Translation text consistency verification method, computing device and storage medium
By obtaining the original text and translated text content during the e-book translation process, determining the words to be detected and finding the translation of the target word, the problem of inconsistent translation results of different users is solved, and the consistency checksum quality improvement of the translated text is achieved.
Patent Information
- Application Number
- CN202011330950.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-11-24
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2040-11-24
AI Technical Summary
During the translation process of e-books, due to the differences in the translation results of the same word by different users, the translation results in the same book are inconsistent, which affects the translation quality.
By obtaining the original text content and the translated text content, determine the words to be detected, and find the target word translation in the database, determine whether the translated word translation contains the target word translation. If not, a correction prompt information is generated for user editing and correction.
It effectively eliminates the differences in translation results, ensures the consistency of the translation of the same word in the same book, improves the quality of translation, and is convenient for users to read.
Smart Images

Figure CN112434537B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a translation text consistency verification method, a computing device and a storage medium. Background Art
[0002] Books in the form of e-books are loved by a large number of people because of their advantages such as easy access. For some books, the text content needs to be translated into a foreign language version for publication so that users who understand foreign languages can read the books. Among them, for the translation of a book, especially a book with a lot of text content, in order to complete the translation of the entire book quickly, it is likely that the text content of the entire book will be divided into multiple translation tasks and assigned to different users for translation. In other words, the translation task of a book is undertaken by different users. The same word is likely to appear in different locations in the same book, such as different chapters or different paragraphs, and the translation results of the same word by different users may be different, resulting in inconsistent translation results of the same word in the same book, poor translation quality, and inconvenience for users to read. Summary of the invention
[0003] In view of the above problems, the present invention is proposed to provide a translation text consistency verification method, computing device and storage medium that overcome the above problems or at least partially solve the above problems.
[0004] According to one aspect of the present invention, a translation text consistency verification method is provided, the method comprising:
[0005] Obtain the original text content and the translated text content to be verified, and determine the words to be detected in the original text content;
[0006] Searching the database for the target word translation corresponding to the word to be detected;
[0007] Determine whether the translation text contains the target word translation;
[0008] If not, correction prompt information including the translation of the target word is generated and presented in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0009] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;
[0010] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations:
[0011] Obtain the original text content and the translated text content to be verified, and determine the words to be detected in the original text content;
[0012] Searching the database for the target word translation corresponding to the word to be detected;
[0013] Determine whether the translation text contains the target word translation;
[0014] If not, correction prompt information including the translation of the target word is generated and presented in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0015] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned translation text consistency verification method.
[0016] According to the technical solution provided by the present invention, the original text content and the translated text content to be verified are obtained, and the words to be detected in the original text content and the target word translations corresponding to the words to be detected in the database are determined. By judging whether the original text content contains the target word translation, it is determined whether the user's translation of the words to be detected is correct. If the user has a deviation in the translation of the words to be detected, correction prompt information containing the target word translation can be automatically generated and presented, so that the user can conveniently edit and correct the translated text content according to the correction prompt information, which effectively ensures the consistency of the translation of the same words to be detected in the same book, effectively improves the translation quality, and facilitates user reading.
[0017] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0019] Figure 1 A schematic diagram of a process of checking the consistency of a translation text according to the first embodiment of the present invention is shown;
[0020] Figure 2a A schematic diagram of a process of checking the consistency of a translation text according to the second embodiment of the present invention is shown;
[0021] Figure 2b A schematic diagram of a translation interface is shown;
[0022] Figure 3 A schematic diagram of the structure of a computing device according to a fourth embodiment of the present invention is shown. DETAILED DESCRIPTION
[0023] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0024] In actual application scenarios, some e-book service operators have the need to translate books into different language versions, for example, Chinese books need to be made into English versions and published online for English users to read. In this scenario, translation tasks can be issued to users, and users undertake translation tasks. Users who undertake translation tasks complete the translation work in a translation tool implemented based on the method of the present invention. Among them, the translation task of a book can be undertaken by different users. For example, users can undertake translation tasks according to the chapters of a book, that is, different chapters of a book can be undertaken by different users. Considering that the same word is likely to appear in multiple locations in a book, and there are certain differences in the translation results of the same word by different users, the present invention provides a translation text consistency verification method, which effectively eliminates the differences in translation results, so as to ensure the consistency of the translation of the same word to be detected in the same book, effectively improve the translation quality, and facilitate user reading. The present invention is introduced below through specific embodiments.
