message of problem when user puts question to;
Problem establishes module, for establishing problem trunk according to the key message of described problem, and according to described problem master
The dry guiding that engages in the dialogue, obtains key problem retrieval type;
Answer enquiry module, for inquiring about the answer to match in question and answer storehouse according to the key problem retrieval type.
In a possible design, the intelligent answer device further includes:
Question and answer storehouse sort module, for classifying to the question and answer storehouse according to Question-Answering Model, obtains multiple function question and answer
Storehouse.
In a possible design, described information extraction module includes:
First extraction unit, for providing the problem of being selected for user class node successively according to classified order,
Described problem class node according to having selected every time engages in the dialogue guiding, and the crucial letter of described problem is extracted in dialog procedure
Breath.
In a possible design, described information extraction module includes:
Second extraction unit, at the same time provide be used for the user selection multiple and different species the problem of classification section
Point, engages in the dialogue guiding according to the described problem class node of the one or more species selected, is extracted in dialog procedure
The key message of described problem.
The third aspect, an embodiment of the present invention provides a kind of intelligent answer terminal, including:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are performed by one or more of processors so that one or more of places
Manage method of the device realization as described in any in above-mentioned first aspect.
Fourth aspect, an embodiment of the present invention provides a kind of computer-readable recording medium, it is stored with computer program,
When the program is executed by processor realize first aspect include it is any as described in method.
A technical solution in above-mentioned technical proposal has the following advantages that or beneficial effect:In the present solution, by that will use
Key message when family is putd question to carries out integration and establishes problem trunk, engages in the dialogue have built up the problem of and draws on the basis of trunk
Lead, obtain key problem retrieval type, the answer to match is inquired about in question and answer storehouse by key problem retrieval type, avoids and is asking
A plurality of service logic and question and answer are established during answering and is intended to logic, reduces developer's workload, question and answer efficiency is improved and question and answer is accurate
True rate.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to is limited in any way.Except foregoing description
Schematical aspect, outside embodiment and feature, it is further by reference to attached drawing and the following detailed description, the present invention
Aspect, embodiment and feature would is that what is be readily apparent that.
Brief description of the drawings
In the accompanying drawings, unless specified otherwise herein, otherwise represent the same or similar through the identical reference numeral of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Some disclosed embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is a kind of intelligent answer method flow schematic diagram that embodiment of the present invention provides;
Fig. 2 is a kind of intelligent answer apparatus structure schematic diagram that embodiment of the present invention provides;
Fig. 3 is a kind of intelligent answer terminal structure schematic diagram that embodiment of the present invention provides.
Embodiment
Hereinafter, some exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be changed by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Embodiment one
An embodiment of the present invention provides a kind of intelligent answer method, as shown in Figure 1, this method mainly includes:
S1:Extract the key message of problem when user puts question to.
Specifically, due to puing question to thinking different with custom, what different users often expressed when puing question to asks
The problem of topic has a more otherness, and according to speech habits, and usually first proposition one is fuzzy direction, therefore, needs first
To extract key message in user's asked questions so that problem definitely, easy to subsequently carry out further determine more
The problem of accurate and answer.
For example, user may first ask:I has wanted to take off the problem of cash is borrowed;I wants to understand the thing refunded;I wants to understand
How to be refunded with mobile phone.During progressively puing question to, key message " cash loan ", " refund ", " mobile phone " are extracted.Carry
Take the mode of key message to be not specifically limited in the present embodiment, can gradually be provided by question and answer system and be selected for user
Key message, alternatively, user can question and answer system at the same time provide multiple key messages in make choice, in this implementation
In the protection domain of example.
S2:Problem trunk is established according to the key message of problem, and is engaged in the dialogue guiding according to problem trunk, obtains core
Problem retrieval type.
Wherein, problem trunk is generated according to the key message of problem, for example, " cash loan+refund+mobile phone ", problem trunk
Illustrate, the problem of user is the problem of keyword surrounded in problem trunk is unfolded, and only problematic trunk can only obtain user
Direction, the real problems that cannot get user are intended to, and therefore, inquiry user kernel are guided by talking with the basis of problem trunk
Problem points, for example, how to go back cash loan, cash is borrowed and is refunded with what mode, the service charge of refund, time of refund etc.,
By talking with guiding and progressively inquiring, by the answer answered each time of user, the final accurate problem of user is progressively obtained,
That is key problem retrieval type.
S3:The answer to match is inquired about in question and answer storehouse according to key problem retrieval type.
Wherein, due to including more specific more accurate key problem, and and key problem in question and answer storehouse
The accurate answer to match, therefore, retrieves matched key problem, and then look for according to key problem retrieval type in question and answer storehouse
To the corresponding accurate answer of key problem.
In the present embodiment, key message during by the way that user being putd question to carries out integration and establishes problem trunk, is having built up
The problem of trunk on the basis of engage in the dialogue guiding, key problem retrieval type is obtained, by key problem retrieval type in question and answer storehouse
It is middle to inquire about the answer to match, the combination of answer matches and dialogue understanding is realized, user can be smoothly in both forms
In switch over, avoid and a plurality of service logic and question and answer are established in question answering process be intended to logic, user can easily from
A variety of paths are gone to ask same problem, and each problem points reduce developer's workload, improve question and answer effect without establishing accurate intention
Rate and question and answer accuracy rate.
On the basis of the first embodiment, inquired about in question and answer storehouse according to key problem retrieval type and examined with key problem
Before cable-styled corresponding answer, further include:
Classify to question and answer storehouse according to Question-Answering Model, obtain multiple function question and answer storehouses.
Wherein, by way of successively refining, it can also realize the subdivision to question and answer storehouse, be divided according to classifying rules
Class so that the problem of the problem of being included in question and answer storehouse and answer are only directed to a certain specific aspect and answer, for example, cash is borrowed
Question and answer storehouse, house ornamentation borrow question and answer storehouse, credit card repayment question and answer storehouse etc..
It is pointed out that question and answer storehouse sorting technique is not specifically limited in the present embodiment, can be as the case may be
Classifying rules is designed, meets the diversity in function question and answer storehouse.
On the basis of the first embodiment, the answer to match is inquired about in question and answer storehouse according to key problem retrieval type
Including:
The function question and answer storehouse to be matched according to the inquiry of key problem retrieval type, and phase is inquired about in the function question and answer storehouse
The answer matched somebody with somebody.
Wherein, the function of being easiest to match accurate answer is directed the user to by rule and key problem retrieval type
Question and answer storehouse.Such as:Key problem retrieval type is guided to cash for " cash loan+refund+mobile phone+service charge " and borrows question and answer storehouse, core
Heart problem retrieval type guides to house ornamentation for " house ornamentation cash loan+refund+mobile phone+service charge " and borrows question and answer storehouse etc., and question and answer are borrowed in cash
Storehouse or house ornamentation, which are borrowed to find in question and answer storehouse, thinks corresponding answer, can not only improve question and answer efficiency, and can also be supplied to user more
Accurate question and answer are added to experience.
On the basis of the first embodiment, the key message of problem when extraction user puts question to, including:
The problem of being selected for user class node is provided successively according to classified order, according to the problem of selection every time points
Class node engages in the dialogue guiding, and the key message of problem is extracted in dialog procedure.
Specifically, provide the problem of class node can be Railway Project classify direction, such as " cash loan ", " credit card loan ",
" bank loan " etc., user select one of Question Classification node, and such as " cash loan ", then user borrows this in cash and asks
The problem of being borrowed on cash is answered under topic class node, guides the true question and answer for drawing user to be intended to by talking with, as user returns
Answer " cash is borrowed and how to refund ", then the problems such as providing " refunding the time ", " refund service charge " node is selected for user, if user
After selection " refunding the time ", continue dialogue guiding, " cash loan ", " refund " are finally extracted in dialogue and " is refunded
The key message of time ".
On the basis of the first embodiment, the key message of problem when extraction user puts question to, including:
The problem of multiple and different species for being used for user's selection are provided at the same time class node, according to one or more selected
The problem of a species, class node engaged in the dialogue guiding, and the key message of problem is extracted in dialog procedure.
Specifically, the problem of multiple and different species are provided at the same time class node, such as " cash loan ", " refunding the time ", " mobile phone
Refund " a series of problems, such as class node, user can with simultaneous selection itself be concerned about one or several Question Classification nodes,
Engage in the dialogue guiding afterwards, and the key message of problem is extracted in dialog procedure.
