CN106446165A - Big data processing based identification method - Google Patents
Big data processing based identification method Download PDFInfo
- Publication number
- CN106446165A CN106446165A CN201610849018.8A CN201610849018A CN106446165A CN 106446165 A CN106446165 A CN 106446165A CN 201610849018 A CN201610849018 A CN 201610849018A CN 106446165 A CN106446165 A CN 106446165A
- Authority
- CN
- China
- Prior art keywords
- sound
- word
- image
- server
- identification
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Facsimiles In General (AREA)
- Mobile Radio Communication Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a big data processing based identification method and relates to the field of data processing. The method includes the following steps: (1) a user acquiring images, voice and/or writing; (2) subjecting the images, voice and/or writing to comparison identification with stored data in a database; (3) if identified, feeding back identification results to users; (4) if not, a server automatically sending the images, voice and/or writing to a plurality of other users, and the other users performing artificial identification on the images, voice and/or writing; (5) summarizing artificial identification results, storing the artificial identification result in the largest proportion into the database as the final identification result, and returning the identification result to the user. The method has the advantages that an identification system can combine and utilize an artificial identification function of the users to continuously improve itself in use, so as to continuously enhance identification capability thereof.
Description
Technical field
The present invention relates to data processing field, more particularly, to a kind of recognition methodss based on big data process.
Background technology
Identifying system is to identify a certain class things using a kind of help people that the equipment such as electronic machine, computer are constituted
Aid system.Identifying system substantially can be divided into image recognition class and two kinds of voice recognition class.With scientific and technological prosperity, identifying system
More and more, more and more intelligently, but existing identifying system cannot carry out self using with the artificial cognition mode with reference to user
Perfect.
Content of the invention
The present invention provides a kind of recognition methodss based on big data process, cannot be utilized and be combined with existing identifying system and use
The shortcoming that the artificial cognition mode at family carries out ego integrity.
The present invention adopts the following technical scheme that：
A kind of recognition methodss based on big data process, comprise the following steps：（1）User obtains image, sound and/or word,
And send image, sound and/or word to server；（2）By server by image, sound and/or word and data base
The data of depositing carry out contrast identification；（3）If server can according in data base deposit data identification image, sound and/or
Word, then feed back to user by recognition result；（4）If server cannot identify image, sound according to the data of depositing in data base
Sound and/or word, then server automatically image, sound and/or word are sent to several other users, by other users pair
Image, sound and/or word carry out artificial cognition；（5）All artificial recognition results are collected, and with the maximum people of quantity accounting
Work recognition result is stored in data base as final recognition result, this recognition result is fed back to user simultaneously.
Further, described step（1）In, user obtains image, sound and/or word by smart mobile phone, and passes through handss
Machine APP will obtain image, sound and/or word and send to server, described step（4）In, other users are connect by mobile phone A PP
Receive image, sound and/or word, and the result of artificial cognition is sent to server.
Further, described step（1）In, user obtains image, sound and/or word by computer, and passes through software
Image, sound and/or word will be obtained send to server, described step（4）In, other users are received by computer software
Image, sound and/or word, and the result of artificial cognition is sent to server.
Further, described step（4）In, image, sound and/or word are sent to m1 other users and are manually known
Not, the artificial cognition quantity that server receives in stipulated time h1 is n1, if n1 >=(50% × m1), execution step
（5）If, n1<(50% × m1), then be sent to (m1-n1) × 3 by image, sound and/or word every a time period h2 new
Other users, until server receive artificial cognition total quantity N >=(50% × m1) when, execution step（5）；Wherein m1 >=
100.
Further, h1 is 5min, and h2 is 30s.
Further, described step（2）In, the content of contrast identification includes recognition of face, speech recognition, Text region, figure
The title of things and/or the title of the affiliated things of sound in picture.
From the above-mentioned description to present configuration, compared to the prior art, the invention has the advantages that：
During one, the present invention include, if server cannot identify image, sound and/or literary composition according to the data of depositing in data base
Word, then server automatically image, sound and/or word are sent to several other users, by other users to image, sound
And/or word carries out artificial cognition；Again all artificial recognition results are collected, and with the maximum artificial cognition result of quantity accounting
It is stored in data base as final recognition result, this recognition result is fed back to user simultaneously.It can be seen that, the present invention can allow
Identifying system in use, can in conjunction with and continuously improved using the artificial cognition function of user and improve itself,
To strengthen the identification ability of identifying system.
Two, step of the present invention（4）In, image, sound and/or word are sent to m1 other users and are manually known
Not, the artificial cognition quantity that server receives in stipulated time h1 is n1, if n1 >=(50% × m1), execution step
（5）If, n1<(50% × m1), then be sent to (m1-n1) × 3 by image, sound and/or word every a time period h2 new
Other users, until server receive artificial cognition total quantity N >=(50% × m1) when, execution step（5）；Wherein m1 >=
100.Improve the credibility of artificial cognition result by the way it is ensured that identifying system health is perfect.
Specific embodiment
Below the technical scheme in the embodiment of the present invention is carried out with clear, complete description it is clear that described embodiment
It is only a part of embodiment of the present invention, rather than whole embodiments.Based on embodiments of the invention, ordinary skill
The every other embodiment that personnel are obtained under the premise of not making creative work, broadly falls into the scope of protection of the invention.
A kind of recognition methodss based on big data process, comprise the following steps：（1）User obtains image, sound and/or literary composition
Word, and image, sound and/or word are sent to server；（2）By server by image, sound and/or word and data base
In the data of depositing carry out contrast identification；（3）If server can according in data base deposit data identification image, sound and/
Or word, then recognition result is fed back to user；（4）If server cannot according in data base deposit data identification image,
Sound and/or word, then server automatically image, sound and/or word are sent to several other users, by other users
Artificial cognition is carried out to image, sound and/or word；（5）All artificial recognition results are collected, and maximum with quantity accounting
Artificial cognition result is stored in data base as final recognition result, this recognition result is fed back to user simultaneously.
Preferably：Above-mentioned steps（1）In, user obtains image, sound and/or word by smart mobile phone, and
Image, sound and/or word will be obtained by mobile phone A PP to send to server, described step（4）In, other users pass through handss
Machine APP receives image, sound and/or word, and the result of artificial cognition is sent to server.
As another kind of preferred version：Above-mentioned steps（1）In, user obtains image, sound and/or literary composition by computer
Word, and image, sound and/or word will be obtained by software send to server, described step（4）In, other users are passed through
Computer software receives image, sound and/or word, and the result of artificial cognition is sent to server.Here computer
Can be panel computer, desktop computer or notebook.
Preferably：Above-mentioned steps（4）In, image, sound and/or word are sent to m1 other users and carry out
Artificial cognition, the artificial cognition quantity that server receives in stipulated time h1 is n1, if n1 >=(50% × m1), executes
Step（5）If, n1<(50% × m1), then be sent to (m1-n1) × 3 by image, sound and/or word every a time period h2
New other users, until server receive artificial cognition total quantity N >=(50% × m1) when, execution step（5）；Wherein
M1 >=100, h1 can be 5min, and h2 can be 30s.The concrete numerical value of m1, h1 and h2 can set according to actual needs, not
It is confined to this.
Preferably：Above-mentioned steps（2）In, the content of contrast identification includes recognition of face, speech recognition, word knowledge
Not, title of the title of things and/or the affiliated things of sound etc. in image.The content of contrast identification can also be existing identification system
The other guide that system can identify, is not limited only to the above-mentioned each content enumerated.
Above are only the specific embodiment of the present invention, but the design concept of the present invention is not limited thereto, all utilize this
Design carries out the change of unsubstantiality to the present invention, all should belong to the behavior invading the scope of the present invention.
Claims (6)
1. a kind of recognition methodss based on big data process, comprise the following steps：（1）User obtains image, sound and/or literary composition
Word, and image, sound and/or word are sent to server；（2）By server by image, sound and/or word and data base
In the data of depositing carry out contrast identification；（3）If server can according in data base deposit data identification image, sound and/
Or word, then recognition result is fed back to user；It is characterized in that：（4）If server cannot be according to depositing money in data base
Material identifies image, sound and/or word, then image, sound and/or word are sent to several other use by server automatically
Family, carries out artificial cognition by other users to image, sound and/or word；（5）All artificial recognition results are collected, and with
The maximum artificial cognition result of quantity accounting is stored in data base as final recognition result, simultaneously will be anti-for this recognition result
Feed user.
2. as claimed in claim 1 a kind of recognition methodss based on big data process it is characterised in that：Described step（1）In,
User obtains image, sound and/or word by smart mobile phone, and will obtain image, sound and/or word by mobile phone A PP
Send to server, described step（4）In, other users receive image, sound and/or word by mobile phone A PP, and will be artificial
The result of identification sends to server.
3. a kind of recognition methodss based on big data process according to claim 1 it is characterised in that：Described step（1）
In, user obtains image, sound and/or word by computer, and will obtain image, sound and/or word by software and send out
Deliver to server, described step（4）In, other users receive image, sound and/or word by computer software, and by people
The result of work identification sends to server.
4. a kind of recognition methodss based on big data process according to claim 1 it is characterised in that：Described step（4）
In, image, sound and/or word are sent to m1 other users and carry out artificial cognition, server connects in stipulated time h1
The artificial cognition quantity receiving is n1, if n1 >=(50% × m1), execution step（5）If, n1<(50% × m1), then by image,
Sound and/or word are sent to the new other users in (m1-n1) × 3 every a time period h2, until what server received
During artificial cognition total quantity N >=(50% × m1), execution step（5）；Wherein m1 >=100.