[0025] Embodiment 1
[0026] Figure 1 A schematic diagram of a translation text consistency verification method according to the first embodiment of the present invention is shown. Figure 1 As shown, the method comprises the following steps:
[0027] Step S101, obtaining the original text content and the translated text content to be verified, and determining the words to be detected in the original text content.
[0028] This embodiment provides a translation interface, and the user can perform translation operations in the translation interface. After the user completes the translation, the translated text content can be submitted. Then, in step S101, the original text content translated by the user can be obtained from the resource file of the book (such as a TXT file, etc.) as the original text content to be verified, and the translated text content submitted by the user can be obtained as the translated text content to be verified. Among them, the resource file can be obtained from a book library or the cloud.
[0029] After obtaining the original text content to be verified, each word contained in the original text content can be analyzed to determine the words to be detected contained in the original text content. Specifically, the words to be detected may include: named entity words such as names of people, places, and names of objects, and may also include words of designated parts of speech whose frequency of appearance in the corresponding books exceeds a preset threshold. Those skilled in the art may set the designated parts of speech according to actual needs, for example, the designated parts of speech may include nouns, verbs, adjectives, etc.
[0030] Step S102, searching the database for the target word translation corresponding to the word to be detected.
[0031] After determining the words to be detected contained in the original text content, the target word translation corresponding to the words to be detected can be searched in the database. Among them, the database may include a pre-established keyword library and a translation database corresponding to a preset translation tool. The keyword library records the word translations corresponding to each named entity word, and can also record the word translations corresponding to each word of a specified part of speech. Specifically, the word translation corresponding to the words to be detected can be preferentially searched in the keyword library. If the word translation corresponding to the words to be detected is not found in the keyword library, then the translation database corresponding to the preset translation tool is searched again to determine the target word translation corresponding to the words to be detected.
[0032] Step S103, determining whether the translation text content contains the target word translation; if so, executing step S104; if not, executing step S105.
[0033] Considering that the grammatical structures of different languages may be different, after translating the original text content into the translated text content, the position of the word to be detected in the original text content and the position of the word translation corresponding to the word to be detected in the translated text content may not be completely consistent, making it difficult to accurately find the word translation corresponding to the word to be detected in the translated text content by position matching. Therefore, in this embodiment, a fuzzy detection method is adopted. As long as the translated text content contains the target word translation corresponding to the word to be detected determined in step S102, it can be considered that the user's translation of the word to be detected is correct. Specifically, it can be determined whether the translated text content contains the target word translation; if so, step S104 is executed; if not, step S105 is executed.
[0034] Step S104: taking the translated text content as the target translated text content.
[0035] If it is determined in step S103 that the translation text content contains the translation of the target word, it can be considered that the user's translation of the detected word is correct, and the translation text content is used as the target translation text content, which refers to the final translation text content.
[0036] Step S105, generating correction prompt information including the translation of the target word, and presenting the correction prompt information in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0037] In the case where the translation text does not contain the target word translation as determined in step S103, it can be considered that the user's translation of the detected word is biased and the translation text needs to be edited and corrected. In step S105, correction prompt information containing the target word translation can be generated and presented in the translation interface, so that the user can conveniently edit and correct the translation text content according to the correction prompt information. Those skilled in the art can set the specific content of the correction prompt information according to actual needs, which is not limited here.
[0038] By utilizing the translation text consistency verification method provided in this embodiment, the original text content and the translated text content to be verified are obtained, and the words to be detected in the original text content and the target word translations corresponding to the words to be detected in the database are determined. By judging whether the original text content contains the target word translation, it is determined whether the user's translation of the words to be detected is correct. If the user's translation of the words to be detected has deviations, correction prompt information containing the target word translation can be automatically generated and presented, so that the user can conveniently edit and correct the translated text content according to the correction prompt information, effectively eliminating the differences in translation results, effectively ensuring the consistency of the translation of the same words to be detected in the same book, effectively improving the translation quality, and facilitating user reading.
[0039] Embodiment 2
[0040] Figure 2a A schematic diagram of a translation text consistency verification method according to Embodiment 2 of the present invention is shown. Figure 2a As shown, the method comprises the following steps:
[0041] Step S201, obtaining the original text content and the translated text content to be verified, and determining the words to be detected in the original text content.
