CN110516043A - Answer generation method and device for question answering system - Google Patents

Answer generation method and device for question answering system Download PDF

Info

Publication number
CN110516043A
CN110516043A CN201910814386.2A CN201910814386A CN110516043A CN 110516043 A CN110516043 A CN 110516043A CN 201910814386 A CN201910814386 A CN 201910814386A CN 110516043 A CN110516043 A CN 110516043A
Authority
CN
China
Prior art keywords
answer
dialogue
user
modal particle
characteristic information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910814386.2A
Other languages
Chinese (zh)
Inventor
戴中原
初敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
AI Speech Ltd
Original Assignee
AI Speech Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by AI Speech Ltd filed Critical AI Speech Ltd
Priority to CN201910814386.2A priority Critical patent/CN110516043A/en
Publication of CN110516043A publication Critical patent/CN110516043A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing

Abstract

The present invention discloses the answer generation method and device for question answering system, wherein a kind of answer generation method for question answering system, comprising: when engaging in the dialogue with user, the dialogue for obtaining session operational scenarios and user is intended to;When receiving user the problem of, characteristic information included in described problem is identified;The problem of based on the user, generates corresponding answer;According to dialogue intention, the session operational scenarios and the characteristic information, at least one modal particle is generated;At least one described modal particle is dynamically inserted to the beginning and/or ending of the corresponding answer, to form treated answer.The scheme that the present processes and device provide is by considering that dialogue is intended to, the influence of session operational scenarios and characteristic information determines corresponding modal particle, modal particle is dynamically inserted into answer later, the effect that answer content can be made to link up closer to true man, user experience are more preferable.

Description

Answer generation method and device for question answering system
Technical field
The invention belongs to Intelligent voice dialog technical field, more particularly, to the answer generation method of question answering system and Device.
Background technique
In the related technology, dialogue designs method general at present is as follows:
A, engaged in the dialogue content design by the way of question and answer pair, and user fills in a problem, is then write one and is answered Case, after hitting this problem, machine chance replys corresponding answer;
B, the mode of knowledge based map engages in the dialogue content design, and user fills in corresponding knowledge content, according to difference Content automatically generate the answer of user.
Inventor has found during realizing the application: above method, is all corresponding using the matching of regulation problem The mode of answer, or the mode of dynamic adjustment answer, but the intention and node letter of session operational scenarios are incorporated without dynamic Breath leads to that session operational scenarios cannot be merged well, feels that dialogue is unnatural, uncoordinated.
Summary of the invention
The embodiment of the present invention provides a kind of answer generation method and device for question answering system, at least solving State one of technical problem.
In a first aspect, the embodiment of the present invention provides a kind of answer generation method for question answering system, comprising: with When family engages in the dialogue, the dialogue for obtaining session operational scenarios and user is intended to;When receiving user the problem of, identify in described problem The characteristic information for being included;The problem of based on the user, generates corresponding answer;It is intended to according to the dialogue, the dialogue Scene and the characteristic information, generate at least one modal particle;At least one described modal particle is dynamically inserted to described right The beginning and/or ending for the answer answered, to form treated answer.
Second aspect, the embodiment of the present invention provide a kind of answer generating means for question answering system, comprising: scene meaning Figure obtains module, is configured to when engaging in the dialogue with user, and the dialogue for obtaining session operational scenarios and user is intended to;Feature identifies mould Block when being configured to when receive user the problem of, identifies characteristic information included in described problem;Answer generation module, configuration The problem of for based on the user, generates corresponding answer;Modal particle generation module is configured to according to dialogue intention, institute Session operational scenarios and the characteristic information are stated, at least one modal particle is generated;And modal particle is inserted into module, being configured to will be described At least one modal particle is dynamically inserted to the beginning and/or ending of the corresponding answer, to form treated answer.
The third aspect provides a kind of electronic equipment comprising: at least one processor, and with described at least one Manage the memory of device communication connection, wherein the memory is stored with the instruction that can be executed by least one described processor, Described instruction is executed by least one described processor, so that at least one described processor is able to carry out any reality of the present invention The step of applying the answer generation method for question answering system of example.
Fourth aspect, the embodiment of the present invention also provide a kind of computer program product, and the computer program product includes The computer program being stored on non-volatile computer readable storage medium storing program for executing, the computer program include program instruction, when Described program instruction is when being computer-executed, and the computer is made to execute the question answering system that is used for of any embodiment of the present invention The step of answer generation method.
The scheme that the present processes and device provide is by first obtaining dialogue meaning according to the problem of dialogue entirety and user Then the characteristic information of figure, session operational scenarios and customer problem is intended to according to dialogue, session operational scenarios and characteristic information determine accordingly Modal particle, modal particle is dynamically inserted into answer later, the effect that answer content can be made to link up closer to true man Fruit, the guidance and feedback of the combing and mood that can be preferably intended to user, user experience are more preferable.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, making required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other Attached drawing.
Fig. 1 is a kind of flow chart for answer generation method for question answering system that one embodiment of the invention provides;
Fig. 2 is a kind of block diagram for answer generating means for question answering system that one embodiment of the invention provides;
Fig. 3 is the structural schematic diagram for the electronic equipment that one embodiment of the invention provides.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people Member's every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Referring to FIG. 1, it illustrates the processes of one embodiment of answer generation method for question answering system of the application Figure, the answer generation method for question answering system of the present embodiment can be adapted for the terminal for having question and answer function, as mobile phone, Plate, computer, intelligent sound TV, intelligent sound box, Intelligent dialogue toy and other existing intelligence for having question and answer function Terminal etc..
As shown in Figure 1, in a step 101, when engaging in the dialogue with user, obtaining session operational scenarios and the dialogue meaning of user Figure;
When in a step 102, when receive user the problem of, characteristic information included in identification problem;
In step 103, the problem of being based on user, generates corresponding answer;
At step 104, according to dialogue intention, session operational scenarios and characteristic information, at least one modal particle is generated;
In step 105, at least one modal particle is dynamically inserted to the beginning of corresponding answer and/or ending, with Form treated answer.
In the present embodiment, for step 101, the answer generating means for question answering system are that user engages in the dialogue When, the dialogue for obtaining session operational scenarios and user corresponding to current session node is intended to, so as to hold well pair The atmosphere of words.Later, for step 102, when receiving user the problem of, characteristic information included in identification problem, the spy Reference breath may include user emotion, the language form and speech habits of entity and user included in problem etc., this Shen Please there is no limit herein.Later, for step 103, the problem of based on the user received, corresponding answer is generated.Then, right At least one is generated according to the dialogue of user intention, locating session operational scenarios and the relevant characteristic information of problem in step 104 A modal particle.Finally for step 105, the modal particle of generation is inserted into the beginning and/or ending of corresponding answer, thus The answer feedback with modal particle is formed to user.
The method of the present embodiment passes through the characteristic information considered the problems of in dialogue intention, session operational scenarios and user, In Corresponding modal particle is added in answer, so that answer more levels off to the dialogue of true man, promotes the dialogue experience of user.
In some alternative embodiments, the above method further include: based on dialogue intention, session operational scenarios and user feeling Determine the rhythm of casting treated answer;Voice broadcast based on rhythm synthesis treated answer simultaneously carries out voice broadcast. So as to determine rhythm when broadcasting according to known information, is then broadcasted using the corresponding rhythm, preferably played The effect of modal particle.
In some alternative embodiments, characteristic information includes user feeling and entity.To by considering user feeling And entity, there can be certain understanding, to the mood of user convenient for drawing by mood of the addition of modal particle to user It leads, promotes the dialogue experience of user.
In further alternative embodiment, when characteristic information is entity, the above method further include: when receiving user The problem of when, entity included in identification problem;According to entity, at least one modal particle is generated;And by least one language Gas word is dynamically inserted before entity and/or back.It, can be with to by adding corresponding modal particle before and after entity User is allowed to have preferably dialogue experience.
In some alternative embodiments, according to dialogue intention, session operational scenarios and characteristic information, at least one language is generated Gas word includes: at least to safeguard a mapping table for dialogue intention, session operational scenarios, characteristic information and modal particle, so as to There is corresponding modal particle in preset dialogue intention and/or preset session operational scenarios and/or preset characteristic information, In, dialogue is intended to, modal particle corresponding to session operational scenarios and characteristic information has preset priority;It is intended to according to dialogue, is right Scene and characteristic information are talked about, at least one corresponding modal particle is generated;And the priority based on corresponding modal particle, to extremely A few corresponding modal particle carries out duplicate removal processing, and duplicate removal processing includes that removal is duplicate and removal modal particle type is identical , wherein the identical beginning for including while being located at sentence of modal particle type, the ending for being located at sentence simultaneously.To subsequent It needs to safeguard the mapping table, preferably a variety of different dialogues can be intended to, different session operational scenarios and different Characteristic information is preferably responded, and user experience is more preferable.
Below to some problems encountered in the implementation of the present invention by description inventor and to finally determination One specific embodiment of scheme is illustrated, so that those skilled in the art more fully understand the scheme of the application.
The present invention proposes a kind of dynamically to add in the conversational system that topic merges QA question and answer and knowledge card to language The method of gas word.In this conversational system, by the intention combing and guidance in dialogue for user, by merging QA The record of question and answer and the dialogue state of knowledge card and identification by dialogue node user feeling, it is corresponding providing user When answer, we add the modal particle of different states, emotion, this needs to incorporate dialogue management, intention assessment, field The relevant complex art such as scape dialogue and Emotion identification.
Innovation point of the invention:
The effective dialog speech word of dynamic generation;
It is significantly reduced the input of dialogue designs answer.
The present invention includes two main flows: talking with the record of intention, context entity, emotion, dialogue node;Another It is based on relevant information dynamic generation and insertion dialog speech word.
1. based on dialogue intention, the record process of context entity, emotion, dialogue node
A dialog text -- it generates and is intended to, entity, emotion;
The information of B record current session node;
C generates corresponding modal particle according to information above
2. based on relevant information dynamic generation and insertion dialog speech word process
A is inserted into corresponding modal particle in the beginning of answer;
B adds corresponding modal particle before or after relevant entity;
C is inserted into corresponding modal particle behind answer;
In model training stage, training two systems, keyword search system and word speed detection system.Wherein keyword The input of detection system is training data, i.e., largely includes or not comprising the recording for waking up word, whether output recording is comprising calling out Awake word.The input of word speed detection system is equally recording data, export for record word speed speed, it is substantially one two Classifier.
In test phase, test recording can be sent into word speed detection and keyword search system;Word speed detection system detects language The quality of speed, if it is fast word speed, keyword search system uses the sliding window of smaller length, if slowly, using relatively greatly enhancing The sliding window of degree;Wake-up is finally provided as a result, whether being keyword.
Above-described embodiment at least can be realized following technical effect:
By considering influence of the word speed to result is waken up word speed detection is added, for difference in scheme provided in this embodiment The voice of word speed uses the sliding window of different length, so as to greatly reduce influence of the word speed to result is waken up.
Referring to FIG. 2, the frame of the answer generating means for question answering system provided it illustrates one embodiment of the invention Figure.
As shown in Fig. 2, a kind of answer generating means 200 for question answering system, including scene intention acquisition module 210, Feature recognition module 220, answer generation module 230, modal particle generation module 240 and modal particle generation module 240.
Wherein, scene is intended to obtain module 210, is configured to when engaging in the dialogue with user, obtains session operational scenarios and user Dialogue be intended to;Feature recognition module 220 when being configured to when receive user the problem of, identifies spy included in described problem Reference breath;Answer generation module 230, generates corresponding answer at the problem of being configured to the user;Modal particle generates mould Block 240 is configured to generate at least one modal particle according to dialogue intention, the session operational scenarios and the characteristic information; And modal particle is inserted into module 250, is configured at least one described modal particle being dynamically inserted to the corresponding answer Beginning and/or ending, to form treated answer.
In some alternative embodiments, for the answer generating means 200 of question answering system further include: the rhythm determines mould Block (not shown) is configured to the dialogue and is intended to, described in the session operational scenarios and the determining casting of the user feeling The rhythm for answer that treated;And broadcasting module (not shown), after being configured to the rhythm synthesis processing Answer voice broadcast and carry out voice broadcast.
In some alternative embodiments, features described above information includes user feeling and entity.
It should be appreciated that all modules recorded in Fig. 2 are corresponding with each step in the method with reference to described in Fig. 1.By This, operation and feature and corresponding technical effect above with respect to method description are equally applicable to all modules in Fig. 2, In This is repeated no more.
It is worth noting that, the scheme that the module in embodiments herein is not intended to limit this application, such as answer Generation module can be described as the problem of based on the user, generate the module of corresponding answer.Furthermore it is also possible to by hard Part processor realizes that related function module, such as answer generation module can also realize that details are not described herein with processor.
In further embodiments, the embodiment of the invention also provides a kind of nonvolatile computer storage medias, calculate Machine storage medium is stored with computer executable instructions, which can be performed above-mentioned any means embodiment In the answer generation method for question answering system;
As an implementation, nonvolatile computer storage media of the invention is stored with the executable finger of computer It enables, computer executable instructions setting are as follows:
When engaging in the dialogue with user, the dialogue for obtaining session operational scenarios and user is intended to;
When receiving user the problem of, characteristic information included in described problem is identified;
The problem of based on the user, generates corresponding answer;
According to dialogue intention, the session operational scenarios and the characteristic information, at least one modal particle is generated;
At least one described modal particle is dynamically inserted to the beginning and/or ending of the corresponding answer, to be formed Answer that treated.
Non-volatile computer readable storage medium storing program for executing may include storing program area and storage data area, wherein storage journey It sequence area can application program required for storage program area, at least one function;Storage data area can be stored according to for question and answer The answer generating means of system use created data etc..In addition, non-volatile computer readable storage medium storing program for executing can wrap High-speed random access memory is included, can also include nonvolatile memory, for example, at least disk memory, a flash memory Device or other non-volatile solid state memory parts.In some embodiments, non-volatile computer readable storage medium storing program for executing can Choosing includes the memory remotely located relative to processor, these remote memories can be by network connection to for question and answer The answer generating means of system.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, moves and lead to Letter net and combinations thereof.
The embodiment of the present invention also provides a kind of computer program product, and computer program product is non-volatile including being stored in Computer program on property computer readable storage medium, computer program includes program instruction, when program instruction is by computer When execution, computer is made to execute the answer generation method that any of the above-described is used for question answering system.
Fig. 3 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 3, the equipment includes: one A or multiple processors 310 and memory 320, in Fig. 3 by taking a processor 310 as an example.Answer for question answering system is raw Equipment at method can also include: input unit 330 and output device 340.Processor 310, memory 320, input unit 330 can be connected with output device 340 by bus or other modes, in Fig. 3 for being connected by bus.Memory 320 be above-mentioned non-volatile computer readable storage medium storing program for executing.Processor 310 is stored in memory 320 by operation Non-volatile software program, instruction and module, thereby executing the various function application and data processing of server, i.e., in fact Existing above method embodiment is used for the answer generation method of question answering system.Input unit 330 can receive the number or character of input Information, and generate key signals related with the user setting of the answer generating means for question answering system and function control Input.Output device 340 may include that display screen etc. shows equipment.
The said goods can be performed the embodiment of the present invention provided by method, have the corresponding functional module of execution method and Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present invention.
As an implementation, above-mentioned electronic apparatus application is in the answer generating means for question answering system, packet It includes: at least one processor;And the memory being connect at least one processor communication;Wherein, be stored with can for memory The instruction executed by least one processor, instruction executed by least one processor so that at least one processor can:
When engaging in the dialogue with user, the dialogue for obtaining session operational scenarios and user is intended to;
When receiving user the problem of, characteristic information included in described problem is identified;
The problem of based on the user, generates corresponding answer;
According to dialogue intention, the session operational scenarios and the characteristic information, at least one modal particle is generated;
At least one described modal particle is dynamically inserted to the beginning and/or ending of the corresponding answer, to be formed Answer that treated.
The electronic equipment of the embodiment of the present application exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone, and Low-end mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment includes: sound Frequently, video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic devices with data interaction function.
The apparatus embodiments described above are merely exemplary, wherein unit can be with as illustrated by the separation member It is or may not be and be physically separated, component shown as a unit may or may not be physical unit, Can be in one place, or may be distributed over multiple network units.It can select according to the actual needs wherein Some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment It can realize by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on such reason Solution, substantially the part that contributes to existing technology can embody above-mentioned technical proposal in the form of software products in other words Out, which may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, packet Some instructions are included to use so that a computer equipment (can be personal computer, server or the network equipment etc.) executes The method of certain parts of each embodiment or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;To the greatest extent Present invention has been described in detail with reference to the aforementioned embodiments for pipe, those skilled in the art should understand that: it is still It is possible to modify the technical solutions described in the foregoing embodiments, or part of technical characteristic is equally replaced It changes;And these are modified or replaceed, the essence for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution Mind and range.

Claims (10)

1. a kind of answer generation method for question answering system, comprising:
When engaging in the dialogue with user, the dialogue for obtaining session operational scenarios and user is intended to;
When receiving user the problem of, characteristic information included in described problem is identified;
The problem of based on the user, generates corresponding answer;
According to dialogue intention, the session operational scenarios and the characteristic information, at least one modal particle is generated;
At least one described modal particle is dynamically inserted to the beginning and/or ending of the corresponding answer, to form processing Answer afterwards.
2. according to the method described in claim 1, wherein, the method also includes:
It is intended to based on the dialogue, the session operational scenarios and the user feeling determine the rhythm of casting treated the answer Rule;
Voice broadcast based on rhythm synthesis treated the answer simultaneously carries out voice broadcast.
3. according to the method described in claim 1, wherein, the characteristic information includes user feeling and entity.
4. according to the method described in claim 3, wherein, when the characteristic information is entity, the method also includes:
When receiving user the problem of, entity included in described problem is identified;
According to the entity, at least one modal particle is generated;
At least one described modal particle is dynamically inserted before the entity and/or back.
5. according to the method described in claim 1, wherein, it is described be intended to according to the dialogue, the session operational scenarios and the spy Reference breath, generating at least one modal particle includes:
For dialogue intention, the session operational scenarios, the characteristic information and the modal particle, a corresponding pass is at least safeguarded It is table, so that there is corresponding language in preset dialogue intention and/or preset session operational scenarios and/or preset characteristic information Gas word, wherein the dialogue is intended to, modal particle corresponding to the session operational scenarios and the characteristic information is with preset preferential Grade;
According to dialogue intention, the session operational scenarios and the characteristic information, at least one corresponding modal particle is generated;
Based on the priority of the corresponding modal particle, duplicate removal processing is carried out at least one described corresponding modal particle, it is described Duplicate removal processing includes that removal is duplicate and removal modal particle type is identical, wherein the modal particle type is identical to include It is located at the beginning of sentence simultaneously, is located at the ending of sentence simultaneously.
6. a kind of answer generating means for question answering system, comprising:
Scene is intended to obtain module, is configured to when engaging in the dialogue with user, and the dialogue for obtaining session operational scenarios and user is intended to;
Feature recognition module when being configured to when receive user the problem of, identifies characteristic information included in described problem;
Answer generation module, generates corresponding answer at the problem of being configured to the user;
Modal particle generation module is configured to be generated at least according to dialogue intention, the session operational scenarios and the characteristic information One modal particle;
Modal particle is inserted into module, is configured at least one described modal particle being dynamically inserted to the beginning of the corresponding answer And/or ending, to form treated answer.
7. device according to claim 6, wherein described device further include:
Rhythm determining module is configured to the dialogue intention, the session operational scenarios and the user feeling and determines casting institute The rhythm for answer of stating that treated;
Broadcasting module is configured to the voice broadcast of rhythm synthesis treated the answer and carries out voice broadcast.
8. device according to claim 6, wherein the characteristic information includes user feeling and entity.
9. a kind of electronic equipment comprising: at least one processor, and deposited with what at least one described processor communication was connect Reservoir, wherein the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least One processor executes, so that at least one described processor is able to carry out the step of any one of claim 1 to 5 the method Suddenly.
10. a kind of electronic equipment comprising: at least one processor, and connect at least one described processor communication Memory, wherein the memory be stored with can by least one described processor execute instruction, described instruction by it is described extremely A few processor executes, so that at least one described processor is able to carry out the step of any one of claim 1 to 5 the method Suddenly.
CN201910814386.2A 2019-08-30 2019-08-30 Answer generation method and device for question answering system Pending CN110516043A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910814386.2A CN110516043A (en) 2019-08-30 2019-08-30 Answer generation method and device for question answering system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910814386.2A CN110516043A (en) 2019-08-30 2019-08-30 Answer generation method and device for question answering system

Publications (1)

Publication Number Publication Date
CN110516043A true CN110516043A (en) 2019-11-29

Family

ID=68628421

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910814386.2A Pending CN110516043A (en) 2019-08-30 2019-08-30 Answer generation method and device for question answering system

Country Status (1)

Country Link
CN (1) CN110516043A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008128423A1 (en) * 2007-04-19 2008-10-30 Shenzhen Institute Of Advanced Technology An intelligent dialog system and a method for realization thereof
CN105929964A (en) * 2016-05-10 2016-09-07 海信集团有限公司 Method and device for human-computer interaction
US20170289093A1 (en) * 2016-03-30 2017-10-05 Notion Ai, Inc. Discovering questions, directives, and requests from, and prioritizing replies to, a preferred message sender method and apparatus
CN108597509A (en) * 2018-03-30 2018-09-28 百度在线网络技术(北京)有限公司 Intelligent sound interacts implementation method, device, computer equipment and storage medium
CN109684459A (en) * 2018-12-28 2019-04-26 联想(北京)有限公司 A kind of information processing method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008128423A1 (en) * 2007-04-19 2008-10-30 Shenzhen Institute Of Advanced Technology An intelligent dialog system and a method for realization thereof
US20170289093A1 (en) * 2016-03-30 2017-10-05 Notion Ai, Inc. Discovering questions, directives, and requests from, and prioritizing replies to, a preferred message sender method and apparatus
CN105929964A (en) * 2016-05-10 2016-09-07 海信集团有限公司 Method and device for human-computer interaction
CN108597509A (en) * 2018-03-30 2018-09-28 百度在线网络技术(北京)有限公司 Intelligent sound interacts implementation method, device, computer equipment and storage medium
CN109684459A (en) * 2018-12-28 2019-04-26 联想(北京)有限公司 A kind of information processing method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
翟飞飞等: "口语对话中冗余词汇识别方法研究", 《中文信息学报》 *

Similar Documents

Publication Publication Date Title
EP3607547B1 (en) Audio-visual speech separation
EP3095113B1 (en) Digital personal assistant interaction with impersonations and rich multimedia in responses
US9621851B2 (en) Augmenting web conferences via text extracted from audio content
EP3611724A1 (en) Voice response method and device, and smart device
CN109145123A (en) Construction method, intelligent interactive method, system and the electronic equipment of knowledge mapping model
CN109326289A (en) Exempt to wake up voice interactive method, device, equipment and storage medium
CN110175012B (en) Skill recommendation method, skill recommendation device, skill recommendation equipment and computer readable storage medium
CN110136749A (en) The relevant end-to-end speech end-point detecting method of speaker and device
CN109951743A (en) Barrage information processing method, system and computer equipment
CN109637548A (en) Voice interactive method and device based on Application on Voiceprint Recognition
CN109147800A (en) Answer method and device
CN109147784B (en) Voice interaction method, device and storage medium
US20200013389A1 (en) Word extraction device, related conference extraction system, and word extraction method
CN108920128A (en) The operating method and system of PowerPoint
CN111081280A (en) Text-independent speech emotion recognition method and device and emotion recognition algorithm model generation method
CN110473556A (en) Audio recognition method, device and mobile terminal
CN110503944B (en) Method and device for training and using voice awakening model
CN112185362A (en) Voice processing method and device for user personalized service
CN110473524B (en) Method and device for constructing voice recognition system
CN110349569B (en) Method and device for training and identifying customized product language model
CN111105803A (en) Method and device for quickly identifying gender and method for generating algorithm model for identifying gender
CN109686370A (en) The method and device of fighting landlord game is carried out based on voice control
CN108847066A (en) A kind of content of courses reminding method, device, server and storage medium
CN110516043A (en) Answer generation method and device for question answering system
US20220076674A1 (en) Cross-device voiceprint recognition

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
CB02 Change of applicant information

Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province

Applicant after: Sipic Technology Co.,Ltd.

Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province

Applicant before: AI SPEECH Ltd.

CB02 Change of applicant information