CN103617796A - Voice recognition method based on cloud computing - Google Patents
Voice recognition method based on cloud computing Download PDFInfo
- Publication number
- CN103617796A CN103617796A CN201310662492.6A CN201310662492A CN103617796A CN 103617796 A CN103617796 A CN 103617796A CN 201310662492 A CN201310662492 A CN 201310662492A CN 103617796 A CN103617796 A CN 103617796A
- Authority
- CN
- China
- Prior art keywords
- client
- cloud server
- cloud
- computing
- cloud computing
- 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 17
- 230000010354 integration Effects 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
Images
Abstract
The invention discloses a voice recognition method based on cloud computing. The voice recognition method is achieved through a cloud server and a client side, wherein the cloud server combines a plurality of computers or servers and storage devices through a cloud computing technology by using a network, the computers or the servers serve as computing nodes, the client side serves as a mobile terminal getting access through a wireless network, a voice input program is arranged on the client side, a voice recognition program is arranged on the cloud server, the client side uploads voice information of a user to the cloud server to be recognized, and the cloud server returns a recognition result to the client side. By means of the cloud computing technology, the recognition service high in computing amount is handed to the cloud server to be completed, due to the facts that the client side only needs to collect the voice information and can obtain the voice recognition result by sending and receiving network information, the mobile terminal is changed to be a simple input and output device, loads of hardware are reduced, and convenience of the mobile terminal is enhanced.
Description
Technical field
The present invention relates to the general field of cloud computing, internet, software development and speech recognition, be specifically related to a kind of cloud computing technology that utilizes, with Mike and can the electronic equipment of connecting Internet on the audio recognition method realized.
Technical background
Progress along with the epoch, the use of the mobile terminal such as smart mobile phone, panel computer is more and more universal, cloud computing technology is gradually ripe being rooted in the hearts of the people also, so be necessary the not high mobile terminal of these hardware performances and cloud computing technology to connect, some are required to too high service to calculated amount and memory space, and the mode by cloud computing realizes.
The proposition of cloud computing concept, makes supercomputing capability become possibility by internet free flow, and has started a kind of brand-new application model for various application.The application of supercomputer is difficult to be promoted because needing the high hardware of price to drop into, and cloud computing is combined into calculating cluster by internet by some common computing machines or server, has declared the low-cost possibility that realizes supercomputing service.User at any time and any place, the service that can both use cloud computing provide by accessing the terminal device of internet.
Summary of the invention
The technical problem to be solved in the present invention is: the feature of and limited storage space very strong for electronic equipment hardware arithmetic capabilities such as smart mobile phone, panel computers, and the feature of speech recognition technology to arithmetic capability and memory requirement higher (especially speech recognition), speech recognition technology by one of cloud platform development based on cloud computing, and provide the speech-recognition services of high-accuracy by wireless network for mobile terminal.
The technical solution adopted in the present invention is:
A kind of audio recognition method based on cloud computing, by Cloud Server and client, realized, wherein Cloud Server utilizes network integration by cloud computing technology by many computing machines or server and memory device, its Computer or server are as computing node, the mobile terminal of described client for accessing by wireless network, client is provided with phonetic entry program, Cloud Server is provided with speech recognition program, client uploads to Cloud Server by user's voice messaging and identifies, and Cloud Server returns to client by recognition result.
The access of each client and phonetic entry identifying operation are processed to different computing nodes by network allocation, and then result is returned to client.
Described Cloud Server is assigned to different computing nodes by different client-requested and processes, each computing node is handed to request according to s own situation suitable thread process in the thread pool itself arranging, request of each thread independent processing in thread pool, returns to corresponding client by result after completing relevant identifying operation.
The treatment scheme of described Cloud Server comprises the following steps:
1) start service, wait for client initiation request;
2) receive the information from client;
3) information client being sent is identified;
4) recognition result is sent to client.
Beneficial effect of the present invention is:
The present invention by cloud computing technology by operand higher identification service give Cloud Server and complete, for client, only need to gather voice messaging, and send and receive the network information and can obtain voice identification result.
The present invention utilizes network integration by cloud computing technology by the logical personal computer of many Daeporis or server and memory device, form supercomputer cluster, the access of subscription client and identifying operation are processed to each computing node by network allocation, and then result returns to client by network again.Thereby make mobile terminal become a simple input-output device, reduced the burden of hardware, more strengthened the convenience of mobile terminal.
Accompanying drawing explanation
Fig. 1 is Cloud Server system framework figure;
Fig. 2 is the drawing of Cloud Server end system request dispenser;
Fig. 3 is workflow diagram.
Embodiment
With reference to the accompanying drawings, the present invention will be described in conjunction with the embodiments:
As shown in Figure 1, a kind of audio recognition method based on cloud computing, by Cloud Server and client, realized, client obtains connection by interactive interface and Cloud Server, what be in Cloud Server upper strata is administration configuration system, what be in Cloud Server lower floor is many physical machine, wherein Cloud Server utilizes network integration by cloud computing technology by many computing machines or server and memory device, its Computer or server are as computing node, the mobile terminal of described client for accessing by wireless network, client is provided with phonetic entry program, Cloud Server is provided with speech recognition program, client uploads to Cloud Server by user's voice messaging and identifies, Cloud Server returns to client by recognition result.
The access of each client and phonetic entry identifying operation are processed to different computing nodes by network allocation, and then result is returned to client.
As shown in Figure 2, when a plurality of users ask simultaneously, described Cloud Server is assigned to different computing nodes by different client-requested and processes, each computing node is handed to request according to s own situation suitable thread process in the thread pool itself arranging, request of each thread independent processing in thread pool, returns to corresponding client by result after completing relevant identifying operation.
As shown in Figure 3, the treatment scheme of described Cloud Server comprises the following steps:
1) start service, wait for client initiation request;
2) receive the information from client;
3) information client being sent is identified;
4) recognition result is sent to client.
Claims (4)
1. the audio recognition method based on cloud computing, it is characterized in that: by Cloud Server and client, realized, wherein Cloud Server utilizes network integration by cloud computing technology by many computing machines or server and memory device, its Computer or server are as computing node, the mobile terminal of described client for accessing by wireless network, client is provided with phonetic entry program, Cloud Server is provided with speech recognition program, client uploads to Cloud Server by user's voice messaging and identifies, and Cloud Server returns to client by recognition result.
2. a kind of audio recognition method based on cloud computing according to claim 1, it is characterized in that: the access of each client and phonetic entry identifying operation are processed to different computing nodes by network allocation, and then result is returned to client.
3. a kind of audio recognition method based on cloud computing according to claim 1 and 2, it is characterized in that: described Cloud Server is assigned to different computing nodes by different client-requested and processes, each computing node is handed to request according to s own situation suitable thread process in the thread pool itself arranging, request of each thread independent processing in thread pool, returns to corresponding client by result after completing relevant identifying operation.
4. a kind of audio recognition method based on cloud computing according to claim 3, is characterized in that: the treatment scheme of described Cloud Server comprises the following steps:
1) start service, wait for client initiation request;
2) receive the information from client;
3) information client being sent is identified;
4) recognition result is sent to client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310662492.6A CN103617796A (en) | 2013-12-10 | 2013-12-10 | Voice recognition method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310662492.6A CN103617796A (en) | 2013-12-10 | 2013-12-10 | Voice recognition method based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103617796A true CN103617796A (en) | 2014-03-05 |
Family
ID=50168499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310662492.6A Pending CN103617796A (en) | 2013-12-10 | 2013-12-10 | Voice recognition method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103617796A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN105355204A (en) * | 2015-11-24 | 2016-02-24 | 广州市海葱科技有限公司 | System and method for voice recognition based on cloud computation |
| CN108519829A (en) * | 2018-04-15 | 2018-09-11 | 深圳市联芯互联科技有限公司 | A kind of artificial intelligence mouse based on cloud platform big data analysis |
| WO2021082460A1 (en) * | 2019-10-29 | 2021-05-06 | 华为技术有限公司 | Ai processing method and device |
-
2013
- 2013-12-10 CN CN201310662492.6A patent/CN103617796A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN105355204A (en) * | 2015-11-24 | 2016-02-24 | 广州市海葱科技有限公司 | System and method for voice recognition based on cloud computation |
| CN108519829A (en) * | 2018-04-15 | 2018-09-11 | 深圳市联芯互联科技有限公司 | A kind of artificial intelligence mouse based on cloud platform big data analysis |
| WO2021082460A1 (en) * | 2019-10-29 | 2021-05-06 | 华为技术有限公司 | Ai processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104995865B (en) | Service based on sound and/or face recognition provides | |
| CN107077661A (en) | Task across the equipment using shared working space is completed | |
| CN110083455B (en) | Graph calculation processing method, graph calculation processing device, graph calculation processing medium and electronic equipment | |
| CN108989397B (en) | Data recommendation method and device and storage medium | |
| CN104202718A (en) | Method and device for providing information for user | |
| US9196250B2 (en) | Application services interface to ASR | |
| CN110807650A (en) | New financial product user invitation method and system | |
| CN103617796A (en) | Voice recognition method based on cloud computing | |
| TW202119255A (en) | Inference system, inference method, electronic device and computer storage medium | |
| US10089070B1 (en) | Voice activated network interface | |
| CN111611368A (en) | Method and device for backtracking common scene conversation in multi-turn conversation | |
| WO2021120868A1 (en) | Resource settlement method and apparatus, electronic device and storage medium | |
| JP2021034003A (en) | Human object recognition method, apparatus, electronic device, storage medium, and program | |
| US20180268344A1 (en) | Virtual dialogue crowdsourcing | |
| CN110889009B (en) | Voiceprint clustering method, voiceprint clustering device, voiceprint processing equipment and computer storage medium | |
| CN113271610A (en) | Network distribution method and device for door lock equipment, door lock equipment and storage medium | |
| US20210098012A1 (en) | Voice Skill Recommendation Method, Apparatus, Device and Storage Medium | |
| EP2733697A9 (en) | Application services interface to ASR | |
| CN109829744A (en) | Consultation method, device, electronic equipment and medium based on natural language processing | |
| CN103024710A (en) | Online music playing method | |
| CN106878761A (en) | Living broadcast interactive method, device and server | |
| CN112765438A (en) | Automatic crawler management method based on micro-service | |
| CN112597022A (en) | Remote diagnosis method, device, storage medium and electronic equipment | |
| KR102628191B1 (en) | Method for hardware resource assigning and online service providing method thereof | |
| US9363307B2 (en) | Method of linking to and monitoring machining devices through a cloud service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140305 |
|
| RJ01 | Rejection of invention patent application after publication |