CN106934452A - Robot dialogue method and system - Google Patents
Robot dialogue method and system Download PDFInfo
- Publication number
- CN106934452A CN106934452A CN201710037951.XA CN201710037951A CN106934452A CN 106934452 A CN106934452 A CN 106934452A CN 201710037951 A CN201710037951 A CN 201710037951A CN 106934452 A CN106934452 A CN 106934452A
- Authority
- CN
- China
- Prior art keywords
- strategy
- dialog
- signal
- answer signal
- robot
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Robotics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of robot dialogue method, comprise the following steps：S100：Various different dialog strategies are pre-stored, the dialog strategy comprises at least absolutely dry pre- dialog strategy, half intervention dialog strategy and nonintervention dialog strategy；S200：According to current session strategy generating answer signal；S300：Current session strategy is converted into selected dialog strategy in response to choosing instruction；S400：Answer signal is regenerated according to selected dialog strategy.The present invention can make robot make the action being adapted with session operational scenarios.
Description
Technical field
Generally the present invention relates to robot, more particularly to a kind of robot dialogue method and system.
Background technology
, by development for many years and research, theoretical system is increasingly complete, generates more complete for natural language processing field
Theory.The product of many practical applications is occurred in that in application field based on these complete theories, dialogue/chat robots are just
It is one kind therein.
Chat robots have generated many representational products by years of researches development, and these products are mainly
Some specific fields are applied to, such as live assistant, question answering system, customer service system etc..Chat robots can receive use
The word at family or phonetic entry, the internals for being then based on system return to the feedback answer of the problem.In recent years, chatting machine
Device people is also endowed specific gable structure and simple emotive function, thus possesses simple limb action and simple emotion
Expression.
But the single, emotion of existing chat robots dialogue is pale, the mode of thinking of the mankind and language side can not be used
Formula answers the problem of user, but the role as playing the part of similar encyclopedia, poor user experience.
The content of the invention
For the defect of prior art, the invention provides a kind of robot dialogue method and system.
A kind of robot dialogue method, comprises the following steps：S100：Various different dialog strategies are pre-stored, it is described right
Words strategy comprises at least absolutely dry pre- dialog strategy, half intervention dialog strategy and nonintervention dialog strategy；S200：According to current right
Words strategy generating answer signal；S300：Current session strategy is converted into selected dialog strategy in response to choosing instruction；
S400：Answer signal is regenerated according to selected dialog strategy.
Optionally, under the absolutely dry pre- dialog strategy, the answer signal is keeper's input signal；Described half-dried
Under pre- dialog strategy, the signal that the answer signal is selected for keeper；Under the nonintervention dialog strategy, the response letter
Number it is the signal automatically generated according to preset rules.It is further comprising the steps of：Receive voice signal, the voice signal that will be received
Answer signal with generation sends to management end jointly.The step S400 includes：When selected dialog strategy intervenes plan for half
When slightly, the answer signal of automatic search voice signal sends to robot the answer signal that management end is selected.The step
S400 includes：When selected dialog strategy is absolutely dry pre- dialog strategy, input answer signal is to management end, and answering input
Signal is answered to send to robot.
A kind of robot conversational system, including with lower unit：Memory cell, for being pre-stored various different dialogue plans
Slightly, the dialog strategy comprises at least absolutely dry pre- dialog strategy, half intervention dialog strategy and nonintervention dialog strategy；First should
Unit is answered, for according to current session strategy generating answer signal；Converting unit, in response to choosing instruction by current session
Strategy is converted to selected dialog strategy；Second response unit, for regenerating answer signal according to selected dialog strategy.
The beneficial effects of the invention are as follows：Chat robots conversational system of the invention, can greatly lift chat machine
The Consumer's Experience of people, there is provided meet the answer of human language custom and diction so that robot is more intelligent, carry
The manual intervention function of confession can greatly expand the application field and scope of chat robots；And can be provided for keeper
Easy-to-use operate interface is answered in letter, facilitates keeper set to the dialog strategy of system.
Brief description of the drawings
Fig. 1 is present system structural representation；
Fig. 2 is the structural representation of cloud server of the present invention；
Fig. 3 is the flow chart of the embodiment of the present invention 1；
Fig. 4 is the structural representation of the embodiment of the present invention 2.
Specific embodiment
To enable the above objects, features and advantages of the present invention more obvious understandable, below in conjunction with the accompanying drawings to the present invention
Specific embodiment be described in detail, above and other purpose of the invention, feature and advantage will be become apparent from.Complete
Identical reference indicates identical part in portion's accompanying drawing.Not deliberately accompanying drawing drawn to scale, it is preferred that emphasis is show this hair
Bright purport.
Fig. 1 is referred to, a summarized introduction is done to system architecture of the invention first.Robot in the present invention can be as
Humanoid robot shown in Fig. 1, it has mobilizable four limbs and head, certainly can also have display screen, phonetic entry/
Output device etc..In Fig. 1, whole system includes robot, cloud server and management end.Robot, cloud service
Communicated between device and management end, communication can use wired or wireless form, for example, can be used wifi, 3G/4G etc.,
The concrete form present invention for communicating is not limited.Robot can be entered into dialogue with people in the present invention, and robot will be received
To voice be sent to cloud server, response text is sent to robot after cloud server treatment, robot by this
Text is converted into voice signal and is exported by speech synthesis technique, so as to the voice to people is responded.Management end is responsible for
Monitoring to whole dialog procedure, by being subsequently discussed in detail as can be seen that can be done to the response of robot by management end
Go out adjustment so that robot makes more appropriate answer, so as to improve Consumer's Experience.
Fig. 2 is the structural representation of cloud server, and in the present invention, cloud server includes control unit, Yi Jiyu
Strategy generating unit, transmitting element, database and receiving unit that control unit is connected respectively.Receiving unit is responsible for receiving machine
The voice signal that people sends, voice signal is that the voice of the people received by robot is transformed, for example, can lead to
Cross the Mike (MIC) that is installed on robot to receive voice, this voice signal can be the voice document of MP3 format,
Can also be the text of txt forms, the present invention is not limited for the concrete form of voice signal.Strategy generating unit exists
Under the manipulation of management end, dialog strategy is sent to control unit, according to this dialog strategy, generation is for receiving for control unit
The answer signal of the voice signal for arriving, similarly, answer signal can also be the voice document of MP3 format or the text of txt forms
File, robot is sent to after answer signal is generated by transmitting element answer signal, and robot plays this answer signal,
So as to complete the dialogue and people between.Management end, can be intelligent mobile terminal, such as smart mobile phone, IPAD, notebook computer
Deng management end is connected with receiving unit and transmitting element, the voice signal that such management end will can be received and sends
Answer signal be shown on management end jointly, be easy to back-stage management personnel according to current session content adjust dialog strategy.
Embodiment 1
The embodiment is introduced robot dialogue method of the invention first, as shown in figure 3, it is comprised the following steps.
S100：Various different dialog strategies are pre-stored, the dialog strategy comprises at least absolutely dry pre- dialog strategy, half-dried
Pre- dialog strategy and nonintervention dialog strategy.
In the present invention, cloud server is stored with various different dialog strategies.Dialog strategy represents that answer signal is given birth to
Into method/rule.In the present invention, interactive degree difference is intervened according to management end/keeper and is divided into dialog strategy
Absolutely dry pre- dialog strategy, half intervene dialog strategy and nonintervention dialog strategy.These strategies are introduced respectively below.
Absolutely dry pre- strategy represents that management staff can completely take over robot conversational system, and answer is automatically generated,
Then the answer of customer problem is directly directly produced by management staff.Under this policy, the voice of user input can be led to
Cross speech recognition and be converted into text input system, user input is presented in cloud server the management end behaviour at management staff
Make on interface, management staff carries out phonetic entry, by system converting to be presented to use by phonetic synthesis again after text
Family.
Half intervenes Policy Table shows that management staff is only responsible for producing answer to be selected or corrected robot system, it
To select afterwards or revised answer feedback will be to user.User is entered text into after phonetic entry by speech recognition
The multiple answers for generating are entered by the answer generating unit of chat robots system after the multiple answers of generation by management staff
The answer of selection was listened phonetic synthesis to be presented to user by row selection, chat robots system.
What nonintervention strategy was represented is generation of management staff's nonintervention robot chat system to answer, only to machine
People's system exercises supervision.Under this policy, carry out chatting with user is carried out by chat robots system completely.Management staff
Only chat robots system is exercised supervision with the session of user, and in the case where needing keeper to be intervened to chatting machine
Device people's system is intervened.
S200：According to current session strategy generating answer signal.
After system starts, the dialog strategy of acquiescence is nonintervention dialog strategy, and under this policy, receiving unit will be received
Voice signal be sent to control unit, control unit is answered according to the automatic problem of being searched for from database of default nonintervention strategy
Case, that is, automatically generate problem answers, answer search for automatically and the process that produces and non-invention emphasis where, no longer go to live in the household of one's in-laws on getting married herein
State.The answer for searching is sent to robot by transmitting element, and answer can be played to use by robot by phonetic synthesis
Family, so as to complete the dialogue and between user.Under this policy, management end only exercises supervision to the dialogue between robot and user,
I.e. keeper can see the response transmitted by voice signal and transmitting element received by receiving unit from management end interface
Signal.
S300：Current session strategy is changed to selected dialog strategy according to instruction is chosen.
Under current session strategy, produced answer signal and language under keeper has found current strategies by management end
When message number is incompatible, new dialog strategy can be again selected by management end, such as keeper can touch or click on
Corresponding policy name sends selection instruction to management end in management end operation interface, and this selection is instructed and sent out by management end afterwards
Strategy generating unit is given, current strategies are converted into selected dialog strategy by strategy generating unit, for example, will can not intervened
Change inpolicy is half Intervention Strategy.Said process is described further below by a detailed example.
For example under current nonintervention dialog strategy, the voice signal received by robot is " good morning ", current
It is " I am fine " by the answer signal produced by automatic search under strategy." good morning " that receiving unit will be received this
Voice signal is sent to management end and is shown, and transmitting element transmits same to " I am fine " this answer signal for generating
Management end shown, keeper when finding that this answer signal is incompatible with voice signal by management end, keeper
" half Intervention Strategy " or " full Intervention Strategy " on display screen can be clicked on, new dialog strategy is selected again, for example, managed
The selected dialog strategy of member is half Intervention Strategy, then can regenerate answer signal according to half Intervention Strategy after system.
S400：Answer signal is regenerated according to selected dialog strategy.
After the conversion for completing dialog strategy, control unit can be believed regenerating according to new dialog strategy for voice
Number answer signal.New dialog strategy is probably half Intervention Strategy or full Intervention Strategy, and it is introduced separately below.
Under half Intervention Strategy, control unit can first based on the automatic search strategy under nonintervention strategy pattern from database
In automatic search voice signal answer, it is however generally that the automatic answer for searching out has multiple, in the case where strategy is not intervened, system
Can one of them be chosen from multiple answers at random or according to setting rule to generate answer signal, complete dialogue.But half-dried
Under pre- strategy, the answer that transmitting element will can be searched out all is sent to management end, and keeper selects wherein one by management end
Individual answer, is sent to robot by transmitting element by this answer afterwards, and robot is selected by speech play keeper
Answer is so as to complete dialogue.
Example is connected, the dialog strategy that keeper selectes again is half Intervention Strategy, the voice signal that receiving unit is received
It is " good morning " that it is " I am fine ", " Good noon ", " good morning ", " evening that control unit searches out possible response from database
It is first-class " etc., in the case where strategy is not intervened, system can automatically choose " I am fine " as answer signal according to setting rule, it is clear that
It is unaccommodated during this answer signal, give an irrelevant answer, poor user experience.And after dialog strategy is changed into Intervention Strategy, control
The all possible response that unit will be searched is sent to management end, and keeper can choose it in these possible responses
In one, can for example click on screen show " good morning ", afterwards management end by " good morning " this regenerate answer
Answer signal and robot is sent to by transmitting element, robot is played by voice answer-back signal, complete the dialogue with user.
Under full Intervention Strategy, management staff can completely take over robot conversational system.Now answer signal will not
Automatic search mechanisms can be depended on, then is directly directly input into the answer of corresponding problem by input window by management staff.
Under this policy, the voice of user input can be converted into text input system by speech recognition, and cloud server will be used
Family input is presented in the management end operation interface at management staff, and management staff carries out phonetic entry, is turned by system
Turn to and user is presented to by phonetic synthesis again after text.
Example in continuation, when keeper has found that answer signal is incompatible with voice signal by management end, keeper can
So that dialog strategy first is converted into half Intervention Strategy, under half Intervention Strategy, the response for searching out automatically be " I am fine ", " in
Noon is good ", " good morning ", " good night ", but current time is afternoon, it is clear that also non-optimal is answered for the automatic above-mentioned response for searching out
Case.Now, keeper can click on the full Intervention Strategy on management end screen, and current session strategy is changed by half Intervention Strategy
It is full Intervention Strategy.Under full Intervention Strategy, it " is now morning that keeper can be input into dialog box", Zhi Houguan
This response is sent to robot by reason end by transmitting element, and robot is presented to user, thus completes by phonetic synthesis
Dialogue.
Certainly, dialog strategy is converted to absolutely dry pre- dialog strategy or half intervene dialog strategy after, keeper can be with
Dialog strategy is converted back by nonintervention dialog strategy by management end, such as by clicking on the nonintervention dialog strategy on screen
Button.Afterwards, system can automatically search for generation answer signal again, repeat no more.
By above-mentioned introduction it can be found that the present invention is due to the intervention for having people (keeper) in dialog procedure so that
Can be interacted with user with the mode of thinking of the mankind and speech habits, solve robot dialogue it is single, emotion is pale
Defect；Various strategy patterns are provided, the switching of specific application model are realized according to actual application scenarios such that it is able to carry
For more preferably Consumer's Experience.
With robot by interactive voice, user is producing answer to user by voice entry system, system by treatment
Also the returning result in the way of voice afterwards.The data-base recording data bank of chat robots, be source that answer is produced and
Basis；Strategy generating unit is the core component of system, is intervened for the generation according to selected strategy to answer signal,
Can freely be changed in the case where nonintervention, half intervene and intervene Three models, so as to correct answer produced by chat robots system
Deviation such that it is able to the dialogue that intelligent chat robots meet human language custom and diction.
Embodiment 2
Accordingly, as shown in figure 4, the invention also discloses a kind of robot conversational system, including with lower unit：Storage is single
Unit, for being pre-stored various different dialog strategies, the dialog strategy comprises at least absolutely dry pre- dialog strategy, half intervention dialogue
Strategy and nonintervention dialog strategy；First response unit, for according to current session strategy generating answer signal；Converting unit,
For current session strategy to be converted into selected dialog strategy in response to choosing instruction；Second response unit, for according to choosing
Fixed dialog strategy regenerates answer signal.
Optionally, also including management end, under the absolutely dry pre- dialog strategy, the answer signal is the input of management end
Signal；Intervene under dialog strategy described half, the answer signal is the signal that management end is selected；In the nonintervention dialogue plan
Under slightly, the answer signal is the signal automatically generated according to preset rules.Also include receiving unit and transmitting element, it is described to connect
Unit is received, for receiving voice signal, and the voice signal that will be received is sent to management end；The transmitting element, for inciting somebody to action
Answer signal is sent to management end.Second response unit, specifically for when selected dialog strategy is half Intervention Strategy,
The answer signal of automatic search voice signal, the answer signal that management end is selected is sent to robot.The second response list
Unit, specifically for when selected dialog strategy is absolutely dry pre- dialog strategy, input answer signal will be input into management end
Answer signal is sent to robot.
Each embodiment in this specification is described by the way of progressive, what each embodiment was stressed be with
The difference of other embodiment, between each embodiment same or analogous part mutually referring to.For the application's
For embodiment of the method, because it is substantially similar to device embodiment, so description is fairly simple, related part is referring to device
The part explanation of embodiment.
Elaborate many details in order to fully understand the present invention in the above description.But above description is only
Presently preferred embodiments of the present invention, the present invention can be implemented with being much different from other manner described here, therefore this
Invention is not limited by specific implementation disclosed above.Any those skilled in the art are not departing from the technology of the present invention simultaneously
In the case of aspects, all make many possible to technical solution of the present invention using the methods and techniques content of the disclosure above
Change and modify, or the Equivalent embodiments for being revised as equivalent variations.Every content without departing from technical solution of the present invention, according to this
The technical spirit of invention still falls within skill of the present invention to any simple modification, equivalent variation and modification made for any of the above embodiments
In the range of the protection of art scheme.
Claims (10)
1. a kind of robot dialogue method, it is characterised in that comprise the following steps：
S100：Various different dialog strategies are pre-stored, the dialog strategy comprises at least absolutely dry pre- dialog strategy, partly intervenes right
Words strategy and nonintervention dialog strategy；
S200：According to current session strategy generating answer signal；
S300：Current session strategy is converted into selected dialog strategy in response to choosing instruction；
S400：Answer signal is regenerated according to selected dialog strategy.
2. robot dialogue method according to claim 1, it is characterised in that under the absolutely dry pre- dialog strategy, institute
Answer signal is stated for keeper's input signal；Intervene under dialog strategy described half, the answer signal is selected for keeper
Signal；Under the nonintervention dialog strategy, the answer signal is the signal automatically generated according to preset rules.
3. robot dialogue method according to claim 1, it is characterised in that further comprising the steps of：Receive voice letter
Number, the voice signal and the answer signal of generation that will be received send to management end jointly.
4. robot dialogue method according to claim 1, it is characterised in that the step S400 includes：When what is selected
When dialog strategy is half Intervention Strategy, the answer signal of automatic search voice signal, the answer signal that management end is selected sends
To robot.
5. robot dialogue method according to claim 1, it is characterised in that the step S400 includes：When what is selected
When dialog strategy is absolutely dry pre- dialog strategy, input answer signal is sent to machine the answer signal of input to management end
People.
6. a kind of robot conversational system, it is characterised in that including with lower unit：
Memory cell, for being pre-stored various different dialog strategies, the dialog strategy comprise at least absolutely dry pre- dialog strategy,
Half intervenes dialog strategy and nonintervention dialog strategy；
First response unit, for according to current session strategy generating answer signal；
Converting unit, for current session strategy to be converted into selected dialog strategy in response to choosing instruction；
Second response unit, for regenerating answer signal according to selected dialog strategy.
7. robot conversational system according to claim 6, it is characterised in that also including management end, described absolutely dry pre-
Under dialog strategy, the answer signal is the input signal of management end；Intervene under dialog strategy described half, the answer signal
For the signal that management end is selected；Under the nonintervention dialog strategy, the answer signal is to be automatically generated according to preset rules
Signal.
8. robot conversational system according to claim 6, it is characterised in that also including receiving unit and transmitting element,
The receiving unit, for receiving voice signal, and the voice signal that will be received is sent to management end；The transmitting element,
For answer signal to be sent to management end.
9. robot conversational system according to claim 6, it is characterised in that second response unit, specifically for
When selected dialog strategy is half Intervention Strategy, the answer signal of automatic search voice signal, the response that management end is selected
Signal is sent to robot.
10. robot conversational system according to claim 6, it is characterised in that second response unit, specifically for
When selected dialog strategy is absolutely dry pre- dialog strategy, input answer signal is to management end, and the answer signal hair that will be input into
Deliver to robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710037951.XA CN106934452A (en) | 2017-01-19 | 2017-01-19 | Robot dialogue method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710037951.XA CN106934452A (en) | 2017-01-19 | 2017-01-19 | Robot dialogue method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106934452A true CN106934452A (en) | 2017-07-07 |
Family
ID=59422840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710037951.XA Pending CN106934452A (en) | 2017-01-19 | 2017-01-19 | Robot dialogue method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106934452A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108600695A (en) * | 2018-04-19 | 2018-09-28 | 广东水利电力职业技术学院（广东省水利电力技工学校） | A kind of intelligent interaction robot control system |
| CN108711423A (en) * | 2018-03-30 | 2018-10-26 | 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 |
| WO2019071599A1 (en) * | 2017-10-13 | 2019-04-18 | Microsoft Technology Licensing, Llc | Providing a response in a session |
| CN110046221A (en) * | 2019-03-01 | 2019-07-23 | 平安科技（深圳）有限公司 | A kind of machine dialogue method, device, computer equipment and storage medium |
| US11100407B2 (en) | 2018-10-10 | 2021-08-24 | International Business Machines Corporation | Building domain models from dialog interactions |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1996022568A1 (en) * | 1995-01-18 | 1996-07-25 | Philips Electronics N.V. | A method and apparatus for providing a human-machine dialog supportable by operator intervention |
| US20040078204A1 (en) * | 2002-10-18 | 2004-04-22 | Xerox Corporation | System for learning a language |
| CN105162688A (en) * | 2015-08-13 | 2015-12-16 | 北京智齿博创科技有限公司 | Method for chatting with online customer service representative |
| CN105207890A (en) * | 2015-08-24 | 2015-12-30 | 北京智齿博创科技有限公司 | Online customer service method |
| CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
| CN105563484A (en) * | 2015-12-08 | 2016-05-11 | 深圳前海达闼云端智能科技有限公司 | Cloud robot system, robot and robot cloud platform |
| CN105591882A (en) * | 2015-12-10 | 2016-05-18 | 北京中科汇联科技股份有限公司 | Method and system for mixed customer services of intelligent robots and human beings |
| CN106021403A (en) * | 2016-05-12 | 2016-10-12 | 北京奔影网络科技有限公司 | Customer service method and apparatus |
-
2017
- 2017-01-19 CN CN201710037951.XA patent/CN106934452A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1996022568A1 (en) * | 1995-01-18 | 1996-07-25 | Philips Electronics N.V. | A method and apparatus for providing a human-machine dialog supportable by operator intervention |
| US20040078204A1 (en) * | 2002-10-18 | 2004-04-22 | Xerox Corporation | System for learning a language |
| CN105162688A (en) * | 2015-08-13 | 2015-12-16 | 北京智齿博创科技有限公司 | Method for chatting with online customer service representative |
| CN105207890A (en) * | 2015-08-24 | 2015-12-30 | 北京智齿博创科技有限公司 | Online customer service method |
| CN105563484A (en) * | 2015-12-08 | 2016-05-11 | 深圳前海达闼云端智能科技有限公司 | Cloud robot system, robot and robot cloud platform |
| CN105591882A (en) * | 2015-12-10 | 2016-05-18 | 北京中科汇联科技股份有限公司 | Method and system for mixed customer services of intelligent robots and human beings |
| CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
| CN106021403A (en) * | 2016-05-12 | 2016-10-12 | 北京奔影网络科技有限公司 | Customer service method and apparatus |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019071599A1 (en) * | 2017-10-13 | 2019-04-18 | Microsoft Technology Licensing, Llc | Providing a response in a session |
| CN110121706A (en) * | 2017-10-13 | 2019-08-13 | 微软技术许可有限责任公司 | Response in session is provided |
| US11487986B2 (en) | 2017-10-13 | 2022-11-01 | Microsoft Technology Licensing, Llc | Providing a response in a session |
| CN108711423A (en) * | 2018-03-30 | 2018-10-26 | 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 |
| CN108600695A (en) * | 2018-04-19 | 2018-09-28 | 广东水利电力职业技术学院（广东省水利电力技工学校） | A kind of intelligent interaction robot control system |
| US11100407B2 (en) | 2018-10-10 | 2021-08-24 | International Business Machines Corporation | Building domain models from dialog interactions |
| CN110046221A (en) * | 2019-03-01 | 2019-07-23 | 平安科技（深圳）有限公司 | A kind of machine dialogue method, device, computer equipment and storage medium |
| WO2020177282A1 (en) * | 2019-03-01 | 2020-09-10 | 平安科技（深圳）有限公司 | Machine dialogue method and apparatus, computer device, and storage medium |
| CN110046221B (en) * | 2019-03-01 | 2023-12-22 | 平安科技（深圳）有限公司 | Machine dialogue method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106934452A (en) | Robot dialogue method and system | |
| JP6726800B2 (en) | Method and apparatus for human-machine interaction based on artificial intelligence | |
| US20190193273A1 (en) | Robots for interactive comedy and companionship | |
| CN104350541B (en) | The robot that natural dialogue with user can be merged into its behavior, and programming and the method using the robot | |
| CN107870994A (en) | Man-machine interaction method and system for intelligent robot | |
| JP2022524944A (en) | Interaction methods, devices, electronic devices and storage media | |
| WO2017189559A1 (en) | Multiple interactive personalities robot | |
| US20080096533A1 (en) | Virtual Assistant With Real-Time Emotions | |
| Mallios et al. | A survey on human machine dialogue systems | |
| WO2018000259A1 (en) | Method and system for generating robot interaction content, and robot | |
| CN112599124A (en) | Voice scheduling method and system for power grid scheduling | |
| CN105488164A (en) | Question and answer (QA) data processing method and device, intelligent robot | |
| CN105723360A (en) | Improving natural language interactions using emotional modulation | |
| US10979242B2 (en) | Intelligent personal assistant controller where a voice command specifies a target appliance based on a confidence score without requiring uttering of a wake-word | |
| CN107330418B (en) | Robot system | |
| WO2004051499A1 (en) | Dialogue control device and method, and robot device | |
| CN109346083A (en) | A kind of intelligent sound exchange method and device, relevant device and storage medium | |
| CN106127526A (en) | Intelligent robot system and method for work thereof | |
| WO2023124393A1 (en) | Intelligent interaction system and method, and electronic device and storage medium | |
| Bozkurt et al. | Technology renovates itself: Key concepts on intelligent personal assistants (IPAs) | |
| CN109830232A (en) | Man-machine interaction method, device and storage medium | |
| CN111739541A (en) | Conference assistance method and system based on voice, storage medium and terminal | |
| CN109473090A (en) | A kind of narration data processing method and processing device towards intelligent robot | |
| CN110110338A (en) | A kind of Dialogue management model application method based on LSTM and slot filling | |
| CN109413663A (en) | A kind of information processing method and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170707 |
|
| RJ01 | Rejection of invention patent application after publication |