CN109871119A - A kind of learning type intellectual voice operating method and system - Google Patents
A kind of learning type intellectual voice operating method and system Download PDFInfo
- Publication number
- CN109871119A CN109871119A CN201811606114.5A CN201811606114A CN109871119A CN 109871119 A CN109871119 A CN 109871119A CN 201811606114 A CN201811606114 A CN 201811606114A CN 109871119 A CN109871119 A CN 109871119A
- Authority
- CN
- China
- Prior art keywords
- input signal
- input
- signal
- several
- user
- 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
Abstract
The invention discloses a kind of learning type intellectual voice operating method and systems, which comprises obtains several operational orders, several first input signals that user inputs；Establish the incidence relation between several first input signals and several operational orders；Obtain the second input signal of user's input；Second input signal is compared with the first input signal, obtains and instructing with the associated object run of the desired input signals in the first signal with the matched desired input signals of the second input signal；It is operated according to object run instruction, in this way, being operated according to the associated operational order of the first input signal when the second input signal is matched with the first input signal, achieving the purpose that directly to be operated by the second input signal.
Description
Technical field
The present invention relates to terminal operation control technology field more particularly to a kind of learning type intellectual voice operating method and it is
System.
Background technique
Speech recognition is a cross discipline.Speech recognition is exactly to allow machine by identification and understanding process voice signal
Be changed into the high-tech of corresponding text or order, speech recognition need to carry out semantics recognition, i.e. machine to voice it is understood that
Then the meaning expressed by voice executes and meaning corresponding operation expressed by voice.
But in daily life and work, in the scene of speech recognition, voice (keyword, sentence that user uses
Son, order) it is often fewer, meanwhile, these voice access times are more frequent, system resource is wasted using speech recognition,
It is secondary, it is lower in the accuracy rate for carrying out speech recognition using intelligent lower terminal, it is again, dialect in user job, special
Pronunciation etc. also will affect the accuracy rate and efficiency of speech recognition.
Summary of the invention
Technical problems based on background technology the invention proposes a kind of learning type intellectual voice operating method and are
System；
A kind of learning type intellectual voice operating method proposed by the present invention, comprising:
Obtain several operational orders, several first input signals that user inputs；
Establish the incidence relation between several first input signals and several operational orders；
Obtain the second input signal of user's input；
Second input signal is compared with the first input signal, obtains matching in the first signal with the second input signal
Desired input signals, and instructed with the associated object run of the desired input signals；
It is operated according to object run instruction.
Preferably, first input signal, comprising: audio, gesture, movement；Second input signal, comprising: sound
Frequently, gesture, movement.
Preferably, the operational order, comprising: the operational order for carrying out once-through operation, the operation operated continuously refer to
It enables.
A kind of learning type intellectual voice operating system, comprising:
First obtains module, for obtaining several operational orders, several first input signals that user inputs；
Relating module, the incidence relation for establishing between several first input signals and several operational orders；
Second obtains module, for obtaining the second input signal of user's input；
Matching module obtains in the first signal with for the second input signal to be compared with the first input signal
The matched desired input signals of two input signals, and instructed with the associated object run of the desired input signals；
Operation module, for being operated according to object run instruction.
Preferably, described first obtain module, be specifically used for: the first input signal of user's input of acquisition includes sound
Frequently, gesture, movement；
Preferably, second obtain module, be specifically used for: the second input signal of user's input of acquisition includes audio, hand
Gesture, movement.
Preferably, described first obtain module, be specifically used for: the operational order of user's input of acquisition includes: carry out one
The operational order of secondary operation, the operational order operated continuously.
In the present invention, several operational orders, several first input signals that user inputs are obtained；Establish several first inputs
Incidence relation between signal and several operational orders；Obtain the second input signal of user's input；By the second input signal with
First input signal is compared, obtain in the first signal with the matched desired input signals of the second input signal, and with this
The associated object run instruction of desired input signals；According to object run instruction operated, in this way, by the second input signal with
First input signal is matched, obtain the first signal in the matched desired input signals of the second input signal, according to target
The associated object run instruction of input signal is operated, and achievees the purpose that directly to be operated by the second input signal,
When first input signal, the second input signal are audio signal, for speech recognition, it can be compared by audio signal
It can directly be operated, without allowing machine to understand the meaning expressed by audio signal, be improved efficiency, secondly, for dialect, spy
For different pronunciation, directly the accuracy rate of comparison audio signal can higher than speech recognition to the recognition accuracy of dialect, special pronunciation,
When the first input signal, the second input signal are hand signal or action signal, it can directly pass through hand signal or movement
Signal fusing can be operated directly, improved working efficiency, saved the time cost and cost of labor of user.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of learning type intellectual voice operating method proposed by the present invention；
Fig. 2 is a kind of module diagram of learning type intellectual voice operating system proposed by the present invention.
Specific embodiment
Referring to Fig.1, a kind of learning type intellectual voice operating method proposed by the present invention, comprising:
Obtain several operational orders, several first input signals that user inputs.
In this step, first input signal includes audio, gesture, movement；The operational order, comprising: carry out one
The operational order of secondary operation, the operational order operated continuously.
Establish the incidence relation between several first input signals and several operational orders.
In concrete scheme, the voice, the hand that obtain voice, gesture or the limb action of user's input, and user is inputted
The operational order that gesture or limb action are inputted with user is associated, and the operational order includes that the operation of progress once-through operation refers to
The operational order for enabling or being operated continuously, i.e. user input the corresponding progress once-through operation of one or more voice or continuous operation
Operational order.
By taking operational order is mobile phone operation instruction as an example: obtaining " opening ", " unlatching " voice of user, by " opening ", " open
Open " it voice and clicks the operational order of a certain application of smart phone and is associated, or, by " opening ", " unlatching " voice and point
It hits a certain application of smart phone and a certain function of clicking the application is that the operational order opened is associated.
Obtain the second input signal of user's input.
In this step, second input signal includes audio, gesture, movement.
Second input signal is compared with the first input signal, obtains matching in the first signal with the second input signal
Desired input signals, and instructed with the associated object run of the desired input signals.
It is operated according to object run instruction.
In concrete scheme, after the first input signal is associated with operational order, the second input signal is obtained, it is defeated by second
Enter signal to be matched with the first input signal, obtain the first signal in the matched desired input signals of the second input signal,
It is operated by desired input signals associated object run instruction, reaches and directly operated by the second input signal
Purpose for speech recognition, can pass through audio when the first input signal, the second input signal are audio signal
Signal fusing can be operated directly, without allowing machine to understand the meaning expressed by audio signal, be improved efficiency, secondly, right
For dialect, special pronunciation, the accuracy rate of directly comparison audio signal can be higher than knowledge of the speech recognition to dialect, special pronunciation
Other accuracy rate；When the first input signal, the second input signal are hand signal or action signal, can directly be believed by gesture
Number or action signal comparison can directly be operated, improve working efficiency, save the time cost and cost of labor of user.
By taking operational order is mobile phone operation instruction as an example: by " opening ", " unlatching " voice and clicking smart phone
After the operational order of a certain application is associated, the voice of user's input is obtained again, by the voice inputted in user and " is beaten
Open ", " unlatching " voice matched, in successful match, smart phone automatically executes a certain application for clicking smart phone
Operation.
Referring to Fig. 2, the present invention proposes a kind of learning type intellectual voice operating system, comprising:
First obtains module, specific to use for obtaining several operational orders, several first input signals that user inputs
In: the first input signal of user's input of acquisition includes audio, gesture, movement；The operational order packet of user's input of acquisition
It includes: the operational order for carrying out once-through operation, the operational order operated continuously.
Relating module, the incidence relation for establishing between several first input signals and several operational orders.
In concrete scheme, the voice, the hand that obtain voice, gesture or the limb action of user's input, and user is inputted
The operational order that gesture or limb action are inputted with user is associated, and the operational order includes that the operation of progress once-through operation refers to
The operational order for enabling or being operated continuously, i.e. user input the corresponding progress once-through operation of one or more voice or continuous operation
Operational order.
By taking operational order is mobile phone operation instruction as an example: obtaining " opening ", " unlatching " voice of user, by " opening ", " open
Open " it voice and clicks the operational order of a certain application of smart phone and is associated, or, by " opening ", " unlatching " voice and point
It hits a certain application of smart phone and a certain function of clicking the application is that the operational order opened is associated.
Second obtains module, for obtaining the second input signal of user's input, is specifically used for: user's input of acquisition
Second input signal includes audio, gesture, movement.
Matching module obtains in the first signal with for the second input signal to be compared with the first input signal
The matched desired input signals of two input signals, and instructed with the associated object run of the desired input signals.
Operation module, for being operated according to object run instruction.
In concrete scheme, after the first input signal is associated with operational order, the second input signal is obtained, it is defeated by second
Enter signal to be matched with the first input signal, obtain the first signal in the matched desired input signals of the second input signal,
It is operated by desired input signals associated object run instruction, reaches and directly operated by the second input signal
Purpose for speech recognition, can pass through audio when the first input signal, the second input signal are audio signal
Signal fusing can be operated directly, without allowing machine to understand the meaning expressed by audio signal, be improved efficiency, secondly, right
For dialect, special pronunciation, the accuracy rate of directly comparison audio signal can be higher than knowledge of the speech recognition to dialect, special pronunciation
Other accuracy rate；When the first input signal, the second input signal are hand signal or action signal, can directly be believed by gesture
Number or action signal comparison can directly be operated, improve working efficiency, save the time cost and cost of labor of user.
By taking operational order is mobile phone operation instruction as an example: by " opening ", " unlatching " voice and clicking smart phone
After the operational order of a certain application is associated, the voice of user's input is obtained again, by the voice inputted in user and " is beaten
Open ", " unlatching " voice matched, in successful match, smart phone automatically executes a certain application for clicking smart phone
Operation.
In present embodiment, several operational orders, several first input signals that user inputs are obtained；Establish several first
Incidence relation between input signal and several operational orders；Obtain the second input signal of user's input；By the second input letter
Number be compared with the first input signal, obtain in the first signal with the matched desired input signals of the second input signal, and
It is instructed with the associated object run of the desired input signals；It is operated according to object run instruction, in this way, the second input is believed
Number matched with the first input signal, obtain in the first signal with the matched desired input signals of the second input signal, according to
The associated object run instruction of desired input signals is operated, and the mesh directly operated by the second input signal is reached
, when the first input signal, the second input signal are audio signal, for speech recognition, can be believed by audio
Number comparison can be operated directly, without allowing machine to understand the meaning expressed by audio signal, be improved efficiency, secondly, for
For dialect, special pronunciation, the accuracy rate of directly comparison audio signal can be higher than identification of the speech recognition to dialect, special pronunciation
Accuracy rate can directly pass through hand signal when the first input signal, the second input signal are hand signal or action signal
Or action signal comparison can be operated directly, improved working efficiency, saved the time cost and cost of labor of user.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (6)
1. a kind of learning type intellectual voice operating method characterized by comprising
Obtain several operational orders, several first input signals that user inputs；
Establish the incidence relation between several first input signals and several operational orders；
Obtain the second input signal of user's input；
Second input signal is compared with the first input signal, obtain in the first signal with the matched mesh of the second input signal
Input signal is marked, and is instructed with the associated object run of the desired input signals；
It is operated according to object run instruction.
2. learning type intellectual voice operating method according to claim 1, which is characterized in that first input signal,
It include: audio, gesture, movement；Second input signal, comprising: audio, gesture, movement.
3. learning type intellectual voice operating method according to claim 1, which is characterized in that the operational order, comprising:
The operational order for carrying out once-through operation, the operational order operated continuously.
4. a kind of learning type intellectual voice operating system characterized by comprising
First obtains module, for obtaining several operational orders, several first input signals that user inputs；
Relating module, the incidence relation for establishing between several first input signals and several operational orders；
Second obtains module, for obtaining the second input signal of user's input；
Matching module obtains defeated with second in the first signal for the second input signal to be compared with the first input signal
Enter the desired input signals of Signal Matching, and is instructed with the associated object run of the desired input signals；
Operation module, for being operated according to object run instruction.
5. learning type intellectual voice operating system according to claim 4, which is characterized in that described first obtains module,
Be specifically used for: the first input signal of user's input of acquisition includes audio, gesture, movement；
Preferably, second obtain module, be specifically used for: the second input signal of user's input of acquisition includes audio, gesture, moves
Make.
6. learning type intellectual voice operating system according to claim 4, which is characterized in that described first obtains module,
Be specifically used for: the operational order of user's input of acquisition includes: the operational order for carrying out once-through operation, the behaviour operated continuously
It instructs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606114.5A CN109871119A (en) | 2018-12-27 | 2018-12-27 | A kind of learning type intellectual voice operating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606114.5A CN109871119A (en) | 2018-12-27 | 2018-12-27 | A kind of learning type intellectual voice operating method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109871119A true CN109871119A (en) | 2019-06-11 |
Family
ID=66917191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811606114.5A Pending CN109871119A (en) | 2018-12-27 | 2018-12-27 | A kind of learning type intellectual voice operating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871119A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110199639A1 (en) * | 2010-02-18 | 2011-08-18 | Takeshi Tani | Operation console providing a plurality of operation methods for one command, electronic device and image processing apparatus provided with the operation console, and method of operation |
| US20160249043A1 (en) * | 2013-08-30 | 2016-08-25 | Beijing Boe Optoelectronics Technology Co., Ltd. | Three dimensional (3d) glasses, 3d display system and 3d display method |
| US20170068646A1 (en) * | 2013-03-15 | 2017-03-09 | Salesforce.Com, Inc. | Systems and methods for creating custom actions |
| US20180081447A1 (en) * | 2016-09-22 | 2018-03-22 | Qualcomm Incorporated | Systems and methods for recording custom gesture commands |
| CN108831469A (en) * | 2018-08-06 | 2018-11-16 | 珠海格力电器股份有限公司 | Voice command method for customizing, device and equipment and computer storage medium |
-
2018
- 2018-12-27 CN CN201811606114.5A patent/CN109871119A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110199639A1 (en) * | 2010-02-18 | 2011-08-18 | Takeshi Tani | Operation console providing a plurality of operation methods for one command, electronic device and image processing apparatus provided with the operation console, and method of operation |
| US20170068646A1 (en) * | 2013-03-15 | 2017-03-09 | Salesforce.Com, Inc. | Systems and methods for creating custom actions |
| US20160249043A1 (en) * | 2013-08-30 | 2016-08-25 | Beijing Boe Optoelectronics Technology Co., Ltd. | Three dimensional (3d) glasses, 3d display system and 3d display method |
| US20180081447A1 (en) * | 2016-09-22 | 2018-03-22 | Qualcomm Incorporated | Systems and methods for recording custom gesture commands |
| CN108831469A (en) * | 2018-08-06 | 2018-11-16 | 珠海格力电器股份有限公司 | Voice command method for customizing, device and equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10515627B2 (en) | Method and apparatus of building acoustic feature extracting model, and acoustic feature extracting method and apparatus | |
| WO2021093449A1 (en) | Wakeup word detection method and apparatus employing artificial intelligence, device, and medium | |
| CN105446159B (en) | Intelligent domestic system and its data processing method | |
| CN105261366B (en) | Audio recognition method, speech engine and terminal | |
| CN108182937B (en) | Keyword recognition method, device, equipment and storage medium | |
| CN101484934B (en) | Method and device for the natural-language recognition of a vocal expression | |
| CN110347863B (en) | Speaking recommendation method and device and storage medium | |
| CN104899002A (en) | Conversation forecasting based online identification and offline identification switching method and system for robot | |
| CN110534109B (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN111968631B (en) | Interaction method, device, equipment and storage medium of intelligent equipment | |
| CN109344258A (en) | A kind of intelligent self-adaptive sensitive data identifying system and method | |
| CN111400438A (en) | Method and device for identifying multiple intentions of user, storage medium and vehicle | |
| US20210097994A1 (en) | Data processing method and apparatus for intelligent device, and storage medium | |
| CN111801731B (en) | Voice control method, voice control device, and computer-executable nonvolatile storage medium | |
| CN108509412A (en) | A kind of data processing method, device, electronic equipment and storage medium | |
| CN106845628A (en) | The method and apparatus that robot generates new command by internet autonomous learning | |
| CN110503943B (en) | Voice interaction method and voice interaction system | |
| CN114694644A (en) | Voice intention recognition method and device and electronic equipment | |
| CN104679733A (en) | Voice conversation translation method, device and system | |
| CN109871119A (en) | A kind of learning type intellectual voice operating method and system | |
| CN113220828A (en) | Intention recognition model processing method and device, computer equipment and storage medium | |
| CN109871128B (en) | Question type identification method and device | |
| CN110674482B (en) | Multi-scene application computer | |
| CN106779817A (en) | Intension recognizing method and system based on various dimensions information | |
| KR101433506B1 (en) | Operation method of energy management system using an isolated language voice recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190611 |