CN109214011A - It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection - Google Patents
It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection Download PDFInfo
- Publication number
- CN109214011A CN109214011A CN201811094264.2A CN201811094264A CN109214011A CN 109214011 A CN109214011 A CN 109214011A CN 201811094264 A CN201811094264 A CN 201811094264A CN 109214011 A CN109214011 A CN 109214011A
- Authority
- CN
- China
- Prior art keywords
- result
- engine
- user feedback
- perfection
- selection strategy
- 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
- 230000001149 cognitive effect Effects 0.000 title claims abstract description 16
- 230000005484 gravity Effects 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/51—Translation evaluation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of by user feedback come the cognitive engine selection strategy of self-perfection, and user can feed back and score for the result translated every time；Server can acquire the delay data of each business；There is a corresponding Engine Listing supported for every kind of language, all engines meet accident specific gravity all having the same；The specific gravity of engine is adjusted for the result of daily user feedback；The specific gravity of engine is adjusted for the delay data of engine；Each business all selects the engine of highest priority to carry out；Step 1 is on translation machine equipment, user can feed back for the result, the result of text translation and the result of TTS of identification, solving accurately to be controlled, most true result can not be obtained by the subjective judgement of a few peoples, manual switching simultaneously can all have certain delay, it corrects engine switchover policy automatically by data analysis and user feedback, and carries out engine switching on suitable opportunity, be easy to use by users.
Description
Technical field
The present invention relates to a kind of by user feedback come the cognitive engine selection strategy of self-perfection, in particular to one kind is logical
The cognitive engine selection strategy that user feedback carrys out self-perfection is crossed, translation engine technical field is belonged to.
Background technique
Translation is that a kind of language message is transformed into another language message on the basis of accurate (letter), clear and coherent (reaching)
Behavior.Translation is that a kind of relatively strange expression way is converted into the process of relatively known expression way.Have in it
Language, text, figure, symbol and video translation.Wherein, in first language and second language, the conversion for both language that " turning over " refers to,
A first language is first converted to a second language, a second language is then converted to first language again；" translating " refers to that both language turn
First language is converted into second language by the process changed, and in the text for being translated into local language, and then understands the meaning of second language.The two is constituted
Translation in general sense, allows more people to understand the meaning of other language.In order to guarantee the quality of translation, translator backstage one
As can all access multiple translation engines, and the selection strategy of translation engine and switchover policy are all to rely on artificial complete at present.
Advantage: background logic realizes that simply disadvantage: can not accurately be controlled, and can not be obtained most by the subjective judgement of a few peoples
Really as a result, manual switching simultaneously can all have certain delay.
Summary of the invention
The invention proposes a kind of by user feedback come the cognitive engine selection strategy of self-perfection, solves existing skill
It can not accurately be controlled, can not be obtained by the subjective judgement of a few peoples most true as a result, manual switching simultaneously in art
Will there are problems that certain delay.
In order to solve the above-mentioned technical problems, the present invention provides the following technical solutions:
The present invention it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, the selection strategy include with
Lower step；
Step 1: user can feed back and score for the result translated every time；
Step 2: server can acquire the delay data of each business；
Step 3: there is the corresponding Engine Listing supported for every kind of language, all engines meet accident all having the same
Specific gravity；
Step 4: the specific gravity of engine is adjusted for the result of daily user feedback；
Step 5: the specific gravity of engine is adjusted for the delay data of engine；
Step 6: each business all selects the engine of highest priority to carry out.
As a preferred technical solution of the present invention, the step 1 and step 2 are data source process.
It is described Step 3: Step 4: step 5 and step 6 are that strategy is excellent as a preferred technical solution of the present invention
Change process.
As a preferred technical solution of the present invention, the result that the step 1 is translated every time includes recognition result, text
This translation result, speech synthesis result.
As a preferred technical solution of the present invention, for the step 1 on translation machine equipment, user can be for knowledge
The result of other result, the result of text translation and TTS is fed back.
As a preferred technical solution of the present invention, identify, translate in each business of step 2 collection of server,
The delay data of synthesis.
The beneficial effects obtained by the present invention are as follows being: it is of the invention it is a kind of by user feedback come the cognitive engine of self-perfection
Selection strategy is solved and can not accurately be controlled, and can not be obtained by the subjective judgement of a few peoples most true as a result, same
When manual switching can all there are problems that certain delay, by data analysis and user feedback come automatically correct engine switching plan
Slightly, and on suitable opportunity engine switching is carried out, be easy to use by users.
Specific embodiment
The preferred embodiment of the present invention is illustrated, it should be understood that preferred embodiment described herein is merely to illustrate
It is of the invention with explaining, it is not intended to limit the present invention.
Embodiment 1
The present invention provide it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, the production method packet
Include following steps；
Step 1: user can feed back and score for the result translated every time；
Step 2: server can acquire the delay data of each business；
Step 3: there is the corresponding Engine Listing supported for every kind of language, all engines meet accident all having the same
Specific gravity；
Step 4: the specific gravity of engine is adjusted for the result of daily user feedback；
Step 5: the specific gravity of engine is adjusted for the delay data of engine；
Step 6: each business all selects the engine of highest priority to carry out.
The step 1 and step 2 are data source process, described Step 3: Step 4: step 5 and step 6 are plan
Slightly Optimizing Flow, the result that the step 1 is translated every time includes recognition result, text translation result, speech synthesis as a result, institute
Step 1 is stated on translation machine equipment, user can carry out for the result, the result of text translation and the result of TTS of identification
It feeds back, the delay data of identification, translation, synthesis in each business of step 2 collection of server.
A kind of solve by user feedback come the cognitive engine selection strategy of self-perfection of the invention can not carry out essence
Quasi- control can not obtain most true as a result, manual switching simultaneously can all exist centainly by the subjective judgement of a few peoples
The problem of delay, corrects engine switchover policy automatically by data analysis and user feedback, and is drawn on suitable opportunity
Switching is held up, is easy to use by users.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention,
Although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art, still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features.
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention
Within protection scope.
Claims (6)
1. it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, which is characterized in that the selection strategy packet
Include following steps；
Step 1: user can feed back and score for the result translated every time；
Step 2: server can acquire the delay data of each business；
Step 3: having a corresponding Engine Listing supported for every kind of language, and all engines meet accident specific gravity all having the same；
Step 4: the specific gravity of engine is adjusted for the result of daily user feedback；
Step 5: the specific gravity of engine is adjusted for the delay data of engine；
Step 6: each business all selects the engine of highest priority to carry out.
2. it is according to claim 1 it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, feature
It is, the step 1 and step 2 are data source process.
3. it is according to claim 1 it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, feature
It is, it is described Step 3: Step 4: step 5 and step 6 are policy optimization process.
4. it is according to claim 1 it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, feature
It is, the result that the step 1 is translated every time includes recognition result, text translation result, speech synthesis result.
5. it is according to claim 1 it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, feature
It is, for the step 1 on translation machine equipment, user can be for the result of identification, the result of text translation and TTS
As a result it is fed back.
6. it is according to claim 1 it is a kind of by user feedback come the cognitive engine selection strategy of self-perfection, feature
It is, identifies, translates in each business of step 2 collection of server, the delay data of synthesis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811094264.2A CN109214011A (en) | 2018-09-19 | 2018-09-19 | It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811094264.2A CN109214011A (en) | 2018-09-19 | 2018-09-19 | It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214011A true CN109214011A (en) | 2019-01-15 |
Family
ID=64984828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811094264.2A Pending CN109214011A (en) | 2018-09-19 | 2018-09-19 | It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214011A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866406A (en) * | 2019-11-15 | 2020-03-06 | 上海醍顶信息科技有限公司 | Translation integration service optimization method, electronic device and storage medium |
| WO2021072649A1 (en) * | 2019-10-15 | 2021-04-22 | 深圳市欢太科技有限公司 | Translation method and apparatus, client, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| US20140358524A1 (en) * | 2011-11-03 | 2014-12-04 | Rex Partners Oy | Machine translation quality measurement |
| CN106021239A (en) * | 2016-04-29 | 2016-10-12 | 北京创鑫旅程网络技术有限公司 | Method for real-time evaluation of translation quality |
| CN107894983A (en) * | 2017-11-08 | 2018-04-10 | 深圳市沃特沃德股份有限公司 | The switching method and device of engine |
| CN108319591A (en) * | 2018-02-05 | 2018-07-24 | 深圳市沃特沃德股份有限公司 | Realize the method, apparatus and speech translation apparatus of voiced translation |
-
2018
- 2018-09-19 CN CN201811094264.2A patent/CN109214011A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358524A1 (en) * | 2011-11-03 | 2014-12-04 | Rex Partners Oy | Machine translation quality measurement |
| CN104168318A (en) * | 2014-08-18 | 2014-11-26 | 中国联合网络通信集团有限公司 | Resource service system and resource distribution method thereof |
| CN106021239A (en) * | 2016-04-29 | 2016-10-12 | 北京创鑫旅程网络技术有限公司 | Method for real-time evaluation of translation quality |
| CN107894983A (en) * | 2017-11-08 | 2018-04-10 | 深圳市沃特沃德股份有限公司 | The switching method and device of engine |
| CN108319591A (en) * | 2018-02-05 | 2018-07-24 | 深圳市沃特沃德股份有限公司 | Realize the method, apparatus and speech translation apparatus of voiced translation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021072649A1 (en) * | 2019-10-15 | 2021-04-22 | 深圳市欢太科技有限公司 | Translation method and apparatus, client, server and storage medium |
| CN110866406A (en) * | 2019-11-15 | 2020-03-06 | 上海醍顶信息科技有限公司 | Translation integration service optimization method, electronic device and storage medium |
| CN110866406B (en) * | 2019-11-15 | 2023-08-15 | 上海醍顶信息科技有限公司 | Translation integration service optimization method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104504150B (en) | News public sentiment monitoring system | |
| CN102194005B (en) | Chat robot system and automatic chat method | |
| CN109214011A (en) | It is a kind of by user feedback come the cognitive engine selection strategy of self-perfection | |
| CN107239538B (en) | Parallel customer service robot system with self-learning function and self-learning method thereof | |
| CN105573994B (en) | Statictic machine translation system based on syntax skeleton | |
| CN103365836A (en) | Natural language utilized distributed intelligent interaction achieving method and system thereof | |
| CN109858357A (en) | A kind of gesture identification method and system | |
| CN107402933A (en) | Entity polyphone disambiguation method and entity polyphone disambiguation equipment | |
| CN109891411A (en) | A kind of speech convertor | |
| CN112148874A (en) | Intention identification method and system capable of automatically adding potential intention of user | |
| CN209657301U (en) | A kind of intelligent translation machine | |
| CN106484660A (en) | Title treating method and apparatus | |
| CN202815832U (en) | Realizing system of distributed intelligent interaction with natural language | |
| CN112270166A (en) | Method for quickly making and creating 5G message | |
| CN104423353A (en) | Method for centrally and coordinatively controlling household appliances on spot by using Chinese speech | |
| Bou-Franch | Communication strategies and topic sequences in the conversational discourse of Spanish learners of English | |
| Gasch-Tomás | The Atlantic World and the Manila Galleons | |
| Wang et al. | Generating valid and natural adversarial examples with large language models | |
| CN106383820A (en) | Foreign text reader | |
| CN101625598A (en) | Technique for Chinese character coding and keyboard input in accordance with character principles | |
| CN106126500B (en) | A kind of statistical method being associated with hot word | |
| CN110413636A (en) | A kind of data processing method and device | |
| Peters | ‘Did you see what your ancestors gave you but your doctor failed to give you?’: Cultural conceptualisations of ancestral communication in Black South African English | |
| EP3928245A1 (en) | Device and method for automatic translation of weather reports into a sign language | |
| CN108630194A (en) | One kind being based on the Sichuan accent of GSP algorithm translations and Italian simultaneous interpretation case |
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: 20190115 |