CN109871195B - Control method and device capable of voice input and recognition - Google Patents
Control method and device capable of voice input and recognition Download PDFInfo
- Publication number
- CN109871195B CN109871195B CN201910156229.7A CN201910156229A CN109871195B CN 109871195 B CN109871195 B CN 109871195B CN 201910156229 A CN201910156229 A CN 201910156229A CN 109871195 B CN109871195 B CN 109871195B
- Authority
- CN
- China
- Prior art keywords
- input
- information
- input information
- voice
- digital
- 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.)
- Active
Links
Images
Abstract
The invention discloses a control method and a device capable of voice input and recognition, wherein the control method comprises the following steps: acquiring input information, wherein the input information is voice input information; analyzing the input information and converting the analyzed input information into a digital signal; acquiring an information input state, wherein the information input state comprises a designated input position and an unspecified input position; when the information input state is at a designated input position, sending digital information to the corresponding designated input position, wherein the digital information is used for information input; and when the information input state is in the unspecified input position, sending digital information to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface. The invention judges the function of the voice input information by acquiring the information input state, thereby realizing the input of the voice to the computer and simultaneously controlling the computer to generate a corresponding functional picture by the voice, and greatly reducing the input and use difficulty of the computer.
Description
Technical Field
The invention relates to the technical field of computer input methods, in particular to a control method and a control device capable of realizing voice input and recognition and realizing the input and control to a computer through voice.
Background
The traditional computer adopts a keyboard as an input tool, but some unfamiliar people, such as the old, children, disabled people, people who do not understand the fingering and are unfamiliar with the input method, and the like, have great influence on the enthusiasm and efficiency of learning and practical computers by using the keyboard input, and often want to complete character input by using a handwriting board, and some computers used by the people have the function of a touch pad but do not have the function of the handwriting board, so that the defects of the keyboard need to be solved by other peripheral equipment; on the other hand, in the existing input device, although the handwriting board can solve the problem of inconvenient keyboard input in the prior art to a certain extent, the input speed is slow, and the language input can only input information under the formulated function interface, so that for people who are not familiar with computers, the problem of inconvenient use still exists, for example, how to open the function interface, such as WeChat and Taobao, is unclear, and therefore, a method capable of realizing both quick input and direct control of opening the function interface is urgently needed.
Disclosure of Invention
Aiming at the defects in the technology, the invention provides a control method and a control device capable of realizing voice input and recognition, which can realize the input to a computer through voice input and control the computer to generate a corresponding functional interface.
In order to achieve the above object, the present invention provides a control method capable of voice input and recognition, comprising:
acquiring input information, wherein the input information is voice input information;
analyzing the input information and converting the analyzed input information into a digital signal;
acquiring an information input state, wherein the information input state comprises a designated input position and an unspecified input position;
when the information input state is in a designated input position, sending the digital information to the corresponding designated input position, wherein the digital information is used for information input;
and when the information input state is in an unspecified input position, sending the digital information to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface.
Wherein the input information further comprises written input information.
The input information further comprises key input information, and the key input information comprises character selection, pen and mouse switching and a right key.
Wherein, before acquiring the input information, further comprising: and acquiring a function selection instruction under an interface in the function selection instruction, wherein the function selection instruction is used for determining whether voice input information or writing input information is to be received.
The function selection instruction comprises a function selection instruction such as voice, text, search, help and language.
When the input information is voice input information, the converting the analyzed input information into a digital signal includes: and recognizing the input information, searching and comparing the input information with a database stored under a voice function selection instruction, translating the input information into a text and converting the text into a digital signal.
When the input information is writing input information, the converting the input information into a digital signal after analyzing the input information includes: detecting an input operation acting on a touch screen, and generating a handwriting track according to the input operation; and recognizing the handwriting into text and converting the text into a digital signal.
Wherein when the information input state is at an unspecified input position, further comprising: judging whether the digital information contains a keyword of an application operation command; and if the keywords of the application operation command are included, the keywords of the application operation command are sent to the computer side, so that the computer side executes the corresponding in-application operation program according to the keywords of the application operation command.
The invention also provides a control device capable of voice input and recognition, comprising:
the system comprises an acquisition input module, a processing module and a processing module, wherein the acquisition input module is used for acquiring input information, and the input information is voice input information;
the analysis module is used for analyzing the input information and then converting the input information into a digital signal;
the system comprises an acquisition state module, a display module and a display module, wherein the acquisition state module is used for acquiring an information input state, and the information input state comprises a designated input position and an unspecified input position;
the execution module is used for sending the digital information to a corresponding specified input position when the information input state is in the specified input position, wherein the digital information is used for information input;
and when the information input state is in an unspecified input position, the digital information is sent to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface.
Wherein the inputting information further comprises obtaining written input information.
The invention has the beneficial effects that: compared with the prior art, the control method and the control device capable of voice input and recognition provided by the invention have the advantages that the input information is acquired through setting, and the input information is voice input information; analyzing the input information and converting the analyzed input information into a digital signal; acquiring an information input state, wherein the information input state comprises a designated input position and an unspecified input position; when the information input state is in a designated input position, sending digital information to the corresponding designated input position, wherein the digital information is used for information entry; when the information input state is in an unspecified input position, the digital information is sent to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding functional interface and the like, and the input information acquisition module, the analysis module, the state acquisition module and the execution module are arranged, so that the function of judging the voice input information by acquiring the information input state is realized, and the corresponding functional picture can be generated by controlling the computer through the voice while the voice is input into the computer, so that the input and use difficulty of the computer is greatly reduced.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a first flowchart of the present invention;
FIG. 3 is a second flowchart of the present invention;
FIG. 4 is a third flowchart of the present invention;
FIG. 5 is a first block diagram of the present invention;
fig. 6 is a second block diagram of the present invention.
Detailed Description
In order to more clearly describe the present invention, the present invention is further described below with reference to the accompanying drawings.
To achieve the above object, please refer to fig. 1, the control method capable of voice input and recognition of the present invention is used for expanding the input mode of a computer and realizing the input and control of the computer without using a keyboard, and mainly includes the following steps:
s2, acquiring input information, wherein the input information is voice input information;
s3, converting the input information into digital signals after analyzing the input information;
s4, acquiring information input states, wherein the information input states comprise a designated input position and an unspecified input position;
s5, when the information input state is at the appointed input position, sending the digital information to the corresponding appointed input position, wherein the digital information is used for information input;
and when the information input state is in the unspecified input position, sending digital information to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface.
The function of judging the voice input information by acquiring the information input state is realized, so that when the voice is input into a computer, the computer can be controlled by the voice to generate a corresponding function picture, the input and use difficulty of the computer is greatly reduced, a specific embodiment is taken as an example, the computer side is assumed to be a desktop computer, equipment provided with an input information device is external input equipment, firstly, the external input equipment with voice input is required to be connected with the computer, for example, the external input equipment is connected through a USB interface, the voice information is input through the external input equipment, the device for acquiring the input voice information can be a microphone or other devices capable of realizing the function, and when the acquired input information is 'Taobao', the input information 'Taobao' is analyzed and then converted into a digital signal; acquiring an information-fetching input state, wherein the information-fetching input state comprises a designated input position and an unspecified input position, the designated input position refers to a corresponding dialog box or a text box of an input file, a flashing vertical line or other marks are displayed on a display screen of a general computer to indicate that the input position is in an editable state at the moment, and digital information is sent to the corresponding designated input position at the moment, wherein the digital information is used for information entry, for example, the designated input position is a text input box of a WeChat dialog box at the moment, so that 'Taobao' is displayed on the text input box and sent out; if the acquired information input state is an unspecified input position, the unspecified input position generally only has an inclined arrow mark on a computer display screen and represents that the computer is in a state of waiting to receive an instruction at present, and therefore, the digital information is sent to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding functional interface, such as inputting 'panning', the control main body on the computer side can open a panning page without clicking the computer interface through a mouse to search for a browser or other software capable of opening the panning page, and for people who do not know the computer, the simplicity of using the computer is greatly improved.
In this embodiment, in order to implement that the method can still be used when the environment is not convenient for speaking, the input information further includes writing input information, the writing input information is implemented by writing without language input information, and the above functions can also be implemented, the writing input information is embodied on hardware, the writing is performed on the touch screen by a writing pen, and in order to extend the writing input function, the input information further includes key input information, the key input information includes word selection, pen and mouse switching, and a right key, wherein when the word selection key is used for inputting information in voice, translation errors are easy to occur due to a large number of accents or homophones, so a word selection key is set, for example, the recognized voice input information is "high-new" and "high salary" needs to be input, and when the word selection input information is received, the word selection input information is used for generating a word selection option box, selection can be carried out; the pen and mouse switch input information is used for judging whether the input information is written or clicked, namely, the small input information can be lost and can be used as a mouse function; the right key input information is used for opening the function of the computer right key, and specifically comprises the following steps: and receiving right key input information, wherein the right key input information is used for controlling the computer to generate a right key function option box.
In the present embodiment, referring to fig. 2, before the obtaining of the input information S2, the method further includes step S1: under the interface of the function selection instruction, acquiring the function selection instruction, wherein the function selection instruction is used for determining whether to receive voice input information or write input information or other input information, thereby avoiding the defect of disordered input information and avoiding inputting unnecessary information, the function selection instruction comprises the function selection instructions of voice, text, search, help, language and the like, wherein the speech is the speech input information, the text is the written input information, the search is a search, and the help is an analysis of the method operation, the speech is a recognizable speech category, such as mandarin, shanghai, etc., when the function selection instruction is acquired, the corresponding input information is acquirable input information, for example, when the acquired function selection instruction is a voice function selection instruction, the acquirable input information is voice input information.
In this embodiment, referring to fig. 3-4, when the input information is voice input information, the step S3 of converting the parsed input information into a digital signal includes the step S31: recognizing input information, searching and comparing the input information with a database stored under a voice function selection instruction, translating the input information into a text and converting the text into a digital signal: when the input information is written input information, the step of converting the parsed input information into a digital signal includes step S32: detecting an input operation acting on the touch screen, and generating a handwriting track according to the input operation; the handwriting is recognized into text and then converted into digital signals, and various input modes are realized through different analysis modes.
In this embodiment, when the information input state is at the unspecified input position, the method further includes: judging whether the digital information contains a keyword of an application operation command; if the keyword of the application operation command is included, the keyword of the application operation command is sent to the computer side, so that the computer side executes the corresponding in-application operation program according to the keyword of the application operation command, and if the keyword of the application operation command is not included in the digital information, the digital information is not sent to the computer side, thereby avoiding the language input in the careless situation, for example, if the keyword of the application operation command included in the digital information is judged to be 'Jingdong', the 'Jingdong' is sent to the computer side as the digital information, so that the computer side executes the corresponding in-application operation program according to the keyword, a webpage interface of the 'Jingdong' is opened, and if the keyword of the application operation command included in the digital information is judged to be 'poor' (in case of no website is assumed), and the computer side does not have software or a folder of 'poor', the digital information is not sent to the computer side, and the accuracy of voice input is greatly improved.
Referring to fig. 5, the present invention further provides a control device capable of voice input and recognition, comprising:
an obtaining input module 101, configured to obtain input information, where the input information is voice input information;
the analysis module 102 is configured to analyze the input information and convert the analyzed input information into a digital signal;
an obtaining state module 103, configured to obtain an information input state, where the information input state includes a designated input position and an unspecified input position;
an executing module 104, configured to send the digital information to a corresponding designated input position when the information input state is at the designated input position, where the digital information is used for information entry;
and when the information input state is in an unspecified input position, the digital information is sent to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface.
In this embodiment, referring to fig. 5 to 6, acquiring the input information acquired by the input module 101 further includes acquiring writing input information, or the writing input information is the same as the method, and the input information further includes key input information, where the key input information includes character selection, pen and mouse switching, and a right key, which is the same as the method; the function selection instruction module 105 is used for acquiring a function selection instruction under an interface of the function selection instruction before acquiring the input information, wherein the function selection instruction is used for deciding whether to receive voice input information or write the input information; the function selection instruction comprises voice, text, search, help, language and other function selection instructions; preferably, when the input information acquired by the acquisition input module 101 is voice input information, the parsing module 102 is configured to: the input information is recognized, after being searched and compared with a database stored under a voice function selection instruction, the input information is translated into a text and converted into a digital signal, and when the input information acquired by the acquisition input module 101 is writing input information, the parsing module 102 is configured to: detecting an input operation acting on the touch screen, and generating a handwriting track according to the input operation; recognizing the handwriting into a text and converting the text into a digital signal; in addition, when the information input state is in the unspecified input position, the execution module 104 is further configured to determine whether the digital information includes a keyword of the application operation command; if the keyword of the application operation command is included, the keyword of the application operation command is sent to the computer side, so that the computer side executes the corresponding in-application operation program according to the keyword of the application operation command, and the accuracy is greatly improved.
The invention has the advantages that:
(1) the function of voice input information is judged by acquiring the information input state, so that the computer can be controlled by voice to generate a corresponding function picture while the voice is input into the computer, and the input and use difficulty of the computer is greatly reduced;
(2) the writing input information is set, so that the voice input and the writing input can be realized, and the input mode is greatly expanded.
The above disclosure is only one or more specific embodiments of the present invention, but the present invention is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present invention.
Claims (5)
1. A control method capable of voice input and recognition is characterized by comprising the following steps:
acquiring input information, wherein the input information is voice input information and/or writing input information;
analyzing the input information and converting the analyzed input information into a digital signal;
acquiring an information input state, wherein the information input state comprises a designated input position and an unspecified input position;
when the information input state is in a designated input position, sending the digital information to the corresponding designated input position, wherein the digital information is used for information input;
when the information input state is in an unspecified input position, the digital information is sent to a control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface;
when the input information is voice input information, the converting the analyzed input information into a digital signal includes: recognizing the input information, searching and comparing the input information with a database stored under a voice function selection instruction, and translating the input information into a text and converting the text into a digital signal;
when the input information is writing input information, the converting the input information into a digital signal after analyzing the input information includes: detecting an input operation acting on a touch screen, and generating a handwriting track according to the input operation; recognizing the handwriting into text and converting the text into a digital signal;
when the information input state is at an unspecified input position, the method further comprises: judging whether the digital information contains a keyword of an application operation command; and if the keywords of the application operation command are included, the keywords of the application operation command are sent to the computer side, so that the computer side executes the corresponding in-application operation program according to the keywords of the application operation command.
2. The control method capable of voice input and recognition according to claim 1, wherein the input information further comprises key input information, and the key input information comprises word selection, pen and mouse switching and a right key.
3. The method of claim 1, further comprising, before obtaining the input information: and acquiring a function selection instruction under an interface in which the function selection instruction is positioned, wherein the function selection instruction is used for determining whether voice input information or writing input information is to be received.
4. The method of claim 3, wherein the function selection instructions include voice, text, search, help, and language function selection instructions.
5. A control device capable of voice input and recognition, comprising:
the acquisition input module is used for acquiring input information, wherein the input information is voice input information and/or writing input information;
the analysis module is used for analyzing the input information and then converting the input information into a digital signal;
the system comprises an acquisition state module, a display module and a display module, wherein the acquisition state module is used for acquiring an information input state, and the information input state comprises a designated input position and an unspecified input position;
the execution module is used for sending the digital information to a corresponding specified input position when the information input state is in the specified input position, wherein the digital information is used for information input;
when the information input state is in an unspecified input position, the digital information is sent to the control main body on the computer side, wherein the digital information is used for controlling the control main body on the computer side to open a corresponding function interface;
when the input information is voice input information, the converting the analyzed input information into a digital signal includes: recognizing the input information, searching and comparing the input information with a database stored under a voice function selection instruction, and translating the input information into a text and converting the text into a digital signal;
when the input information is writing input information, the converting the input information into a digital signal after analyzing the input information includes: detecting an input operation acting on a touch screen, and generating a handwriting track according to the input operation; recognizing the handwriting into text and converting the text into a digital signal;
when the information input state is at an unspecified input position, the method further comprises: judging whether the digital information contains a keyword of an application operation command; and if the keyword of the application operation command is included, sending the keyword of the application operation command to the computer side so that the computer side executes the corresponding in-application operation program according to the keyword of the application operation command.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910156229.7A CN109871195B (en) | 2019-03-01 | 2019-03-01 | Control method and device capable of voice input and recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910156229.7A CN109871195B (en) | 2019-03-01 | 2019-03-01 | Control method and device capable of voice input and recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109871195A CN109871195A (en) | 2019-06-11 |
| CN109871195B true CN109871195B (en) | 2022-05-20 |
Family
ID=66919612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910156229.7A Active CN109871195B (en) | 2019-03-01 | 2019-03-01 | Control method and device capable of voice input and recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871195B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199033B (en) * | 2020-09-30 | 2023-06-20 | 北京搜狗科技发展有限公司 | Voice input method and device and electronic equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7389236B2 (en) * | 2003-09-29 | 2008-06-17 | Sap Aktiengesellschaft | Navigation and data entry for open interaction elements |
| CN102929921A (en) * | 2012-09-20 | 2013-02-13 | 腾讯科技（深圳）有限公司 | Information operational method and client |
| CN107436749A (en) * | 2017-08-03 | 2017-12-05 | 安徽智恒信科技有限公司 | Character input method and system based on three-dimension virtual reality scene |
| CN108182944A (en) * | 2018-01-18 | 2018-06-19 | 吴波 | Control the method, apparatus and intelligent terminal of intelligent terminal |
| CN108616646A (en) * | 2018-03-13 | 2018-10-02 | 努比亚技术有限公司 | A kind of sound control method, equipment and computer readable storage medium |
| CN109388699A (en) * | 2018-10-24 | 2019-02-26 | 北京小米移动软件有限公司 | Input method, device, equipment and storage medium |
-
2019
- 2019-03-01 CN CN201910156229.7A patent/CN109871195B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109871195A (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107210035B (en) | Generation of language understanding systems and methods | |
| US5884249A (en) | Input device, inputting method, information processing system, and input information managing method | |
| US9299342B2 (en) | User query history expansion for improving language model adaptation | |
| US8150699B2 (en) | Systems and methods of a structured grammar for a speech recognition command system | |
| US8886521B2 (en) | System and method of dictation for a speech recognition command system | |
| US10114809B2 (en) | Method and apparatus for phonetically annotating text | |
| US8538757B2 (en) | System and method of a list commands utility for a speech recognition command system | |
| RU2477518C2 (en) | Recognition architecture for generating asian hieroglyphs | |
| US11521603B2 (en) | Automatically generating conference minutes | |
| US20140019462A1 (en) | Contextual query adjustments using natural action input | |
| CN111611468B (en) | Page interaction method and device and electronic equipment | |
| RU2015104790A (en) | METHOD AND DEVICE OF THE USER INTERFACE FOR THE USER TERMINAL | |
| CN108932218B (en) | Instance extension method, device, equipment and medium | |
| KR20190032498A (en) | Acoustic model training using modified terms | |
| JP2011154099A (en) | Dictionary for speech recognition utilized in speech recognition device and learning method of language model for speech recognition | |
| CN109871195B (en) | Control method and device capable of voice input and recognition | |
| CN103164398A (en) | Chinese-Uygur language electronic dictionary and automatic translating Chinese-Uygur language method thereof | |
| CN107590140B (en) | Document missing item processing method | |
| CN103164396A (en) | Chinese-Uygur language-Kazakh-Kirgiz language electronic dictionary and automatic translating Chinese-Uygur language-Kazakh-Kirgiz language method thereof | |
| CN113268981B (en) | Information processing method and device and electronic equipment | |
| CN111652005A (en) | Synchronous inter-translation system and method for Chinese and Urdu | |
| KR101099010B1 (en) | Method and apparatus for providing on online dictionary service, and computer-readable recorded medium | |
| CN108932326B (en) | Instance extension method, device, equipment and medium | |
| WO2016131260A1 (en) | Word processing method and apparatus | |
| CN108959617B (en) | Grammar feature matching method, device, medium and computing equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |