CN109815321A - Question answering method, device, equipment and storage medium - Google Patents
Question answering method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109815321A CN109815321A CN201811602582.5A CN201811602582A CN109815321A CN 109815321 A CN109815321 A CN 109815321A CN 201811602582 A CN201811602582 A CN 201811602582A CN 109815321 A CN109815321 A CN 109815321A
- Authority
- CN
- China
- Prior art keywords
- customer problem
- key message
- answer
- information
- semantic understanding
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The present disclosure provides a question answering method, including: receiving a user question; performing semantic understanding on the received user questions; based on semantic understanding, intention classification is carried out on the user questions, and key information in the user questions is extracted; selecting a corresponding task line based on the intent classification; and generating an answer to the user question based on the selected task line and the key information. The disclosure also provides a question answering device, an electronic device and a readable storage medium.
Description
Technical field
This disclosure relates to a kind of answering method, question and answer system, electronic equipment and readable storage medium storing program for executing.
Background technique
Current question answering system such as game knowledge Q-A system, the mode for being based primarily upon template matching carry out, and store up in advance
There are some problem template and answer, customer problem is matched with template problem, and exports most matched template problem
Answer supports type to increase, it is necessary to increase corresponding template.This system lacks flexibility, needs a large amount of template, and
Maintenance cost is higher, shows " stiff ", " machinery ".
Such as based in matched game question answering system, a typical system structure is as follows:
Dialog state information --- template matching --- answer output.
This method and system based on template matching is easy to construct, but during expansion needs to be continuously added new
Template, with increasing for Questions types, template number is presented exponential type and increases, it is difficult to safeguard, while lack flexibility.
Summary of the invention
At least one of in order to solve the above-mentioned technical problem, present disclose provides a kind of answering method, question and answer system, electricity
Sub- equipment and readable storage medium storing program for executing.
According to one aspect of the disclosure, a kind of answering method, comprising: receive customer problem;To received customer problem
Carry out semantic understanding;Based on semantic understanding, intent classifier is carried out to customer problem, extracts the key message in customer problem;Base
In intent classifier, corresponding task line is selected;And task line and key message based on selection, generate answering for customer problem
Case.
According at least one embodiment of the disclosure, key message is the combination more than one or two of following:
Entity, attribute, relationship.
According at least one embodiment of the disclosure, it is intended that classification is including being intended to region and being intended to content, based on intention
When the corresponding task line of categorizing selection, based on being intended to regional choice task line.
According at least one embodiment of the disclosure, further includes: to the key son letter of the key message in customer problem
Breath carries out missing judgement, if some crucial sub-information or certain several crucial sub-information are lacked, to this customer problem
The crucial sub-information of the upper problem of same user or upper several problems inquiry missing, if inquiring the key son letter of missing
Breath, then inherit the key sub-information;Key message includes one or more crucial sub-information.
According at least one embodiment of the disclosure, further includes: if not inquiring the crucial sub-information of missing, give birth to
At feedback information.
It further include being carried out to the entity in the key message in customer problem according at least one embodiment of the disclosure
It refers to judgement: according to the attribute or relationship in the key message in customer problem, judging reference of the entity in knowledge mapping.
According at least one embodiment of the disclosure, task line and key message based on selection obtain customer problem
When answer, external search engine is called according to task line options or inquires knowledge mapping to generate the answer of customer problem.
According at least one embodiment of the disclosure, task line and key message based on selection obtain customer problem
When answer, corresponding answer template is selected according to intent classifier, answer template is filled according to the answer of key message and acquisition.
According to another aspect of the present disclosure, a kind of question and answer system, comprising: problem receiving module, problem receiving module receive
Customer problem;Semantic understanding module, semantic understanding module carry out semantic understanding to received customer problem;Dialogue management module,
Dialogue management module is based on semantic understanding, carries out intent classifier to customer problem, extracts the key message in customer problem;It is based on
Intent classifier selects corresponding task line;And answer generation module, task line and key of the answer generation module based on selection
Information generates the answer of customer problem.
According to the another aspect of the disclosure, a kind of electronic equipment, comprising: memory, memory storage computer execution refer to
It enables;And processor, processor executes the computer executed instructions of memory storage, so that processor executes above-mentioned method.
According to the another further aspect of the disclosure, a kind of readable storage medium storing program for executing is stored with computer execution in readable storage medium storing program for executing
Instruction, for realizing above-mentioned method when computer executed instructions are executed by processor.
Detailed description of the invention
Attached drawing shows the illustrative embodiments of the disclosure, and it is bright together for explaining the principles of this disclosure,
Which includes these attached drawings to provide further understanding of the disclosure, and attached drawing is included in the description and constitutes this
Part of specification.
Fig. 1 is the schematic flow chart according to the answering method of one embodiment of the disclosure.
Fig. 2 is the key that the schematic stream of sub-information inheritance method in the answering method according to one embodiment of the disclosure
Cheng Tu.
Fig. 3 is the key that the schematic stream of sub-information inheritance method in the answering method according to one embodiment of the disclosure
Cheng Tu.
Fig. 4 is the schematic flow chart of the reference resolution method in the answering method according to one embodiment of the disclosure.
Fig. 5 is the schematic flow chart of the call method in the answering method according to one embodiment of the disclosure.
Fig. 6 is the structural schematic diagram according to the question and answer system of one embodiment of the disclosure.
Fig. 7 is the structural schematic diagram according to the question and answer system of one embodiment of the disclosure.
Fig. 8 is the structural schematic diagram according to the electronic equipment of one embodiment of the disclosure.
Specific embodiment
The disclosure is described in further detail with embodiment with reference to the accompanying drawing.It is understood that this place
The specific embodiment of description is only used for explaining related content, rather than the restriction to the disclosure.It also should be noted that being
Convenient for description, part relevant to the disclosure is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can
To be combined with each other.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with embodiment.
In accordance with one embodiment of the present disclosure, a kind of answering method is provided, as shown in Figure 1, answering method includes step
S11, S12, S13, S14 and S15 are specifically included: receiving customer problem S11;Semantic understanding is carried out to received customer problem
S12;Based on semantic understanding, intent classifier is carried out to customer problem, extracts the key message S13 in customer problem;Based on intention
Classification, selects corresponding task line S14;And task line and key message based on selection, generate the answer of customer problem
S15。
Wherein, received customer problem can be text formatting, phonetic matrix or other methods known in the art record
The customer problem entered.
Semantic understanding is carried out to received customer problem.For example, by using the methods of condition random field or regular expression into
Row semantic understanding.
Intent classifier is carried out to customer problem.In an embodiment of the disclosure, it is intended that classification includes being intended to region
With intention content, when selecting corresponding task line based on intent classifier, it is based on being intended to regional choice task line.Such as answering method
When applied in game knowledge Q-A system, with customer problem " attack of Zhang Fei is how many? " for, it is intended that it is classified as " people
Object " (be intended to region) and " attack " (intention content), with customer problem " lethality of zhang eight snake lances is how many? " for, meaning
Figure is classified as " article " (being intended to region) and " lethality " (being intended to content).
Extract the key message in customer problem.Still with above-mentioned customer problem " attack of Zhang Fei is how many? " for into
Row explanation.Key message includes entity and attribute or entity and relationship etc..In customer problem, " attack of Zhang Fei is more
It is few? " in, entity is " Zhang Fei ", and attribute is " attack ", then the key message extracted is " personage: Zhang Fei;Attribute: attack
Power." for example customer problem " whom Zhang Fei restrains? " in, key message includes entity and relationship, and in customer problem, " Zhang Fei restrains
Who? " in, entity is " Zhang Fei ", and relationship is " restraint ", then the key message for extracting family is " personage: Zhang Fei;Relationship: gram
System.", the answer of this customer problem is the worrior personage that Zhang Fei restrains.
Based on intent classifier, corresponding task line is selected.I.e. according to different intent classifiers, different task lines is selected,
Such as according to the graph region that disagrees in above-mentioned example, personage or article, to select corresponding task line.
Task line and key message based on selection, generate the answer of customer problem.Such as by executing corresponding task
It line and is inquired in knowledge mapping using key message, obtains answer.
In an embodiment of the disclosure, key message is the combination more than one or two of following: entity,
Attribute, relationship.
In an embodiment of the disclosure, in answering method, including crucial sub-information inheritance method, such as Fig. 2 institute
Show, specifically: missing is carried out to the crucial sub-information of the key message in customer problem and judges S21, if lacking some pass
Key sub-information or certain several crucial sub-information S22, then to the upper problem of the same user of this customer problem or several upper
The crucial sub-information S23 of problem inquiry missing inherits the key sub-information if inquiring the crucial sub-information S24 of missing
S25;Key message therein includes one or more crucial sub-information.Crucial sub-information can be " personage ", " attribute ",
" relationship " etc..
Such as the first problem of user is " attack of Zhang Fei is how many? ", answering method can extract " personage:
Zhang Fei;Attribute: attack ", the Second Problem of user is " his phylactic power defensive power? ", gone to appointing for people information inquiry
Business line, but lack necessary " personage " this crucial sub-information, therefore the Second Problem of user is needed the first of user
Crucial sub-information " personage: Zhang Fei " succession in a problem comes.
Such as user first problem is " whom Zhang Fei restrains? " again, answering method can extract " personage: Zhang Fei;It closes
System: restrain ", the Second Problem of user is " Na Guanyu? ", the task line of people information inquiry has been gone to, but lack
The key sub-information such as necessary " attribute " or " relationship ", therefore the Second Problem of user is needed the first problem of user
In crucial sub-information " relationship: restraining " inherit.
In an embodiment of the disclosure, as shown in figure 3, crucial sub-information inheritance method further include: if do not looked into
The crucial sub-information S242 for asking missing, then generate feedback information S252.
For example, the n-th problem of user is " attack is how many? ", crucial sub-information is lacked, then to the upper of same user
The crucial sub-information of one problem or upper several problems inquiry missing needs to generate feedback information if still do not inquired,
Such as: ask user " needing that whose is inquired? ".
It in accordance with one embodiment of the present disclosure, further include reference resolution method in answering method, as shown in figure 4, referring to
Digestion procedure, which is specifically included, carries out reference judgement to the entity in the key message in customer problem: according to the pass in customer problem
Attribute or relationship in key information judge reference S44 of the entity in knowledge mapping.Receiving customer problem S41, docking
The customer problem of receipts carries out semantic understanding S42, is based on semantic understanding, carries out intent classifier to customer problem, extracts customer problem
In key message S43 after, execute above-mentioned reference resolution method.
For example, for customer problem " attack of Zhang Fei is how many ", but have Zhang Fei in A game and B game, lead to
Cross known to inquiry knowledge mapping: Zhang Fei is a businessman in A game, does not have this attribute of attack, and Zhang Fei is war in B game
Scholar has this attribute of attack, then can be inferred that Zhang Fei herein refers to the Zhang Fei in B game.I.e. not according to attribute
It is same to realize reference resolution.
In accordance with one embodiment of the present disclosure, the task line based on selection and key message obtain the answer of customer problem
When, answering method further includes call method, as shown in figure 5, calling external search engine or inquiry to know according to task line options
Map is known to generate the answer S55 of customer problem.Is receiving customer problem S51, semantic reason is carried out to received customer problem
It solves S52, be based on semantic understanding, intent classifier is carried out to customer problem, extract the key message S53 in customer problem, be based on meaning
Figure classification, after selecting corresponding task line S54, executes above-mentioned call method.
For example, weather lookup needs to call other searching resources such as corresponding weather of search engine removal search, and " Zhang Fei
Attack be how many "/" whom jinx of Zhang Fei is "/" jinx of Zhang Fei has several "/" attack is highest in the jinx of Zhang Fei
Whom is " then need to be converted to corresponding query statement, it calls knowledge mapping to do corresponding inquiry, obtains problem answers.
In accordance with one embodiment of the present disclosure, the task line based on selection and key message obtain the answer of customer problem
When, corresponding answer template is selected according to intent classifier, answer template is filled according to the answer of key message and acquisition.
For example, all information obtained in above-mentioned answering method are formed problem answers, for example " personage looks into according to intention
The $ attribute $ of inquiry " selection answer template $ people $ is $ number $.By " personage: Zhang Fei;Attribute: attack." and
The result inquired " attack: 35 " inserts corresponding position, obtains problem answers " attack of Zhang Fei is 35 ".Pass through meaning
The corresponding answer template of figure categorizing selection, according to the key message extracted from customer problem and the result inquired to answer mould
Plate is filled.