Embodiment two
In another specific embodiment, there is provided a kind of intelligent answer device, as shown in Fig. 2, including:
Information extraction modules 100, for extracting the key message of problem when user puts question to;
Problem establishes module 200, for establishing problem trunk according to the key message of described problem, and according to described problem
Trunk engages in the dialogue guiding, obtains key problem retrieval type;
Answer enquiry module 300, for inquiring about the answer to match in question and answer storehouse according to the key problem retrieval type.
In a possible design, intelligent answer device further includes:
Question and answer storehouse sort module, for classifying to the question and answer storehouse according to Question-Answering Model, obtains multiple function question and answer
Storehouse.
In a possible design, information extraction modules 100 include:
First extraction unit, for providing the problem of being selected for user class node successively according to classified order,
Described problem class node according to having selected every time engages in the dialogue guiding, and the crucial letter of described problem is extracted in dialog procedure
Breath.
In a possible design, information extraction modules 100 include:
Second extraction unit, at the same time provide be used for the user selection multiple and different species the problem of classification section
Point, engages in the dialogue guiding according to the described problem class node of the one or more species selected, is extracted in dialog procedure
The key message of described problem.
Embodiment three
In another embodiment, there is provided a kind of intelligent answer terminal, as shown in figure 3, including:
Memory 32 and processor 31,32 memory of memory contain the computer program that can be run on processor 31.Place
Reason device 31 realizes the intelligent answer method in above-described embodiment when performing the computer program.Memory 32 and processor 31
Quantity can be one or more.
Communication interface 33, communicates for memory 32 and processor 31 with outside.
Memory 32 may include high-speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
If memory 32, processor 31 and the independent realization of communication interface 33, memory 32, processor 31 and communication connect
Mouth 33 can be connected with each other by bus and complete mutual communication.The bus can be industry standard architecture
(ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral
Component) bus or extended industry-standard architecture (EISA, Extended Industry Standard
Component) bus etc..The bus can be divided into address bus, data/address bus, controlling bus etc..For ease of representing, Fig. 3
In only represented with a thick line, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 32, processor 31 and communication interface 33 are integrated in chip piece
On, then memory 32, processor 31 and communication interface 33 can complete mutual communication by internal interface.
Example IV
In another embodiment, there is provided a kind of computer-readable recording medium, it is stored with computer journey
Sequence, when which is executed by processor realize first aspect include it is any as described in method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment of the present invention or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the different embodiments or example described in this specification and different embodiments or exemplary spy
Sign is combined and combines.
In addition, term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, " first " is defined, the feature of " second " can be expressed or hidden
Include at least one this feature containing ground.In the description of the present invention, " multiple " are meant that two or more, unless otherwise
It is clearly specific to limit.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used for realization specific logical function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic at the same time in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.
Computer-readable medium described in the embodiment of the present invention can be that computer-readable signal media or computer can
Read storage medium either the two any combination.The more specifically example of computer-readable recording medium is at least (non-poor
Property list to the greatest extent) including following:Electrical connection section (electronic device) with one or more wiring, portable computer diskette box (magnetic
Device), random access memory (RAM), read-only storage (ROM), erasable edit read-only storage (EPROM or flash
Memory), fiber device, and portable read-only storage (CDROM).In addition, computer-readable recording medium even can be with
It is the paper or other suitable media that can print described program on it, because can be for example by being carried out to paper or other media
Optical scanner, is then handled described electronically to obtain into edlin, interpretation or if necessary with other suitable methods
Program, is then stored in computer storage.
In embodiments of the present invention, computer-readable signal media can be included in a base band or as a carrier wave part
The data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of
Form, includes but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also
Can be any computer-readable medium beyond computer-readable recording medium, which can send, pass
Either transmission is broadcast for instruction execution system, input method or device use or program in connection.Computer can
The program code for reading to include on medium can be transmitted with any appropriate medium, be included but not limited to:Wirelessly, electric wire, optical cable, penetrate
Frequently (Radio Frequency, RF) etc., or above-mentioned any appropriate combination.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized:With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In readable storage medium storing program for executing.The storage medium can be read-only storage, disk or CD etc..
