CN110275946A - A kind of FAQ automatic question-answering method and device - Google Patents
A kind of FAQ automatic question-answering method and device Download PDFInfo
- Publication number
- CN110275946A CN110275946A CN201910399206.9A CN201910399206A CN110275946A CN 110275946 A CN110275946 A CN 110275946A CN 201910399206 A CN201910399206 A CN 201910399206A CN 110275946 A CN110275946 A CN 110275946A
- Authority
- CN
- China
- Prior art keywords
- question sentence
- user
- input
- faq
- sentence
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The inquiry question sentence of user's input can more effectively be combined to the technical solution for expanding existing FAQ text library, raising user experience with existing FAQ text library information to provide one kind, a kind of FAQ automatic question-answering method is inventor provided, comprising steps of obtaining the inquiry question sentence information of user's input；Vector Processing is carried out to the inquiry question sentence；The similarity that question sentence is preset in the inquiry question sentence and text library is calculated according to Vector Processing sentence vector obtained；It searches and exports the default question sentence of inquiry Question sentence parsing highest preset quantity with user's input.Inventor provides the FAQ automatic call answering arrangement for realizing above-mentioned FAQ automatic question-answering method simultaneously.Stating technical solution can more effectively combine the inquiry question sentence of user's input with existing FAQ text library information to expand existing FAQ text library, to which more effectively building provides the software systems for being directed to new input text and providing reply automatically, sufficiently raising user experience.
Description
Technical field
The present invention relates to computer software fields, in particular to a kind of FAQ automatic question-answering method and device.
Background technique
FAQ is the abbreviation of English Frequently Asked Questions, and the Chinese meaning is exactly that " that often asks asks
Topic ", or more generically it is called " frequently asked questions and corresponding answer ".FAQ is that the main means of online help are provided in current network, is passed through
Better possible often ask is organized to answer questions (Question Answer Pair) in advance, publication is on webpage or in chat group
User provides counseling services.
Question and answer robot is to be given automatically using resources such as existing question and answer, interaction corpus of text for new input text
The software systems replied out.Question and answer robot different applications be also referred to as intelligent Answer System, automatically request-answering system,
Intelligent customer service robot, chat robots etc..Question and answer robot is widely transported as a kind of basic interactive means
Used in fields such as customer service, education, call center, company, navigation, administrative assistants.For relevant enterprise unit, customer service it is automatic
Change and intelligence can reduce cost of labor, shorten the problem response time, the consistency that security problem is replied, to improve user
Experience.
Summary of the invention
For this reason, it may be necessary to provide a kind of inquiry question sentence that can more effectively input user and existing FAQ text library information
Combine the technical solution for expanding existing FAQ text library, improving user experience.
Based on this, a kind of FAQ automatic question-answering method is inventor provided, is included the following steps:
Obtain the inquiry question sentence information of user's input；
Vector Processing is carried out to the inquiry question sentence；
The similarity that question sentence is preset in the inquiry question sentence and text library is calculated according to Vector Processing sentence vector obtained；
It searches and exports the default question sentence of inquiry Question sentence parsing highest preset quantity with user's input.
Further, in the FAQ automatic question-answering method, step " carries out Vector Processing to the inquiry question sentence information "
The Vector Processing specifically includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
Further, it in the FAQ automatic question-answering method, " searches and exports and asked with the inquiry of user's input in step
Sentence similarity highest preset quantity answers sentence " after further comprise the steps of: prompt user in the default question sentence of the preset quantity
Selection, and obtain the selection result of user's input.
Further, in the FAQ automatic question-answering method, in step, " prompt user is default in the preset quantity
Selected in question sentence, and obtain the selection result of user's input " selection result that the user that will acquire inputs is further comprised the steps of: later
It is stored with the inquiry question sentence composition sentence pair of user's input.
Further, in the FAQ automatic question-answering method, step " will acquire user input selection result with
User input inquiry question sentence composition sentence pair store " after further comprise the steps of: to before all storage results 30% carry out people
Work mark.
Inventor additionally provides a kind of FAQ automatic call answering arrangement simultaneously, including input unit, vector processing unit, similar
Spend computing unit, searching unit and output unit；
The input unit is used to obtain the inquiry question sentence information of user's input；
The vector processing unit is used to carry out Vector Processing to the inquiry question sentence；
The similarity calculated is used to calculate the inquiry question sentence and text according to Vector Processing sentence vector obtained
Ben Kunei presets the similarity of question sentence；
The default question sentence of inquiry Question sentence parsing highest preset quantity that the searching unit is used to input with user；
The output unit is used to export puts up a question in advance with the inquiry Question sentence parsing highest preset quantity of user's input
Sentence.
Further, in the FAQ automatic call answering arrangement, the Vector Processing that vector processing unit is carried out specifically is wrapped
It includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
Further, further include feedback unit in the FAQ automatic call answering arrangement, for output unit output with
After the default question sentence of inquiry Question sentence parsing highest preset quantity of user's input, prompt user in the preset quantity
It is selected in default question sentence, and obtains the selection result of user's input.
It further, further include storage unit in the FAQ automatic call answering arrangement, user's input for will acquire
Selection result inputted with user inquiry question sentence composition sentence pair store.
It further, further include mark unit, for all storage results in the FAQ automatic call answering arrangement
Preceding 30% is manually marked.
It is different from the prior art, above-mentioned technical proposal can be more effectively by the inquiry question sentence and existing FAQ of user's input
Text library information combines to expand existing FAQ text library, so that more effectively building is provided for new input text
This provides the software systems of reply automatically, fully improves user experience.
Detailed description of the invention
Fig. 1 is the flow chart of FAQ automatic question-answering method described in an embodiment of the present invention；
Fig. 2 is the structural schematic diagram of FAQ automatic call answering arrangement described in an embodiment of the present invention.
Description of symbols:
1- input unit
2- vector processing unit
3- similarity calculated
4- searching unit
5- output unit
6- feedback unit
7- storage unit
8- marks unit
Specific embodiment
Technology contents, construction feature, the objects and the effects for detailed description technical solution, below in conjunction with specific reality
It applies example and attached drawing is cooperated to be explained in detail.
Referring to Fig. 1, for a kind of flow chart of FAQ automatic question-answering method described in an embodiment of the present invention, the side
Method includes the following steps:
S1, the inquiry question sentence information for obtaining user's input；
S2, Vector Processing is carried out to the inquiry question sentence；
S3, to calculate the inquiry question sentence according to Vector Processing sentence vector obtained similar with question sentence default in text library
Degree；
S4, lookup simultaneously export and a default question sentence of the highest preset quantity of inquiry Question sentence parsing of user's input.
Further, in step s 2, specifically, the Vector Processing specifically includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
In other embodiments, it " searches and exports similar to the inquiry question sentence of user's input described in the step S4
Spend highest preset quantity and answer sentence " after further include step S5: prompt user selects in the default question sentence of the preset quantity,
And obtain the selection result of user's input.The selection information of the available user of the operating result of this step, to judge FAQ text
The collocation degree of question sentence and user's question sentence that this library provides, and hereafter pushed away for user according to user's selection result further to be promoted
Send the precision of question sentence.
It in other embodiments, after step s 5 further include step S6: the selection knot for the user's input that will acquire
The inquiry question sentence composition sentence pair that fruit inputs with user stores；And step S7: it is carried out to before all storage results 30%
Artificial mark.
Step S6 and S7 can further realize the technical effect for expanding the FAQ automatic question answering function precision of this method.
Referring to Fig. 2, being a kind of structural schematic diagram of FAQ automatic call answering arrangement, the FAQ automatic call answering arrangement includes defeated
Enter unit 1, vector processing unit 2, similarity calculated 3, searching unit 4 and output unit 5；
The input unit 1 is used to obtain the inquiry question sentence information of user's input；
The vector processing unit 2 is used to carry out Vector Processing to the inquiry question sentence；
The similarity calculated 3 is used to calculate the inquiry question sentence and text according to Vector Processing sentence vector obtained
Ben Kunei presets the similarity of question sentence；
The default question sentence of inquiry Question sentence parsing highest preset quantity that the searching unit 4 is used to input with user；
The output unit 5 is used to export puts up a question in advance with the inquiry Question sentence parsing highest preset quantity of user's input
Sentence.
Further, in the FAQ automatic call answering arrangement, the Vector Processing that vector processing unit 2 is carried out specifically is wrapped
It includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
Further, further include feedback unit 6 in the FAQ automatic call answering arrangement, for output unit output with
After the default question sentence of inquiry Question sentence parsing highest preset quantity of user's input, prompt user in the preset quantity
It is selected in default question sentence, and obtains the selection result of user's input.The technical effect of feedback unit 6 essentially consists in available use
The selection information at family, to judge the collocation degree for the question sentence and user's question sentence that FAQ text library provides, and according to user's selection result
Further to promote the precision for hereafter pushing question sentence for user.
In other embodiments, the FAQ automatic call answering arrangement further includes storage unit 7, for what be will acquire
The inquiry question sentence composition sentence pair that the selection result of user's input is inputted with user stores；And mark unit 8, for institute
Have storage result preceding 30% is manually marked.
The combination of storage unit 7 and mark unit 8 can be on the basis of FAQ automatic call answering arrangement basic function, into one
Step realizes the technical effect for expanding the FAQ automatic question answering function precision of this method.
It is different from the prior art, above-mentioned technical proposal can be more effectively by the inquiry question sentence and existing FAQ of user's input
Text library information combines to expand existing FAQ text library, so that more effectively building is provided for new input text
This provides the software systems of reply automatically, fully improves user experience.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or the terminal device that include a series of elements not only include those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or end
The intrinsic element of end equipment.In the absence of more restrictions, being limited by sentence " including ... " or " including ... "
Element, it is not excluded that there is also other elements in process, method, article or the terminal device for including the element.This
Outside, herein, " being greater than ", " being less than ", " being more than " etc. are interpreted as not including this number；" more than ", " following ", " within " etc. understand
Being includes this number.
It should be understood by those skilled in the art that, the various embodiments described above can provide as method, apparatus or computer program production
Product.Complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in these embodiments
Form.The all or part of the steps in method that the various embodiments described above are related to can be instructed by program relevant hardware come
It completes, the program can store in the storage medium that computer equipment can be read, for executing the various embodiments described above side
All or part of the steps described in method.The computer equipment, including but not limited to: personal computer, server, general-purpose computations
It is machine, special purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, smart home device, wearable
Smart machine, vehicle intelligent equipment etc.；The storage medium, including but not limited to: RAM, ROM, magnetic disk, tape, CD, sudden strain of a muscle
It deposits, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage etc..
The various embodiments described above are referring to the method according to embodiment, equipment (system) and computer program product
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Program instruction generates a machine to the processor of computer equipment, so that the finger executed by the processor of computer equipment
It enables and generates to specify in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of function.
These computer program instructions, which may also be stored in, to be able to guide computer equipment computer operate in a specific manner and sets
In standby readable memory, so that the instruction being stored in the computer equipment readable memory generates the manufacture including command device
Product, command device realization refer in one or more flows of the flowchart and/or one or more blocks of the block diagram
Fixed function.
These computer program instructions can also be loaded into computer equipment, so that executing on a computing device a series of
Operating procedure is to generate computer implemented processing, so that the instruction executed on a computing device is provided for realizing in process
The step of function of being specified in figure one process or multiple processes and/or block diagrams one box or multiple boxes.
Although the various embodiments described above are described, once a person skilled in the art knows basic wounds
The property made concept, then additional changes and modifications can be made to these embodiments, so the above description is only an embodiment of the present invention,
It is not intended to limit scope of patent protection of the invention, it is all to utilize equivalent structure made by description of the invention and accompanying drawing content
Or equivalent process transformation, being applied directly or indirectly in other relevant technical fields, similarly includes in patent of the invention
Within protection scope.
Claims (10)
1. a kind of FAQ automatic question-answering method, which comprises the steps of:
Obtain the inquiry question sentence information of user's input；
Vector Processing is carried out to the inquiry question sentence；
The similarity that question sentence is preset in the inquiry question sentence and text library is calculated according to Vector Processing sentence vector obtained；
It searches and exports the default question sentence of inquiry Question sentence parsing highest preset quantity with user's input.
2. FAQ automatic question-answering method as described in claim 1, which is characterized in that step " carries out the inquiry question sentence information
Vector Processing described in Vector Processing " specifically includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
3. FAQ automatic question-answering method as claimed in claim 1 or 2, which is characterized in that " search and export and user in step
The inquiry Question sentence parsing highest preset quantity of input answers sentence " after further comprise the steps of: prompt user in the preset quantity
It is selected in a default question sentence, and obtains the selection result of user's input.
4. FAQ automatic question-answering method as claimed in claim 3, which is characterized in that in step, " prompt user is in the present count
Measure and selected in a default question sentence, and obtain the selection result of user's input " the user's input that will acquire is further comprised the steps of: later
The inquiry question sentence composition sentence pair that selection result is inputted with user stores.
5. FAQ automatic question-answering method as claimed in claim 4, which is characterized in that in the step " choosing for the user's input that will acquire
Select result and user input inquiry question sentence composition sentence pair store " after further comprise the steps of: to before all storage results
30% is manually marked.
6. a kind of FAQ automatic call answering arrangement, which is characterized in that including input unit, vector processing unit, similarity calculation list
Member, searching unit and output unit；
The input unit is used to obtain the inquiry question sentence information of user's input；
The vector processing unit is used to carry out Vector Processing to the inquiry question sentence；
The similarity calculated is used to calculate the inquiry question sentence and text library according to Vector Processing sentence vector obtained
The similarity of interior default question sentence；
The default question sentence of inquiry Question sentence parsing highest preset quantity that the searching unit is used to input with user；
The output unit is used to export the default question sentence of inquiry Question sentence parsing highest preset quantity with user's input.
7. FAQ automatic call answering arrangement as claimed in claim 6, which is characterized in that at the vector that vector processing unit is carried out
Reason specifically includes:
The inquiry question sentence is segmented, word list is obtained；
The word list is successively calculated using word2vec, term vector is obtained；
All term vectors are added up and obtain a vector.
8. FAQ automatic call answering arrangement as claimed in claims 6 or 7, which is characterized in that further include feedback unit, for defeated
Unit output prompts user in institute with after the default question sentence of inquiry Question sentence parsing highest preset quantity of user's input out
It states and is selected in the default question sentence of preset quantity, and obtain the selection result of user's input.
9. FAQ automatic call answering arrangement as claimed in claim 8, which is characterized in that further include storage unit, for what be will acquire
The inquiry question sentence composition sentence pair that the selection result of user's input is inputted with user stores.
10. FAQ automatic call answering arrangement as claimed in claim 9, which is characterized in that further include mark unit, for all
Preceding the 30% of storage result is manually marked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910399206.9A CN110275946A (en) | 2019-05-14 | 2019-05-14 | A kind of FAQ automatic question-answering method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910399206.9A CN110275946A (en) | 2019-05-14 | 2019-05-14 | A kind of FAQ automatic question-answering method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110275946A true CN110275946A (en) | 2019-09-24 |
Family
ID=67959893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910399206.9A Pending CN110275946A (en) | 2019-05-14 | 2019-05-14 | A kind of FAQ automatic question-answering method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110275946A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797217A (en) * | 2020-06-29 | 2020-10-20 | 中国平安财产保险股份有限公司 | Information query method based on FAQ matching model and related equipment thereof |
| CN113053393A (en) * | 2021-03-30 | 2021-06-29 | 福州市长乐区极微信息科技有限公司 | Audio annotation processing device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
| CN106484664A (en) * | 2016-10-21 | 2017-03-08 | 竹间智能科技（上海）有限公司 | Similarity calculating method between a kind of short text |
| US20170249320A1 (en) * | 2016-02-26 | 2017-08-31 | Fujitsu Limited | Computer-readable recording medium, information processing apparatus, and information processing method |
| CN108595619A (en) * | 2018-04-23 | 2018-09-28 | 海信集团有限公司 | A kind of answering method and equipment |
-
2019
- 2019-05-14 CN CN201910399206.9A patent/CN110275946A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104657346A (en) * | 2015-01-15 | 2015-05-27 | 深圳市前海安测信息技术有限公司 | Question matching system and question matching system in intelligent interaction system |
| US20170249320A1 (en) * | 2016-02-26 | 2017-08-31 | Fujitsu Limited | Computer-readable recording medium, information processing apparatus, and information processing method |
| CN106484664A (en) * | 2016-10-21 | 2017-03-08 | 竹间智能科技（上海）有限公司 | Similarity calculating method between a kind of short text |
| CN108595619A (en) * | 2018-04-23 | 2018-09-28 | 海信集团有限公司 | A kind of answering method and equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797217A (en) * | 2020-06-29 | 2020-10-20 | 中国平安财产保险股份有限公司 | Information query method based on FAQ matching model and related equipment thereof |
| CN111797217B (en) * | 2020-06-29 | 2023-09-26 | 中国平安财产保险股份有限公司 | Information query method based on FAQ matching model and related equipment thereof |
| CN113053393A (en) * | 2021-03-30 | 2021-06-29 | 福州市长乐区极微信息科技有限公司 | Audio annotation processing device |
| CN113053393B (en) * | 2021-03-30 | 2024-04-30 | 闽江学院 | Audio annotation processing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7108720B2 (en) | Knowledge sharing method between dialogue systems, dialogue method, knowledge sharing device, dialogue device, electronic device and storage medium | |
| CN104951428B (en) | User's intension recognizing method and device | |
| US9858358B1 (en) | Session-based query suggestions | |
| CN113590776B (en) | Knowledge graph-based text processing method and device, electronic equipment and medium | |
| CN107492008A (en) | Information recommendation method, device, server and computer-readable storage medium | |
| CN103870505A (en) | Query term recommending method and query term recommending system | |
| US20150254568A1 (en) | Boosted Ensemble of Segmented Scorecard Models | |
| KR20210106398A (en) | Conversation-based recommending method, conversation-based recommending apparatus, and device | |
| CN108519998B (en) | Problem guiding method and device based on knowledge graph | |
| US9588819B2 (en) | System and method of assigning requests to resources using constraint programming | |
| US20230177088A1 (en) | Method and system for predicative q&a and resource suggestions | |
| CN110275946A (en) | A kind of FAQ automatic question-answering method and device | |
| CN110362665A (en) | A kind of question answering system and method based on semantic similarity | |
| CN107562847A (en) | Information processing method and related product | |
| CN113961679A (en) | Intelligent question and answer processing method and system, electronic equipment and storage medium | |
| CN109992659B (en) | Method and device for text sorting | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN110008396B (en) | Object information pushing method, device, equipment and computer readable storage medium | |
| CN117521625A (en) | Question answering method, question answering device, electronic equipment and medium | |
| CN109800286B (en) | Dialog generation method and device | |
| CN110275937A (en) | A kind of construction method and device of question and answer robot | |
| CN116992000A (en) | Interactive information processing method, device, electronic equipment and computer readable medium | |
| CN117009541A (en) | Method, device, equipment and medium for constructing and applying clinical medicine inspection knowledge base | |
| CN116049370A (en) | Information query method and training method and device of information generation model | |
| CN116662495A (en) | Question-answering processing method, and method and device for training question-answering processing model |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Ge Inventor after: Xue Mufan Inventor after: Wang Weijian Inventor after: Chen Linying Inventor after: Zheng Junjie Inventor after: Fang Youxin Inventor after: Lin Ruyan Inventor after: Tang Weimian Inventor before: Xue Mufan Inventor before: Wang Weijian Inventor before: Chen Linying Inventor before: Zheng Junjie Inventor before: Fang Youxin Inventor before: Lin Ruyan Inventor before: Tang Weimian Inventor before: Xu Ge |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190924 |