CN107452373A - Robot interactive method and system - Google Patents
Robot interactive method and system Download PDFInfo
- Publication number
- CN107452373A CN107452373A CN201710616293.XA CN201710616293A CN107452373A CN 107452373 A CN107452373 A CN 107452373A CN 201710616293 A CN201710616293 A CN 201710616293A CN 107452373 A CN107452373 A CN 107452373A
- Authority
- CN
- China
- Prior art keywords
- voice messaging
- user
- identity relation
- reply message
- voice
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 43
- 230000003993 interaction Effects 0.000 claims abstract description 20
- 241001672694 Citrus reticulata Species 0.000 abstract description 7
- 238000004891 communication Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/065—Adaptation
- G10L15/07—Adaptation to the speaker
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0631—Creating reference templates; Clustering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0638—Interactive procedures
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Manipulator (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention discloses a kind of robot interactive method and system, methods described includes：Receive the first voice messaging of user；When the corresponding target response information failure of matching first voice messaging, user's repeated interaction is asked；When the request reply message for receiving the user is the second voice messaging, the identity relation of first voice messaging and second voice messaging is established；The identity relation is stored to information matches database.The embodiment of the present invention solve the problems, such as in the prior art robot identification user speech information difficulty, especially for netspeak, non-standard mandarin can Rapid matching go out response message, improve the communication efficiency between user.
Description
Technical field
The present embodiments relate to robotic technology field, more particularly to a kind of robot interactive method and system.
Background technology
Robot (Robot) is the automatic machine system for performing work.It can both receive mankind commander, can run again
The program of advance layout, can also be according to the principle guiding principle action formulated with artificial intelligence technology, for assisting or substituting the mankind
Work.
At present, with the fast development of science and technology, robot can with speech recognition, can also face recognition, therefore machine
Device people can realize to be interacted with the normal of the mankind.Even, the robot of prior art can accomplish dialect, mandarin, English etc.
The identification of multilingual.But in actual applications, robot exchanges with user or can run into many problems, for example, user
Mandarin is nonstandard, user possesses individual using online emerging term or user and spoken custom etc., machine identifies not per capita
Go out.Therefore, when user language is between dialect and mandarin, robot often can not identify the meaning that user is intended by
Think.
The content of the invention
The embodiment of the present invention provides a kind of robot interactive method and system, can solve the problem that existing robot identification user's language
The problem of message breath is difficult.
In a first aspect, the embodiments of the invention provide a kind of robot interactive method, including：
Receive the first voice messaging of user；
When the corresponding target response information failure of matching first voice messaging, the user is asked to repeat to hand over
Mutually；
When the request reply message for receiving the user is the second voice messaging, establish first voice messaging with it is described
The identity relation of second voice messaging；
The identity relation is stored to information matches database.
Further, stored by the identity relation to information matches database, in addition to：
When the reception user is with the first voice messaging identical voice messaging, the second voice letter is obtained
The response message of breath is as target response information.
Further, before the identity relation for establishing first voice messaging with second voice messaging,
After second voice messaging for receiving the user, in addition to：
Preset times threshold value is set；
Accordingly, when the request reply message for receiving the user is the second voice messaging, first language is established
Message ceases to be included with the identity relation of second voice messaging：
When the first voice messaging number for receiving the user reaches the preset times threshold value, first language is established
Message ceases the identity relation with second voice messaging；Or reach in the second voice messaging number for receiving the user
During the preset times threshold value, the identity relation of first voice messaging and second voice messaging is established.
Further, the identity relation for establishing first voice messaging and second voice messaging, including：
Reach preset matching number threshold in the matching times for receiving first voice messaging and second voice messaging
During value, the identity relation of first voice messaging and second voice messaging is established.
Further, the identity relation for establishing first voice messaging and second voice messaging, in addition to：
In the first voice messaging that n-th receives, the 3rd voice messaging be present is the request reply message, the described 3rd
When voice messaging is with the second voice messaging difference, it is determined that correct first request reply message；
Establish the identity relation of first voice messaging and the described first request reply message；
Wherein, N is the positive integer less than preset matching frequency threshold value.
Further, after the second voice messaging of the user is received, it is described establish first voice messaging with
The identity relation of second voice messaging, in addition to：
Circulation receives the request reply message of the user；
If the request reply message is the 4th voice messaging, the 4th voice messaging and second voice messaging are not
Meanwhile it is determined that correct second request reply message；
Establish the identity relation of first voice messaging and the described second request reply message.
Second aspect, the embodiment of the present invention additionally provide a kind of robot interactive system, including：
First voice messaging receiving module, to receive the first voice messaging of user；
Interactive module is asked, when the corresponding target response information failure of matching first voice messaging, to ask
Seek user's repeated interaction；
Identity relation establishes module, when to receive the request reply message of the user being the second voice messaging, establishes
The identity relation of first voice messaging and second voice messaging；
Identity relation memory module, the identity relation is stored to information matches database.
Further, it is characterised in that also include：
Target response data obtaining module, to be stored by the identity relation to information matches database, in
Receive the user with the first voice messaging identical voice messaging when, obtain the response letter of second voice messaging
Breath is used as target response information.
Further, it is characterised in that also include：
Preset times threshold module, to it is described establish first voice messaging and second voice messaging etc.
Before relation, after second voice messaging for receiving the user, preset times threshold value is set；
Accordingly, the identity relation establish module specifically to：
When the first voice messaging number for receiving the user reaches the preset times threshold value, first language is established
Message ceases the identity relation with second voice messaging；Or reach in the second voice messaging number for receiving the user
During the preset times threshold value, the identity relation of first voice messaging and second voice messaging is established.
Further, the identity relation establish module specifically to：
Reach preset matching number threshold in the matching times for receiving first voice messaging and second voice messaging
During value, the identity relation of first voice messaging and second voice messaging is established.
Further, the identity relation establish module specifically to：
In the first voice messaging that n-th receives, the 3rd voice messaging be present is the request reply message, the described 3rd
When voice messaging is with the second voice messaging difference, it is determined that correct first request reply message；Establish first voice
Information and the identity relation of the described first request reply message；Wherein, N is the positive integer less than preset matching frequency threshold value.
Further, the identity relation establish module specifically to：
After the second voice messaging of the user is received, circulation receives the request reply message of the user；If institute
It is the 4th voice messaging to state request reply message, when the 4th voice messaging is with the second voice messaging difference, it is determined that just
The second true request reply message；Establish the identity relation of first voice messaging and the described second request reply message.
The embodiments of the invention provide a kind of robot interactive method and system, and when matching, the first voice messaging is corresponding
When target response information fails, user's repeated interaction is asked；When the request reply message for receiving user is the second voice messaging, build
The identity relation of vertical first voice messaging and second voice messaging；Identity relation is stored to information matches database, solution
The problem of robot identification user speech information difficulty in the prior art of having determined, especially for netspeak, non-standard mandarin
Can Rapid matching go out response message, improve the communication efficiency between user.
Brief description of the drawings
Fig. 1 is a kind of flow chart of robot interactive method in the embodiment of the present invention one；
Fig. 2 is a kind of flow chart of robot interactive method in the embodiment of the present invention two；
Fig. 3 is a kind of structure chart of robot interactive system in the embodiment of the present invention three.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart of the exchange method for robot that the embodiment of the present invention one provides, and the present embodiment is applicable
In the situation of the interaction of various robots, this method can be held by the interactive system of robot provided in an embodiment of the present invention
OK.As shown in figure 1, specifically include：
S110, the first voice messaging for receiving user.
Wherein, when the first voice messaging can be that user links up with robot, user thinks any voice messaging of expression, example
Mood such as on living, working or user expresses.Because robot memory capacity is limited, thus by data storage and
Complex calculation is transferred to the robot server end being connected with robot, is handled by server, is not influenceing robot original
While having running status, the storage and processing of more data can be realized.
Specifically, robot server receives the first voice messaging that robot uploads, wherein, the first voice messaging can be with
It is shorter several words or longer one or more words.
S120, when first voice messaging corresponding target response information failure is matched, ask user's weight
Reestablish diplomatic relations mutually.
Wherein, target response information is that can reply the response message of the first voice messaging, and target response information can be with
For text message or voice messaging.But when robot server can not identify the first voice messaging of user, then can not
The target response information corresponding with the first voice messaging is matched to be replied.At this moment, server will indicate that robot is defeated
The order of user's repeated interaction is sold, for example, when the target response information failure of the voice messaging of server matches first, then it is defeated
Go out voice " I does not understand what you are saying ", or the similar voice for allowing user's repeat specification such as " owner your no matter what one says ".
It should be noted that the process that robot server matches the corresponding target response information of the first voice messaging can
To be：After server receives the first voice messaging of user, the first voice messaging can be converted to text message, then
The target response information corresponding with text information is matched in information matches database.
When S130, the request reply message of the reception user are the second voice messaging, first voice messaging is established
With the identity relation of second voice messaging.
Wherein, because the second voice messaging is the voice messaging of repeated interaction, so the second voice messaging should be and
The voice messaging of one voice messaging equivalent meanings.Identity relation has been to determine after the second voice messaging can be identified, directly
Connect and the first voice messaging is equal to the second voice messaging.
Specifically, when robot asks user's repeated interaction, user's the first voice letter expressed before can be appreciated that
Not the problem of breath statement is not known.Therefore, when the request reply message that server receives is different with the first voice messaging
But during implication the second voice messaging of identical, and when server can identify the second voice messaging, establish the first voice messaging
With the identity relation of the second voice messaging.
S140, the identity relation stored to information matches database.
Wherein, information matches database is to be stored with the database largely talked with so that server is receiving user's
After voice messaging, the response message of the voice messaging can be matched in information matches database.
In addition, in embodiments of the present invention, information matches database not only stores a large amount of dialogues, also store identification and lose
Lose voice messaging and identify the identity relation of successfully voice messaging.For example, when server receives the first voice of user again
During information, it can be obtained and first voice messaging implication the second language of identical by matching relationship in information matches database
Message ceases.Talked between following robot and user and be illustrated：
" owner is commonly talked about using non-standard：abcd.
Robot is not understood, and can say：Your no matter what one says of owner
Owner says repetition：Room is swept
Robot is answered：Sweep and be over.”
Exemplified by dialogue between above-mentioned robot and user, when robot server receives the first voice messaging
Recognition failures when " abcd ", therefore user repeated interaction " owner your no matter what one says " is asked, user clearly expresses the second voice messaging
" room is swept", because robot can clearly identify the second voice messaging, thus can establish " abcd " with
The identity relation of " having swept room ", and the identity relation is stored into information matches database.
Exemplary, stored by the identity relation to information matches database, in addition to：In the reception use
Family with the first voice messaging identical voice messaging when, obtain the response message of second voice messaging as target
Response message.
Specifically, after robot server receives the second voice messaging of user, due to can recognize that user's
Second voice messaging, therefore in information matches database, the response message of the second voice messaging is replied.In this implementation
In example, after the identity relation containing the first voice messaging and the second voice messaging in information matches database, robot server
Receive again with after the first voice messaging identical voice messaging, can be directly using the response message of the second voice messaging as mesh
Mark response message.
Such as the dialogue of above-mentioned owner and robot, can be with after voice messaging " abcd " that robot receives again
Directly the response message " sweep and be over " of the second voice messaging " having swept room " is replied.
Exemplary, before the identity relation for establishing first voice messaging with second voice messaging,
After second voice messaging for receiving the user, in addition to：
Preset times threshold value is set；Accordingly, the request reply message for receiving the user is the second voice messaging
When, establishing the identity relation of first voice messaging and second voice messaging includes：In the first of the reception user
When voice messaging number reaches the preset times threshold value, establish first voice messaging and second voice messaging etc.
Same relation；Or when the second voice messaging number for receiving the user reaches the preset times threshold value, establish described the
The identity relation of one voice messaging and second voice messaging.
Wherein, preset times threshold value can be the quiescent value of robot acquiescence, or user sets according to demand
Dynamic value.By set preset times threshold value can robot just establish the first voice after multiple identical situation
Information and the identity relation of the second voice messaging, many rarely needed voice messagings of storage are avoided, or contingency can not
The voice messaging of identification, save the memory space of server info matching database.
After preset times threshold value is set, robot server can be according to the first voice messaging number for receiving user
When reaching the preset times threshold value, the identity relation of the first voice messaging and the second voice messaging is established.For example, above-mentioned owner
With in the dialogue of robot, setting preset times threshold value as 3, when robot asks user mutual repeatedly, robot server
When at least have received that voice messaging is " abcd " three times, the information that receives next time can identify that user is actual and want to express
After meaning " having swept room ", the first voice messaging " abcd " and the second voice messaging " room has been swept into
" carry out the association of identity relation.
Or robot server can reach the preset times according to the second voice messaging number for receiving user
During threshold value, the identity relation of the first voice messaging and the second voice messaging is established.For example, the dialogue of above-mentioned owner and robot
In, preset times threshold value is set as 3, and when robot asks user mutual repeatedly, owner " has swept room in triplicate
", the conscious identity relation for wanting to allow robot to remember " abcd " and " having swept room ", therefore, the machine talent will
First voice messaging " abcd " carries out associating for identity relation with the second voice messaging " having swept room ".
The embodiments of the invention provide a kind of exchange method of robot, when the corresponding target of the first voice messaging of matching
When response message fails, user's repeated interaction is asked；The request reply message of user is received when being the second voice messaging, establishes the
The identity relation of one voice messaging and second voice messaging；Identity relation is stored to information matches database, solved
, can especially for netspeak, non-standard mandarin in the prior art the problem of robot identification user speech information difficulty
Rapid matching goes out response message, improves the communication efficiency between user.
Embodiment two
Fig. 2 is a kind of flow chart for robot interactive method that the embodiment of the present invention two provides, and the present embodiment is in above-mentioned reality
Apply and optimize on the basis of example, there is provided being equal for first voice messaging and second voice messaging is established in optimization
The processing method of relation, it is specifically：Reach in the matching times for receiving first voice messaging and second voice messaging
During preset matching frequency threshold value, the identity relation of first voice messaging and second voice messaging is established.
Accordingly, the method for the present embodiment includes：
S210, the first voice messaging for receiving user.
S220, when first voice messaging corresponding target response information failure is matched, ask user's weight
Reestablish diplomatic relations mutually.
S230, the request reply message of the reception user are the second voice messaging, in reception first voice messaging
When reaching preset matching frequency threshold value with the matching times of second voice messaging, establish first voice messaging with it is described
The identity relation of second voice messaging.
Wherein, preset matching frequency threshold value is similar with preset times threshold value, can be set as the fixed value of robot, also may be used
With the dynamic value set according to user's request.Preset matching frequency threshold value is unlike preset times threshold value, preset matching
Frequency threshold value is the first voice messaging recognition failures received when server, and after asking user's repeated interaction, what is received please
When to seek reply message be the second voice messaging, such a complete procedure is just properly termed as the first voice messaging and the second voice is believed
The match is successful for breath, is designated as matching times as 1.
Specifically, because robot and user can repeat identical dialogue in different time, therefore, can user with
The number that robot repeats equally to talk with establishes the first voice messaging and the second voice messaging when reaching certain threshold value.So, exist
Robot server should receive the first voice messaging and the matching times of the second voice messaging reach preset matching number
During threshold value, the identity relation of the first voice messaging and the second voice messaging is just established.Such as the dialogue of above-mentioned owner and robot
In, it can just establish the identity relation of the first voice messaging and the second voice messaging in different time in triplicate.
S240, the identity relation stored to information matches database.
Exemplary, the identity relation for establishing first voice messaging and second voice messaging, in addition to：
In the first voice messaging that n-th receives, the 3rd voice messaging be present is the request reply message, the 3rd voice messaging
During with the second voice messaging difference, it is determined that correct first request reply message；Establish first voice messaging and institute
State the identity relation of the first request reply message；Wherein, N is the positive integer less than preset matching frequency threshold value.
Wherein, the 3rd voice messaging and the first voice messaging, the second voice messaging are different.In the first voice messaging and
Before the identity relation of two voice messagings is not set up, occur when the result of robot request user's repeated interaction is believed with the second voice
Cease different, then the correct first request reply message of user will be inquired, and reply message and the first language are asked by first
Message breath establishes identity relation.For example, the dialogue of above-mentioned owner and robot occurs in other times, and as robot request master
During people's repeated interaction, the 3rd voice messaging that server receives is " to have swept the floor", because the 3rd voice messaging " is swept the floor
" with the second voice messaging " swept room" different, therefore, robot can inquire that correct voice messaging is used as the
One request reply message, and establish the identity relation of the first voice messaging " abcd " and the first request reply message.
It is to ensure the first voice messaging it should be noted that N to be set smaller than to the positive integer of preset matching frequency threshold value
Do not established with the second voice messaging before identity relation.
It is exemplary, after the second voice messaging of the user is received, it is described establish first voice messaging with
The identity relation of second voice messaging also includes：Circulation receives the request reply message of the user；If the request is answered
Complex information is the 4th voice messaging, when the 4th voice messaging is with the second voice messaging difference, it is determined that correct second
Ask reply message；Establish the identity relation of first voice messaging and the described second request reply message.
Specifically, after robot server asks user's repeated interaction, it is more likely that the request that user provides replies letter
There is mistake in breath, when user has found, while when correcting in time, the fourth voice letter different from the second voice messaging occur in time
Breath, at this moment robot can determine correct voice messaging as the second request reply message to user, and establish the first voice
Information and the identity relation of the second request reply message.For example, in the dialogue of above-mentioned owner and robot, when robot asks to lead
During people's repeated interaction, what owner first answered " has swept room" it is the second voice messaging, but owner recognizes more at once
Accurate saying is " room, which is swept, to be over" and say, therefore " room, which is swept, to be over " is the 4th voice messaging, robot
It is determined that after correct second request reply message, the correct second request reply message can be equal with the first voice messaging
The association of relation.
The present embodiment passes through to establishing the first voice messaging and the refinement of the identity relation of second voice messaging；Can
The probability that the identity relation establishes mistake is reduced, the situation for repeating to link up between user is reduced, improves between user
Communication efficiency, while also improve the accuracy of robot response message.
Embodiment three
Fig. 3 is a kind of structural representation for robot interactive system that the embodiment of the present invention three provides, and the present embodiment can fit
Situation for the interaction of various robots.As shown in figure 3, specifically include：First voice messaging receiving module 31, request interaction
Module 32, identity relation establish module 33 and identity relation memory module 34.
First voice messaging receiving module 31, to receive the first voice messaging of user；
Interactive module 32 is asked, to when first voice messaging corresponding target response information failure is matched,
Ask user's repeated interaction；
Identity relation establishes module 33, when to receive the request reply message of the user being the second voice messaging, builds
Found the identity relation of first voice messaging and second voice messaging；
Identity relation memory module 34, the identity relation is stored to information matches database.
On the basis of above-described embodiment, in addition to：Target response data obtaining module 35.
Target response data obtaining module 35, to be stored by the identity relation to information matches database,
When the reception user is with the first voice messaging identical voice messaging, the response of second voice messaging is obtained
Information is as target response information.
On the basis of above-described embodiment, in addition to：Preset times threshold module 36.
Preset times threshold module 36, to establish first voice messaging and second voice messaging described
Before identity relation, after second voice messaging for receiving the user, preset times threshold value is set；
Accordingly, the identity relation establish module 33 specifically to：In the first voice messaging for receiving the user
When number reaches the preset times threshold value, the identity relation of first voice messaging and second voice messaging is established；Or
Person, when the second voice messaging number for receiving the user reaches the preset times threshold value, establish the first voice letter
The identity relation of breath and second voice messaging.
On the basis of above-described embodiment, the identity relation establish module 33 specifically to：In reception first voice
When the matching times of information and second voice messaging reach preset matching frequency threshold value, establish first voice messaging with
The identity relation of second voice messaging.
On the basis of above-described embodiment, the identity relation establish module 33 specifically to：In the first language that n-th receives
Message ceases, and the 3rd voice messaging be present is the request reply message, the 3rd voice messaging and second voice messaging
When different, it is determined that correct first request reply message；Establish first voice messaging and the described first request reply message
Identity relation；Wherein, N is the positive integer less than preset matching frequency threshold value.
On the basis of above-described embodiment, the identity relation establish module 33 specifically to：Receiving the of the user
After two voice messagings, circulation receives the request reply message of the user；If the request reply message is believed for the 4th voice
Breath, when the 4th voice messaging is with the second voice messaging difference, it is determined that correct second request reply message；Establish institute
State the identity relation of the first voice messaging and the described second request reply message.
, should when matching the corresponding target of the first voice messaging the embodiments of the invention provide a kind of robot interactive system
When answering information failure, user's repeated interaction is asked；When the request reply message for receiving user is the second voice messaging, first is established
The identity relation of voice messaging and second voice messaging；Identity relation is stored to information matches database, solved existing
There is in technology the problem of robot identifies user speech information difficulty, can be fast especially for netspeak, non-standard mandarin
Speed matches response message, improves the communication efficiency between user.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (12)
- A kind of 1. robot interactive method, it is characterised in that including：Receive the first voice messaging of user；When the corresponding target response information failure of matching first voice messaging, user's repeated interaction is asked；When the request reply message for receiving the user is the second voice messaging, first voice messaging and described second is established The identity relation of voice messaging；The identity relation is stored to information matches database.
- 2. according to the method for claim 1, it is characterised in that stored by the identity relation to information matches database Afterwards, in addition to：When the reception user is with the first voice messaging identical voice messaging, second voice messaging is obtained Response message is as target response information.
- 3. according to the method for claim 1, it is characterised in that establish first voice messaging and described second described Before the identity relation of voice messaging, after second voice messaging for receiving the user, in addition to：Preset times threshold value is set；Accordingly, when the request reply message for receiving the user is the second voice messaging, the first voice letter is established Cease includes with the identity relation of second voice messaging：When the first voice messaging number for receiving the user reaches the preset times threshold value, the first voice letter is established The identity relation of breath and second voice messaging；Or reach described in the second voice messaging number for receiving the user During preset times threshold value, the identity relation of first voice messaging and second voice messaging is established.
- 4. according to the method for claim 1, it is characterised in that described to establish first voice messaging and second language The identity relation of message breath, including：When the matching times for receiving first voice messaging and second voice messaging reach preset matching frequency threshold value, Establish the identity relation of first voice messaging and second voice messaging.
- 5. according to the method for claim 4, it is characterised in that described to establish first voice messaging and second language The identity relation of message breath, in addition to：In the first voice messaging that n-th receives, the 3rd voice messaging be present is the request reply message, the 3rd voice When information is with the second voice messaging difference, it is determined that correct first request reply message；Establish the identity relation of first voice messaging and the described first request reply message；Wherein, N is the positive integer less than preset matching frequency threshold value.
- 6. according to the method for claim 1, it is characterised in that after the second voice messaging of the user is received, institute State and establish the identity relation of first voice messaging and second voice messaging and also include：Circulation receives the request reply message of the user；If the request reply message is the 4th voice messaging, the 4th voice messaging is different from second voice messaging When, it is determined that correct second request reply message；Establish the identity relation of first voice messaging and the described second request reply message.
- A kind of 7. robot interactive system, it is characterised in that including：First voice messaging receiving module, to receive the first voice messaging of user；Interactive module is asked, when the corresponding target response information failure of matching first voice messaging, to ask institute State user's repeated interaction；Identity relation establishes module, when to receive the request reply message of the user being the second voice messaging, described in foundation The identity relation of first voice messaging and second voice messaging；Identity relation memory module, the identity relation is stored to information matches database.
- 8. system according to claim 7, it is characterised in that also include：Target response data obtaining module, to be stored by the identity relation to information matches database, in reception The user with the first voice messaging identical voice messaging when, the response message for obtaining second voice messaging is made For target response information.
- 9. system according to claim 7, it is characterised in that also include：Preset times threshold module, to it is described establish first voice messaging and second voice messaging be equal to pass Before system, after second voice messaging for receiving the user, preset times threshold value is set；Accordingly, the identity relation establish module specifically to：When the first voice messaging number for receiving the user reaches the preset times threshold value, the first voice letter is established The identity relation of breath and second voice messaging；Or reach described in the second voice messaging number for receiving the user During preset times threshold value, the identity relation of first voice messaging and second voice messaging is established.
- 10. system according to claim 7, it is characterised in that the identity relation establish module specifically to：When the matching times for receiving first voice messaging and second voice messaging reach preset matching frequency threshold value, Establish the identity relation of first voice messaging and second voice messaging.
- 11. system according to claim 10, it is characterised in that the identity relation establish module specifically to：In the first voice messaging that n-th receives, the 3rd voice messaging be present is the request reply message, the 3rd voice When information is with the second voice messaging difference, it is determined that correct first request reply message；Establish first voice messaging With the identity relation of the described first request reply message；Wherein, N is the positive integer less than preset matching frequency threshold value.
- 12. system according to claim 7, it is characterised in that the identity relation establish module specifically to：After the second voice messaging of the user is received, circulation receives the request reply message of the user；If described please It is the 4th voice messaging to seek reply message, when the 4th voice messaging is with the second voice messaging difference, it is determined that correctly Second request reply message；Establish the identity relation of first voice messaging and the described second request reply message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710616293.XA CN107452373A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710616293.XA CN107452373A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107452373A true CN107452373A (en) | 2017-12-08 |
Family
ID=60488176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710616293.XA Pending CN107452373A (en) | 2017-07-26 | 2017-07-26 | Robot interactive method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107452373A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110910890A (en) * | 2019-12-11 | 2020-03-24 | 微创(上海)网络技术股份有限公司 | Natural language identification processing method and system |
| CN112154640A (en) * | 2018-07-04 | 2020-12-29 | 华为技术有限公司 | Message playing method and terminal |
| CN117301074A (en) * | 2023-11-17 | 2023-12-29 | 浙江孚宝智能科技有限公司 | Control method and chip of intelligent robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5897616A (en) * | 1997-06-11 | 1999-04-27 | International Business Machines Corporation | Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases |
| US20010010714A1 (en) * | 2000-01-26 | 2001-08-02 | International Business Machines Corporation | Automatic voice response system using voice recognition means and method of the same |
| JP2001236091A (en) * | 2000-02-23 | 2001-08-31 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for error correcting voice recognition result |
| CN106057200A (en) * | 2016-06-23 | 2016-10-26 | 广州亿程交通信息有限公司 | Semantic-based interaction system and interaction method |
-
2017
- 2017-07-26 CN CN201710616293.XA patent/CN107452373A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5897616A (en) * | 1997-06-11 | 1999-04-27 | International Business Machines Corporation | Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases |
| US20010010714A1 (en) * | 2000-01-26 | 2001-08-02 | International Business Machines Corporation | Automatic voice response system using voice recognition means and method of the same |
| JP2001236091A (en) * | 2000-02-23 | 2001-08-31 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for error correcting voice recognition result |
| CN106057200A (en) * | 2016-06-23 | 2016-10-26 | 广州亿程交通信息有限公司 | Semantic-based interaction system and interaction method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112154640A (en) * | 2018-07-04 | 2020-12-29 | 华为技术有限公司 | Message playing method and terminal |
| US11837217B2 (en) | 2018-07-04 | 2023-12-05 | Huawei Technologies Co., Ltd. | Message playing method and terminal |
| CN112154640B (en) * | 2018-07-04 | 2024-04-30 | 华为技术有限公司 | Message playing method and terminal |
| CN110910890A (en) * | 2019-12-11 | 2020-03-24 | 微创(上海)网络技术股份有限公司 | Natural language identification processing method and system |
| CN117301074A (en) * | 2023-11-17 | 2023-12-29 | 浙江孚宝智能科技有限公司 | Control method and chip of intelligent robot |
| CN117301074B (en) * | 2023-11-17 | 2024-04-30 | 浙江孚宝智能科技有限公司 | Control method and chip of intelligent robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319599B (en) | Man-machine conversation method and device | |
| CN109361703B (en) | Voice equipment binding method, device, equipment and computer readable medium | |
| CN107452373A (en) | Robot interactive method and system | |
| KR102030803B1 (en) | An appratus and a method for processing conversation of chatter robot | |
| CN104916283A (en) | Voice recognition method and device | |
| CN109376354A (en) | Fraud recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN113840040B (en) | Man-machine cooperation outbound method, device, equipment and storage medium | |
| CN110795939A (en) | Text processing method and device | |
| CN111858874B (en) | Dialogue service processing method, device, equipment and computer readable storage medium | |
| CN105227557A (en) | A kind of account number processing method and device | |
| US20220294856A1 (en) | Arrangements for detecting bi-directional artificial intelligence (ai) voice communications and negotiating direct digital communications | |
| JP2016057508A (en) | Voice interactive device, control method and control program for the voice interactive device | |
| CN116432665B (en) | Dialogue model construction method, text generation method, device, system and equipment | |
| CN111031063B (en) | Data transmission method and device based on family education machine | |
| CN105099727A (en) | Method of adding group member and apparatus thereof | |
| WO2023226767A1 (en) | Model training method and apparatus, and speech meaning understanding method and apparatus | |
| Byalpi | Alexa based Real-Time Attendance System | |
| CN109462539A (en) | Multi-person speech chat system and method | |
| CN115098661A (en) | Method, electronic device and computer storage medium for assisting disease screening | |
| CN112201248A (en) | Streaming voice recognition method and system based on long connection | |
| CN112966077B (en) | Method, device and equipment for determining conversation state and storage medium | |
| CN114179083B (en) | Leading robot voice information generation method and device and leading robot | |
| CN113139392A (en) | Method and device for generating conference summary and storage medium | |
| CN115879583B (en) | Method and device for processing work order data and computer readable storage medium | |
| CN114221920A (en) | Automatic contact method, device, computer equipment and medium based on artificial intelligence |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171208 |