CN118278427A - Translation optimization method, translation method, electronic device, and readable storage medium - Google Patents
Translation optimization method, translation method, electronic device, and readable storage medium Download PDFInfo
- Publication number
- CN118278427A CN118278427A CN202211743193.0A CN202211743193A CN118278427A CN 118278427 A CN118278427 A CN 118278427A CN 202211743193 A CN202211743193 A CN 202211743193A CN 118278427 A CN118278427 A CN 118278427A
- Authority
- CN
- China
- Prior art keywords
- translation
- translation result
- candidate
- preset
- content
- 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
- 238000013519 translation Methods 0.000 title claims abstract description 1626
- 238000005457 optimization Methods 0.000 title claims abstract description 161
- 238000000034 method Methods 0.000 title claims abstract description 126
- 230000000875 corresponding effect Effects 0.000 claims description 475
- 238000006243 chemical reaction Methods 0.000 claims description 134
- 238000004590 computer program Methods 0.000 claims description 21
- 230000002596 correlated effect Effects 0.000 claims description 8
- 230000014616 translation Effects 0.000 description 1430
- 238000004891 communication Methods 0.000 description 36
- 230000006854 communication Effects 0.000 description 36
- 238000011156 evaluation Methods 0.000 description 36
- 230000006870 function Effects 0.000 description 25
- 239000010410 layer Substances 0.000 description 18
- 230000008569 process Effects 0.000 description 15
- 238000012545 processing Methods 0.000 description 14
- 230000005236 sound signal Effects 0.000 description 13
- 230000000694 effects Effects 0.000 description 12
- 238000010295 mobile communication Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000012937 correction Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 229920001621 AMOLED Polymers 0.000 description 2
- 230000003416 augmentation Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 239000012792 core layer Substances 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000002096 quantum dot Substances 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The application is suitable for the technical field of terminals, and particularly relates to a translation optimization method, a translation method, electronic equipment and a readable storage medium. In the method, the electronic device can acquire a first candidate translation result corresponding to the preset content translated by the first machine translation service, and can automatically determine the translation quality of the first candidate translation result so as to identify a translation result with poor translation quality of the first machine translation service. For the translation result with poor translation quality of the first machine translation service, the electronic device can automatically call the second machine translation service to translate the preset content, so that the translation result with poor translation quality of the first machine translation service is automatically optimized through the second candidate translation result obtained by the second machine translation service, the accuracy of the translation result corresponding to the preset content can be ensured, the identification and optimization of the translation result do not need to be manually carried out, the efficiency of optimizing the translation result can be effectively improved, and the user experience is improved.
Description
Technical Field
The application belongs to the technical field of terminals, and particularly relates to a translation optimization method, a translation method, electronic equipment and a readable storage medium.
Background
In the use process of electronic devices, it is often required to translate one language into another language, for example, in a cross-border e-commerce scenario, a multi-language e-commerce website generally takes english as an index, that is, when the content input by a user is not english, the e-commerce website may call a certain machine translation service to translate the content input by the user into english, and then the e-commerce website may search for a target according to the translated english by a search engine and display the searched target in a page for selection by the user. The machine translation service has the problem of poor translation accuracy, and the current machine translation cannot automatically identify and optimize a poor translation result, so that user experience is greatly influenced.
Disclosure of Invention
The embodiment of the application provides a translation optimization method, a translation method, electronic equipment and a computer readable storage medium, which can automatically identify and optimize a translation result with poor translation of a machine translation service, thereby improving the accuracy of the machine translation and improving the user experience.
In a first aspect, an embodiment of the present application provides a translation optimization method, which is applied to an electronic device, where a first machine translation service is provided, and the method may include:
Acquiring a first candidate translation result, wherein the first candidate translation result is a translation result acquired through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is content expressed in a first language, the first candidate translation result is content expressed in a second language, and the first language is different from the second language;
determining the translation quality of the first candidate translation result;
When the translation quality of the first candidate translation result does not meet a first preset condition, at least one second candidate translation result corresponding to the preset content is obtained through at least one second machine translation service, wherein the second machine translation service is different from the first machine translation service;
And determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
In the above translation optimizing method, the electronic device may obtain a first candidate translation result corresponding to the preset content translated by the first machine translation service, and may automatically determine the translation quality of the first candidate translation result, so as to identify a translation result with poor translation quality of the first machine translation service. For the translation result with poor translation quality of the first machine translation service, the electronic device can automatically call the second machine translation service to translate the preset content, so that the translation result with poor translation quality of the first machine translation service is automatically optimized through the second candidate translation result obtained by the second machine translation service, the accuracy of the translation result corresponding to the preset content can be ensured, the identification and optimization of the translation result do not need to be manually carried out, the efficiency of optimizing the translation result can be effectively improved, and the user experience is improved.
Illustratively, the determining the translation quality of the first candidate translation result includes:
obtaining a conversion rate corresponding to the first candidate translation result, wherein the conversion rate corresponding to the first candidate translation result is the click rate of a target corresponding to the first candidate translation result within a preset duration;
And determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
Optionally, the determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result includes:
and when the conversion rate corresponding to the first candidate translation result is smaller than a first preset threshold value, determining that the translation quality of the first candidate translation result does not meet the first preset condition.
In the translation optimization method provided by the implementation manner, the electronic device can determine the preset content with high exposure (i.e. more translation times) and low conversion (i.e. lower conversion rate) according to the conversion rate, so that the preset content with high probability of translation errors (i.e. poor translation quality) can be rapidly determined to perform translation optimization, and the efficiency of translation optimization can be improved.
It should be appreciated that for the preset content, each of the second machine translation services corresponds to a translation result.
In one possible implementation manner, the determining, according to at least one second candidate translation result corresponding to the preset content, a target translation result corresponding to the preset content includes:
Determining a third candidate translation result with the largest number of the at least one second candidate translation result according to the translation result corresponding to each second machine translation service, wherein the third candidate translation result is one of the at least one second candidate translation result;
And when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
In the translation optimization method provided by the implementation manner, the electronic device can acquire the translation result with high probability and accuracy of the second machine translation service translation from the translation result corresponding to the second machine translation service through the voting mechanism, so that the translation optimization is performed on the first candidate translation result obtained by the first machine translation service translation, the accuracy of the translation result corresponding to the preset content can be effectively improved, and the user experience is improved.
Optionally, when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold, determining, according to the third candidate translation results, a target translation result corresponding to the preset content includes:
when the proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold value, determining whether the third candidate translation results are the same as the first candidate translation results;
and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
In the translation optimization method provided by the implementation manner, the electronic device may first determine whether the third candidate translation result is the same as the first candidate translation result. When the third candidate translation result is different from the first candidate translation result, the electronic device may determine a target translation result corresponding to the preset content according to the third candidate translation result. When the third candidate translation result is the same as the first candidate translation result, the electronic device may determine that the translation result obtained by the second machine translation service cannot optimize the first candidate translation result obtained by the first machine translation service, so the electronic device may not optimize the first candidate translation result according to the result obtained by the translation of the second machine translation service, so as to ensure the validity of the target translation result and ensure the effect of translation optimization.
Optionally, the determining, according to the third candidate translation result, the target translation result corresponding to the preset content includes:
Obtaining a conversion rate corresponding to the third candidate translation result;
And when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
In the translation optimization method provided by the implementation manner, the electronic device can determine the accuracy of the third candidate translation result according to the conversion rate corresponding to the third candidate translation result in the specified time period, so that whether the third candidate translation result needs to be determined as the target translation result corresponding to the preset content is determined, the accuracy of the target translation result corresponding to the preset content is ensured, the translation optimization effect is ensured, and the user experience is improved.
In one example, after the determining the target translation result corresponding to the preset content, the method further includes:
and storing the preset content and the target translation result corresponding to the preset content in a preset intervention table in a correlated mode.
In another example, the method further comprises:
acquiring a translation request, wherein the translation request is used for requesting to translate content to be translated into content expressed in a second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
When the preset intervention table is determined to comprise the content to be translated, acquiring a target translation result corresponding to the content to be translated from the preset intervention table, wherein the target translation result corresponding to the content to be translated is the content expressed by the second language;
And when the preset intervention table does not contain the content to be translated, acquiring a target translation result corresponding to the content to be translated through the first machine translation service.
In the translation optimizing method provided by the implementation manner, after the target translation result corresponding to the preset content is determined, the electronic device can store the preset content and the target translation result corresponding to the preset content in the preset intervention table in a correlated manner, so that when the preset content is translated through the first machine translation service, the accurate target translation result corresponding to the preset content can be obtained directly according to the preset intervention table, and the translation accuracy is improved.
In a second aspect, an embodiment of the present application provides a translation method, applied to an electronic device, where a first machine translation service is provided in the electronic device, the method includes:
acquiring a translation request, wherein the translation request is used for requesting to translate content to be translated into content expressed in a second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
When the content to be translated is determined to be included in a preset intervention table, a target translation result corresponding to the content to be translated is obtained from the preset intervention table, the target translation result corresponding to the content to be translated is content represented by a second language, the second language is different from the first language, the content represented by the first language and the corresponding content represented by the second language are included in the preset intervention table, the content represented by the first language included in the preset intervention table is content, the translation quality obtained by the first machine translation service does not meet a first preset condition, the content represented by the second language included in the preset intervention table is obtained by at least one second machine translation service, and the second machine translation service is different from the first machine translation service;
And when the preset intervention table does not contain the content to be translated, acquiring a target translation result corresponding to the content to be translated through the first machine translation service.
In the above translation method, when the electronic device obtains a translation request, the translation request is used for requesting that the content to be translated, which is represented by the first language, be translated into the content in the second language by the first machine translation service, the electronic device may first determine whether the preset intervention table includes the content to be translated. When the preset intervention table comprises the content to be translated, the electronic equipment can directly acquire the target translation result corresponding to the content to be translated from the preset intervention table, namely, the target translation result with better translation quality can be directly acquired from the preset intervention table, and the content to be translated does not need to be translated through the first machine translation service, so that the acquisition of the translation result with poorer translation quality can be avoided, the accuracy of the translation result corresponding to the content to be translated is effectively improved, and the user experience is improved.
In one possible implementation, before determining that the content to be translated is included in the preset intervention table, the method further includes:
Acquiring a first candidate translation result, wherein the first candidate translation result is a translation result acquired through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is the content expressed by the first language, and the first candidate translation result is the content expressed by the second language;
determining the translation quality of the first candidate translation result;
When the translation quality of the first candidate translation result does not meet the first preset condition, at least one second candidate translation result corresponding to the preset content is obtained through at least one second machine translation service;
Determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content;
and storing the preset content and the target translation result corresponding to the preset content in the preset intervention table in a correlated mode.
Optionally, the determining the translation quality of the first candidate translation result includes:
obtaining a conversion rate corresponding to the first candidate translation result, wherein the conversion rate corresponding to the first candidate translation result is the click rate of a target corresponding to the first candidate translation result within a preset duration;
And determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
Illustratively, the determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result includes:
and when the conversion rate corresponding to the first candidate translation result is smaller than a first preset threshold value, determining that the translation quality of the first candidate translation result does not meet the first preset condition.
It should be appreciated that for the preset content, each of the second machine translation services corresponds to a translation result.
In one example, the determining, according to the at least one second candidate translation result corresponding to the preset content, the target translation result corresponding to the preset content includes:
determining the third candidate translation result with the largest number from the at least one second candidate translation result according to the translation result corresponding to each second machine translation service, wherein the third candidate translation result is one of the at least one second candidate translation result;
And when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold, determining, according to the third candidate translation results, a target translation result corresponding to the preset content includes:
when the proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold value, determining whether the third candidate translation results are the same as the first candidate translation results;
and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, the determining, according to the third candidate translation result, the target translation result corresponding to the preset content includes:
Obtaining a conversion rate corresponding to the third candidate translation result;
And when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
In a third aspect, an embodiment of the present application provides a translation optimization method, which is applied to an electronic device, where a first machine translation service is provided in the electronic device, and the apparatus may include:
The first candidate translation result obtaining module is used for obtaining a first candidate translation result, wherein the first candidate translation result is a translation result obtained through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is content expressed in a first language, the first candidate translation result is content expressed in a second language, and the first language is different from the second language;
a translation quality determining module, configured to determine a translation quality of the first candidate translation result;
The second candidate translation result obtaining module is used for obtaining at least one second candidate translation result corresponding to the preset content through at least one second machine translation service when the translation quality of the first candidate translation result does not meet a first preset condition, wherein the second machine translation service is different from the first machine translation service;
and the target translation result determining module is used for determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
The translation quality determining module is specifically configured to obtain a conversion rate corresponding to the first candidate translation result, where the conversion rate corresponding to the first candidate translation result is a click rate of a target corresponding to the first candidate translation result within a preset duration; and determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
Optionally, the translation quality determining module is further configured to determine that the translation quality of the first candidate translation result does not meet the first preset condition when the conversion rate corresponding to the first candidate translation result is smaller than a first preset threshold.
It should be appreciated that for the preset content, each of the second machine translation services corresponds to a translation result.
In a possible implementation manner, the target translation result determining module is specifically configured to determine, according to the translation results corresponding to each of the second machine translation services, a third candidate translation result with the largest number of the at least one second candidate translation results, where the third candidate translation result is one of the at least one second candidate translation results; and when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, the target translation result determining module is further configured to determine whether the third candidate translation result is the same as the first candidate translation result when a proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold; and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, the target translation result determining module is further configured to obtain a conversion rate corresponding to the third candidate translation result; and when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
In one example, the apparatus may further include:
and the translation result storage module is used for storing the preset content and the target translation result corresponding to the preset content in a preset intervention table in a correlated mode.
In another example, the apparatus further comprises:
The request acquisition module is used for acquiring a translation request, wherein the translation request is used for requesting to translate the content to be translated into the content expressed in the second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
The first translation module is used for acquiring a target translation result corresponding to the content to be translated from the preset intervention table when the content to be translated is determined to be included in the preset intervention table, wherein the target translation result corresponding to the content to be translated is the content expressed by the second language;
And the second translation module is used for acquiring a target translation result corresponding to the content to be translated through the first machine translation service when the content to be translated is not included in the preset intervention table.
In a fourth aspect, an embodiment of the present application provides a translation apparatus, which is applied to an electronic device, where a first machine translation service is provided, and the apparatus includes:
The request acquisition module is used for acquiring a translation request, wherein the translation request is used for requesting to translate the content to be translated into the content expressed in the second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
The first translation module is configured to obtain, when it is determined that the preset intervention table includes the content to be translated, a target translation result corresponding to the content to be translated from the preset intervention table, where the target translation result corresponding to the content to be translated is content represented by a second language, the second language is different from the first language, the preset intervention table includes content represented by the first language and content represented by the corresponding second language, the content represented by the first language included in the preset intervention table is content, the translation quality obtained by the first machine translation service does not meet a first preset condition, and the content represented by the second language included in the preset intervention table is obtained by at least one second machine translation service, where the second machine translation service is different from the first machine translation service;
And the second translation module is used for acquiring a target translation result corresponding to the content to be translated through the first machine translation service when the content to be translated is not included in the preset intervention table.
In one possible implementation, the apparatus further includes:
The first candidate translation result obtaining module is used for obtaining a first candidate translation result, wherein the first candidate translation result is a translation result obtained through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is the content represented by the first language, and the first candidate translation result is the content represented by the second language;
a translation quality determining module, configured to determine a translation quality of the first candidate translation result;
The second candidate translation result obtaining module is used for obtaining at least one second candidate translation result corresponding to the preset content through at least one second machine translation service when the translation quality of the first candidate translation result does not meet the first preset condition;
The target translation result determining module is used for determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content;
And the translation result storage module is used for storing the preset content and the target translation result corresponding to the preset content in the preset intervention table in a correlated mode.
Optionally, the translation quality determining module is specifically configured to obtain a conversion rate corresponding to the first candidate translation result, where the conversion rate corresponding to the first candidate translation result is a click rate of a target corresponding to the first candidate translation result within a preset duration; and determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
The translation quality determining module is further configured to determine that the translation quality of the first candidate translation result does not meet the first preset condition when the conversion rate corresponding to the first candidate translation result is less than a first preset threshold.
It should be appreciated that for the preset content, each of the second machine translation services corresponds to a translation result.
In one example, the target translation result determining module is specifically configured to determine, according to the translation result corresponding to each of the second machine translation services, a third candidate translation result with the largest number from the at least one second candidate translation result, where the third candidate translation result is one of the at least one second candidate translation result; and when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, the target translation result determining module is further configured to determine whether the third candidate translation result is the same as the first candidate translation result when a proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold; and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
Optionally, the target translation result determining module is further configured to obtain a conversion rate corresponding to the third candidate translation result; and when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
In a fifth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to cause the electronic device to implement the translation optimization method according to any one of the first aspect or implement the translation method according to any one of the second aspect.
In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, where the computer program when executed by a computer causes the computer to implement the translation optimization method according to any one of the first aspect or implement the translation method according to any one of the second aspect.
In a seventh aspect, embodiments of the present application provide a computer program product, which when run on an electronic device, causes the electronic device to perform the translation optimization method according to any one of the first aspects or to implement the translation method according to any one of the second aspects.
It will be appreciated that the advantages of the second to seventh aspects may be found in the relevant description of the first aspect, and are not described here again.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device to which a translation optimization method and a translation method according to an embodiment of the present application are applicable;
FIG. 2 is a schematic diagram of a translation optimization method and a software architecture to which the translation method is applicable according to an embodiment of the present application;
FIG. 3 is a flow chart of a translation optimization method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a timing task setup provided by an embodiment of the present application;
FIG. 5 is a schematic diagram showing the effect of the conversion rate change corresponding to a search term according to an embodiment of the present application;
Fig. 6 is a flow chart of a translation method according to an embodiment of the present application.
Detailed Description
It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
Furthermore, references to "a plurality of" in embodiments of the present application should be interpreted as two or more.
The translation optimization method and the steps involved in the translation method provided in the embodiments of the present application are merely examples, not all steps are necessarily performed, or not all information or contents in a message are necessarily selected, and may be increased or decreased as needed in the use process. The same steps or messages having the same function in the embodiments of the present application may be referred to and used by reference between different embodiments.
The service scenario described in the embodiment of the present application is for more clearly describing the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application, and as a person of ordinary skill in the art can know that, with the evolution of the network architecture and the appearance of a new service scenario, the technical solution provided by the embodiment of the present application is applicable to similar technical problems.
In the use process of electronic equipment, it is often required to translate one language into another language, for example, in a cross-border e-commerce scenario, a multi-language e-commerce website generally takes english as an index, that is, when the content input by a user is not english, the e-commerce website can call a certain machine translation service to translate the content input by the user into english, then the e-commerce website can search for a target according to the translated english by a search engine, and display the searched target in a page for viewing and selecting by the user.
Among them, the machine translation service is generally based on a translation service of statistical machine translation (STATISTICAL MACHINE translation, SMT). SMT typically trains a natural language model by a unigram corpus and trains a translation model by a bilingual corpus, and finally translates a source language into a target language by a decoder. Because SMT translation is not necessarily accurate, the problem of poor translation accuracy exists in machine translation service, but at present, specialized translation personnel are required to manually identify the translation result so as to identify the translation result with poor quality, and manually correct the translation result with poor quality, so that the cost is high, and the optimization efficiency is low. The existing machine translation cannot automatically identify and optimize the poor translation result, so that the optimization efficiency of the translation result is low, and the user experience is greatly influenced.
For example, in a cross-border e-commerce scenario, when a user wants to search for a bag, the user may enter a "bag" in the search box of an e-commerce website, which may invoke some machine translation service to translate the "bag" into "bag" in english. Then, the e-commerce website can search for 'bag' through a search engine, and the searched schoolbag is displayed in the page. However, the existing machine translation service has a problem of poor accuracy, for example, the machine translation service may translate a "book" into a "book", and at this time, the content searched by the e-commerce website through the search engine is related to the "book" and not related to the "book", which is obviously not the result desired by the user, but the existing machine translation service cannot automatically identify and optimize the poor translation result, which affects not only the use experience of the user, but also the transformation of the website.
To solve the above problems, embodiments of the present application provide a translation optimization method, a translation method, an electronic device, and a computer-readable storage medium, where a first machine translation service may be provided in the electronic device. In the method, the electronic device may acquire a first candidate translation result, where the first candidate translation result is a translation result acquired through a first machine translation service, the first candidate translation result is a translation result corresponding to a preset content, the preset content is a content represented by a first language, the first candidate translation result is a content represented by a second language, and the first language is different from the second language. Then, the electronic device may determine a translation quality of the first candidate translation result, and when the translation quality of the first candidate translation result does not meet a first preset condition, obtain at least one second candidate translation result corresponding to the preset content through at least one second machine translation service, where the second machine translation service is different from the first machine translation service. Then, the electronic device may determine a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
In other words, in the embodiment of the present application, the electronic device may obtain a first candidate translation result corresponding to the preset content translated by the first machine translation service, and may automatically determine the translation quality of the first candidate translation result, so as to identify a translation result with poor translation quality of the first machine translation service. For the translation result with poor translation quality of the first machine translation service, the electronic device can automatically call the second machine translation service to translate the preset content, so that the translation result with poor translation quality of the first machine translation service is automatically optimized through the second candidate translation result obtained by the second machine translation service, the accuracy of the translation result corresponding to the preset content can be ensured, the identification and optimization of the translation result do not need to be manually carried out, the efficiency of optimizing the translation result can be effectively improved, and the user experience is improved.
In the embodiment of the application, the electronic device may be an electronic device, a tablet, an intelligent television, a vehicle-mounted device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), a desktop computer, an intelligent television, an intelligent large screen, or the like.
The following first describes an electronic device according to an embodiment of the present application. Referring to fig. 1, fig. 1 shows a schematic structural diagram of an electronic device 100.
The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (universal serial bus, USB) interface 130, an antenna 1, an antenna 2, a mobile communication module 140, a wireless communication module 150, an audio module 160, a speaker 160A, a receiver 160B, a microphone 160C, an earpiece interface 160D, a sensor module 180, a camera 170, and a display screen 190, among others. The sensor module 180 may include a pressure sensor 180A, a gyro sensor 180B, a magnetic sensor 180C, an acceleration sensor 180D, a distance sensor 180E, a fingerprint sensor 180F, a touch sensor 180G, and the like.
It should be understood that the illustrated structure of the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the application, electronic device 100 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The processor 110 may include one or more processing units, such as: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (IMAGE SIGNAL processor, ISP), a controller, a video codec, a digital signal processor (DIGITAL SIGNAL processor, DSP), a baseband processor, and/or a neural-Network Processor (NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.
The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.
A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby improving the efficiency of the system.
In some embodiments, the processor 110 may include one or more interfaces. The interfaces may include an integrated circuit (inter-INTEGRATED CIRCUIT, I2C) interface, an integrated circuit built-in audio (inter-INTEGRATED CIRCUIT SOUND, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (universal asynchronous receiver/transmitter, UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.
The I2C interface is a bi-directional synchronous serial bus comprising a serial data line (SERIAL DATA LINE, SDA) and a serial clock line (derail clock line, SCL). In some embodiments, the processor 110 may contain multiple sets of I2C buses. The processor 110 may be coupled to the touch sensor 180G, the camera 170, etc., respectively, through different I2C bus interfaces. For example: the processor 110 may be coupled to the touch sensor 180G through an I2C interface, such that the processor 110 communicates with the touch sensor 180G through an I2C bus interface to implement a touch function of the electronic device 100.
The I2S interface may be used for audio communication. In some embodiments, the processor 110 may contain multiple sets of I2S buses. The processor 110 may be coupled to the audio module 160 via an I2S bus to enable communication between the processor 110 and the audio module 160. In some embodiments, the audio module 160 may transmit an audio signal to the wireless communication module 150 through the I2S interface, to implement a function of answering a call through a bluetooth headset.
PCM interfaces may also be used for audio communication to sample, quantize and encode analog signals. In some embodiments, the audio module 160 and the wireless communication module 150 may be coupled by a PCM bus interface. In some embodiments, the audio module 160 may also transmit audio signals to the wireless communication module 150 through the PCM interface to implement a function of answering a call through the bluetooth headset. Both the I2S interface and the PCM interface may be used for audio communication.
The UART interface is a universal serial data bus for asynchronous communications. The bus may be a bi-directional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is typically used to connect the processor 110 with the wireless communication module 150. For example: the processor 110 communicates with a bluetooth module in the wireless communication module 150 through a UART interface to implement a bluetooth function. In some embodiments, the audio module 160 may transmit an audio signal to the wireless communication module 150 through a UART interface, so as to implement a function of playing music through a bluetooth headset.
The MIPI interface may be used to connect the processor 110 to peripheral devices such as the display screen 190, the camera 170, and the like. The MIPI interfaces include camera serial interfaces (CAMERA SERIAL INTERFACE, CSI), display serial interfaces (DISPLAY SERIAL INTERFACE, DSI), and the like. In some embodiments, processor 110 and camera 170 communicate through a CSI interface to implement the photographing function of electronic device 100. Processor 110 and display screen 190 communicate via a DSI interface to implement the display functionality of electronic device 100.
The GPIO interface may be configured by software. The GPIO interface may be configured as a control signal or as a data signal. In some embodiments, a GPIO interface may be used to connect the processor 110 with the camera 170, the display screen 190, the wireless communication module 150, the audio module 160, the sensor module 180, and the like. The GPIO interface may also be configured as an I2C interface, an I2S interface, a UART interface, an MIPI interface, etc.
The USB interface 130 is an interface conforming to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, or the like. The USB interface 130 may be used to connect a charger to charge the electronic device 100, and may also be used to transfer data between the electronic device 100 and a peripheral device. And can also be used for connecting with a headset, and playing audio through the headset. The interface may also be used to connect other electronic devices, such as AR devices, etc.
It should be understood that the interfacing relationship between the modules illustrated in the embodiments of the present application is only illustrative, and is not meant to limit the structure of the electronic device 100. In other embodiments of the present application, the electronic device 100 may also employ different interfacing manners in the above embodiments, or a combination of multiple interfacing manners.
The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 140, the wireless communication module 150, a modem processor, a baseband processor, and the like.
The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in the electronic device 100 may be used to cover a single or multiple communication bands. Different antennas may also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed into a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.
The mobile communication module 140 may provide a solution for wireless communication including 2G/3G/4G/5G, etc., applied on the electronic device 100. The mobile communication module 140 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), etc. The mobile communication module 140 may receive electromagnetic waves from the antenna 1, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation. The mobile communication module 140 can amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 1 to radiate. In some embodiments, at least some of the functional modules of the mobile communication module 140 may be disposed in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 140 may be disposed in the same device as at least some of the modules of the processor 110.
The modem processor may include a modulator and a demodulator. The modulator is used for modulating the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used for demodulating the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low frequency baseband signal to the baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and then transferred to the application processor. The application processor outputs sound signals through an audio device (not limited to the speaker 160A, the receiver 160B, etc.), or displays images or videos through the display screen 190. In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be provided in the same device as the mobile communication module 140 or other functional module, independent of the processor 110.
The wireless communication module 150 may provide solutions for wireless communication including wireless local area network (wireless local area networks, WLAN) (e.g., wireless fidelity (WIRELESS FIDELITY, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation SATELLITE SYSTEM, GNSS), frequency modulation (frequency modulation, FM), near field communication (NEAR FIELD communication, NFC), infrared (IR), etc., applied to the electronic device 100. The wireless communication module 150 may be one or more devices that integrate at least one communication processing module. The wireless communication module 150 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signals, filters the electromagnetic wave signals, and transmits the processed signals to the processor 110. The wireless communication module 150 may also receive a signal to be transmitted from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2.
In some embodiments, antenna 1 and mobile communication module 140 of electronic device 100 are coupled, and antenna 2 and wireless communication module 150 are coupled, such that electronic device 100 may communicate with a network and other devices through wireless communication techniques. The wireless communication techniques can include the Global System for Mobile communications (global system for mobile communications, GSM), general packet radio service (GENERAL PACKET radio service, GPRS), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (wideband code division multiple access, WCDMA), time division code division multiple access (time-division code division multiple access, TD-SCDMA), long term evolution (long term evolution, LTE), BT, GNSS, WLAN, NFC, FM, and/or IR techniques, among others. The GNSS may include a global satellite positioning system (global positioning system, GPS), a global navigation satellite system (global navigation SATELLITE SYSTEM, GLONASS), a beidou satellite navigation system (beidou navigation SATELLITE SYSTEM, BDS), a quasi zenith satellite system (quasi-zenith SATELLITE SYSTEM, QZSS) and/or a satellite based augmentation system (SATELLITE BASED AUGMENTATION SYSTEMS, SBAS).
The electronic device 100 implements display functions through a GPU, a display screen 190, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 190 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.
The display screen 190 is used to display images, videos, and the like. The display screen 190 includes a display panel. The display panel may employ a Liquid Crystal Display (LCD) CRYSTAL DISPLAY, an organic light-emitting diode (OLED), an active-matrix organic LIGHT EMITTING diode (AMOLED), a flexible light-emitting diode (FLED), miniled, microLed, micro-oLed, a quantum dot LIGHT EMITTING diode (QLED), or the like. In some embodiments, the electronic device 100 may include 1 or N display screens 190, N being a positive integer greater than 1.
The electronic device 100 may implement photographing functions through an ISP, a camera 170, a video codec, a GPU, a display screen 190, an application processor, and the like.
The ISP is used to process the data fed back by the camera 170. For example, when photographing, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, the optical signal is converted into an electric signal, and the camera photosensitive element transmits the electric signal to the ISP for processing and is converted into an image visible to naked eyes. ISP can also optimize the noise, brightness and skin color of the image. The ISP can also optimize parameters such as exposure, color temperature and the like of a shooting scene. In some embodiments, the ISP may be provided in the camera 170.
The camera 170 is used to capture still images or video. The object generates an optical image through the lens and projects the optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, which is then transferred to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or the like format. In some embodiments, the electronic device 100 may include 1 or N cameras 170, N being a positive integer greater than 1.
The digital signal processor is used for processing digital signals, and can process other digital signals besides digital image signals. For example, when the electronic device 100 selects a frequency bin, the digital signal processor is used to fourier transform the frequency bin energy, or the like.
Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 may play or record video in a variety of encoding formats, such as: dynamic picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4, etc.
The NPU is a neural-network (NN) computing processor, and can rapidly process input information by referencing a biological neural network structure, for example, referencing a transmission mode between human brain neurons, and can also continuously perform self-learning. Applications such as intelligent awareness of the electronic device 100 may be implemented through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, etc.
The external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to enable expansion of the memory capabilities of the electronic device 100. The external memory card communicates with the processor 110 through an external memory interface 120 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.
The internal memory 121 may be used to store computer executable program code including instructions. The internal memory 121 may include a storage program area and a storage data area. The storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, etc. The storage data area may store data created during use of the electronic device 100 (e.g., audio data, phonebook, etc.), and so on. In addition, the internal memory 121 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like. The processor 110 performs various functional applications of the electronic device 100 and data processing by executing instructions stored in the internal memory 121 and/or instructions stored in a memory provided in the processor.
The electronic device 100 may implement audio functions through an audio module 160, a speaker 160A, a receiver 160B, a microphone 160C, an earphone interface 160D, an application processor, and the like. Such as music playing, recording, etc.
The audio module 160 is used to convert digital audio information into an analog audio signal output and also to convert an analog audio input into a digital audio signal. The audio module 160 may also be used to encode and decode audio signals. In some embodiments, the audio module 160 may be disposed in the processor 110, or some functional modules of the audio module 160 may be disposed in the processor 110.
The speaker 160A, also referred to as a "horn," is used to convert audio electrical signals into sound signals. The electronic device 100 may listen to music, or to hands-free conversations, through the speaker 160A.
A receiver 160B, also referred to as a "earpiece", is used to convert the audio electrical signal into a sound signal. When electronic device 100 is answering a telephone call or voice message, voice may be received by placing receiver 160B in close proximity to the human ear.
Microphone 160C, also referred to as a "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or transmitting voice information, the user can sound near the microphone 160C through the mouth, inputting a sound signal to the microphone 160C. The electronic device 100 may be provided with at least one microphone 160C. In other embodiments, the electronic device 100 may be provided with two microphones 160C, and may implement a noise reduction function in addition to collecting sound signals. In other embodiments, the electronic device 100 may also be provided with three, four, or more microphones 160C to enable collection of sound signals, noise reduction, identification of sound sources, directional recording, etc.
The earphone interface 160D is used to connect a wired earphone. The headset interface 160D may be a USB interface 130 or a 3.5mm open mobile electronic device platform (open mobile terminal platform, OMTP) standard interface, a american cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.
The pressure sensor 180A is used to sense a pressure signal, and may convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A may be disposed on the display screen 190. The pressure sensor 180A is of various types, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like. The capacitive pressure sensor may be a capacitive pressure sensor comprising at least two parallel plates with conductive material. The capacitance between the electrodes changes when a force is applied to the pressure sensor 180A. The electronic device 100 determines the strength of the pressure from the change in capacitance. When a touch operation is applied to the display screen 190, the electronic apparatus 100 detects the touch operation intensity according to the pressure sensor 180A. The electronic device 100 may also calculate the location of the touch based on the detection signal of the pressure sensor 180A. In some embodiments, touch operations that act on the same touch location, but at different touch operation strengths, may correspond to different operation instructions. For example: and executing an instruction for checking the short message when the touch operation with the touch operation intensity smaller than the first pressure threshold acts on the short message application icon. And executing an instruction for newly creating the short message when the touch operation with the touch operation intensity being greater than or equal to the first pressure threshold acts on the short message application icon.
The gyro sensor 180B may be used to determine a motion gesture of the electronic device 100. In some embodiments, the angular velocity of electronic device 100 about three axes (i.e., x, y, and z axes) may be determined by gyro sensor 180B. The gyro sensor 180B may be used for photographing anti-shake. For example, when the shutter is pressed, the gyro sensor 180B detects the shake angle of the electronic device 100, calculates the distance to be compensated by the lens module according to the angle, and makes the lens counteract the shake of the electronic device 100 through the reverse motion, so as to realize anti-shake. The gyro sensor 180B may also be used for navigating, somatosensory game scenes.
The magnetic sensor 180C includes a hall sensor. The electronic device 100 may detect the opening and closing of the flip cover using the magnetic sensor 180C. In some embodiments, when the electronic device 100 is a flip machine, the electronic device 100 may detect the opening and closing of the flip according to the magnetic sensor 180C. And then according to the detected opening and closing state of the leather sheath or the opening and closing state of the flip, the characteristics of automatic unlocking of the flip and the like are set.
The acceleration sensor 180D may detect the magnitude of acceleration of the electronic device 100 in various directions (typically three axes). The magnitude and direction of gravity may be detected when the electronic device 100 is stationary. The electronic equipment gesture recognition method can also be used for recognizing the gesture of the electronic equipment, and is applied to horizontal and vertical screen switching, pedometers and other applications.
A distance sensor 180E for measuring a distance. The electronic device 100 may measure the distance by infrared or laser. In some embodiments, the electronic device 100 may range using the distance sensor 180E to achieve quick focus.
The fingerprint sensor 180F is used to collect a fingerprint. The electronic device 100 may utilize the collected fingerprint feature to unlock the fingerprint, access the application lock, photograph the fingerprint, answer the incoming call, etc.
The touch sensor 180G, also referred to as a "touch device". The touch sensor 180G may be disposed on the display screen 190, and the touch sensor 180G and the display screen 190 form a touch screen, which is also referred to as a "touch screen". The touch sensor 180G is used to detect a touch operation acting thereon or thereabout. The touch sensor may communicate the detected touch operation to the application processor to determine the touch event type. Visual output related to the touch operation may be provided through the display screen 190. In other embodiments, the touch sensor 180G may also be disposed on the surface of the electronic device 100 at a different location than the display 190.
The software system of the electronic device 100 may employ a layered architecture, an event driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. For example, the software System of the electronic device 100 may employ a hierarchical android Operating System (OS), a hong operating System (Harmony OS), an IOS, or the like. In the embodiment of the application, taking an Android system with a layered architecture as an example, a software structure of the electronic device 100 is illustrated.
Fig. 2 is a software configuration block diagram of the electronic device 100 according to the embodiment of the present application.
The layered architecture divides the software into several layers, each with distinct roles and branches. The layers communicate with each other through a software interface. In some embodiments, the Android system is divided into four layers, from top to bottom, an application layer, an application framework layer, an Zhuoyun rows (Android runtime) and system libraries, and a kernel layer, respectively.
The application layer may include a series of application packages.
As shown in fig. 2, the application package may include applications for cameras, gallery, calendar, phone calls, maps, navigation, WLAN, bluetooth, music, video, short messages, etc.
The application framework layer provides an application programming interface (application programming interface, API) and programming framework for the application of the application layer. The application framework layer includes a number of predefined functions.
As shown in FIG. 2, the application framework layer may include a window manager, a content provider, a view system, a telephony manager, a resource manager, a notification manager, and the like.
The window manager is used for managing window programs. The window manager can acquire the size of the display screen, judge whether a status bar exists, lock the screen, intercept the screen and the like.
The content provider is used to store and retrieve data and make such data accessible to applications. The data may include video, images, audio, calls made and received, browsing history and bookmarks, phonebooks, etc.
The view system includes visual controls, such as controls to display text, controls to display pictures, and the like. The view system may be used to build applications. The display interface may be composed of one or more views. For example, a display interface including a text message notification icon may include a view displaying text and a view displaying a picture.
The telephony manager is used to provide the communication functions of the electronic device 100. Such as the management of call status (including on, hung-up, etc.).
The resource manager provides various resources for the application program, such as localization strings, icons, pictures, layout files, video files, and the like.
The notification manager allows the application to display notification information in a status bar, can be used to communicate notification type messages, can automatically disappear after a short dwell, and does not require user interaction. Such as notification manager is used to inform that the download is complete, message alerts, etc. The notification manager may also be a notification in the form of a chart or scroll bar text that appears on the system top status bar, such as a notification of a background running application, or a notification that appears on the screen in the form of a dialog window. For example, a text message is prompted in a status bar, a prompt tone is emitted, the electronic device vibrates, and an indicator light blinks, etc.
Android run time includes a core library and virtual machines. Android runtime is responsible for scheduling and management of the android system.
The core library consists of two parts: one part is a function which needs to be called by java language, and the other part is a core library of android.
The application layer and the application framework layer run in a virtual machine. The virtual machine executes java files of the application program layer and the application program framework layer as binary files. The virtual machine is used for executing the functions of object life cycle management, stack management, thread management, security and exception management, garbage collection and the like.
The system library may include a plurality of functional modules. For example: surface manager (surface manager), media Libraries (Media Libraries), three-dimensional graphics processing Libraries (e.g., openGL ES), 2D graphics engines (e.g., SGL), etc.
The surface manager is used to manage the display subsystem and provides a fusion of 2D and 3D layers for multiple applications.
Media libraries support a variety of commonly used audio, video format playback and recording, still image files, and the like. The media library may support a variety of audio video encoding formats, such as: MPEG4, h.264, MP3, AAC, AMR, JPG, PNG, etc.
The three-dimensional graphic processing library is used for realizing three-dimensional graphic drawing, image rendering, synthesis, layer processing and the like.
The 2D graphics engine is a drawing engine for 2D drawing.
The kernel layer is a layer between hardware and software. The inner core layer at least comprises a display driver, a camera driver, an audio driver and a sensor driver.
The translation optimization method and the translation method provided by the embodiment of the application are described in detail below with reference to the accompanying drawings and specific application scenes.
Referring to fig. 3, fig. 3 is a schematic flow chart of a translation optimization method according to an embodiment of the present application. The method may be applied to an electronic device in which a first machine translation service may be provided. As shown in fig. 3, the method may include:
S301, the electronic device acquires a first candidate translation result, wherein the first candidate translation result is a translation result acquired through a first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is content expressed in a first language, the first candidate translation result is content expressed in a second language, and the first language is different from the second language.
S302, the electronic equipment determines the translation quality of the first candidate translation result.
And S303, when the translation quality of the first candidate translation result does not meet the first preset condition, the electronic equipment acquires at least one second candidate translation result corresponding to the preset content through at least one second machine translation service, wherein the second machine translation service is different from the first machine translation service.
S304, the electronic equipment determines a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
In the embodiment of the application, the electronic device can acquire the first candidate translation result corresponding to the preset content translated by the first machine translation service, and can automatically determine the translation quality of the first candidate translation result so as to identify the translation result with poor translation quality of the first machine translation service. For the translation result with poor translation quality of the first machine translation service, the electronic device can automatically call the second machine translation service to translate the preset content, so that the translation result with poor translation quality of the first machine translation service is automatically optimized through the second candidate translation result obtained by the second machine translation service, the accuracy of the translation result corresponding to the preset content can be ensured, the identification and optimization of the translation result do not need to be manually carried out, the efficiency of optimizing the translation result can be effectively improved, and the user experience is improved.
The first machine translation service may be, for example, any translation service. Alternatively, the first machine translation service may be a translation service that is self-contained with the electronic device system. For example, the first machine translation service may be a translation application or a translation engine or the like that is native to the electronic device system. Or the first machine translation service may be a translation service provided by a third party downloaded by the electronic device from the application marketplace. For example, the first machine translation service may be a translation application or translation engine or the like downloaded by the electronic device from an application marketplace.
Similarly, the second machine translation service may be any translation service, that is, the second machine translation service may be any translation application or translation engine. However, the second machine translation service and the first machine translation service need to be different translation services, so that a translation result with higher accuracy can be obtained through different translation services, and therefore a translation result with poorer quality translated by the first machine translation service can be optimized according to the translation result with higher accuracy, and the accuracy of the translation result corresponding to the preset content is ensured.
It can be appreciated that, in the embodiment of the present application, the number of the second machine translation services is not limited, and may be set by default by the electronic device or may be set by user definition. For example, the technician may determine the number of second machine translation services according to the actual application scenario, and the electronic device may determine the number of second machine translation services determined by the technician as a default setting of the electronic device.
For example, when the first machine translation service is a translation application or a translation engine of the electronic device system, the technician may determine the second machine translation service as a translation application or a translation engine provided by a third party according to an actual application scenario, and may determine the number of second machine translation services according to the actual application scenario, for example, the number of second machine translation services may be set to any one of 3, 5, or 10, etc. At this time, the electronic device may determine the number of second machine translation services (e.g., 5) determined by the technician as the number of second machine translation services set by default in the electronic device.
Similarly, the embodiment of the application does not limit the specific type of the second machine translation service, and the second machine translation service can be set by default by the electronic equipment or can be set by user definition. For example, the technician may specifically determine each second machine translation service according to the actual application scenario, and the electronic device may determine each second machine translation service determined by the technician as a default setting of the electronic device. For example, to ensure an optimized effect of translation optimization, and improve the user experience, a technician may determine a translation application or translation engine with better translation quality as the second machine translation service. For example, when the technician sets the number of the second machine translation services to 5 according to the actual application scenario, the technician may also perform better translation quality according to the actual application scenarioTranslation of,Translation of,Translation of,Translation and translationThe translation is determined to be a second machine translation service, and so on.
The content related to the user-defined setting of the second machine translation service (for example, the number and specific type of the second machine translation service) may refer to the following description, which is not repeated herein. For example, a user may submit a timed task in a translation optimization system corresponding to a first machine translation service, and may customize a second machine translation service in the timed task. I.e. the timing task may include information about the second machine translation service.
It should be noted that, the preset content may be a word, a phrase, a long sentence, etc., and the embodiment of the present application does not limit the length of the preset content. Optionally, in order to ensure the optimization effect of the translation result, the preset content in the embodiment of the present application may be a word or a phrase. That is, embodiments of the present application may be used to translate and optimize words or phrases translated by a first machine translation service.
For example, the first language (may also be referred to as a source language) corresponding to the preset content may be any language, and the second language (may also be referred to as a target language) corresponding to the first candidate translation result may be any language different from the first language. The embodiment of the application does not limit the types of the first language and the second language, can be specifically determined by a technician according to the actual application scene (namely, can be set by default by the electronic equipment), and can also be set by user definition.
For example, a technician may determine that the first language is chinese and the second language is english according to an actual application scenario. That is, the first machine translation service may be used to translate chinese content into english content, and at this time, the electronic device may perform translation optimization on the first candidate translation result (i.e., the translation result translated from chinese to english) with poor translation quality obtained by the first machine translation service.
For example, a technician may determine that the first language is russian and the second language is english according to an actual application scenario. That is, the first machine translation service may be used to translate russian content into english content, where the electronic device may optimize the russian english performed by the first machine translation service to obtain a first candidate translation result (i.e., a translation result translated from russian to english) with poor translation quality.
For example, a technician may determine that the first language is english and the second language is french according to an actual application scenario. That is, the first machine translation service may be used to translate english content into french content, where the electronic device may optimize the first candidate translation result (i.e., the translation result from english to french) that is obtained by the english-to-english method performed by the first machine translation service and has poor translation quality.
The process of the electronic device obtaining the first candidate translation result will be described in detail below.
In one possible implementation manner, the electronic device may obtain a translation result corresponding to the preset content obtained by the first machine translation service in a preset time period, and may perform translation optimization according to the translation result corresponding to each preset content in the preset time period. That is, the electronic device may determine the first candidate translation result according to the translation result corresponding to each preset content in the preset time period, so as to perform translation optimization.
In one example, when the electronic device translates each preset content through the first machine translation service to obtain a translation result corresponding to each preset content, the electronic device may obtain a translation time corresponding to each preset content, and may store each preset content and a translation result corresponding to each preset content locally to the electronic device or store the translation result corresponding to each preset content in another device in communication with the electronic device according to the translation time corresponding to each preset content. That is, the electronic device may store all preset contents translated by the first machine translation service and translation results corresponding to the preset contents in association with corresponding translation times. Therefore, when the translation result corresponding to the first machine translation service needs to be optimized, the electronic device may obtain, from preset contents and corresponding translation results stored in the electronic device locally or from other devices communicatively connected to the electronic device, each preset content and the translation result corresponding to each preset content in the preset time period according to the translation time corresponding to each preset content, and may determine the first candidate translation result according to the translation result corresponding to each preset content in the preset time period, so as to perform translation optimization according to each first candidate translation result.
In another example, when the electronic device translates each preset content through the first machine translation service to obtain a translation result corresponding to each preset content, the electronic device may obtain a translation time corresponding to each preset content, and may determine preset content located in the preset time period according to the translation time corresponding to each preset content. And then, the electronic equipment can store the preset content with the translation time within the preset time period and the translation result corresponding to the preset content in a local mode of the electronic equipment or other equipment in communication connection with the electronic equipment. That is, the electronic device only needs to store each preset content translated by the first machine translation service and the translation result corresponding to each preset content in the preset time period, but does not need to store all preset contents translated by the first machine translation service and the translation result corresponding to each preset content, so that the data volume required to be stored can be effectively reduced, and the memory occupation of the electronic device or other devices can be reduced. Therefore, when the translation result corresponding to the first machine translation service needs to be optimized, the electronic device can directly determine the first candidate translation result according to the translation result corresponding to each preset content in the local electronic device or other devices connected with the electronic device in a communication manner, so as to perform translation optimization according to the first candidate translation result.
It can be appreciated that the preset time period may be specifically set by a technician according to an actual application scenario, or may be set by a user in a user-defined manner, which is not limited in the embodiment of the present application.
For example, the technician may set the preset time period to the last 10 days according to the actual application scenario. Therefore, when the translation optimization is required, the electronic device may acquire the translation results corresponding to the preset contents acquired through the first machine translation service within the last 10 days, so as to determine the first candidate translation result according to the translation results corresponding to the preset contents within the last 10 days, so as to perform the translation optimization.
For example, the technician may set the preset time period to the last 24 hours according to the actual application scenario. Therefore, when the translation optimization is required, the electronic device may acquire the translation results corresponding to the preset contents acquired through the first machine translation service within the last 24 hours, so as to determine the first candidate translation result according to the translation results corresponding to the preset contents within the last 24 hours, so as to perform the translation optimization.
For example, the technician may set the preset time period to the last month according to the actual application scenario. Therefore, when the translation optimization is required, the electronic device may acquire the translation result corresponding to each preset content acquired through the first machine translation service in the last month, so as to determine the first candidate translation result according to the translation result corresponding to each preset content in the last month, so as to perform the translation optimization.
For example, the electronic device may determine, within a preset period of time, the translation results corresponding to each preset content as the first candidate translation result.
For example, the electronic device may determine, as the first candidate translation result, only a translation result corresponding to a part of the preset content in the preset period of time, so as to reduce the number of translation optimizations each time and improve the efficiency of the translation optimizations. That is, when performing each translation optimization, the electronic device may only acquire a part of the translation results corresponding to the preset contents (for example, a specified number of translation results corresponding to the preset contents) within a preset period of time, so as to determine whether the translation results have a problem of poor translation quality, so as to determine whether the translation results of the preset contents need to be optimized.
It should be noted that the specified number may be specifically set by a technician according to an actual application scenario, which is not limited in any way by the embodiment of the present application. For example, the technician may set the designated number to any one of 500, 2000, 10000, or the like according to the actual application scenario. For example, when the technician sets the designated number to 10000 according to the actual application scenario, assuming that the number of preset contents translated by the first machine translation service is 100000 in the preset time period, the electronic device may select 10000 preset contents from the 100000 preset contents, and determine the translation result corresponding to the 10000 preset contents as the first candidate translation result, so as to perform the translation optimization at the present time.
It may be appreciated that the manner of determining the specified number of preset contents may be set by default (for example, by a technician according to an actual application scenario) of the electronic device, or may be set by user-definition, which is not limited in any way in the embodiment of the present application.
For example, the technician may set the determination manner of the specified number of preset contents according to the actual application scene to be determined according to the distance of time. At this time, the electronic device may obtain the translation time corresponding to each preset content in the preset time period, and may select a specified number of preset contents from the preset contents in the preset time period according to the sequence of the translation time from near to far, and determine the translation result corresponding to the specified number of preset contents as the first candidate translation result, so as to perform translation optimization. Wherein the closer the translation time is to the current time (i.e., the time at which the translation optimization is performed), the easier the preset content is determined as one of the preset contents of the specified number.
For example, the user may customize the determination of the specified number of presets to be determined based on how many translations are. At this time, the electronic device may obtain the number of translations corresponding to each preset content, and may select, according to the order of at least more translations, a specified number of preset contents from the preset contents in the preset time period, and determine the translation result corresponding to the specified number of preset contents as the first candidate translation result, so as to perform translation optimization, so as to ensure accuracy of the translation result corresponding to the preset contents that are frequently used by the user, thereby effectively improving user experience. Wherein the more the number of translations of the preset contents, the easier it is to determine as one of the preset contents of the specified number.
Optionally, the number of translations corresponding to the preset content may refer to the number of translations of the preset content by the first machine translation service from the beginning of the first translation of the content by the electronic device by the first machine translation service to the current time (i.e. the time when the translation is optimized). Assuming that the time for performing the content translation by the first machine translation service for the first time is 2022, 9 and 10 days, and the time for performing the translation optimization currently is 2022, 12 and 13 days, the number of translations corresponding to the preset content may be the number of translations of the preset content by the electronic device by the first machine translation service from 2022, 9 and 10 days to 2022, 12 and 13 days. That is, from the translation of the preset content by the electronic device through the first machine translation service for the first time, the electronic device may record and store the translation times corresponding to each preset content, so that when the translation optimization is required, the electronic device may obtain the translation times corresponding to each preset content in the preset time period, so as to determine the preset content with a specified number according to the translation times corresponding to each preset content, determine the first candidate translation result according to the translation result corresponding to the preset content with a specified number, and perform the translation optimization according to the first candidate translation result.
Optionally, the number of times of translation corresponding to the preset content may also refer to the number of times of translation of the preset content by the first machine translation service in a preset time period, so as to determine a specified number of first candidate translation results to perform translation optimization according to the translation results corresponding to the preset content that is frequently used by the user recently, thereby ensuring that the effect of translation optimization meets the recent use requirement of the user. For example, when the preset time period is the last week, the number of translations corresponding to the preset content refers to the number of translations of the preset content by the electronic device through the first machine translation service. That is, when each preset content is translated through the first machine translation service, the electronic device may record and store only the number of translations corresponding to each preset content in a preset time period, and determine a specified number of preset contents according to the number of translations corresponding to each preset content in the preset time period, so as to determine a first candidate translation result according to the translation result corresponding to the specified number of preset contents, thereby performing translation optimization according to the first candidate translation result.
For example, when the specified number is 10000, the electronic device may obtain the translation times corresponding to each preset content in a preset period. That is, for each preset content, the electronic device may obtain the number of times the preset content is translated by the first machine translation service in a preset period of time. Then, the electronic device may obtain the first 10000 preset contents with the largest translation times and the translation results corresponding to the 10000 preset contents, and determine the translation results corresponding to the 10000 preset contents as the first candidate translation results, so as to perform translation optimization.
The process of determining the translation quality of the first candidate translation result by the electronic device will be described in detail below.
In one possible implementation, for any first candidate translation result (e.g., the first candidate translation result a), the electronic device may obtain a conversion rate corresponding to the first candidate translation result a. Then, the electronic device may determine the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result a.
For example, when the conversion rate corresponding to the first candidate translation result a is smaller than the first preset threshold, the electronic device may determine that the translation quality of the first candidate translation result a does not meet the first preset condition, that is, it may determine that the translation quality of the first candidate translation result a is poor.
It should be understood that the first preset threshold may be set by default by the electronic device, or may be set by user-definition, which is not limited in this embodiment of the present application. For example, the technician may set the first preset threshold to 1/2 according to the actual application scenario and determine it as a default setting of the electronic device. That is, when the conversion rate corresponding to the first candidate translation result a is less than 1/2, the electronic device may determine that the translation quality of the first candidate translation result a does not meet the first preset condition, that is, indicate that the first candidate translation result a is a translation result with poor quality.
Optionally, the conversion rate corresponding to the first candidate translation result a may be a click-through-rate (CTR) of the target corresponding to the first candidate translation result a in the first specified period. The target corresponding to the first candidate translation result a may include one or more targets. For example, in the first specified period, the electronic device searches and displays the targets corresponding to the first candidate translation result a for 10 times according to the first candidate translation result a, and if the electronic device detects that at least one target among the targets displayed for the first time, the second time, the fifth time, the eighth time and the ninth time is clicked, the electronic device may determine that the click rate of the target corresponding to the first candidate translation result a is 5/10.
It should be understood that the first specified period of time may be set by default by the electronic device or may be set by user-definition, which is not limited in any way by the embodiment of the present application. For example, the electronic device may default to the first specified period of time to the preset period of time described previously. For example, the electronic device may default to the first specified time period or the user may customize the first specified time period to any other time period.
For example, in a cross-border e-commerce scenario, a multi-language e-commerce website typically uses a certain language (e.g., a second language) as an index to search and display. When the content entered by the user in the e-commerce web site is not in the second language, such as when the content entered by the user is in the first language, the electronic device may invoke the first machine translation service to translate the content in the first language into the content in the second language. Then, the electronic device can search for targets according to the content of the second language through the search engine, and can display the searched targets in the page for the user to view, select and the like.
When the translation quality of the content in the second language is good (i.e., accuracy is high), the target displayed in the page is the target that the user actually wants to search, and at this time, the user generally clicks on the target in the page to view details of the target, and so on. When the translation quality of the content in the second language is poor (i.e., the accuracy is low), the target displayed in the page is not the target that the user actually wants to search, and the user does not click on the target in the page. Therefore, for the first candidate translation result a, the electronic device may obtain the click rate of the target corresponding to the first candidate translation result a (i.e., the target searched and displayed in the page according to the first candidate translation result a) within the first preset period of time, so as to determine the translation quality of the first candidate translation result a according to the click rate of the target corresponding to the first candidate translation result a.
It should be understood that the higher the click rate of the target corresponding to the first candidate translation result a, the better the translation quality of the first candidate translation result a. The lower the click rate of the target corresponding to the first candidate translation result a is, the poorer the translation quality of the first candidate translation result a is.
In another possible implementation manner, for any first candidate translation result (for example, the first candidate translation result a), the electronic device may obtain, in the second specified period of time, a proportion of the frontal evaluation corresponding to the first candidate translation result a. Then, the electronic device may determine the translation quality of the first candidate translation result a according to the proportion of the frontal evaluation corresponding to the first candidate translation result a.
The higher the proportion of the positive evaluation corresponding to the first candidate translation result A, the better the translation quality of the first candidate translation result A. The lower the proportion of the positive evaluation corresponding to the first candidate translation result A is, the poorer the translation quality of the first candidate translation result A is. The second designated time period may be set by default by the electronic device or may be set by user-definition, which is not limited in any way by the embodiment of the present application. For example, the electronic device may default to the second specified period of time to the preset period of time described previously.
It should be appreciated that the function of evaluating the translation result may be provided in the electronic device. Therefore, after the first candidate translation result (for example, the first candidate translation result a) corresponding to any preset content is obtained through the first machine translation service, the user can evaluate the first candidate translation result a according to the translation quality. For example, when it is determined that the translation quality of the first candidate translation result a is good, the user may perform positive evaluation on it in the electronic device. When it is determined that the translation quality of the first candidate translation result a is poor, the user may negatively evaluate it in the electronic device. Therefore, the electronic device can determine the proportion of the front evaluation corresponding to the first candidate translation result a according to the total number of the evaluations corresponding to the first candidate translation result a and the number of the front evaluations within the second specified time period. Assuming that the total number of the evaluations corresponding to the first candidate translation result a is 20 in the second specified period, and when the number of the front evaluations is 7, the electronic device may determine that the ratio of the front evaluations corresponding to the first candidate translation result a is 7/20.
For example, in the cross-border e-commerce scenario, when the electronic device displays the target corresponding to the first candidate translation result a in the page according to the first candidate translation result a, it may also display "whether the target displayed in the page is the target that you actually want to search? "and displays the" yes "button and the" no "button. When the yes button is detected to be touched, the electronic device may determine that the translation quality of the first candidate translation result a is better, that is, increase the front evaluation corresponding to the first candidate translation result a by one count unit, for example, increase once, so as to determine the proportion of the front evaluation corresponding to the first candidate translation result a in the second specified period, thereby determining the translation quality of the first candidate translation result a.
For example, in a general translation scenario (that is, only the preset content in the first language needs to be translated into the content in the second language, and no other operation needs to be performed), after the electronic device obtains the first candidate translation result a through the first machine translation service, the first candidate translation result a may be displayed in the interface. Meanwhile, the electronic device may display the evaluation prompt content corresponding to the first candidate translation result a, for example, "what is you feel that the translation result is correct? "and" yes "and" no "buttons. When the yes button is detected to be touched, the electronic device may determine that the translation quality of the first candidate translation result a is better, that is, increase the front evaluation corresponding to the first candidate translation result a by one count unit, for example, increase once, so as to determine the proportion of the front evaluation corresponding to the first candidate translation result a in the second specified period, thereby determining the translation quality of the first candidate translation result a.
For example, when the proportion of the positive evaluation corresponding to the first candidate translation result a is smaller than the preset proportion, the electronic device may determine that the translation quality of the first candidate translation result a does not meet the first preset condition, that is, may determine that the first candidate translation result a is a poor-quality translation result.
The preset proportion can be set by default by the electronic device or can be set by user definition, and the embodiment of the application does not limit the application. For example, the electronic device may count the proportion of the positive evaluation corresponding to all the first candidate translation results obtained through the first machine translation service in a certain period of time, and determine an average value of the proportions. The electronic device may then default the average of these ratios to a preset ratio.
The following describes in detail a process of determining, by the electronic device, a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
For any preset content (for example, preset content a), the electronic device may translate the preset content a through each second machine translation service to obtain each translation result corresponding to the preset content a, that is, may translate the preset content a in the first language into the content in the second language through each second machine translation service to obtain the translation result corresponding to each second machine translation service. That is, for the preset content a, each of the second machine translation services may translate to obtain a corresponding translation result. It should be understood that, for the preset content a, the translation results corresponding to the second machine translation services may be the same or different.
For example, when the second machine translation service includesTranslation of,Translation of,Translation of,Translation and translation In translation, for preset content A, the electronic equipment can pass throughTranslating to obtain a corresponding translation result A1 byTranslating to obtain a corresponding translation result A1 byTranslating to obtain a corresponding translation result A2 byTranslating to obtain a corresponding translation result A2 and byAnd during translation, a corresponding translation result A2 is obtained. I.e. for the preset content a,Translation and translationThe translation results corresponding to the translations are the same,Translation of,Translation and translationThe translation results corresponding to the translations are the same.
Optionally, the electronic device may determine at least one second candidate translation result according to the translation result corresponding to each second machine translation service, and determine a third candidate translation result with the largest number of at least one second candidate translation result, where the third candidate translation result is one of the at least one second candidate translation result. Then, the electronic device may determine whether a proportion of the number of third candidate translation results is greater than or equal to a second preset threshold. When the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold, the electronic device can determine a target translation result corresponding to the preset content according to the third candidate translation result.
The second candidate translation results are translation results obtained by removing repeated translation results from the translation results corresponding to the second machine translation services. I.e. the number of second candidate translation results may be less than or equal to the number of second machine translation services. The second preset threshold may be set by default by the electronic device, or may be set by user-definition, which is not limited in this embodiment of the present application. For example, the electronic device may default the second preset threshold to any one of 1/2, 2/3, or 3/4, etc.
It should be understood that the ratio of the number of the third candidate translation results is the number of the third candidate translation results/the total number of the translation results corresponding to the second machine translation service.
For example, when the second machine translation service includesTranslation of,Translation of,Translation of,Translation and translation During translation, for a preset content 'schoolbag', the electronic equipment can pass throughTranslating to obtain a translation result schoolbag corresponding to the schoolbag throughTranslating to obtain a translation result "bag" corresponding to the "schoolbag" throughTranslating to obtain a translation result "bag" corresponding to the "schoolbag" throughTranslating to obtain a translation result 'schoolbag' corresponding to 'schoolbag', and performing translation byAnd translating to obtain a translation result 'schoolbag' corresponding to the 'schoolbag'. Accordingly, the electronic device may determine that the second candidate translation result corresponding to the "schoolbag" may include "schoolbag" and "bag", and may determine that the number of "schoolbag" is 3, and the number of "bag" is 2. Subsequently, the electronic device may determine that the third candidate translation result is "schoolbag" according to the number of "schoolbag" and the number of "bag", and may determine that the ratio of "schoolbag" is 3/5. Assume that the user has custom set the second preset threshold to 1/2. At this time, the electronic device may determine that the proportion of the third candidate translation result is greater than the second preset threshold, so the electronic device may determine, according to the third candidate translation result (i.e., "schoolbag"), the target translation result corresponding to "schoolbag".
In one example, to ensure the effect of translation optimization, the electronic device may first determine whether the third candidate translation result is the same as the first candidate translation result when determining that the proportion of the number of third candidate translation results is greater than or equal to a second preset threshold. When the third candidate translation result is different from the first candidate translation result, the electronic device may determine a target translation result corresponding to the preset content according to the third candidate translation result. When the third candidate translation result is the same as the first candidate translation result, the electronic device may determine that the translation result obtained by the second machine translation service cannot optimize the first candidate translation result obtained by the first machine translation service, and therefore, the electronic device may not optimize the first candidate translation result according to the result obtained by the translation by the second machine translation service. For example, in the current translation optimization, the electronic device may not optimize the first candidate translation result corresponding to the preset content. That is, the next time the translation result corresponding to the preset content is obtained through the first machine translation service is still the first candidate translation result.
In one possible implementation manner, after determining a third candidate translation result corresponding to a certain preset content (for example, preset content a), the electronic device may obtain a conversion rate corresponding to the third candidate translation result within a third specified period, and determine, according to the conversion rate corresponding to the third candidate translation result, whether the translation quality of the third candidate translation result is better than that of the first candidate translation result, so as to determine whether the first candidate translation result corresponding to the preset content a needs to be optimized to the third candidate translation result, that is, determine whether the third candidate translation result needs to be determined to be a target translation result corresponding to the preset content a.
For example, the electronic device may determine whether the second preset condition is satisfied between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result. When the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result meet the second preset condition, the electronic device can determine that the translation quality of the third candidate translation result is better than that of the first candidate translation result, and at this time, the electronic device can optimize the first candidate translation result corresponding to the preset content a to be the third candidate translation result, namely, can determine the third candidate translation result to be the target translation result corresponding to the preset content a. And subsequently, when the electronic equipment translates the preset content A through the first machine translation service, the obtained translation result is a third candidate translation result.
In the embodiment of the present application, when the preset content a is translated by the first machine translation service in a third specified period after the third candidate translation result is determined, the electronic device may determine the third candidate translation result as a translation result corresponding to the preset content a, so as to display the third candidate translation result to the user. Therefore, in the third specified period, the electronic device may obtain a conversion rate corresponding to the third candidate translation result.
The third designated time period may be set by default or user-defined by the electronic device, which is not limited in the embodiment of the present application. For example, the electronic device may default to the third specified period of time to be any period of time of ten days, one month, etc. after the third candidate translation result is obtained.
It should be understood that the method for obtaining the conversion rate corresponding to the third candidate translation result is the same as the method for obtaining the conversion rate corresponding to the first candidate translation result, and specific reference may be made to the specific content of the method for obtaining the conversion rate corresponding to the first candidate translation result, which is not described herein for brevity.
Optionally, the second preset condition may be that a difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is greater than a third preset threshold. That is, when the conversion rate corresponding to the third candidate translation result minus the conversion rate corresponding to the first candidate translation result is greater than the third preset threshold, the electronic device may determine that the second preset condition is satisfied between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result. The third preset threshold may be set by default or user-defined by the electronic device, which is not limited in the embodiment of the present application.
For example, the electronic device may default to the third preset threshold to 0, that is, when the conversion rate corresponding to the third candidate translation result is greater than the conversion rate corresponding to the first candidate translation result, the electronic device may determine that the second preset condition is satisfied between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result. For example, the electronic device may also default to the third preset threshold to any value greater than 0.
In another possible implementation manner, after determining the third candidate translation result corresponding to the preset content a, the electronic device may obtain a proportion of the front evaluation corresponding to the third candidate translation result in a third specified period, and determine, according to the proportion of the front evaluation corresponding to the third candidate translation result, whether the translation quality of the third candidate translation result is better than that of the first candidate translation result, so as to determine whether the second candidate translation result needs to be determined as the target translation result corresponding to the preset content a.
For example, the electronic device may determine whether the second preset condition is satisfied between the proportion of the front side evaluation corresponding to the third candidate translation result and the proportion of the front side evaluation corresponding to the first candidate translation result. When the ratio of the front evaluation corresponding to the third candidate translation result and the ratio of the front evaluation corresponding to the first candidate translation result meet the second preset condition, the electronic device may determine that the translation quality of the third candidate translation result is better than that of the first candidate translation result, and at this time, the electronic device may optimize the first candidate translation result corresponding to the preset content a to be the third candidate translation result, that is, may determine the third candidate translation result to be the target translation result corresponding to the preset content a. And subsequently, when the electronic equipment translates the preset content A through the first machine translation service, the obtained translation result is a third candidate translation result.
At this time, the second preset condition may be that a difference between a proportion of the front side evaluation corresponding to the third candidate translation result and a proportion of the front side evaluation corresponding to the first candidate translation result is greater than a fourth preset threshold. The fourth preset threshold may be specifically determined according to an actual situation, which is not limited in the embodiment of the present application. For example, the fourth preset threshold may be set to 0 according to the actual situation.
It should be understood that, the obtaining manner of the proportion of the front evaluation corresponding to the third candidate translation result is the same as the obtaining manner of the proportion of the front evaluation corresponding to the first candidate translation result, and specific reference may be made to the specific content of the obtaining manner of the conversion rate corresponding to the first candidate translation result, which is not described herein.
In another possible implementation manner, after determining the third candidate translation result corresponding to the preset content a, the electronic device may obtain the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result in the third specified period, and may determine, according to the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result in the third specified period, whether the translation quality of the third candidate translation result is better than the translation quality of the first candidate translation result, so as to determine whether the first candidate translation result corresponding to the preset content a needs to be optimized to the third candidate translation result, and determine, according to the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result in the same period, whether the translation quality of the third candidate translation result is better than the translation quality of the first candidate translation result, so as to ensure the validity of the translation quality comparison, thereby improving the accuracy of the translation optimization.
In other words, in a third designated period after the third candidate translation result is determined, when the preset content a is translated through the first machine translation service, for half of the translations, the electronic device may determine the third candidate translation result as a translation result corresponding to the preset content a, so as to display the third candidate translation result to the user. For the translation of the other half, the electronic device may still determine the first candidate translation result as a translation result corresponding to the preset content a, so as to display the first candidate translation result to the user. Therefore, in the third specified period, the electronic device may respectively obtain the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, so as to determine whether the third candidate translation result needs to be determined as the target translation result corresponding to the preset content a according to whether the second preset condition is satisfied between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result in the third specified period.
It should be understood that, in the embodiment of the present application, after determining the third candidate translation result corresponding to the preset content a, the electronic device may obtain the proportion occupied by the front evaluation corresponding to the third candidate translation result and the proportion occupied by the front evaluation corresponding to the first candidate translation result in the third specified period, and may determine, according to the proportion occupied by the front evaluation corresponding to the third candidate translation result and the proportion occupied by the front evaluation corresponding to the first candidate translation result in the third specified period, whether the translation quality of the third candidate translation result is better than the translation quality of the first candidate translation result, so as to determine whether the first candidate translation result corresponding to the preset content a needs to be optimized to the third candidate translation result.
The principle of determining whether the third candidate translation result needs to be determined as the target translation result corresponding to the preset content a according to the proportion of the front evaluation in the third specified time period is the same as the principle of determining whether the third candidate translation result needs to be determined as the target translation result corresponding to the preset content a according to the conversion rate in the third specified time period, and for simplicity, the description is omitted here.
In the embodiment of the application, after determining the target translation result corresponding to a certain preset content (for example, the preset content a), the electronic device may store the preset content a and the target translation result corresponding to the preset content a in association with the preset intervention table, and may store the preset intervention table locally in the electronic device, for example, the preset intervention table may be stored together with a first machine translation service local to the electronic device, so as to conveniently optimize the translation result obtained by translating the first machine translation service and having poor quality. Or the preset intervention table may be stored in other devices communicatively connected to the electronic device, for example, in a cloud communicatively connected to the electronic device, etc.
In one example, after determining the third candidate translation result corresponding to the preset content a, the electronic device may first store the third candidate translation result corresponding to the preset content a in the temporary intervention table to determine whether the translation quality of the third candidate translation result is better than the translation quality of the first candidate translation result in a third specified period of time, so as to determine whether the third candidate translation result needs to be determined as the target translation result corresponding to the preset content a. In a third appointed time period, when the preset content A is translated through the first machine translation service, the electronic device can acquire a third candidate translation result corresponding to the preset content A from the temporary intervention table, and display the third candidate translation result to the user. Meanwhile, the electronic device may obtain the conversion rate corresponding to the third candidate translation result or the proportion occupied by the positive evaluation corresponding to the third candidate translation result in the third specified period, so as to determine whether the first candidate translation result corresponding to the preset content a needs to be optimized to the third candidate translation result. When determining that the first candidate translation result corresponding to the preset content a needs to be optimized as the third candidate translation result, the electronic device may store the association between the preset content a and the third candidate translation result corresponding to the preset content a in the preset intervention table, so as to serve as the target translation result corresponding to the preset content a.
It should be appreciated that, when it is determined that the first candidate translation result corresponding to the preset content a does not need to be optimized as the third candidate translation result, the electronic device may delete the preset content a and the third candidate translation result corresponding to the preset content a from the temporary intervention table. For example, when it is determined that the second preset condition is not satisfied between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, the electronic device may determine that the first candidate translation result corresponding to the preset content a does not need to be optimized to the third candidate translation result, and at this time, the electronic device may delete the preset content a and the third candidate translation result corresponding to the preset content a from the temporary intervention table.
It should be noted that, when performing the translation optimization, after determining the first candidate translation result (for example, the first candidate translation result a) with poor translation quality, the electronic device may determine whether the first candidate translation result a has been subjected to the translation optimization, for example, determine whether the first candidate translation result a exists in the temporary intervention table and the preset intervention table. When it is determined that the first candidate translation result a has been subjected to translation optimization, for example, when the first candidate translation result a exists in the temporary intervention table or the preset intervention table, in the current translation optimization, the electronic device may not need to perform translation optimization on the first candidate translation result a, so that repeated optimization is avoided, and efficiency of translation optimization is improved.
In the embodiment of the application, when the electronic device obtains the translation request, the translation request is used for requesting to translate the content to be translated, which is represented by the first language, into the content in the second language through the first machine translation service, and the electronic device can firstly determine whether the preset intervention table comprises the content to be translated. When the preset intervention table comprises the content to be translated, the electronic equipment can directly acquire the target translation result corresponding to the content to be translated from the preset intervention table, namely, the target translation result with better translation quality can be directly acquired from the preset intervention table, and the content to be translated does not need to be translated through the first machine translation service, so that the acquisition of the translation result with poorer translation quality can be avoided, the accuracy of the translation result corresponding to the content to be translated is effectively improved, and the user experience is improved.
It should be understood that when it is determined that the preset intervention table does not include the content to be translated, that is, it indicates that an optimized translation result corresponding to the content to be translated does not exist in the preset intervention table, at this time, the electronic device may translate the content to be translated through the first machine translation service, so as to obtain a target translation result corresponding to the content to be translated.
In one possible implementation, the electronic device may periodically perform translation optimization on the translation result obtained by the translation of the first machine translation service, where the translation result is of poor quality. That is, the electronic device may perform translation optimization on the translation result with poor quality obtained by translating by the first machine translation service according to a preset execution period and execution time. It can be understood that, the embodiment of the application does not limit the execution period and specific execution time of translation optimization, and the execution period and specific execution time can be set by default by the electronic device or can be set by user definition.
In one example, a technician may set a translation optimized execution period and a specific execution time according to an actual application scenario, and may determine the set execution period and specific execution time as a default setting of the electronic device. That is, the electronic device may perform translation optimization on the translation result with poor quality obtained by translating the first machine translation service according to the execution period and the specific execution time set by the technician.
For example, the technician may determine the execution period of the translation optimization to be 24 hours and the specific execution time to be 7:00 according to the actual application scenario. Therefore, the electronic device can automatically perform translation optimization on the translation result with poor quality, which is obtained by translating by the first machine translation service, in 7:00 a day in the morning.
For example, the technician may determine the execution period of the translation optimization as one week, and the specific execution time as 24:00 of monday, or the specific execution time as 24:00 of Saturday according to the actual application scenario. Thus, the electronic device may automatically perform translation optimization on the translation result of the first machine translation service, which is obtained by translating the translation result with poor quality, at 24:00 on monday weekly, or 24:00 on friday weekly.
For example, a technician may determine the execution period of translation optimization as one month according to the actual application scenario, and determine the specific execution time as 12:00 of 1 day per month. Therefore, the electronic device can automatically perform translation optimization on the translation result with poor quality, which is obtained by translating by the first machine translation service, at 12:00 of 1 day per month.
In another example, the user may customize the execution period and/or specific execution time of the translation optimization according to his/her needs. That is, the user can set the execution period and specific execution time of the translation optimization in a self-defined manner, or can set the execution period or specific execution time of the translation optimization in a self-defined manner only. That is, the execution period and the specific execution time of the translation optimization may be set by user customization, or only one of them may be set by user customization. It should be appreciated that when the user only custom sets one of the execution period and the specific execution time, the other may then be set by default by the electronic device. For example, when the user only custom sets the execution period of the translation optimization, the electronic device may determine the execution time of the translation optimization by default. For example, when the user only custom sets the execution time of the translation optimization, the electronic device may determine the execution period of the translation optimization by default.
For example, a translation optimizing system corresponding to the first machine translation service may be provided in the electronic device, and a user may set an execution period and/or an execution time of the translation optimization through the translation optimizing system in a user-defined manner. For example, a user may set a translation optimization timing task in the translation optimization system, where the timing task may include information such as an execution period and/or a specific execution time. The user can set the execution period and/or execution time of the translation optimization through the timing task in a self-defining way, so that the electronic equipment can translate and optimize the translation result with poor quality, which is obtained by translating the first machine translation service, according to the execution period and/or execution time set in the timing task in a self-defining way.
For example, the user can customize the execution period and execution time through the translation optimization system. I.e. the timing tasks may include information about the execution period and the execution time. At this time, the electronic device may determine an execution period of the translation optimization according to the related information of the execution period included in the timing task, and may determine an execution time of the translation optimization according to the related information of the execution time included in the timing task, so as to perform the translation optimization on the translation result with poor quality obtained by translating the first machine translation service according to the execution period and the execution time set by user definition.
For example, a user may customize the execution period through the translation optimization system. I.e. only relevant information of the execution period may be included in the timed task. At this time, the electronic device may determine an execution period of the translation optimization according to the related information of the execution period included in the timing task, and may determine an execution time of the translation optimization according to a default setting in the electronic device, so as to perform the translation optimization on a translation result obtained by translating the first machine translation service and having poor quality according to the execution period set by a user and the execution time set by the electronic device by default. Or the user can customize the execution time through the translation optimization system. The timing task may include information about the execution time. At this time, the electronic device may determine execution time of the translation optimization according to the related information of the execution time included in the timing task, and may determine an execution period of the translation optimization according to a default setting in the electronic device, so as to perform the translation optimization on the translation result with poor quality obtained by translating the first machine translation service according to the execution period set by the default setting of the electronic device and the execution time set by the user.
As can be seen from the foregoing description, in the embodiment of the present application, the number and specific type of the second machine translation services may also be set by user definition. In one example, the user may also make custom settings for the second machine translation service through the translation optimization system. For example, the user may also set the second machine translation service through the timing task in a customized manner, that is, the timing task may further include information about the second machine translation service. Therefore, when the translation optimization is required, the electronic device may determine the second machine translation service according to the related information of the second machine translation service included in the timing task, so as to translate the preset content corresponding to the first candidate translation result with poor translation quality through the second machine translation service, and obtain a second candidate translation result corresponding to the preset content, thereby optimizing the translation result corresponding to the preset content according to the second candidate translation result.
Similarly, as can be seen from the foregoing description, in the embodiment of the present application, the electronic device may perform the translation optimization according to only the translation result corresponding to a part of the preset content. For example, the electronic device may perform translation optimization only according to the translation results corresponding to the specified number of preset contents within the preset period. The determining mode of the preset content with the specified number can also be set by user definition. Alternatively, the user may customize the manner in which the specified number of presets are set by translating the timing tasks in the optimization system. I.e. the timing task may also include information about the manner in which a specified number of presets are determined. Therefore, when translation optimization is required, the electronic device can acquire a specified number of preset contents according to the related information of the determination mode included in the timing task.
In the embodiment of the application, during translation optimization, the electronic equipment can optimize only the first candidate translation result with poor translation quality. Whether the translation quality of the first candidate translation result is poor or not can be determined according to a first preset condition. The first preset condition may be set by default by the electronic device, or may be set by user definition. Optionally, the user may also set the first preset condition by translating a timing task in the optimization system. I.e. the timing task may also comprise information about the first preset condition. Therefore, when the translation optimization is required, the electronic device can determine the first preset condition according to the related information of the first preset condition included in the timing task, so as to determine whether the translation quality of the first candidate translation result is poor, and further determine whether the first candidate translation result is required to be optimized.
As can be seen from the foregoing description, in the embodiment of the present application, the electronic device may determine whether to determine the target translation result corresponding to the preset content according to the third candidate translation result according to the second preset threshold. The second preset threshold may be set by user-definition. Illustratively, the user may set a second preset threshold (which may also be referred to as a voting threshold) by custom definition of the timing tasks in the translation optimization system. I.e. the timing task may also include information about the voting threshold. Therefore, when the translation optimization is required, the electronic device may determine the third candidate translation result from the translation results corresponding to the second machine translation services according to the relevant information of the voting threshold value included in the timing task, so as to optimize the first candidate translation result according to the third candidate translation result.
Optionally, the user may further set a source language (i.e. the first language) and a target language (i.e. the second language) of the translation optimization by defining the timing task in the translation optimization system, so as to instruct the electronic device to optimize the translation result from the source language to the target language performed by the first machine translation service through the source language and the target language set by the user. I.e. the timing tasks may include information related to the source language and information related to the target language. Therefore, when the translation is optimized, the electronic device can determine the source language corresponding to the preset content and the target language corresponding to the translation result according to the related information of the source language and the related information of the target language included in the timing task, and call the second machine translation service to translate the preset content of the source language into the content of the target language. When the second machine translation service is called to translate the preset content, the electronic device can determine the current language type of the preset content according to the related information of the source language in the timing task, and can determine the language type corresponding to the translation result according to the related information of the target language in the timing task. The electronic device may then invoke a second machine translation service to translate the preset content in the source language into content in the target language.
For example, when the first machine translation service needs to be optimized for russian (i.e., the russian content is translated into english content), the user may set a timing task in the translation optimizing system corresponding to the first machine translation service, where the timing task may include that the source language is russian and the target language is english. Therefore, when the translation is optimized, the electronic device can determine the target language for translation by the second machine translation service according to the timing task, that is, can call the second machine translation service to translate the preset Russian content into English content.
Alternatively, the machine translation service may generally automatically identify the language type of the content to be translated. Therefore, in the embodiment of the application, the user can only set the target language (namely the second language) of the translation optimization through the translation optimization system in a self-defined mode. I.e. only the target language may be included in the timed task.
It should be noted that, when the first machine translation service may perform multi-language translation, if the user wants to perform translation optimization on multiple language translations corresponding to the first machine translation service, for each language, the user may set a timing task custom setting execution period and/or execution time of the translation optimization for the language, the second machine translation service, a determination manner of a specified number of preset contents, the first preset condition, the source language and the target language, and so on.
For example, when the first machine translation service may perform the in-process (i.e., translate chinese content into english content), the in-process (i.e., translate chinese content into french content), the in-process (i.e., translate chinese content into english content), the in-process (i.e., translate english content into french content), the in-process (i.e., translate russian content into russian content), the in-process (i.e., translate russian content into french content) and the in-process (i.e., translate russian content into german content), if the user wants to perform the optimization of the first candidate translation result a with poor translation quality for the in-process of the first machine translation service and the first candidate translation result B with poor translation quality for the in-process of the first machine translation service, the user may perform the optimization of the first candidate translation result a with a timing task for optimizing the first candidate translation result a and the timing task B for performing the optimization for the first candidate translation result B with self-definition in the translation optimization system corresponding to the first machine translation service, and the electronic device may include the first candidate translation result a with poor translation result B with a timing task and the first candidate result B with poor translation result B with relevant task may include the first candidate result B with relevant task.
For example, the timing task a may include a source language (i.e., chinese) corresponding to the preset content, an execution period (e.g., 24 hours), a second machine translation service (e.g.Translation of,Translation of,Translation of,Translation and translationTranslation), a specified number of predetermined content (may be referred to as predetermined content a) determining manner (e.g., 10000 high-frequency words, i.e., the first 10000 predetermined content determined according to the number of translations), a first predetermined condition (may be referred to as a first predetermined condition a, and may be, for example, a conversion rate lower than half of the average value of the website), and a target language (i.e., english), etc. It is assumed that the execution time of the default setting in the electronic device is 7:00, so when performing translation optimization, the electronic device may obtain preset contents a of the first 10000 chinese characters with a large number of translations and each first candidate translation result a corresponding to the 10000 preset contents a according to the timing task a, and determine a first candidate translation result a (hereinafter referred to as a first candidate translation result a 11) of the 10000 first candidate translation results a, where the translation quality does not satisfy the first preset condition a. Subsequently, the electronic device may call 7:00 in the morning, respectivelyTranslation of,Translation of,Translation of,Translation and translationAnd translating, namely translating preset content A of Chinese into corresponding English content to obtain each translation result corresponding to the preset content A, and determining a second candidate translation result A12 according to each translation result, so that a target translation result corresponding to the preset content A can be determined according to the second candidate translation result A12 corresponding to the preset content A, and optimizing the translation result with poor quality obtained by performing the middle-turn of the first machine translation service to ensure the accuracy of the translation result.
For example, the timing task B may include a source language (i.e., english) corresponding to the preset content, an execution period (e.g., one week), an execution time (e.g., 23:00 of sunday), and a second machine translation service (e.g., one week)Translation of,Translation of,Translation of, Translation and translationTranslation), a specified number of predetermined contents (hereinafter referred to as predetermined contents B) and a target language (i.e., french), for example, 8000 high-frequency words, i.e., the first 8000 predetermined contents determined according to the number of translations, a first predetermined condition (which may be referred to as a first predetermined condition B, which may be that the conversion rate is lower than the average value of the web site, for example). Therefore, in performing the translation optimization, the electronic device may obtain, according to the timing task B, the first 8000 english preset contents B with a large number of translations and the first candidate translation results B corresponding to the 8000 preset contents B, and determine the first candidate translation result B (hereinafter may be referred to as the first candidate translation result B11) of the 8000 first candidate translation results B, where the translation quality does not satisfy the first preset condition B. The electronic device may then call at 23:00 of sunday, respectivelyTranslation of,Translation of,Translation of,Translation and translationAnd translating, namely translating English preset content B into corresponding French content to obtain each translation result corresponding to the preset content B, and determining a second candidate translation result B12 according to each translation result, so that a target translation result corresponding to the preset content B can be determined according to the second candidate translation result B12 corresponding to the preset content B, and optimizing the translation result with poor quality, which is obtained by performing an English inversion method on the first machine translation service, and ensuring the accuracy of the translation result.
After executing the translation optimization according to the related information of the timing task user-defined setting corresponding to the user, the electronic device may analyze the translation optimization corresponding to each timing task to obtain a task list, so that the user may know the execution condition, the optimization effect, and the like of the translation optimization corresponding to each timing task according to the task list. The task list may include information set by a user in a user-defined manner, accumulated correction numbers, operation information corresponding to each timing task, and the like. Alternatively, the operation information may include a "pause" button, a "terminate" button, and a "view business data" button. The user can pause the timed task, i.e., pause the translation optimization corresponding to the timed task, via a "pause" button. The user can terminate the timed task, i.e., terminate the translation optimization corresponding to the timed task, via a "terminate" button. The user can view the business data corresponding to the timing task through a 'view business data' button, namely view the related data of the translation optimization corresponding to the timing task, for example, the related data of the translation optimization can comprise a final lifting number, an average lifting conversion rate and the like.
It should be understood that the cumulative correction number refers to the number of translation results corrected by the translation optimization performed by the timed task. The final increment may refer to the number of translations results that are incremented in terms of conversion or the proportion of positive evaluation in the corrected translation result as compared to its original translation result. Average conversion rate may refer to the conversion rate or the average value corresponding to the translation result in which the proportion of the positive evaluation is increased.
In another example, when only one target language corresponding to the first machine translation service is available, or when only translation optimization needs to be performed on a certain target language translated by the first machine translation service, when a user sets a timing task in a translation optimization system corresponding to the first machine translation service, a source language (i.e., the first language) corresponding to the preset content may be set only in the timing task, without setting the target language, and the electronic device may determine the target language according to information related to the first machine translation service.
It can be appreciated that the translation optimization method provided by the embodiment of the application can be applied to any machine translation scene. For example, it may be applicable to a search scenario across e-commerce and a scenario where a translation application or translation engine performs a general translation (i.e., only needs to translate preset content into content in a target language, without performing other operations), etc. Taking a search scene of a cross-border electronic commerce as an example, the translation optimization method provided by the embodiment of the application is exemplified below. In the cross-border e-commerce searching scenario, the e-commerce website can search and display targets by taking a second language (for example, english) as an index.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating a timing task setting according to an embodiment of the application.
In a cross-border e-commerce search scenario, when translation optimization needs to be performed on a first machine translation service (for example, a translation application of an electronic device system), a user can set a timing task in a translation optimization system corresponding to the first machine translation service, and relevant content of the translation optimization is defined and set. As shown in fig. 4, the timing task may include a source language (e.g. russian) corresponding to the preset content, a determination method (e.g. high frequency word, top 10000) of a specified number of preset contents, a first preset condition (e.g. conversion rate is lower than half of an average value of a website), a second machine translation service (also referred to as an automatic error correction engine, for example)Translation of,Translation of,Translation of,Translation and translationTranslation), a second preset threshold (which may also be referred to as a voting threshold, e.g., 1/2), and an execution period (which may also be referred to as an execution frequency, e.g., once a day), and a button to create a task (i.e., after setting up the relevant information, the user may click on the button to create a task to create a timed task), etc. The top10000 refers to the first 10000 preset contents with more times determined according to the translation times.
After the electronic device obtains the timing task set by user definition, the language type corresponding to the preset content can be determined to be Russian according to the source language included in the timing task, the determination mode of determining the preset content of the appointed number according to the high-frequency word, top10000 "included in the timing task is to determine the first 10000 preset contents with more translation times according to the translation times, the first candidate translation result with poor translation quality is determined according to the conversion rate being lower than half of the average value of the website, and the second machine translation service is determined to include according to the automatic error correction engineTranslation of,Translation of,Translation of,Translation and translationAnd translating, determining a second preset threshold value to be 1/2 according to the voting threshold value, and determining an execution period to be 24 hours according to the execution frequency. Meanwhile, the electronic device may determine that the target language is english according to a default setting, a specific execution time (e.g., 24:00), and a preset time period (e.g., 24 hours).
When the translation result corresponding to the first machine translation service needs to be optimized, for example, in 24:00 a day, the electronic device may acquire the received russian search terms (i.e. preset contents) within the first 24 hours, acquire the first 10000 search terms (hereinafter referred to as search terms a) with a large translation number within the 24 hours, and obtain the first candidate translation result obtained by translating the 10000 search terms a through the first machine translation service. Meanwhile, the electronic device may determine the conversion rates corresponding to the 10000 search terms a within the 24 hours, and determine whether the conversion rate corresponding to each search term a is lower than half of the average conversion rate of the website, so as to determine a search term (hereinafter referred to as a search term B) with poor translation quality of the first candidate translation result. For example, when the average conversion rate of the web site is 30%, it may be determined whether the conversion rate corresponding to each search term a is lower than 15%. When the conversion rate corresponding to a certain search word a is lower than 15%, the electronic device may determine that the translation quality of the first candidate translation result corresponding to the search word a is poor.
It should be appreciated that the average conversion rate of the website may be determined by the electronic device according to the conversion rate corresponding to each search term during the preset time of the history.
After determining the search word B with poor translation quality, for each search word B, the electronic device can respectively pass through Translation of,Translation of,Translation of,Translation and translationAnd translating the search word B to obtain English translation results, and determining second candidate translation results corresponding to the search word B and the number of the second candidate translation results according to the translation results. Then, the electronic device may determine a third candidate translation result according to the voting threshold 1/2 and the number of each second candidate translation result, and put the third candidate translation result into the temporary intervention table, so as to observe the conversion rate corresponding to the third candidate translation result in a specified future time period (for example, 10 days). When the conversion rate corresponding to the third candidate translation result and the conversion rate of the first candidate translation result corresponding to the search word B satisfy the second preset condition, for example, when the conversion rate corresponding to the third candidate translation result is greater than the conversion rate corresponding to the first candidate translation result, the electronic device may determine that the third candidate translation result is the target translation result corresponding to the search word B, and may store the search word B and the target translation result corresponding to the search word in a preset intervention table in an associated manner.
Therefore, when the search word B is received in the website, the electronic device can directly obtain the target translation result corresponding to the search word B from the preset intervention table, and can directly search and display the content according to the target translation result corresponding to the search word B.
In the search scene of the cross-border electronic commerce, the electronic equipment can quickly determine the search word with high probability of translating error (namely poorer translation quality) by determining the search word with high exposure (namely more translation times) and low conversion (namely lower conversion rate), so that the translation optimization can be performed on the search word with translating error by acquiring the result with high probability of translating accuracy through a voting mechanism of an automatic error correction engine, the accuracy of the translation result corresponding to the search word can be effectively improved, and the accuracy of website searching is improved, thereby improving website conversion.
It can be understood that after the translation optimization is executed according to the related information set by the user through the timing task customization, the electronic device may analyze the translation optimization corresponding to each timing task to obtain a task list, for example, obtain a task list shown in table 1, so that the user may know the execution condition and the execution effect of the translation optimization corresponding to each timing task according to the task list shown in table 1. The task list shown in table 1 may include information set by a user, accumulated correction numbers, operation information corresponding to each timing task, and the like. Alternatively, the operation information may include a "pause" button, a "terminate" button, and a "view business data" button. The user can pause the timed task, i.e., pause the translation optimization corresponding to the timed task, via a "pause" button. The user can terminate the timed task, i.e., terminate the translation optimization corresponding to the timed task, via a "terminate" button. The user can view the business data corresponding to the timing task through a 'view business data' button, namely view the related data of the translation optimization corresponding to the timing task, for example, the related data of the translation optimization can comprise a final lifting number, an average lifting conversion rate and the like.
TABLE 1
Referring to fig. 5, fig. 5 is a schematic diagram showing the effect of the conversion rate change corresponding to a certain search term according to an embodiment of the application.
As shown in fig. 5, for the search term, the electronic device may obtain a specified period of time (for example, ten days) before the translation optimization and a specified period of time (for example, ten days) after the translation optimization, where the conversion rate corresponding to the search term, that is, the conversion rate of the first candidate translation result corresponding to the search term, and the conversion rate of the target translation result corresponding to the search term, within ten days after the translation optimization, may be obtained by the electronic device. As can be seen from the effect diagram shown in FIG. 5, after the translation optimization method provided by the embodiment of the application optimizes the translation of the first machine translation service, the conversion rate corresponding to the search term can be effectively improved, so that the conversion of the website is improved.
Referring to fig. 6, fig. 6 shows a translation method according to an embodiment of the present application, where the method may be applied to an electronic device, and a first machine translation service is provided in the electronic device. As shown in fig. 6, the method may include:
S601, the electronic equipment acquires a translation request, wherein the translation request is used for requesting to translate content to be translated into content expressed in a second language through a first machine translation service, and the content to be translated is the content expressed in the first language;
S602, when it is determined that the preset intervention table includes content to be translated, the electronic device obtains a target translation result corresponding to the content to be translated from the preset intervention table, the target translation result corresponding to the content to be translated is content represented by a second language, the second language is different from the first language, the preset intervention table includes content represented by the first language and content represented by the corresponding second language, the content represented by the first language included in the preset intervention table is content, the translation quality obtained by a first machine translation service does not meet a first preset condition, the content represented by the second language included in the preset intervention table is obtained by at least one second machine translation service, and the second machine translation service is different from the first machine translation service;
S603, when the fact that the content to be translated is not included in the preset intervention table is determined, the electronic device obtains a target translation result corresponding to the content to be translated through the first machine translation service.
In the embodiment of the application, when the electronic device obtains the translation request, the translation request is used for requesting to translate the content to be translated, which is represented by the first language, into the content in the second language through the first machine translation service, and the electronic device can firstly determine whether the preset intervention table comprises the content to be translated. When the preset intervention table comprises the content to be translated, the electronic equipment can directly acquire the target translation result corresponding to the content to be translated from the preset intervention table, namely, the target translation result with better translation quality can be directly acquired from the preset intervention table, and the content to be translated does not need to be translated through the first machine translation service, so that the acquisition of the translation result with poorer translation quality can be avoided, the accuracy of the translation result corresponding to the content to be translated is effectively improved, and the user experience is improved.
Illustratively, before determining that the preset intervention table includes the content to be translated, the method may further include:
Acquiring a first candidate translation result, wherein the first candidate translation result is a translation result acquired through a first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is content expressed in a first language, and the first candidate translation result is content expressed in a second language;
Determining translation quality of the first candidate translation result;
when the translation quality of the first candidate translation result does not meet the first preset condition, at least one second candidate translation result corresponding to preset content is obtained through at least one second machine translation service;
determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content;
And storing the preset content and the target translation result corresponding to the preset content in a preset intervention table in a correlated mode.
The specific content for obtaining the first candidate translation result may refer to the specific content for obtaining the first candidate translation result shown in fig. 3, which is not described herein.
Similarly, the specific content for determining the translation quality of the first candidate translation result may also refer to the specific content for determining the translation quality of the first candidate translation result shown in fig. 3, which is not described herein.
Similarly, the specific content of the at least one second candidate translation result corresponding to the preset content obtained through the at least one second machine translation service may also refer to the specific content of the at least one second candidate translation result corresponding to the preset content obtained through the at least one second machine translation service shown in fig. 3, which is not described herein.
Similarly, determining the specific content of the target translation result corresponding to the preset content according to the at least one second candidate translation result corresponding to the preset content may refer to the at least one second candidate translation result corresponding to the preset content shown in fig. 3, and the specific content of the target translation result corresponding to the preset content is determined and will not be described herein.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
Corresponding to the translation optimization method described in the above embodiment, the embodiment of the present application further provides a translation optimization device, where each module of the device may correspondingly implement each step of the translation optimization method.
Corresponding to the translation method described in the foregoing embodiments, the embodiment of the present application further provides a translation device, where each module of the device may correspondingly implement each step of the translation method.
It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The embodiment of the application also provides an electronic device, which comprises at least one memory, at least one processor and a computer program stored in the at least one memory and capable of running on the at least one processor, wherein the processor executes the computer program to enable the electronic device to realize the steps in any of the method embodiments. The structure of the electronic device may be as shown in fig. 1, for example.
Embodiments of the present application also provide a computer-readable storage medium storing a computer program which, when executed by a computer, causes the computer to implement the steps of any of the respective method embodiments described above.
Embodiments of the present application provide a computer program product for causing an electronic device to carry out the steps of any of the various method embodiments described above when the computer program product is run on the electronic device.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable storage medium may include at least: any entity or device capable of carrying computer program code to an apparatus/electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (random access memory, RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer-readable storage media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (17)
1. A translation optimization method applied to an electronic device, wherein a first machine translation service is provided in the electronic device, the method comprising:
Acquiring a first candidate translation result, wherein the first candidate translation result is a translation result acquired through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is content expressed in a first language, the first candidate translation result is content expressed in a second language, and the first language is different from the second language;
determining the translation quality of the first candidate translation result;
When the translation quality of the first candidate translation result does not meet a first preset condition, at least one second candidate translation result corresponding to the preset content is obtained through at least one second machine translation service, wherein the second machine translation service is different from the first machine translation service;
And determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content.
2. The method of claim 1, wherein said determining a translation quality of said first candidate translation result comprises:
obtaining a conversion rate corresponding to the first candidate translation result, wherein the conversion rate corresponding to the first candidate translation result is the click rate of a target corresponding to the first candidate translation result within a preset duration;
And determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
3. The method according to claim 2, wherein determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result comprises:
and when the conversion rate corresponding to the first candidate translation result is smaller than a first preset threshold value, determining that the translation quality of the first candidate translation result does not meet the first preset condition.
4. A method according to any one of claims 1 to 3, wherein for said preset content, each of said second machine translation services corresponds to a translation result;
The determining, according to the at least one second candidate translation result corresponding to the preset content, a target translation result corresponding to the preset content includes:
Determining a third candidate translation result with the largest number of the at least one second candidate translation result according to the translation result corresponding to each second machine translation service, wherein the third candidate translation result is one of the at least one second candidate translation result;
And when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
5. The method of claim 4, wherein determining, according to the third candidate translation result, the target translation result corresponding to the preset content when the proportion of the number of third candidate translation results is greater than or equal to a second preset threshold value, includes:
when the proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold value, determining whether the third candidate translation results are the same as the first candidate translation results;
and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
6. The method according to claim 4 or 5, wherein the determining, according to the third candidate translation result, the target translation result corresponding to the preset content includes:
Obtaining a conversion rate corresponding to the third candidate translation result;
And when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
7. The method according to any one of claims 1 to 6, wherein after the determining the target translation result corresponding to the preset content, the method further comprises:
and storing the preset content and the target translation result corresponding to the preset content in a preset intervention table in a correlated mode.
8. The method of claim 7, wherein the method further comprises:
acquiring a translation request, wherein the translation request is used for requesting to translate content to be translated into content expressed in a second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
When the preset intervention table is determined to comprise the content to be translated, acquiring a target translation result corresponding to the content to be translated from the preset intervention table, wherein the target translation result corresponding to the content to be translated is the content expressed by the second language;
And when the preset intervention table does not contain the content to be translated, acquiring a target translation result corresponding to the content to be translated through the first machine translation service.
9. A translation method applied to an electronic device, wherein a first machine translation service is provided in the electronic device, the method comprising:
acquiring a translation request, wherein the translation request is used for requesting to translate content to be translated into content expressed in a second language through the first machine translation service, and the content to be translated is the content expressed in the first language;
When the content to be translated is determined to be included in a preset intervention table, a target translation result corresponding to the content to be translated is obtained from the preset intervention table, the target translation result corresponding to the content to be translated is content represented by a second language, the second language is different from the first language, the content represented by the first language and the corresponding content represented by the second language are included in the preset intervention table, the content represented by the first language included in the preset intervention table is content, the translation quality obtained by the first machine translation service does not meet a first preset condition, the content represented by the second language included in the preset intervention table is obtained by at least one second machine translation service, and the second machine translation service is different from the first machine translation service;
And when the preset intervention table does not contain the content to be translated, acquiring a target translation result corresponding to the content to be translated through the first machine translation service.
10. The method of claim 9, wherein prior to determining that the content to be translated is included in a preset intervention table, the method further comprises:
Acquiring a first candidate translation result, wherein the first candidate translation result is a translation result acquired through the first machine translation service, the first candidate translation result is a translation result corresponding to preset content, the preset content is the content expressed by the first language, and the first candidate translation result is the content expressed by the second language;
determining the translation quality of the first candidate translation result;
When the translation quality of the first candidate translation result does not meet the first preset condition, at least one second candidate translation result corresponding to the preset content is obtained through at least one second machine translation service;
Determining a target translation result corresponding to the preset content according to at least one second candidate translation result corresponding to the preset content;
and storing the preset content and the target translation result corresponding to the preset content in the preset intervention table in a correlated mode.
11. The method of claim 10, wherein the determining the translation quality of the first candidate translation result comprises:
obtaining a conversion rate corresponding to the first candidate translation result, wherein the conversion rate corresponding to the first candidate translation result is the click rate of a target corresponding to the first candidate translation result within a preset duration;
And determining the translation quality of the first candidate translation result according to the conversion rate corresponding to the first candidate translation result.
12. The method of claim 11, wherein determining the translation quality of the first candidate translation result based on the conversion rate corresponding to the first candidate translation result comprises:
and when the conversion rate corresponding to the first candidate translation result is smaller than a first preset threshold value, determining that the translation quality of the first candidate translation result does not meet the first preset condition.
13. The method according to any one of claims 10 to 12, wherein for the preset content, each of the second machine translation services corresponds to a translation result;
The determining, according to the at least one second candidate translation result corresponding to the preset content, a target translation result corresponding to the preset content includes:
determining the third candidate translation result with the largest number from the at least one second candidate translation result according to the translation result corresponding to each second machine translation service, wherein the third candidate translation result is one of the at least one second candidate translation result;
And when the proportion of the number of the third candidate translation results is greater than or equal to a second preset threshold value, determining a target translation result corresponding to the preset content according to the third candidate translation result.
14. The method of claim 13, wherein determining, according to the third candidate translation result, the target translation result corresponding to the preset content when the proportion of the number of third candidate translation results is greater than or equal to a second preset threshold value, includes:
when the proportion of the number of the third candidate translation results is greater than or equal to the second preset threshold value, determining whether the third candidate translation results are the same as the first candidate translation results;
and when the third candidate translation result is different from the first candidate translation result, determining a target translation result corresponding to the preset content according to the third candidate translation result.
15. The method according to claim 13 or 14, wherein determining the target translation result corresponding to the preset content according to the third candidate translation result includes:
Obtaining a conversion rate corresponding to the third candidate translation result;
And when a second preset condition is met between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result, determining the third candidate translation result as a target translation result corresponding to the preset content, wherein the second preset condition is that the difference between the conversion rate corresponding to the third candidate translation result and the conversion rate corresponding to the first candidate translation result is larger than a third preset threshold value.
16. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, causes the electronic device to implement the translation optimization method according to any one of claims 1 to 8 or to implement the translation method according to any one of claims 9 to 15.
17. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a computer, causes the computer to implement the translation optimization method according to any one of claims 1 to 8 or to implement the translation method according to any one of claims 9 to 15.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211743193.0A CN118278427A (en) | 2022-12-30 | 2022-12-30 | Translation optimization method, translation method, electronic device, and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211743193.0A CN118278427A (en) | 2022-12-30 | 2022-12-30 | Translation optimization method, translation method, electronic device, and readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118278427A true CN118278427A (en) | 2024-07-02 |
Family
ID=91649040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211743193.0A Pending CN118278427A (en) | 2022-12-30 | 2022-12-30 | Translation optimization method, translation method, electronic device, and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118278427A (en) |
-
2022
- 2022-12-30 CN CN202211743193.0A patent/CN118278427A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113905179B (en) | Method for switching cameras by terminal and terminal | |
CN115473957B (en) | Image processing method and electronic equipment | |
CN115866121B (en) | Application interface interaction method, electronic device and computer readable storage medium | |
CN110543287B (en) | Screen display method and electronic equipment | |
CN116069212B (en) | Quick looking-up method for application card, electronic equipment and storage medium | |
CN110138999B (en) | Certificate scanning method and device for mobile terminal | |
CN113542580B (en) | Method and device for removing light spots of glasses and electronic equipment | |
CN115050358A (en) | Voice control command generation method and terminal | |
CN115129410B (en) | Desktop wallpaper configuration method and device, electronic equipment and readable storage medium | |
CN115543145A (en) | Folder management method and device | |
CN112740148A (en) | Method for inputting information into input box and electronic equipment | |
CN115437601B (en) | Image ordering method, electronic device, program product and medium | |
CN112416984A (en) | Data processing method and device | |
WO2022078116A1 (en) | Brush effect picture generation method, image editing method and device, and storage medium | |
CN117880645A (en) | Image processing method and device, electronic equipment and storage medium | |
CN117009005A (en) | Display method, automobile and electronic equipment | |
CN111339513B (en) | Data sharing method and device | |
CN115730091A (en) | Comment display method and device, terminal device and readable storage medium | |
CN118278427A (en) | Translation optimization method, translation method, electronic device, and readable storage medium | |
CN115185441A (en) | Control method, control device, electronic equipment and readable storage medium | |
CN114093368A (en) | Cross-device voiceprint registration method, electronic device and storage medium | |
US20220058225A1 (en) | Information display method and apparatus | |
CN113986406B (en) | Method, device, electronic equipment and storage medium for generating doodle pattern | |
CN116703741B (en) | Image contrast generation method and device and electronic equipment | |
CN115619628B (en) | Image processing method and terminal equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication |