CN102073629A - Computer translation system and method - Google Patents
Computer translation system and method Download PDFInfo
- Publication number
- CN102073629A CN102073629A CN2009102261363A CN200910226136A CN102073629A CN 102073629 A CN102073629 A CN 102073629A CN 2009102261363 A CN2009102261363 A CN 2009102261363A CN 200910226136 A CN200910226136 A CN 200910226136A CN 102073629 A CN102073629 A CN 102073629A
- Authority
- CN
- China
- Prior art keywords
- character string
- language character
- database
- universal networking
- machine translation
- 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
Images
Landscapes
- Machine Translation (AREA)
Abstract
The invention relates to a computer translation system and method. The computer translation method comprises the following steps of: firstly, receiving a first language character string; secondly, converting the first language character string into a first general network language character string; thirdly, searching a database to retrieve at least one second general network language character string similar to the first general network language character string; and fourthly, acquiring a corresponding second language character string from the database according to the second general network language character string.
Description
Technical field
The present invention relates to a kind of machine translation and get system and machine translation method, and be particularly related to a kind of machine translation system and machine translation method with human translation resource.
Background technology
If utilize the mode of translation machine to translate, normally a certain language conversion is become another kind of language, and when translation machine is translated a longer character string, can't obtain the translation result of sentence meaning.If when utilizing existing translation engine to translate, though can be multilingual with a certain language conversion, translating by translation engine be employing mechanical translation, has the situation of distortion.If utilize the mode of human translation to translate, though then the translation result behind its human translation can to press close to the sentence meaning comparatively accurate, can't be shared or utilize again.
Summary of the invention
Present invention is directed to a kind of machine translation system and machine translation method thereof, it provides the result who carries out human translation to come the accuracy rate of translating with increase for searching (that is pressing close to the sentence meaning), and also can provide each simultaneously corresponding to multi-lingual translation result, to allow the user select according to its demand.
According to an aspect of the present invention, a kind of machine translation system is proposed.The machine translation method comprises the following steps.At first, receive a first language character string.Then, will change this first language character string is one first Universal Networking Language (Universal Networking Language) character string.Afterwards, search a database, to capture at least one second Universal Networking Language character string that is similar to this first Universal Networking Language character string.Then, according to the second Universal Networking Language character string, obtain a corresponding second language character string from database.
According to a further aspect in the invention, propose a kind of machine translation system, comprise database, receiving element, converting unit and search the unit.Receiving element is in order to receive a first language character string.Converting unit is the first Universal Networking Language character string in order to conversion first language character string.Search the unit in order to searching database, capturing at least one second Universal Networking Language character string that is similar to the first Universal Networking Language character string, and in database, obtain the second language character string of the corresponding second logical fortune netspeak character string.
Effect of the present invention is, the above embodiment of the present invention disclosed machine translation system and machine translation method thereof, be to utilize to search database to capture the second language character string that is relevant to the first language character string, to obtain translation result (second language character string).Machine translation system that present embodiment is relevant and machine translation method thereof have and can translate the advantage that character string (first language character string) obtains corresponding a plurality of second language character strings (corresponding to a state or multi-lingual) according to desire, can be from corresponding to selecting required translation result (second language character string) the multinational second language character string for the user, and (in the database) searches the relevant character string to translate from the character string of human translation, is that higher accuracy and the translation result of pressing close to the sentence meaning can be provided.
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
Description of drawings
Fig. 1 illustrates the block scheme of the machine translation system of one embodiment of the invention;
Fig. 2 illustrates the process flow diagram of the machine translation method of one embodiment of the invention.
Wherein, Reference numeral
100: the machine translation system
70: search the unit
50: converting unit
30: receiving element
10: database
S202～S208: process step
Embodiment
Below in conjunction with accompanying drawing structural principle of the present invention and principle of work are done concrete description:
Please refer to Fig. 1, it illustrates the block scheme of the machine translation system of one embodiment of the invention.As shown in Figure 1, machine translation system 100 comprises database 10, receiving element 30, converting unit 50 and searches unit 70.The translation result that database 10 stores by human translation.For instance, for example the information (for example be Chinese from English Translation) of foreign books after carrying out human translation can be stored in the database 10, also Universal Networking Language (the Universal Networking Language) character string with correspondence stores it.Receiving element 30 for example is user's input interface.In an example, user's input interface is to be button or Touch Screen (Touch Panel), to receive the information that the user was imported (for example desire translate character string).Converting unit 50 for example is that the character string that will desire to translate is converted to corresponding Universal Networking Language character string.Search unit 70 in order to search database 10 to find out the information of desiring to translate character string that is relevant to.
As for above-mentioned each assembly how to carry out below the machine translation be the collocation flowchart text as follows.Certainly, those of ordinary skill should be understood in the art, and the machine translation method is not defined in the machine translation system 100 that is applied in shown in Fig. 1, and the step of machine translation method and the order also can modify and adjust according to the practical application situation.
Please refer to Fig. 2, it illustrates the process flow diagram of the machine translation method of one embodiment of the invention.At first, in step S202, receiving element 30 receives the first language character string.For instance, the first language character string for example can be corresponding to the one of a plurality of countries.For instance, suppose that the user is the Englishman, the first language character string that receiving element 30 is received may be English.Certainly, if the user has multi-lingual ability, the first language character string also may be other national language.Be to be that English is that example is done explanation with the first language character string herein, right, also can design according to user's demand and adjust among the Yu Shizuo, be not restriction with this example.
In step S204, converting unit 50 conversion first language character strings are the first Universal Networking Language character string.For instance, suppose that the first language character string is " Blue Sky " (for example for English), after converting unit 50 conversions, the first Universal Networking Language character string for example be " blue (and icl＞color), sky (icl＞atmosphere＞thing) ".In this step, first Universal Networking Language character string system changes the first language character string automatically by a computing machine and obtains.
In step S206, search unit 70 and search database 10, to capture at least one second Universal Networking Language character string that is similar to the first Universal Networking Language character string.For instance, have a plurality of second language character strings in the database 10, each second language character string is a corresponding language form (for example Chinese, Japanese, a Korean), and each second language character string is corresponding to one second Universal Networking Language character string.The second language character string is by being stored in behind the human translation in the database 10.In this, search unit 70 and can in database 10, search the second Universal Networking Language character string that is similar to the first Universal Networking Language character string.
In step S208, search unit 70 according to the second Universal Networking Language character string, obtain corresponding second language character string from database 10.For instance, suppose and search the second Universal Networking Language character string that unit 70 searches three approximate first Universal Networking Language character strings, these three character strings for example be all " blue (and icl＞color); sky (icl＞atmosphere＞thing) ", search unit 70 this moment and understand these a little pen second Universal Networking Language character strings according to each, from database 10, obtain corresponding second language character string, for example be " blue sky " (corresponding to Chinese), " Block Le one ス カ ィ " (corresponding to Japanese) and
(corresponding to Korean).
For instance, database 10 has the character string (corresponding to multi-lingual) via human translation, and corresponding to the Universal Networking Language character string of these a little character strings, so the obtainable second language character string that is relevant to first language character string (Blue Sky) for example is that blue sky, Block Le one ス カ ィ reach
In this, except the translation result (that is second language character string) of a plurality of category of language (for example Taiwan, Japan, Korea S, Britain) about the first language character string can be provided, it also can be from the character string after carrying out human translation (database), hunt out corresponding translation result, thereby obtain high accuracy and press close to the translation of the meaning of one's words.
Further, the degree of approximation of these a little second Universal Networking Language character strings and the first Universal Networking Language character string is greater than a predetermined value.For instance, suppose search the second universal network character string that unit 70 searched for example for " blue (and icl＞color); cat (icl＞feline＞thing) ", the first Universal Networking Language character string in the step S204 (" blue (icl＞color); sky (icl＞atmosphere＞thing) "), the second, has a different place between the first Universal Networking Language character string, for example be " cat (icl＞feline＞thing) ", and this different place is relevant with degree of approximation.
For instance, the different place between first, second Universal Networking Language character string is many more, then represents the degree of approximation of second, the first Universal Networking Language character string more little.Relative, if the different place between first, second Universal Networking Language character string is few more, then represent the degree of approximation of second, the first Universal Networking Language character string big more, that is accuracy is high more.In addition, the user also can design and adjust this predetermined value according to actual conditions except can obtaining the high second language character string of accuracy.Suppose that predetermined value is 80%, can obtain other is second language character string more than 80% similar in appearance to first language character string and degree of approximation.
In an example, receiving element 10 for example can be provided with in the portable electronic devices (not illustrating) with converting unit 30.Portable electronic devices for example be mobile phone, numeral with oneself the assistant (Personal Digital Assistance, PDA), intelligent mobile phone.Database 10 and 70 of unit of search for example are arranged in the remote server.
For instance, the user can transfer to the first Universal Networking Language character string (corresponding to the first language character string) in the remote server by portable electronic devices, if the search unit 70 of remote server has searched the second corresponding Universal Networking Language character string, at this moment, portable electronic devices can be obtained second language character string (translation back character string) according to the second Universal Networking Language character string.
The above embodiment of the present invention disclosed machine translation system and machine translation method thereof are to utilize to search database to capture the second language character string that is relevant to the first language character string, to obtain translation result (second language character string).Machine translation system that present embodiment is relevant and machine translation method thereof have and can translate the advantage that character string (first language character string) obtains corresponding a plurality of second language character strings (corresponding to a state or multi-lingual) according to desire, can be from corresponding to selecting required translation result (second language character string) the multinational second language character string for the user, and (in the database) searches the relevant character string to translate from the character string of human translation, is that higher accuracy and the translation result of pressing close to the sentence meaning can be provided.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.
Claims (10)
1. a machine translation method is characterized in that, comprising:
Receive a first language character string;
Changing this first language character string is one first Universal Networking Language character string;
Search a database, to capture at least one second Universal Networking Language character string that is similar to this first Universal Networking Language character string; And
According to this second Universal Networking Language character string, obtain a corresponding second language character string from this database.
2. machine translation method according to claim 1 is characterized in that, searches in the step of this second Universal Networking Language character string, and the degree of approximation of this second Universal Networking Language character string and this first Universal Networking Language character string is greater than a predetermined value.
3. machine translation method according to claim 2 is characterized in that, this first Universal Networking Language character string is to change this first language character string automatically by a computing machine to obtain.
4. machine translation method according to claim 2 is characterized in that, this second language character string is by being stored in this database behind the human translation.
5. a machine translation system is characterized in that, comprising:
One database;
One receiving element is in order to receive a first language character string;
One converting unit is one first Universal Networking Language character string in order to change this first language character string; And
One searches the unit, in order to search this database, capturing at least one second Universal Networking Language character string that is similar to this first Universal Networking Language character string, and obtain in this database certainly a second language character string that should the second Universal Networking Language character string.
6. machine translation system and device according to claim 5 is characterized in that, the degree of approximation of this second Universal Networking Language character string and this first Universal Networking Language character string is greater than a predetermined value.
7. machine translation according to claim 6 system is characterized in that this first Universal Networking Language character string is to change this first language character string automatically by a computing machine to obtain.
8. machine translation according to claim 6 system is characterized in that this second language character string is by being stored in behind the human translation in this database.
9. machine translation according to claim 6 system is characterized in that this receiving element and this converting unit are for being provided with in the portable electronic devices.
10. machine translation according to claim 6 system is characterized in that this database and this search unit are for being arranged in the remote server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102261363A CN102073629A (en) | 2009-11-20 | 2009-11-20 | Computer translation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102261363A CN102073629A (en) | 2009-11-20 | 2009-11-20 | Computer translation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102073629A true CN102073629A (en) | 2011-05-25 |
Family
ID=44032174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102261363A Pending CN102073629A (en) | 2009-11-20 | 2009-11-20 | Computer translation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102073629A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105338161A (en) * | 2014-06-30 | 2016-02-17 | 展讯通信（上海）有限公司 | Statement information matching system, method and mobile terminal |
| CN107402918A (en) * | 2017-06-19 | 2017-11-28 | 上海青橙实业有限公司 | The character string translation processing method and device of electric terminal |
| CN107430598A (en) * | 2015-03-18 | 2017-12-01 | 三菱电机株式会社 | Multilingual translation device and multi-language translation method |
-
2009
- 2009-11-20 CN CN2009102261363A patent/CN102073629A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105338161A (en) * | 2014-06-30 | 2016-02-17 | 展讯通信（上海）有限公司 | Statement information matching system, method and mobile terminal |
| CN107430598A (en) * | 2015-03-18 | 2017-12-01 | 三菱电机株式会社 | Multilingual translation device and multi-language translation method |
| CN107402918A (en) * | 2017-06-19 | 2017-11-28 | 上海青橙实业有限公司 | The character string translation processing method and device of electric terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101000623A (en) | Method for image identification search by mobile phone photographing and device using the method | |
| WO2009056920A1 (en) | System and method for input of text to an application operating on a device | |
| CN102520843A (en) | Input method used for collecting image as candidate item and system | |
| CN101539836A (en) | Human-machine interface interactive system and method | |
| CN106384108A (en) | Text content retrieval method, word interpreting device and mobile terminal | |
| CN103186574A (en) | Method and device for generating searching result | |
| CN101853297A (en) | Method for fast obtaining expected image in electronic equipment | |
| WO2010124511A1 (en) | Intelligent operating system and method | |
| CN101651938A (en) | Telephone number recognition system for mobile terminal and application method thereof | |
| CN107885826A (en) | Method for broadcasting multimedia file, device, storage medium and electronic equipment | |
| CN102929994A (en) | Method and device for adding remarks | |
| CN103279262A (en) | Method and device for extracting content from image | |
| CN100456293C (en) | Information fast searching device, client end, system and method | |
| CN102073629A (en) | Computer translation system and method | |
| Cemerlang et al. | Towards automatic mobile blogging | |
| CN102436458A (en) | Command analyzing method and system | |
| CN101777067B (en) | System for recognizing and managing web page contents for mobile communication equipment terminals | |
| CN102567121B (en) | Realize the method and apparatus of converged communication | |
| Vicente et al. | Astrometry with carte du ciel plates, san fernando zone-i. digitization and measurement using a flatbed scanner | |
| JP2014137654A (en) | Translation system and translation method thereof | |
| CN110955752A (en) | Information display method and device, electronic equipment and computer storage medium | |
| CN101324906A (en) | Apparatus and method capable of searching across data bases | |
| Chies-Santos et al. | High resolution imaging of the early-type galaxy NGC 1380: an insight into the nature of extended extragalactic star clusters | |
| JP7464462B2 (en) | Human-computer interaction method and device | |
| CN113359998B (en) | Information query method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110525 |