5. a kind of recognition methodss based on big data process according to claim 5 it is characterised in that：H1 is 5min, h2
For 30s.
6. a kind of recognition methodss based on big data process according to claim 1 it is characterised in that：Described step（2）
In, the content of contrast identification is included belonging to recognition of face, speech recognition, Text region, the title of things and/or sound in image
The title of things.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610849018.8A CN106446165A (en) | 2016-09-26 | 2016-09-26 | Big data processing based identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610849018.8A CN106446165A (en) | 2016-09-26 | 2016-09-26 | Big data processing based identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106446165A true CN106446165A (en) | 2017-02-22 |
Family
ID=58169342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610849018.8A Pending CN106446165A (en) | 2016-09-26 | 2016-09-26 | Big data processing based identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446165A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539253A (en) * | 2020-09-18 | 2021-10-22 | 厦门市和家健脑智能科技有限公司 | Audio data processing method and device based on cognitive assessment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763662A (en) * | 2005-06-10 | 2010-06-30 | 埃森哲环球服务有限公司 | Electronic toll management |
| US20100215277A1 (en) * | 2009-02-24 | 2010-08-26 | Huntington Stephen G | Method of Massive Parallel Pattern Matching against a Progressively-Exhaustive Knowledge Base of Patterns |
| CN102354366A (en) * | 2011-09-23 | 2012-02-15 | 上海合合信息科技发展有限公司 | Network based image recognition method and system |
| CN104346616A (en) * | 2013-08-09 | 2015-02-11 | 北大方正集团有限公司 | Character recognition device and character recognition method |
-
2016
- 2016-09-26 CN CN201610849018.8A patent/CN106446165A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763662A (en) * | 2005-06-10 | 2010-06-30 | 埃森哲环球服务有限公司 | Electronic toll management |
| US20100215277A1 (en) * | 2009-02-24 | 2010-08-26 | Huntington Stephen G | Method of Massive Parallel Pattern Matching against a Progressively-Exhaustive Knowledge Base of Patterns |
| CN102354366A (en) * | 2011-09-23 | 2012-02-15 | 上海合合信息科技发展有限公司 | Network based image recognition method and system |
| CN104346616A (en) * | 2013-08-09 | 2015-02-11 | 北大方正集团有限公司 | Character recognition device and character recognition method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539253A (en) * | 2020-09-18 | 2021-10-22 | 厦门市和家健脑智能科技有限公司 | Audio data processing method and device based on cognitive assessment |
| CN113539253B (en) * | 2020-09-18 | 2024-05-14 | 厦门市和家健脑智能科技有限公司 | Audio data processing method and device based on cognitive assessment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930429A (en) | Music recommendation method and apparatus | |
| CN102339193A (en) | Voice control conference speed method and system | |
| CN105898584A (en) | Voice message feedback method and device and television set | |
| US11341959B2 (en) | Conversation sentiment identifier | |
| CN109685301A (en) | Method for managing resource, device, equipment and readable storage medium storing program for executing | |
| CN106775948A (en) | A kind of cloud method for scheduling task and device based on priority | |
| CN111223487B (en) | Information processing method and electronic equipment | |
| CN110286838A (en) | Processing method, device, terminal and the storage medium of session object | |
| US10437830B2 (en) | Method and apparatus for identifying media files based upon contextual relationships | |
| CN105721222A (en) | Method and system for classifying music contents and providing special sound effects | |
| CN106446165A (en) | Big data processing based identification method | |
| CN109783678B (en) | Image searching method and device | |
| EP3582158A1 (en) | Dialog device, control device, dialog system, dialog method, and control method | |
| CN102902574A (en) | Cooperative processing method and device of multiple information flow nodes | |
| WO2023193717A1 (en) | Group chat session management method and apparatus, electronic device and readable storage medium | |
| CN108769730B (en) | Video playing method and device, computing equipment and storage medium | |
| US8654942B1 (en) | Multi-device video communication session | |
| CN112256844A (en) | Text classification method and device | |
| CN105653533A (en) | Method and device for updating classified associated word set | |
| CN106998386A (en) | The method and its device, user terminal of a kind of newly-increased contact method | |
| US11275862B2 (en) | Data processing apparatus for assigning an access right to a file linked in a message | |
| CN108881479B (en) | Integrated message queue and message management method | |
| CN101706931A (en) | Method and equipment for processing accounts in multi-mode information interaction mode | |
| CN106326010B (en) | A kind of control plays the method and intelligent sound box of synchronization | |
| CN111191063A (en) | Picture classification method and device, terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |