CN109901707A - A kind of learning-oriented operation module being configured in system - Google Patents
A kind of learning-oriented operation module being configured in system Download PDFInfo
- Publication number
- CN109901707A CN109901707A CN201811606127.2A CN201811606127A CN109901707A CN 109901707 A CN109901707 A CN 109901707A CN 201811606127 A CN201811606127 A CN 201811606127A CN 109901707 A CN109901707 A CN 109901707A
- Authority
- CN
- China
- Prior art keywords
- unit
- input
- several
- input signal
- order
- 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
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of learning-oriented operation module being configured in system, the operation module includes: acquiring unit, construction unit, storage unit, analytical unit and control unit;Acquiring unit, for obtaining several system operatio orders, several first input signals, the second input signal of user's input;Construction unit, the incidence relation for establishing between several first input signals and several system operatio orders;Storage unit, for storing the incidence relation between the first input signal and system operatio order;Analytical unit, analysis obtain in several first input signals with the matched desired input signals of the second input signal, and with the associated goal systems operational order of the desired input signals;Control unit, for making the system execute the goal systems operational order.
Description
Technical field
The present invention relates to technical field of system control more particularly to a kind of learning-oriented system operatio moulds being configured in system
Block.
Background technique
Speech recognition is exactly to allow machine that voice signal is changed into corresponding text or order by identification and understanding process
High-tech, speech recognition need to voice carry out semantics recognition, i.e., machine is it is understood that the meaning expressed by voice, then holds
Meaning corresponding operation expressed by capable and voice, in daily life and work, in the scene of speech recognition, user is used
Voice (keyword, sentence, order) it is often fewer, meanwhile, these voice access times are more frequent, use speech recognition
System resource is wasted, secondly, it is lower in the accuracy rate for carrying out speech recognition using intelligent lower system, again, Yong Hugong
Dialect, special pronunciation in work 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-oriented system behaviour being configured in system
Make module;
A kind of learning-oriented operation module being configured in system proposed by the present invention, the operation module packet
It includes: acquiring unit, construction unit, storage unit, analytical unit and control unit;
Acquiring unit, for obtaining several system operatio orders, several first input signals, the second input of user's input
Signal;
Construction unit, the incidence relation for establishing between several first input signals and several system operatio orders;
Storage unit, for storing the incidence relation between the first input signal and system operatio order;
Analytical unit, analysis obtain believing in several first input signals with the matched target input of the second input signal
Number, and with the associated goal systems operational order of the desired input signals;
Control unit, for making the system execute the goal systems operational order.
Preferably, the acquiring unit, is specifically used for: the first input signal of user's input of acquisition includes audio, hand
Gesture, movement;Second input signal of user's input of acquisition includes audio, gesture, movement.
Preferably, the construction unit, is specifically used for: each system operatio order can be built with several the first input signals
Vertical incidence relation.
Preferably, the construction unit, is specifically used for: each first input signal is only established with a system operatio order
Incidence relation.
Preferably, the acquiring unit, is specifically used for:
The system operatio order of user's input of acquisition include system carry out the system operatio order of once-through operation, system into
The system operatio order of row continuous operation.
In the present invention, acquiring unit be used for obtain user input several system operatio orders, several first input signals,
Second input signal;Construction unit is for establishing being associated between several first input signals and several system operatio orders
System;Storage unit is used to store the incidence relation between the first input signal and system operatio order;Analytical unit is analyzed to obtain
With the matched desired input signals of the second input signal in several first input signals, and it is associated with the desired input signals
Goal systems operational order;Control unit, for making the system execute the goal systems operational order, in this way, the
When two input signals are matched with the first input signal, control unit makes the system execute the goal systems operational order, reaches
To the purpose for passing through the direct operating system of the second input signal, when the first input signal, the second input signal are audio signal,
For speech recognition, can directly by audio signal compare can direct operating system, without allow machine understand sound
The meaning expressed by frequency signal, improves efficiency, secondly, directly comparison audio signal is accurate for dialect, special pronunciation
Rate can be higher than speech recognition to the recognition accuracy of dialect, special pronunciation, be gesture in the first input signal, the second input signal
When signal or action signal, can directly by hand signal or action signal compare can direct operating system, improve work
Efficiency saves the time cost and cost of labor of user.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram for the learning-oriented operation module being configured in system proposed by the present invention.
Specific embodiment
Referring to Fig.1, a kind of learning-oriented operation module being configured in system proposed by the present invention, the system operatio
Module includes: acquiring unit, construction unit, storage unit, analytical unit and control unit;
Acquiring unit, for obtaining several system operatio orders, several first input signals, the second input of user's input
Signal.
Acquiring unit is specifically used for: the first input signal of user's input of acquisition includes audio, gesture, movement;It obtains
User input the second input signal include audio, gesture, movement;The system operatio order of user's input of acquisition includes being
The system operatio order that system carries out the system operatio order of once-through operation, system is operated continuously.
In concrete scheme, voice signal, hand signal or the limb action signal of acquisition user's input, user can pass through
The system operatio order that editing system operational order or the mode of direct-execution system operation input, using system as smart phone system
For system: after being equipped with the system application of calendar in smart phone, what user inputted the calendar that one section can open smart phone is
Operational order of uniting opens intelligent hand or, user carries out the operation of the icon of the calendar of the smart phone on click desktop with input
The system operatio order of the calendar of machine.
Construction unit, the incidence relation for establishing between several first input signals and several system operatio orders.
Construction unit is specifically used for: each system operatio order can establish incidence relation with several the first input signals;
Each first input signal only establishes incidence relation with a system operatio order.
Storage unit, for storing the incidence relation between the first input signal and system operatio order.
Analytical unit, analysis obtain believing in several first input signals with the matched target input of the second input signal
Number, and with the associated goal systems operational order of the desired input signals.
Control unit, for making the system execute the goal systems operational order.
In concrete scheme, acquiring unit obtains several system operatio orders of user's input, several first input signals
Afterwards, several first input signals (voice, gesture or limb action) are associated with several system operatio orders, such as: it uses
Family inputs the system operatio order that one or more voice correspondence system carries out once-through operation or continuous operation, specifically, each
System operatio order can establish incidence relation with several the first input signals, and each first input signal is only grasped with a system
Make order and establish incidence relation, first input signal is prevented to be associated with a variety of different system operatio orders;Using system as intelligence
For energy cell phone system: " opening " voice association " the system operatio order for opening wechat ", or, " opening " voice association " is opened
Wechat and the user for searching for the entitled AA of wechat, the system operatio order to AA initiating speech conversation ", or, " opening ", " unlatching "
Voice association " the system operatio order for opening wechat ", " the system behaviour of opening wechat cannot be associated with simultaneously by still " opening " voice
Order " and " the system operatio order for opening QQ ".
After incidence relation between the first input signal and system operatio order is stored in storage unit, it is defeated to obtain user
The second input signal entered matches the second input signal with the first input signal, defeated in the second input signal and first
When entering Signal Matching success, i.e. the second input signal is consistent with the first input signal, similarity reaches preset similarity threshold
Or when identical, control unit makes system execute the goal systems operational order, reaches and is directly operated by the second input signal
The purpose of system, when the first input signal, the second input signal are audio signal, for speech recognition, Ke Yizhi
Connected audio signal compare can direct operating system, without allow machine understand audio signal expressed by the meaning, improve effect
Rate, secondly, directly the accuracy rate of comparison audio signal can be higher than speech recognition to dialect, spy for dialect, special pronunciation
The recognition accuracy very to pronounce can be direct when the first input signal, the second input signal are hand signal or action signal
By hand signal or action signal compare can direct operating system, improve working efficiency, save user time cost and
Cost of labor.
In present embodiment, acquiring unit is used to obtain several system operatio orders of user's input, several first inputs
Signal, the second input signal;Construction unit is for establishing the pass between several first input signals and several system operatio orders
Connection relationship;Storage unit is used to store the incidence relation between the first input signal and system operatio order;Analytical unit analysis
Obtain in several first input signals with the matched desired input signals of the second input signal, and with the desired input signals
Associated goal systems operational order;Control unit, for making the system execute the goal systems operational order, in this way,
When the second input signal is matched with the first input signal, control unit refers to the system execution goal systems operation
It enables, achievees the purpose that through the direct operating system of the second input signal, be audio letter in the first input signal, the second input signal
Number when, for speech recognition, can directly by audio signal compare can direct operating system, without allowing machine
The meaning expressed by audio signal is solved, is improved efficiency, secondly, directly comparing audio signal for dialect, special pronunciation
Accuracy rate can be higher than speech recognition to the recognition accuracy of dialect, special pronunciation, be in the first input signal, the second input signal
When hand signal or action signal, can directly by hand signal or action signal compare can direct operating system, improve
Working efficiency saves 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 (5)
1. a kind of learning-oriented operation module being configured in system, which is characterized in that the operation module includes: to obtain
Take unit, construction unit, storage unit, analytical unit and control unit;
Acquiring unit, for obtaining several system operatio orders, several first input signals, the second input letter of user's input
Number;
Construction unit, the incidence relation for establishing between several first input signals and several system operatio orders;
Storage unit, for storing the incidence relation between the first input signal and system operatio order;
Analytical unit, analysis obtain in several first input signals with the matched desired input signals of the second input signal, with
And with the associated goal systems operational order of the desired input signals;
Control unit, for making the system execute the goal systems operational order.
2. the learning-oriented operation module according to claim 1 being configured in system, which is characterized in that the acquisition
Unit is specifically used for: the first input signal of user's input of acquisition includes audio, gesture, movement;User's input of acquisition
Second input signal includes audio, gesture, movement.
3. the learning-oriented operation module according to claim 1 being configured in system, which is characterized in that the building
Unit is specifically used for: each system operatio order can establish incidence relation with several the first input signals.
4. the learning-oriented operation module according to claim 1 being configured in system, which is characterized in that the building
Unit is specifically used for: each first input signal only establishes incidence relation with a system operatio order.
5. the learning-oriented operation module according to claim 1 being configured in system, which is characterized in that the acquisition
Unit is specifically used for:
The system operatio order of user's input of acquisition includes that system carries out the system operatio order of once-through operation, system connects
The system operatio order of continuous operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811606127.2A CN109901707A (en) | 2018-12-27 | 2018-12-27 | A kind of learning-oriented operation module being configured in system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811606127.2A CN109901707A (en) | 2018-12-27 | 2018-12-27 | A kind of learning-oriented operation module being configured in system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109901707A true CN109901707A (en) | 2019-06-18 |
Family
ID=66943423
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811606127.2A Pending CN109901707A (en) | 2018-12-27 | 2018-12-27 | A kind of learning-oriented operation module being configured in system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109901707A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163124A (en) * | 2010-02-18 | 2011-08-24 | 夏普株式会社 | Operation console, electronic device and image processing apparatus and method of operation |
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 |
CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
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 CN201811606127.2A patent/CN109901707A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102163124A (en) * | 2010-02-18 | 2011-08-24 | 夏普株式会社 | Operation console, electronic device and image processing apparatus and method of operation |
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 |
CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
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 |
---|---|---|
JP7005099B2 (en) | Voice keyword recognition methods, devices, computer-readable storage media, and computer devices | |
WO2021093449A1 (en) | Wakeup word detection method and apparatus employing artificial intelligence, device, and medium | |
WO2021051544A1 (en) | Voice recognition method and device | |
EP3522153A1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
JP5672487B2 (en) | Spoken language identification device learning device, spoken language identification device, and program therefor | |
CN103745722B (en) | Voice interaction smart home system and voice interaction method | |
Miao et al. | A New Time-Frequency Attention Mechanism for TDNN and CNN-LSTM-TDNN, with Application to Language Identification. | |
CN102664011B (en) | Method for quickly recognizing speaker | |
CN111880856B (en) | Voice wakeup method and device, electronic equipment and storage medium | |
Keshet et al. | Pac-bayesian approach for minimization of phoneme error rate | |
KR20120011010A (en) | Handwriting recognition method and device | |
CN111400438A (en) | Method and device for identifying multiple intentions of user, storage medium and vehicle | |
US9799333B2 (en) | System and method for processing speech to identify keywords or other information | |
CN101923857A (en) | Extensible audio recognition method based on man-machine interaction | |
CN103514879A (en) | Local voice recognition method based on BP neural network | |
CN109074804A (en) | Voice recognition processing method, electronic equipment and storage medium based on accent | |
CN110503962A (en) | Speech recognition and setting method, device, computer equipment and storage medium | |
CN109901707A (en) | A kind of learning-oriented operation module being configured in system | |
CN110674482B (en) | Multi-scene application computer | |
CN111048068B (en) | Voice wake-up method, device and system and electronic equipment | |
CN102938811A (en) | Household mobile phone communication system based on voice recognition | |
CN104424942A (en) | Method for improving character speed input accuracy | |
KR101433506B1 (en) | Operation method of energy management system using an isolated language voice recognition | |
James et al. | Recurrent neural network-based speech recognition using MATLAB | |
CN109871128B (en) | Question type identification method and device |
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: 20190618 |
|
RJ01 | Rejection of invention patent application after publication |