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, its various change or replacement can be readily occurred in,
These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
Protect subject to scope.
Claims (11)
- A kind of 1. intelligent answer method, it is characterised in that including:Extract the key message of problem when user puts question to;Problem trunk is established according to the key message of described problem, and is engaged in the dialogue guiding according to described problem trunk, obtains core Heart problem retrieval type;The answer to match is inquired about in question and answer storehouse according to the key problem retrieval type.
- 2. according to the method described in claim 1, it is characterized in that, it is described according to the key problem retrieval type in question and answer storehouse Inquire about before the answer to match, further include:Classify to the question and answer storehouse according to Question-Answering Model, obtain multiple function question and answer storehouses.
- 3. according to the method described in claim 2, it is characterized in that, it is described according to the key problem retrieval type in question and answer storehouse Inquiring about the answer to match includes:The function question and answer storehouse to be matched according to key problem retrieval type inquiry, and inquired about in the function question and answer storehouse The answer to match.
- 4. according to the method described in claim 1, it is characterized in that, the key message for extracting problem when user puts question to, bag Include:The problem of being selected for user class node is provided successively according to classified order, is asked according to having selected every time Topic class node engages in the dialogue guiding, the key message of extraction described problem in dialog procedure.
- 5. according to the method described in claim 1, it is characterized in that, the key message for extracting problem when user puts question to, bag Include:The problem of multiple and different species for being used for user selection are provided at the same time class node, according to one or more selected The described problem class node of a species engages in the dialogue guiding, and the key message of described problem is extracted in dialog procedure.
- A kind of 6. intelligent answer device, it is characterised in that including:Information extraction modules, for extracting the key message of problem when user puts question to;Problem establishes module, for establishing problem trunk according to the key message of described problem, and according to described problem trunk into Row dialogue guiding, obtains key problem retrieval type;Answer enquiry module, for inquiring about the answer to match in question and answer storehouse according to the key problem retrieval type.
- 7. intelligent answer device as claimed in claim 6, it is characterised in that further include:Question and answer storehouse sort module, for classifying to the question and answer storehouse according to Question-Answering Model, obtains multiple function question and answer storehouses.
- 8. intelligent answer device as claimed in claim 6, it is characterised in that described information extraction module includes:First extraction unit, for providing the problem of being used for user selection class node successively in sequence, according to each The described problem class node selected engages in the dialogue guiding, and the key message of described problem is extracted in dialog procedure.
- 9. intelligent answer device as claimed in claim 6, it is characterised in that described information extraction module includes:Second extraction unit, multiple Question Classification nodes of user selection is used for for providing at the same time, according to what is selected One or more described problem class nodes engage in the dialogue guiding, and the key message of described problem is extracted in dialog procedure.
- A kind of 10. intelligent answer terminal, it is characterised in that including:One or more processors;Memory, for storing one or more programs;When one or more of programs are performed by one or more of processors so that one or more of processors Realize the method as described in any in claim 1-5.
- 11. a kind of computer-readable recording medium, it is stored with computer program, it is characterised in that the program is held by processor The method as described in any in claim 1-5 is realized during row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711249343.1A CN107958059B (en) | 2017-12-01 | 2017-12-01 | Intelligent question answering method, device, terminal and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711249343.1A CN107958059B (en) | 2017-12-01 | 2017-12-01 | Intelligent question answering method, device, terminal and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107958059A true CN107958059A (en) | 2018-04-24 |
CN107958059B CN107958059B (en) | 2020-07-10 |
Family
ID=61962870
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711249343.1A Active CN107958059B (en) | 2017-12-01 | 2017-12-01 | Intelligent question answering method, device, terminal and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107958059B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532366A (en) * | 2019-09-03 | 2019-12-03 | 出门问问(武汉)信息科技有限公司 | A kind of pattern rule management method, language generation method, apparatus and storage equipment |
WO2020038251A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳追一科技有限公司 | Process customizing system and method, and computer readable storage medium |
CN111552787A (en) * | 2020-04-23 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Question and answer processing method, device, equipment and storage medium |
CN111626452A (en) * | 2019-02-28 | 2020-09-04 | 百度在线网络技术(北京)有限公司 | Intelligent government affair processing method, device, terminal and medium |
CN113297361A (en) * | 2021-05-24 | 2021-08-24 | 陕西合友网络科技有限公司 | Intelligent question-answer interaction system and method based on visual flow chart |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1928864A (en) * | 2006-09-22 | 2007-03-14 | 浙江大学 | FAQ based Chinese natural language ask and answer method |
US20130204430A1 (en) * | 2011-08-29 | 2013-08-08 | Neil S. Davey | Pharmacy automation using autonomous robot |
CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
CN104331148A (en) * | 2014-09-23 | 2015-02-04 | 普强信息技术(北京)有限公司 | Voice user interface information interaction method |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
-
2017
- 2017-12-01 CN CN201711249343.1A patent/CN107958059B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1928864A (en) * | 2006-09-22 | 2007-03-14 | 浙江大学 | FAQ based Chinese natural language ask and answer method |
US20130204430A1 (en) * | 2011-08-29 | 2013-08-08 | Neil S. Davey | Pharmacy automation using autonomous robot |
CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
CN104331148A (en) * | 2014-09-23 | 2015-02-04 | 普强信息技术(北京)有限公司 | Voice user interface information interaction method |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020038251A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳追一科技有限公司 | Process customizing system and method, and computer readable storage medium |
CN111626452A (en) * | 2019-02-28 | 2020-09-04 | 百度在线网络技术(北京)有限公司 | Intelligent government affair processing method, device, terminal and medium |
CN111626452B (en) * | 2019-02-28 | 2023-08-04 | 百度在线网络技术(北京)有限公司 | Intelligent government affair processing method, device, terminal and medium |
CN110532366A (en) * | 2019-09-03 | 2019-12-03 | 出门问问(武汉)信息科技有限公司 | A kind of pattern rule management method, language generation method, apparatus and storage equipment |
CN111552787A (en) * | 2020-04-23 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Question and answer processing method, device, equipment and storage medium |
CN111552787B (en) * | 2020-04-23 | 2023-06-30 | 支付宝(杭州)信息技术有限公司 | Question-answering processing method, device, equipment and storage medium |
CN113297361A (en) * | 2021-05-24 | 2021-08-24 | 陕西合友网络科技有限公司 | Intelligent question-answer interaction system and method based on visual flow chart |
Also Published As
Publication number | Publication date |
---|---|
CN107958059B (en) | 2020-07-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107958059A (en) | Intelligent answer method, apparatus, terminal and computer-readable recording medium | |
US11645517B2 (en) | Information processing method and terminal, and computer storage medium | |
CN107609186A (en) | Information processing method and device, terminal device and computer-readable recording medium | |
CN108170859A (en) | Method, apparatus, storage medium and the terminal device of speech polling | |
CN108170792A (en) | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence | |
CN107590216A (en) | Answer preparation method, device and computer equipment | |
CN107729251A (en) | Testing case management and device | |
CN109299375A (en) | Information personalized push method, device, electronic equipment and storage medium | |
CN106844341A (en) | News in brief extracting method and device based on artificial intelligence | |
CN107733984A (en) | A kind of method, terminal and computer-readable recording medium for pushing screen locking information | |
CN106874259A (en) | A kind of semantic analysis method and device, equipment based on state machine | |
CN111182162A (en) | Telephone quality inspection method, device, equipment and storage medium based on artificial intelligence | |
CN109783624A (en) | Answer generation method, device and the intelligent conversational system in knowledge based library | |
CN105989067A (en) | Method for generating text abstract from image, user equipment and training server | |
CN109582882A (en) | Search result shows method, apparatus and electronic equipment | |
CN112364622B (en) | Dialogue text analysis method, device, electronic device and storage medium | |
CN109739969A (en) | Answer generation method and intelligent conversational system | |
CN108039175A (en) | Audio recognition method, device and server | |
CN110059178A (en) | Problem distributing method and device | |
CN108304374A (en) | Information processing method and related product | |
CN108694183A (en) | A kind of search method and device | |
CN109903122A (en) | House prosperity transaction information processing method, device, equipment and storage medium | |
CN113139816A (en) | Information processing method, device, electronic equipment and storage medium | |
CN109493186A (en) | The method and apparatus for determining pushed information | |
CN113726942A (en) | Intelligent telephone answering method, system, medium and electronic terminal |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |