CN107170446A - Semantic processes server and the method for semantic processes - Google Patents
Semantic processes server and the method for semantic processes Download PDFInfo
- Publication number
- CN107170446A CN107170446A CN201710361264.3A CN201710361264A CN107170446A CN 107170446 A CN107170446 A CN 107170446A CN 201710361264 A CN201710361264 A CN 201710361264A CN 107170446 A CN107170446 A CN 107170446A
- Authority
- CN
- China
- Prior art keywords
- information
- semantic
- intended
- voice recognition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000008569 process Effects 0.000 title claims abstract description 31
- 230000010365 information processing Effects 0.000 claims abstract description 6
- 238000003058 natural language processing Methods 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 24
- 238000003672 processing method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of method the invention discloses semantic processes server and for semantic processes, belongs to technical field of information processing.This method includes：Obtain voice recognition information；Analyze the semantic information in voice recognition information；Being generated according to semantic information includes the understanding information of semantic intention；It will be understood that information is sent to corresponding functional module according to the classification that semanteme is intended to.According to above-mentioned technical proposal, obtain voice recognition information, by analyzing the semantic information in voice recognition information, generation includes the understanding information of semantic intention, and the classification being intended to according to semanteme will be understood that information is sent to corresponding functional module and handled, the understanding processing of robot voice identification information can be realized, it is not necessary to a large amount of voice messagings are stored in the database of robot, the processing speed of robot is improved.
Description
Technical field
The present invention relates to technical field of information processing, more particularly to a kind of semantic processes server and for semantic processes
Method.
Background technology
With the fast development of computer technology, human society has stepped into the increasingly automated and information-based epoch.Can
The progress of human society is greatly accelerated with the development for saying computer technology.And the progress of human society is in turn to computer
The development of technology proposes higher requirement and challenge.The direction that robot is increasingly combined to intellectuality with hommization is developed,
So that people's an urgent demand Voice command robot.
Semantic processes play significant role in the contacts in terms of the man-machine interaction between the mankind.But due to generally a variety of
A large amount of voice messagings, shadow are stored in the same function of voice request information correspondence robot, robot data storehouse of the prior art
Ring the processing speed of robot.
The content of the invention
A kind of method the embodiments of the invention provide semantic processes server and for semantic processes, it is intended to solve existing
A large amount of voice messagings are stored in robot data storehouse in technology, the problem of influenceing the processing speed of robot.
There is a basic understanding for some aspects of the embodiment to disclosure, shown below is simple summary.Should
Summarized section is not extensive overview, nor to determine key/critical component or describe the protection domain of these embodiments.
Its sole purpose is that some concepts are presented with simple form, in this, as the preamble of following detailed description.
In a first aspect, the embodiments of the invention provide a kind of method for semantic processes, including：
Obtain voice recognition information；
Analyze the semantic information in voice recognition information；
Being generated according to semantic information includes the understanding information of semantic intention；
It will be understood that information is sent to corresponding functional module according to the classification that semanteme is intended to.
Second aspect, the embodiments of the invention provide a kind of method for semantic processes, including：
Obtain voice recognition information；
Voice recognition information is sent to natural language understanding (English full name：Natural Language
Understanding, english abbreviation：NLU) equipment；
Receive the understanding information of semantic information generation of the NLU equipment in voice recognition information；Wherein, packet is understood
Include semantic intention；
It will be understood that information is sent to corresponding functional module according to the classification that semanteme is intended to.
Optionally, the either method of the embodiment of the present invention, obtains voice recognition information, including：
Receive the voice recognition information that machine human hair is sent；Or,
Receive the voice messaging that send of machine human hair and voice messaging is identified acquisition voice recognition information.
Optionally, the either method of the embodiment of the present invention, understands that information includes dialogue and is intended to category information, or function is intended to class
Information, or business skill are intended to category information.
Optionally, the either method of the embodiment of the present invention, functional module includes natural language processing (English full name：
Natural Language Processing, english abbreviation：NLP) equipment, or robot each business skill module, or machine
The session module of people.
Optionally, the either method of the embodiment of the present invention,
When understanding that information includes dialogue intention category information, transmission understands session module of the information to robot；
When understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment；
When understanding that information includes business skill intention category information, transmission understands corresponding service technical ability of the information to robot
Module.
The third aspect, the embodiments of the invention provide a kind of server of semantic processes, including：
Processor, for obtaining the semantic information in voice recognition information, analysis voice recognition information, according to semantic information
Generation includes the understanding information of semantic intention；
First transmitting element, the classification for being intended to according to semanteme will be understood that information is sent to corresponding functional module.
Fourth aspect, the embodiments of the invention provide a kind of server of semantic processes, including：
Processor, for obtaining voice recognition information；
Second transmitting element, the voice recognition information for processor to be obtained is sent to NLU equipment；
Second receiving unit, for receiving the voice recognition information that NLU equipment is sent according to the second transmitting element of analysis
Semantic information generation includes the understanding information of semantic intention；
First transmitting element, the classification for being intended to according to semanteme will be understood that information is sent to corresponding functional module.
Optionally, any server of the embodiment of the present invention, in addition to the first receiving unit；
First receiving unit is used to receive the voice recognition information that machine human hair is sent, and processor is used to obtain the first reception list
The voice recognition information that member is received；Or,
First receiving unit is used to receive the voice messaging that machine human hair is sent；Processor is additionally operable to be carried out according to voice messaging
Identification obtains voice recognition information.
Optionally, any server of the embodiment of the present invention, understands that information includes dialogue and is intended to category information, or function is intended to
Category information, or business skill are intended to category information.
Optionally, any server of the embodiment of the present invention, functional module include NLP equipment, or robot each business
Technical ability module, or robot session module.
Optionally, any server of the embodiment of the present invention, the first transmitting element is used for：
When understanding that information includes dialogue intention category information, transmission understands session module of the information to robot；
When understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment；
When understanding that information includes business skill intention category information, transmission understands corresponding service technical ability of the information to robot
Module.
According to above-mentioned technical proposal, voice recognition information is obtained, it is raw by analyzing the semantic information in voice recognition information
Into the understanding information being intended to including semanteme, and the classification being intended to according to semanteme will be understood that information is sent to corresponding functional module and entered
Row processing, it is possible to achieve the understanding processing of robot voice identification information, it is not necessary to store a large amount of in the database of robot
Voice messaging, improves the processing speed of robot.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
Can the limitation present invention.
Brief description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the implementation for meeting the present invention
Example, and for explaining principle of the invention together with specification.
Fig. 1 is a kind of flow chart of method for semantic processes according to an exemplary embodiment；
Fig. 2 is a kind of flow chart of method for semantic processes according to an exemplary embodiment；
Fig. 3 is a kind of flow chart of method for semantic processes according to an exemplary embodiment；
Fig. 4 is a kind of flow chart of method for semantic processes according to an exemplary embodiment
Fig. 5 is a kind of structured flowchart of the server of semantic processes according to an exemplary embodiment；
Fig. 6 is a kind of structured flowchart of the server of semantic processes according to an exemplary embodiment.
Description of reference numerals：110th, processor；120th, the first receiving unit；130th, the first transmitting element；140th, NLU is set
It is standby；150th, NLP equipment；160th, the second receiving unit；170th, the second transmitting element.
Embodiment
The following description and drawings fully show specific embodiments of the present invention, to enable those skilled in the art to
Put into practice them.Embodiment only represents possible change.Unless explicitly requested, otherwise single components and functionality is optional, and
And the order of operation can change.The part of some embodiments and feature can be included in or replace other embodiments
Part and feature.The scope of embodiment of the present invention includes the gamut of claims, and claims institute
There is obtainable equivalent.Herein, each embodiment can individually or generally be represented that this is only with term " invention "
It is merely for convenience, and if in fact disclosing the invention more than one, it is not meant to automatically limit the scope of the application
For any single invention or inventive concept.Herein, such as first and second or the like relational terms are used only for one
Entity or operation make a distinction with another entity or operation, exist without requiring or implying between these entities or operation
Any actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant be intended to it is non-exclusive
Property include so that process, method or equipment including a series of key elements not only include those key elements, but also including
Other key elements being not expressly set out.Each embodiment herein is described by the way of progressive, and each embodiment is stressed
Be all between difference with other embodiment, each embodiment identical similar portion mutually referring to.For implementing
For example disclosed structure, product etc., because it is corresponding with part disclosed in embodiment, so fairly simple, the phase of description
Part is closed referring to method part illustration.
The server of semantic processes provided in an embodiment of the present invention and the method for semantic processes, can be carried for robot
For semantic processes service, robot only needs to solicited message being sent to server, and server can be to provide clothes for robot
Business.
In some embodiments of the present invention, the voice messaging that solicited message can send for robot, or request letter
Cease for the voice recognition information after being recognized through robot voice.
In some embodiments of the present invention, solicited message can include：Robot ID, understands that information can also include：
Robot ID.
In some embodiments of the present invention, machine information people can include：The business skill that robot ID, robot have
Energy module, and the corresponding business skill type of business skill module that robot has.For example, the service technique technical ability of robot
Type includes：Take pictures, call and dance.The service technique module of robot includes：Photo module, call module and
Dancing module.
In some embodiments of the present invention, dialogue, which is intended to category information, to be included：The attribute of robot, robot general knowledge
Question and answer and robot are chatted.
When robot will contain：The dialogue that the attribute or robot general knowledge question and answer or robot of robot are chatted is intended to
When the solicited message of class is sent to server, server obtains the semantic letter in voice recognition information, analysis voice recognition information
Breath, being generated according to semantic information includes the understanding information of semantic intention, and this is included into the understanding information that dialogue is intended to category information
It is sent to the session module of robot.The session module of robot will be understood that information is played by player, or pass through display
Device, which is shown, understands information.
When robot will contain：The dialogue that the attribute or robot general knowledge question and answer or robot of robot are chatted is intended to
When the solicited message of class is sent to server, server obtains voice recognition information, and server can also be by voice recognition information
The semantic information in NLU equipment 140, the analysis voice recognition information of NLU equipment 140 is sent to, is included according to semantic information generation
The understanding information that semanteme is intended to, when understanding that information includes dialogue intention category information, NLU equipment 140 is it will be understood that information is sent to
Server, robot is sent to by server.So that server is managed collectively.
Wherein, the list of multiple NLU equipment 140 can be stored in the server, so as to which voice recognition information is sent out
Multiple NLU equipment 140 are given, and understand that information determines optimal understanding information according to multiple NLU equipment 140.
In some embodiments, function, which is intended to category information, to include：Third party's function, for example, weather forecast, music
The information that NLP equipment 150 is provided is needed with news etc..
When robot will contain：When the solicited message that the function of third party's function is intended to category information is sent to server, clothes
Business device obtains the semantic information in voice recognition information, analysis voice recognition information, includes function meaning according to semantic information generation
The understanding information is sent to NLP equipment 150 by the understanding information of figure category information, server.Wherein, understand that information can include：
Robot ID, NLP equipment 150 is according to information generation processing information is understood, NLP equipment 150 be able to will be handled by robot ID
Information is transmitted directly to robot, and server can also be notified to have completed to understand the processing of information simultaneously；Or NLP equipment
Processing information can also be sent to server by 150, and robot is sent to by server.
When robot will contain：When the solicited message that the function of third party's function is intended to category information is sent to server, clothes
Business device obtains voice recognition information, and voice recognition information can be sent to NLU equipment 140, the basis of NLU equipment 140 by server
The understanding information for being intended to category information including function of semantic information generation in voice recognition information, it will be understood that information is sent to clothes
The understanding information is sent to NLP equipment 150 by business device, server.NLP equipment 150 according to understand information generate processing information, its
In understand that information can include robot ID, processing information can be transmitted directly to machine by NLP equipment 150 by robot ID
Device, and server can also be notified to have completed to understand the processing of information simultaneously；Or NLP equipment 150 can be by processing information
Server is sent to, robot is sent to by server.
The list of multiple NLP equipment 150 can be wherein stored in processor 110, so that server can will be understood that letter
Breath is sent to multiple NLP equipment 150, and determines optimal processing information according to the processing information of multiple NLP equipment 150.Wherein
Mainly processing contains the functional understanding information for being intended to category information to NLP equipment 150.Because storing multiple NLP equipment 150 in server
List, to be sent to suitable NLP equipment 150 by server, there is provided more professional service.
In some embodiments, business skill, which is intended to category information, to include：Take pictures, call and dance.
When robot will contain：The solicited message that the business skill taken pictures, call and danced is intended to is sent to service
During device, server obtains the semantic information in voice recognition information, analysis voice recognition information, is included according to semantic information generation
The understanding information that semanteme is intended to, and this is understood that information is sent to the corresponding industry of robot including business skill intention category information
Business technical ability module.Each business skill module of robot is according to understanding that information performs corresponding order.
When robot will contain：The solicited message that the business skill taken pictures, call and danced is intended to is sent to service
During device, server obtains voice recognition information, and voice recognition information can also be sent to NLU equipment 140 by server, and NLU is set
Semantic information in standby 140 analysis voice recognition information, being generated according to semantic information includes the understanding information of semantic intention, NLU
The understanding information for being intended to category information including business skill is sent to server by equipment 140, and robot is sent to by server
Corresponding service technical ability module.
Wherein, be stored with the machine information of robot in the server, and machine information can include the industry that robot have
It is engaged in skillset, so that server understands that information is sent to the corresponding service of robot by be intended to category information including business skill
Technical ability module.
Wherein, including business skill is intended to category information and understands that information can include the instruction of control machine human action.
As shown in figure 1, the embodiments of the invention provide a kind of information processing method, including：
S101, acquisition voice recognition information；
Semantic information in S102, analysis voice recognition information；
S103, generated according to semantic information and include the semantic understanding information being intended to；
S104, the classification being intended to according to semanteme will be understood that information is sent to corresponding functional module.
According to above-mentioned technical proposal, voice recognition information is obtained, it is raw by analyzing the semantic information in voice recognition information
Into the understanding information being intended to including semanteme, and the classification being intended to according to semanteme will be understood that information is sent to corresponding functional module and entered
Row processing, it is possible to achieve the understanding processing of robot voice identification information, it is not necessary to store a large amount of in the database of robot
Voice messaging, improves the processing speed of robot.
As shown in Fig. 2 the embodiment of the present invention additionally provides a kind of information processing method, including：
S201, acquisition voice recognition information；
S202, voice recognition information is sent to NLU equipment；
S203, the understanding information for receiving semantic information generation of the NLU equipment in voice recognition information；Wherein, understand
Information includes semantic be intended to；
S204, the classification being intended to according to semanteme will be understood that information is sent to corresponding functional module.
The list of multiple NLU equipment can be stored in the server, it is multiple so as to which voice recognition information is sent to
NLU equipment 140, and understand that information determines optimal understanding information according to multiple NLU equipment 140.
According to above-mentioned technical proposal, voice recognition information is obtained, is analyzed by NLU equipment 140 in voice recognition information
Semantic information, generation includes the understanding information of semantic intention, and the classification being intended to according to semanteme will be understood that information is sent to correspondence
Functional module handled, it is possible to achieve the understanding of robot voice identification information processing, it is not necessary in the data of robot
A large amount of voice messagings are stored in storehouse, the processing speed of robot is improved.Voice recognition information is carried out by NLU equipment 140
Understand to obtain more professional semantic understanding information.
The processing method of the embodiment of the present invention, step S101 or step S201 can include：
Receive the voice recognition information that machine human hair is sent；Or,
Receive the voice messaging that send of machine human hair and voice messaging is identified acquisition voice recognition information.
Sound identification module can be set in robot, and the sound identification module of robot carries out voice to voice messaging
Identifying processing, generates voice recognition information.Sound identification module can also be set in the server, and robot can be directly by language
Message breath is sent to server, voice messaging is identified processing by the sound identification module in server, and generation voice is known
Other information.
The processing method of the embodiment of the present invention, understands that information includes dialogue and is intended to category information, or function is intended to category information, or
Business skill is intended to category information.
The processing method of the embodiment of the present invention, functional module include NLP equipment, or robot each business skill module,
Or the session module of robot.
As shown in Figure 3 and Figure 4, the processing method of the embodiment of the present invention, step 104 and step 204 can include：
When understanding that information includes dialogue intention category information, transmission understands session module of the information to robot；
When understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment；
When understanding that information includes business skill intention category information, transmission understands corresponding service technical ability of the information to robot
Module.
Server is different according to the semantic intention for understanding information, using different processing modes, makes the server division of labor more
Finely, to improve the processing speed of server.
Wherein, when understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment, wherein understanding
Information includes robot IP, and NLP equipment 150 will be sent to machine by robot IP according to the processing information for understanding information generation
People.To reduce procedure links, it is not necessary to processing information is sent into server, then robot, and energy are sent to by server
The saving time, improve Consumer's Experience.
The processing method of the embodiment of the present invention, can also include before step S101 and 201：
S105, acquisition robot information；
S106, the functional module for determining according to robot information robot.
In the processing method of another embodiment, it can also include before step S101 and 201：Obtain robot letter
Breath, the business skill module that robot has, the business skill module class having according to robot are determined according to robot information
Type judges to understand the correctness of information.Because the business skill module of different robots may be different, pass through the industry of robot
Business technical ability module, which can be verified, understands whether information is correct, so that server provides more excellent service for robot.
As shown in figure 5, the embodiments of the invention provide a kind of server of semantic processes, including：
Processor 110, for obtaining the semantic information in voice recognition information, analysis voice recognition information, according to semanteme
Information generation includes the understanding information of semantic intention；
First transmitting element 130, the classification for being intended to according to semanteme will be understood that information is sent to corresponding functional module.
According to above-mentioned technical proposal, processor 110, for obtaining voice recognition information, by analyzing voice recognition information
In semantic information, generation includes the understanding information of semantic intention, the first transmitting element 130, for dividing for being intended to according to semanteme
Class will be understood that information is sent to corresponding functional module and handled, it is possible to achieve at the understanding of robot voice identification information
Reason, it is not necessary to a large amount of voice messagings are stored in the database of robot, the processing speed of robot is improved.
As shown in fig. 6, the embodiments of the invention provide a kind of server of semantic processes, including：
Processor 110, for obtaining voice recognition information；
Second transmitting element 170, the voice recognition information for processor 110 to be obtained is sent to NLU equipment 140；
Second receiving unit 160, knows for receiving the voice that NLU equipment 140 is sent according to the second transmitting element 170 of analysis
The semantic information generation of other information includes the understanding information of semantic intention；
First transmitting element 130, the classification for being intended to according to semanteme will be understood that information is sent to corresponding functional module.
The list of multiple NLU equipment 140 can be stored in the server, it is many so as to which voice recognition information is sent to
Individual NLU equipment 140, and understand that information determines optimal understanding information according to multiple NLU equipment 140.
According to above-mentioned technical proposal, processor 110, for obtaining voice recognition information, passes through the analytic language of NLU equipment 140
Semantic information in sound identification information, generation includes the understanding information of semantic intention, and the classification being intended to according to semanteme will be understood that
Information is sent to corresponding functional module and handled, it is possible to achieve the understanding processing of robot voice identification information, it is not necessary to
A large amount of voice messagings are stored in the database of robot, the processing speed of robot is improved.By NLU equipment 140 to language
Sound identification information is understood to obtain more professional semantic understanding information.
The server of the embodiment of the present invention, can also include the first receiving unit 120；
First receiving unit 120 is used to receive the voice recognition information that machine human hair is sent, and processor 110 is used to obtain first
The voice recognition information that receiving unit 120 is received；Or,
First receiving unit 120 is used to receive the voice messaging that machine human hair is sent；Processor 110 is additionally operable to be believed according to voice
Acquisition voice recognition information is identified in breath.
Sound identification module can be set in robot, and the sound identification module of robot carries out voice to voice messaging
Identifying processing, generates voice recognition information.Sound identification module can also be set in the server, and robot can be directly by language
Message breath is sent to server, voice messaging is identified processing by the sound identification module in server, and generation voice is known
Other information.
The server of the embodiment of the present invention, understands that information includes dialogue and is intended to category information, or function is intended to category information, or industry
Technical ability of being engaged in is intended to category information.
The server of the embodiment of the present invention, functional module include NLP equipment 150, or robot each business skill module,
Or the session module of robot.
The server of the embodiment of the present invention, the first transmitting element 130 is used for：
When understanding that information includes dialogue intention category information, transmission understands session module of the information to robot；
When understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment 150；
When understanding that information includes business skill intention category information, transmission understands corresponding service technical ability of the information to robot
Module.
Server is different according to the semantic intention for understanding information, using different processing modes, makes the server division of labor more
Finely, to improve the processing speed of server.
Wherein, when understanding that information includes function intention category information, it will be understood that information is sent to NLP equipment 150, wherein managing
Solving information includes robot IP, and NLP equipment 150 will be sent to machine by robot IP according to the processing information for understanding information generation
Device people.To reduce procedure links, it is not necessary to processing information is sent into server, then robot is sent to by server, and
The time can be saved, Consumer's Experience is improved.
The server of the embodiment of the present invention, processor 110 is additionally operable to：
Obtain robot information；
The functional module of robot is determined according to robot information.
The server of the embodiment of the present invention, processor 110 is additionally operable to：Robot information is obtained, it is true according to robot information
Determine the business skill module that robot has, the business skill module type having according to robot judges to understand the correct of information
Property.Because the business skill module of different robots may be different, reason can be verified by the business skill module of robot
Whether correct information is solved, so that server provides more excellent service for robot.
It should be appreciated that the invention is not limited in the flow and structure for being described above and being shown in the drawings,
And various modifications and changes can be being carried out without departing from the scope.The scope of the present invention is only limited by appended claim
System.
Claims (12)
1. a kind of method for semantic processes, it is characterised in that including：
Obtain voice recognition information；
Analyze the semantic information in the voice recognition information；
The understanding information of semantic intention is included according to institute's semantic information generation；
Understand that information is sent to corresponding functional module by described according to the semantic classification being intended to.
2. a kind of method for semantic processes, it is characterised in that including：
Obtain voice recognition information；
The voice recognition information is sent to natural language understanding NLU equipment；
Receive the understanding letter of semantic information generation of the natural language understanding NLU equipment in the voice recognition information
Breath；Wherein, it is described to understand that information includes semantic be intended to；
Understand that information is sent to corresponding functional module by described according to the semantic classification being intended to.
3. method according to claim 1 or 2, it is characterised in that the acquisition voice recognition information, including：
Receive the voice recognition information that machine human hair is sent；Or,
Receive the voice messaging that send of machine human hair and the voice messaging is identified the acquisition voice recognition information.
4. method according to claim 3, it is characterised in that described to understand that information includes dialogue and is intended to category information, or work(
Category information can be intended to, or business skill is intended to category information.
5. information processing method according to claim 4, it is characterised in that the functional module includes natural language processing
NLP equipment, or the robot each business skill module, or the robot session module.
6. method according to claim 5, it is characterised in that
When it is described understand that information includes dialogue and is intended to category information when, send the dialogue mould for understanding information to the robot
Block；
When it is described understand information include function be intended to category information when, understand that information is sent to natural language processing NLP and set by described
It is standby；
When it is described understand that information includes business skill and is intended to category information when, send and described understand information to the corresponding of the robot
Business skill module.
7. a kind of server of semantic processes, it is characterised in that including：
Processor, for obtaining voice recognition information, analyzes the semantic information in the voice recognition information, according to the semanteme
Information generation includes the understanding information of semantic intention；
First transmitting element, for understanding that information is sent to corresponding function mould by described according to the semantic classification being intended to
Block.
8. a kind of server of semantic processes, it is characterised in that including：
Processor, for obtaining voice recognition information；
Second transmitting element, the voice recognition information for the processor to be obtained is sent to natural language understanding NLU
Equipment；
Second receiving unit, sends for receiving the natural language understanding NLU equipment according to second transmitting element is analyzed
The semantic information generation of the voice recognition information include the semantic understanding information being intended to；
First transmitting element, for understanding that information is sent to corresponding function mould by described according to the semantic classification being intended to
Block.
9. the server according to claim 7 or 8, it is characterised in that also including the first receiving unit；
First receiving unit is used to receive the voice recognition information that machine human hair is sent, and the processor is used to obtain institute
State the voice recognition information of the first receiving unit reception；Or,
First receiving unit is used to receive the voice messaging that machine human hair is sent；The processor is additionally operable to according to the voice
The acquisition voice recognition information is identified in information.
10. server according to claim 9, it is characterised in that described to understand that information includes dialogue and is intended to category information, or
Function is intended to category information, or business skill is intended to category information.
11. server according to claim 10, it is characterised in that the functional module includes natural language processing NLP
Equipment, or the robot each business skill module, or the robot session module.
12. server according to claim 11, it is characterised in that first transmitting element is used for：
When it is described understand that information includes dialogue and is intended to category information when, send the dialogue mould for understanding information to the robot
Block；
When it is described understand information include function be intended to category information when, understand that information is sent to natural language processing NLP and set by described
It is standby；
When it is described understand that information includes business skill and is intended to category information when, send and described understand information to the corresponding of the robot
Business skill module.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710361264.3A CN107170446A (en) | 2017-05-19 | 2017-05-19 | Semantic processes server and the method for semantic processes |
| US15/712,072 US10529323B2 (en) | 2017-05-19 | 2017-09-21 | Semantic processing method of robot and semantic processing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710361264.3A CN107170446A (en) | 2017-05-19 | 2017-05-19 | Semantic processes server and the method for semantic processes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107170446A true CN107170446A (en) | 2017-09-15 |
Family
ID=59815294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710361264.3A Pending CN107170446A (en) | 2017-05-19 | 2017-05-19 | Semantic processes server and the method for semantic processes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107170446A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943834A (en) * | 2017-10-25 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Interactive implementation method, device, equipment and storage medium |
| CN108376544A (en) * | 2018-03-27 | 2018-08-07 | 京东方科技集团股份有限公司 | A kind of information processing method, device, equipment and computer readable storage medium |
| CN108984157A (en) * | 2018-07-27 | 2018-12-11 | 苏州思必驰信息科技有限公司 | Technical ability configuration and call method and system for voice dialogue platform |
| CN109346078A (en) * | 2018-11-09 | 2019-02-15 | 泰康保险集团股份有限公司 | Voice interactive method, device and electronic equipment, computer-readable medium |
| CN109961780A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | A kind of man-machine interaction method, device, server and storage medium |
| CN110263128A (en) * | 2019-06-24 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | The method, apparatus and computer readable storage medium of interaction question and answer |
| CN110348002A (en) * | 2018-04-05 | 2019-10-18 | 通用汽车环球科技运作有限责任公司 | The system and method for realizing voice request |
| CN110491383A (en) * | 2019-09-25 | 2019-11-22 | 北京声智科技有限公司 | A kind of voice interactive method, device, system, storage medium and processor |
| CN110728978A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Voice conversation method and system based on artificial intelligence |
| CN110728977A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Voice conversation method and system based on artificial intelligence |
| WO2020073248A1 (en) * | 2018-10-10 | 2020-04-16 | 华为技术有限公司 | Human-computer interaction method and electronic device |
| CN111951808A (en) * | 2019-04-30 | 2020-11-17 | 深圳市优必选科技有限公司 | Voice interaction method, device, terminal equipment and medium |
| WO2021120876A1 (en) * | 2019-12-18 | 2021-06-24 | 华为技术有限公司 | Corpus identification method, device, terminal apparatus, and medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080201133A1 (en) * | 2007-02-20 | 2008-08-21 | Intervoice Limited Partnership | System and method for semantic categorization |
| CN102968987A (en) * | 2012-11-19 | 2013-03-13 | 百度在线网络技术（北京）有限公司 | Speech recognition method and system |
| CN103151043A (en) * | 2013-01-31 | 2013-06-12 | 上海斐讯数据通信技术有限公司 | Wireless voice control system based on network equipment |
| CN104318924A (en) * | 2014-11-12 | 2015-01-28 | 沈阳美行科技有限公司 | Method for realizing voice recognition function |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN105425648A (en) * | 2016-01-11 | 2016-03-23 | 北京光年无限科技有限公司 | Portable robot and data processing method and system thereof |
| CN106184000A (en) * | 2016-07-05 | 2016-12-07 | 深圳市爱培科技术股份有限公司 | A kind of sound control method based on Car intellectual backsight mirror and system |
| CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
| CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
| CN106297801A (en) * | 2016-08-16 | 2017-01-04 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN106560892A (en) * | 2015-09-30 | 2017-04-12 | 深圳光启合众科技有限公司 | Intelligent robot and cloud side interactive method and cloud side interactive system thereof |
| CN106601232A (en) * | 2017-01-04 | 2017-04-26 | 江西沃可视发展有限公司 | Vehicle mounted terminal oriented man-machine interaction system based on speech recognition |
| CN106663424A (en) * | 2014-03-31 | 2017-05-10 | 三菱电机株式会社 | Device and method for understanding user intent |
-
2017
- 2017-05-19 CN CN201710361264.3A patent/CN107170446A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080201133A1 (en) * | 2007-02-20 | 2008-08-21 | Intervoice Limited Partnership | System and method for semantic categorization |
| CN102968987A (en) * | 2012-11-19 | 2013-03-13 | 百度在线网络技术（北京）有限公司 | Speech recognition method and system |
| CN103151043A (en) * | 2013-01-31 | 2013-06-12 | 上海斐讯数据通信技术有限公司 | Wireless voice control system based on network equipment |
| CN106663424A (en) * | 2014-03-31 | 2017-05-10 | 三菱电机株式会社 | Device and method for understanding user intent |
| CN104318924A (en) * | 2014-11-12 | 2015-01-28 | 沈阳美行科技有限公司 | Method for realizing voice recognition function |
| CN104965426A (en) * | 2015-06-24 | 2015-10-07 | 百度在线网络技术（北京）有限公司 | Intelligent robot control system, method and device based on artificial intelligence |
| CN106560892A (en) * | 2015-09-30 | 2017-04-12 | 深圳光启合众科技有限公司 | Intelligent robot and cloud side interactive method and cloud side interactive system thereof |
| CN105425648A (en) * | 2016-01-11 | 2016-03-23 | 北京光年无限科技有限公司 | Portable robot and data processing method and system thereof |
| CN106184000A (en) * | 2016-07-05 | 2016-12-07 | 深圳市爱培科技术股份有限公司 | A kind of sound control method based on Car intellectual backsight mirror and system |
| CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
| CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
| CN106297801A (en) * | 2016-08-16 | 2017-01-04 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN106601232A (en) * | 2017-01-04 | 2017-04-26 | 江西沃可视发展有限公司 | Vehicle mounted terminal oriented man-machine interaction system based on speech recognition |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943834A (en) * | 2017-10-25 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Interactive implementation method, device, equipment and storage medium |
| CN107943834B (en) * | 2017-10-25 | 2021-06-11 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for implementing man-machine conversation |
| CN109961780B (en) * | 2017-12-22 | 2024-02-02 | 深圳市优必选科技有限公司 | A man-machine interaction method a device(s) Server and storage medium |
| CN109961780A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | A kind of man-machine interaction method, device, server and storage medium |
| CN108376544A (en) * | 2018-03-27 | 2018-08-07 | 京东方科技集团股份有限公司 | A kind of information processing method, device, equipment and computer readable storage medium |
| CN110348002A (en) * | 2018-04-05 | 2019-10-18 | 通用汽车环球科技运作有限责任公司 | The system and method for realizing voice request |
| CN110728978A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Voice conversation method and system based on artificial intelligence |
| CN110728977A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Voice conversation method and system based on artificial intelligence |
| CN108984157A (en) * | 2018-07-27 | 2018-12-11 | 苏州思必驰信息科技有限公司 | Technical ability configuration and call method and system for voice dialogue platform |
| CN108984157B (en) * | 2018-07-27 | 2022-01-11 | 思必驰科技股份有限公司 | Skill configuration and calling method and system for voice conversation platform |
| WO2020073248A1 (en) * | 2018-10-10 | 2020-04-16 | 华为技术有限公司 | Human-computer interaction method and electronic device |
| US11636852B2 (en) | 2018-10-10 | 2023-04-25 | Huawei Technologies Co., Ltd. | Human-computer interaction method and electronic device |
| CN109346078B (en) * | 2018-11-09 | 2021-06-18 | 泰康保险集团股份有限公司 | Voice interaction method and device, electronic equipment and computer readable medium |
| CN109346078A (en) * | 2018-11-09 | 2019-02-15 | 泰康保险集团股份有限公司 | Voice interactive method, device and electronic equipment, computer-readable medium |
| CN111951808A (en) * | 2019-04-30 | 2020-11-17 | 深圳市优必选科技有限公司 | Voice interaction method, device, terminal equipment and medium |
| CN111951808B (en) * | 2019-04-30 | 2023-09-08 | 深圳市优必选科技有限公司 | Voice interaction method, device, terminal equipment and medium |
| CN110263128A (en) * | 2019-06-24 | 2019-09-20 | 百度在线网络技术（北京）有限公司 | The method, apparatus and computer readable storage medium of interaction question and answer |
| CN110491383A (en) * | 2019-09-25 | 2019-11-22 | 北京声智科技有限公司 | A kind of voice interactive method, device, system, storage medium and processor |
| CN110491383B (en) * | 2019-09-25 | 2022-02-18 | 北京声智科技有限公司 | Voice interaction method, device and system, storage medium and processor |
| WO2021120876A1 (en) * | 2019-12-18 | 2021-06-24 | 华为技术有限公司 | Corpus identification method, device, terminal apparatus, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107170446A (en) | Semantic processes server and the method for semantic processes | |
| CN105592237B (en) | A kind of method, apparatus and intelligent customer service robot of session switching | |
| CN105391730B (en) | A kind of information feedback method, apparatus and system | |
| US20200059559A1 (en) | System and Method for Dialogue Tree Generation | |
| CN107645562A (en) | Data transmission processing method, device, equipment and system | |
| JP6756017B2 (en) | Sequence-dependent data message integration in a voice-activated computer network environment | |
| US8226477B1 (en) | Automatic simulation of call center scenarios | |
| CN101741759B (en) | Instant communication-based intelligent interactive system and interactive method | |
| CN105512153A (en) | Method and device for service provision of online customer service system, and system | |
| TWI798652B (en) | A method and system for automatically generating a data collection module | |
| CN101963976A (en) | Information searching method for mobile terminal and mobile terminal | |
| CN109857524B (en) | Stream computing method, device, equipment and computer readable storage medium | |
| CN110781180A (en) | Data screening method and data screening device | |
| CN109002434A (en) | Customer service question and answer matching process, server and storage medium | |
| CN107194580A (en) | A kind of order of translating sends method and apparatus with charge free | |
| CN101794283A (en) | Method and system for processing character strings and matcher | |
| CN108597499B (en) | Voice processing method and voice processing device | |
| CN110418181A (en) | To the method for processing business of smart television, device, smart machine and storage medium | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN113271250A (en) | Multi-channel multi-format instant message forwarding method, system and computer equipment | |
| WO2021169424A1 (en) | Online message processing method, apparatus and device, and readable storage medium | |
| CN107888690A (en) | The statistical method and system of response time | |
| CN107315739A (en) | A kind of semantic analysis | |
| WO2016201810A1 (en) | Log generation method and device | |
| CN111047362A (en) | Statistical management method and system for use activity of intelligent sound box |
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: 20170915 |
|
| RJ01 | Rejection of invention patent application after publication |