In an embodiment of the disclosure, as shown in fig. 6, additionally providing a kind of question and answer system, question and answer system 10 is wrapped
Include: problem receiving module 101, problem receiving module 101 receive customer problem;Semantic understanding module 102, semantic understanding module
102 pairs of received customer problems carry out semantic understanding;Dialogue management module 103, dialogue management module 103 are based on semantic understanding,
Intent classifier is carried out to customer problem, extracts the key message in customer problem;Based on intent classifier, corresponding task is selected
Line;And answer generation module 104, task line and key message of the answer generation module 104 based on selection generate customer problem
Answer.Question and answer system 10 can call external search engine 105 and/or call knowledge mapping 106.Knowledge mapping 106 can be with
Configuration, referring to Fig. 6, also can be only fitted to except question and answer system 10, referring to Fig. 7 among question and answer system 10.In knowledge mapping 106
The information such as entity, relationship, attribute are stored, answer template is stored.
In an embodiment of the disclosure, semantic understanding module 102 executes intent classifier and pass in the above method
Key information extracts.
In an embodiment of the disclosure, semantic understanding module 102 executes the reference resolution method in the above method.
In an embodiment of the disclosure, semantic understanding module 102 executes the calling to knowledge mapping 106.
In an embodiment of the disclosure, dialogue management module 103 executes the task line options in the above method.
In an embodiment of the disclosure, dialogue management module 103 executes the reference resolution method in the above method.
In an embodiment of the disclosure, dialogue management module 103 execute the above method in crucial sub-information after
Hold method.
In an embodiment of the disclosure, dialogue management module 103 executes the calling to external search engine 105.
In an embodiment of the disclosure, dialogue management module 103 executes the calling to knowledge mapping 106.
In an embodiment of the disclosure, answer generation module 104 executes the calling to knowledge mapping 106.
The disclosure also provides a kind of electronic equipment, as shown in figure 8, the equipment includes: communication interface 1000, memory 2000
With processor 3000.Communication interface 1000 carries out data interaction for being communicated with external device.In memory 2000
It is stored with the computer program that can be run on processor 3000.Processor 3000 is realized above-mentioned when executing the computer program
Method in embodiment.The quantity of the memory 2000 and processor 3000 can be one or more.
Memory 2000 may include high speed RAM memory, can also further include nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
If communication interface 1000, memory 2000 and the independent realization of processor 3000, communication interface 1000, memory
2000 and processor 3000 can be connected with each other by bus and complete mutual communication.The bus can be industrial 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, control bus etc..For convenient for expression, the figure
In only indicated with a thick line, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if communication interface 1000, memory 2000 and processor 3000 are integrated in one
On block chip, then communication interface 1000, memory 2000 and processor 3000 can complete mutual lead to by internal interface
Letter.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the disclosure includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the disclosure
Embodiment person of ordinary skill in the field understood.Processor executes each method as described above and processing.
For example, the method implementation in the disclosure may be implemented as software program, it is tangibly embodied in machine readable media,
Such as memory.In some embodiments, some or all of of software program can be via memory and/or communication interface
And it is loaded into and/or installs.When software program is loaded into memory and is executed by processor, above-described side can be executed
One or more steps in method.Alternatively, in other embodiments, processor can pass through other any modes appropriate
(for example, by means of firmware) and be configured as executing one of above method.
Expression or logic and/or step described otherwise above herein in flow charts, may be embodied in any
In readable storage medium storing program for executing, so that (such as computer based system is including processor for instruction execution system, device or equipment
Unite or other can be from instruction execution system, device or equipment instruction fetch and the system executed instruction) it uses, or refer in conjunction with these
It enables and executes system, device or equipment and use.
For the purpose of this specification, " readable storage medium storing program for executing " can be it is any may include, store, communicate, propagate, or transport
Program is for instruction execution system, device or equipment or the device used in conjunction with these instruction execution systems, device or equipment.
The more specific example (non-exhaustive list) of readable storage medium storing program for executing include the following: there is the electrical connection section of one or more wirings
(electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory (ROM) are erasable
Except editable read-only memory (EPROM or flash memory), fiber device and portable read-only memory (CDROM).Separately
Outside, readable storage medium storing program for executing can even is that the paper that can print described program on it or other suitable media, because can example
Such as by carrying out optical scanner to paper or other media, is then edited, interpreted or when necessary with the progress of other suitable methods
Processing is then stored in memory electronically to obtain described program.
It should be appreciated that each section of the disclosure can be realized with hardware, software or their combination.In above-mentioned embodiment party
In formula, multiple steps or method can carry out reality in memory and by the software that suitable instruction execution system executes with storage
It is existing.It, and in another embodiment, can be in following technology well known in the art for example, if realized with hardware
Any one or their combination are realized: having a discrete logic for realizing the logic gates of logic function to data-signal
Circuit, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), field-programmable gate array
Arrange (FPGA) etc..
Those skilled in the art are understood that realize all or part of the steps of above embodiment method
It is that relevant hardware can be instructed to complete by program, the program can store in a kind of readable storage medium storing program for executing, should
Program when being executed, includes the steps that one or a combination set of method implementation.
In addition, can integrate in a processing module in each functional unit in each embodiment of the disclosure, it can also
To be that each unit physically exists alone, can also be integrated in two or more units in a module.It is above-mentioned integrated
Module both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module
If in the form of software function module realize and when sold or used as an independent product, also can store readable at one
In storage medium.The storage medium can be read-only memory, disk or CD etc..
In the description of this specification, reference term " an embodiment/mode ", " some embodiment/modes ",
The description of " example ", " specific example " or " some examples " etc. means the embodiment/mode or example is combined to describe specific
Feature, structure, material or feature are contained at least one embodiment/mode or example of the application.In this specification
In, schematic expression of the above terms are necessarily directed to identical embodiment/mode or example.Moreover, description
Particular features, structures, materials, or characteristics can be in any one or more embodiment/modes or example in an appropriate manner
In conjunction with.In addition, without conflicting with each other, those skilled in the art can be by different implementations described in this specification
Mode/mode or example and different embodiments/mode or exemplary feature are combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
It will be understood by those of skill in the art that above embodiment is used for the purpose of clearly demonstrating the disclosure, and simultaneously
Non- be defined to the scope of the present disclosure.For those skilled in the art, may be used also on the basis of disclosed above
To make other variations or modification, and these variations or modification are still in the scope of the present disclosure.
Claims (10)
1. a kind of answering method characterized by comprising
Receive customer problem;
Semantic understanding is carried out to received customer problem;
Based on the semantic understanding, intent classifier is carried out to customer problem, extracts the key message in customer problem;
Based on the intent classifier, corresponding task line is selected;And
Task line and the key message based on selection, generate the answer of the customer problem.
2. answering method according to claim 1, which is characterized in that
The key message is the combination more than one or two of following:
Entity, attribute, relationship.
3. answering method according to claim 1 or 2, which is characterized in that
The intent classifier includes being intended to region and being intended to content, when selecting corresponding task line based on intent classifier, is based on institute
It states and is intended to regional choice task line.
4. answering method according to claim 2 or 3, which is characterized in that further include:
Missing judgement is carried out to the crucial sub-information of the key message in customer problem, if lack some crucial sub-information or
Certain several crucial sub-information, then lack to the upper problem of the same user of this customer problem or the inquiry of upper several problems
Crucial sub-information inherits the key sub-information if inquiring the crucial sub-information of missing;The key message includes one
Or more than two crucial sub-informations.
5. answering method according to claim 4, which is characterized in that further include: if not inquiring key of missing
Information then generates feedback information.
6. answering method according to any one of claim 1 to 3, which is characterized in that further include in customer problem
Entity in key message carries out reference judgement: according to the attribute or relationship in the key message in customer problem, judging reality
Reference of the body in knowledge mapping.
7. answering method according to any one of claim 1 to 3, which is characterized in that task line and institute based on selection
When stating key message and obtaining the answer of the customer problem, external search engine or inquiry are called according to the task line options
Knowledge mapping generates the answer of customer problem.
8. a kind of question and answer system characterized by comprising
Problem receiving module, described problem receiving module receive customer problem;
Semantic understanding module, the semantic understanding module carry out semantic understanding to received customer problem;
Dialogue management module, the dialogue management module are based on the semantic understanding, carry out intent classifier to customer problem, extract
Key message in customer problem;Based on the intent classifier, corresponding task line is selected;And
Answer generation module, task line and the key message of the answer generation module based on selection, generates the user
The answer of problem.
9. a kind of electronic equipment characterized by comprising
Memory, the memory storage execute instruction;And
Processor, the processor execute executing instruction for the memory storage, so that the processor is executed as right is wanted
Method described in asking any one of 1 to 7.
10. a kind of readable storage medium storing program for executing, which is characterized in that it is stored with and executes instruction in the readable storage medium storing program for executing, the execution
For realizing the method as described in any one of claims 1 to 7 when instruction is executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811602582.5A CN109815321B (en) | 2018-12-26 | 2018-12-26 | Question answering method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811602582.5A CN109815321B (en) | 2018-12-26 | 2018-12-26 | Question answering method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109815321A true CN109815321A (en) | 2019-05-28 |
CN109815321B CN109815321B (en) | 2020-12-11 |
Family
ID=66602549
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811602582.5A Active CN109815321B (en) | 2018-12-26 | 2018-12-26 | Question answering method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109815321B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110263051A (en) * | 2019-06-11 | 2019-09-20 | 出门问问信息科技有限公司 | Question and answer for question answering system are to update method, device, equipment and storage medium |
CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
CN110516054A (en) * | 2019-08-15 | 2019-11-29 | 出门问问(武汉)信息科技有限公司 | A kind of garbage classification answering method, equipment and readable storage medium storing program for executing |
CN110619051A (en) * | 2019-08-16 | 2019-12-27 | 科大讯飞(苏州)科技有限公司 | Question and sentence classification method and device, electronic equipment and storage medium |
CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
CN111611382A (en) * | 2020-05-22 | 2020-09-01 | 贝壳技术有限公司 | Dialect model training method, dialog information generation method, device and system |
CN114840671A (en) * | 2022-04-29 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue generation method, model training method, device, equipment and medium |
CN116737910A (en) * | 2023-08-10 | 2023-09-12 | 腾讯科技(深圳)有限公司 | Intelligent dialogue processing method, device, equipment and storage medium |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101257512A (en) * | 2008-02-02 | 2008-09-03 | 黄伟才 | Inquiry answer matching method used for inquiry answer system as well as inquiry answer method and system |
CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技(深圳)有限公司 | Automatic question-answering system and method |
CN104809103A (en) * | 2015-04-29 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Man-machine interactive semantic analysis method and system |
US20160117386A1 (en) * | 2014-10-22 | 2016-04-28 | International Business Machines Corporation | Discovering terms using statistical corpus analysis |
CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技(上海)有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
US20170177715A1 (en) * | 2015-12-21 | 2017-06-22 | Adobe Systems Incorporated | Natural Language System Question Classifier, Semantic Representations, and Logical Form Templates |
CN107229684A (en) * | 2017-05-11 | 2017-10-03 | 合肥美的智能科技有限公司 | Statement classification method, system, electronic equipment, refrigerator and storage medium |
CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技(深圳)有限公司 | Intelligent answer method and device |
CN107908803A (en) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | The response method and device, storage medium, terminal of question and answer interaction |
CN107977236A (en) * | 2017-12-21 | 2018-05-01 | 上海智臻智能网络科技股份有限公司 | Generation method, terminal device, storage medium and the question answering system of question answering system |
US20180210883A1 (en) * | 2017-01-25 | 2018-07-26 | Dony Ang | System for converting natural language questions into sql-semantic queries based on a dimensional model |
CN108345612A (en) * | 2017-01-25 | 2018-07-31 | 北京搜狗科技发展有限公司 | A kind of question processing method and device, a kind of device for issue handling |
-
2018
- 2018-12-26 CN CN201811602582.5A patent/CN109815321B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101257512A (en) * | 2008-02-02 | 2008-09-03 | 黄伟才 | Inquiry answer matching method used for inquiry answer system as well as inquiry answer method and system |
CN104598445A (en) * | 2013-11-01 | 2015-05-06 | 腾讯科技(深圳)有限公司 | Automatic question-answering system and method |
US20160117386A1 (en) * | 2014-10-22 | 2016-04-28 | International Business Machines Corporation | Discovering terms using statistical corpus analysis |
CN104809103A (en) * | 2015-04-29 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Man-machine interactive semantic analysis method and system |
US20170177715A1 (en) * | 2015-12-21 | 2017-06-22 | Adobe Systems Incorporated | Natural Language System Question Classifier, Semantic Representations, and Logical Form Templates |
CN105608221A (en) * | 2016-01-11 | 2016-05-25 | 北京光年无限科技有限公司 | Self-learning method and device for question-answering system |
CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技(上海)有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
US20180210883A1 (en) * | 2017-01-25 | 2018-07-26 | Dony Ang | System for converting natural language questions into sql-semantic queries based on a dimensional model |
CN108345612A (en) * | 2017-01-25 | 2018-07-31 | 北京搜狗科技发展有限公司 | A kind of question processing method and device, a kind of device for issue handling |
CN107229684A (en) * | 2017-05-11 | 2017-10-03 | 合肥美的智能科技有限公司 | Statement classification method, system, electronic equipment, refrigerator and storage medium |
CN107301213A (en) * | 2017-06-09 | 2017-10-27 | 腾讯科技(深圳)有限公司 | Intelligent answer method and device |
CN107977236A (en) * | 2017-12-21 | 2018-05-01 | 上海智臻智能网络科技股份有限公司 | Generation method, terminal device, storage medium and the question answering system of question answering system |
CN107908803A (en) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | The response method and device, storage medium, terminal of question and answer interaction |
Non-Patent Citations (1)
Title |
---|
张娜: "问答系统中基于语义概念的问题答案形成方法研究", 《西华大学学报(自然科学版)》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110263051A (en) * | 2019-06-11 | 2019-09-20 | 出门问问信息科技有限公司 | Question and answer for question answering system are to update method, device, equipment and storage medium |
CN110516054A (en) * | 2019-08-15 | 2019-11-29 | 出门问问(武汉)信息科技有限公司 | A kind of garbage classification answering method, equipment and readable storage medium storing program for executing |
CN110619051A (en) * | 2019-08-16 | 2019-12-27 | 科大讯飞(苏州)科技有限公司 | Question and sentence classification method and device, electronic equipment and storage medium |
CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
CN111611382A (en) * | 2020-05-22 | 2020-09-01 | 贝壳技术有限公司 | Dialect model training method, dialog information generation method, device and system |
CN114840671A (en) * | 2022-04-29 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue generation method, model training method, device, equipment and medium |
CN116737910A (en) * | 2023-08-10 | 2023-09-12 | 腾讯科技(深圳)有限公司 | Intelligent dialogue processing method, device, equipment and storage medium |
CN116737910B (en) * | 2023-08-10 | 2024-03-29 | 腾讯科技(深圳)有限公司 | Intelligent dialogue processing method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109815321B (en) | 2020-12-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109815321A (en) | Question answering method, device, equipment and storage medium | |
CN105183422B (en) | The method and apparatus of voice control application program | |
CN107329967B (en) | Question answering system and method based on deep learning | |
CN105159650B (en) | Method and system for the power consumption management of pattern-recognition processor | |
CN108021554A (en) | Audio recognition method, device and washing machine | |
CN106528400A (en) | MOCK testing method and device | |
CN110673748A (en) | Method and device for providing candidate long sentences in input method | |
US20090106680A1 (en) | Drag and drop object attribute assignment for objects in a graphical user interface (gui) | |
CN105117387B (en) | A kind of intelligent robot interactive system | |
CN108287815A (en) | Information input method, device, terminal and computer readable storage medium | |
CN108011928A (en) | A kind of information-pushing method, terminal device and computer-readable medium | |
US11050688B2 (en) | Apparatus and method for improving communication between matched individuals | |
CN108091324A (en) | Tone recognition methods, device, electronic equipment and computer readable storage medium | |
CN108830394A (en) | Call subscription method, processing method, device, equipment and the medium of asking for leave of attending a banquet | |
CN110569924A (en) | Icon processing method and device, readable storage medium and computer equipment | |
CN109637536A (en) | A kind of method and device of automatic identification semantic accuracy | |
CN109992652A (en) | A kind of information replying method, device, equipment and storage medium | |
CN107291508A (en) | A kind of transaction record method, relevant device and computer-readable recording medium | |
CN107292614A (en) | Pay class application management method, device and mobile terminal | |
US20200364295A1 (en) | Methods, apparatus, and systems to generate regex and detect data similarity | |
CN106209599A (en) | The Notification Method of a kind of information and terminal | |
CN105913215A (en) | Email processing method and equipment | |
CN111143558B (en) | Message identification method and system based on single layered multitasking model | |
CN105162933B (en) | A kind of method, apparatus managing address book contact and a kind of intelligent terminal | |
CN113868396A (en) | Task intelligent dialogue construction method and system based on knowledge graph |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220507 Address after: 210034 floor 8, building D11, Hongfeng Science Park, Nanjing Economic and Technological Development Zone, Jiangsu Province Patentee after: New Technology Co.,Ltd. Patentee after: Volkswagen (China) Investment Co., Ltd Address before: 100094 1001, 10th floor, office building a, 19 Zhongguancun Street, Haidian District, Beijing Patentee before: MOBVOI INFORMATION TECHNOLOGY Co.,Ltd. |