[0042] In order to facilitate users to translate, this embodiment provides a translation interface, and users can perform translation operations in the translation interface. Figure 2b A schematic diagram of a translation interface is shown, such as Figure 2b As shown, the translation interface includes a first area, a second area, a third area, and a fourth area. The book to which the translation task undertaken by the user belongs is called a designated book, and the user can undertake the translation task of at least one chapter of the designated book. In this embodiment, the text content of the Chinese book is translated into English, where "X" represents Chinese characters and "*" represents English characters. Specifically, the first area is used to display at least one chapter label element corresponding to at least one chapter of the designated book undertaken by the user. The chapter label element may include relevant information such as the serial number and title of the chapter for the user to view, such as Figure 2b The first area displays the chapter label elements from Chapter 1 to Chapter 10, where "Chapter 1 XXX" is the chapter number and "XXX" is the chapter title. Users can trigger any chapter label element to display the original text content of each text block corresponding to the chapter label element in the second area.
[0043] In order to facilitate users' translation, the original text content corresponding to the chapter label elements can be divided into text blocks according to dimensions such as paragraphs or sentences to obtain multiple text blocks and determine the serial number label of each text block. Using the text block as the smallest translation unit helps to improve the accuracy and efficiency of translation. The second area is used to display the original text content of each text block corresponding to any chapter label element for users to refer to during the translation process. The original text content can be obtained through the resource file of the specified book, such as a TXT file, etc. The resource file can be obtained from a book library or the cloud. Figure 2b As shown, the display content in the first row of the table in the second area includes: serial number label 1 and the text block corresponding to serial number label 1, and the display content in the second row of the table includes: serial number label 2 and the text block corresponding to serial number label 2...
[0044] The third area and the fourth area are used to display the initial translation text content corresponding to each text block. The initial translation text content corresponding to each text block is obtained by inputting each text block into a designated translation tool for translation processing, so as to provide a reference for the user when translating, which helps to improve the user's translation efficiency. Those skilled in the art can select the designated translation tool according to actual needs, which is not limited here. For example, the designated translation tool can be an online translation tool or a local translation tool. Among them, the initial translation text of each text block can be displayed in a separate line. Figure 2b As shown, Figure 2b The display content in the first row of the table in the third area is: the initial translation text content of the text block corresponding to serial number label 1, the display content in the second row is: the initial translation text content of the text block corresponding to serial number label 2, and so on.
[0045] The fourth area is the translation editing area. When initialized, the fourth area is used to display the initial translation text content corresponding to each text block, which is the same as the initial translation text content displayed in the third area. The user can perform editing processing such as addition, deletion, and modification on the initial translation text content displayed in the fourth area to form the edited translation text content, and update the edited translation text content to be displayed in the fourth area, that is, the fourth area is also used to display the edited translation text content of the initial translation text content. If the user believes that the initial translation text content corresponding to a text block has been translated relatively accurately and does not need to be modified, then the initial translation text content does not need to be edited.
[0046] After the user completes the translation of several text blocks, the user can determine the initial translation text content or the edited translation text content to be submitted by checking the selection elements in the fourth area, and submit it by triggering the "Submit Translation" control in the translation interface; or, in the translation interface, a corresponding submission control ( Figure 2b ), and the corresponding initial translated text content or the edited translated text content is submitted by triggering the submit control. Then in step S201, in response to the user's submission operation for the initial translated text content or the edited translated text content corresponding to at least one text block, the original text content of at least one text block is obtained as the original text content to be verified, and the initial translated text content or the edited translated text content corresponding to at least one text block in the fourth area is obtained as the translated text content to be verified.
[0047] After obtaining the original text content to be verified, it is necessary to analyze each word contained in the original text content to determine the words to be detected contained in the original text content. In order to accurately and quickly determine the words to be detected contained in the original text content, a set of words to be detected for a specified book can be pre-established before determining the words to be detected in the original text content. Among them, named entity words such as names of people, places, and names of objects in the specified book can be added to the set of words to be detected as words to be detected, and words of the specified part of speech whose word frequency exceeds a preset threshold in the specified book can also be added to the set of words to be detected as words to be detected. Specifically, the resource file of the specified book is retrieved, the text content of the specified book is obtained from the resource file, the text content is segmented to obtain a second word set, and the named entity words and / or words of the specified part of speech whose word frequency exceeds a preset threshold are searched in the second word set to establish a set of words to be detected containing multiple words to be detected.
[0048] Among them, the words that match the named entity word library can be searched in the second word set, so as to determine the named entity words included in the second word set, and the determined named entity words are added to the word set to be detected as words to be detected. Those skilled in the art can set the preset threshold and the specified part of speech according to actual needs, which is not limited here. For example, the preset threshold can be set to 10, and the specified part of speech can be set to include nouns, verbs and adjectives. Then, the frequency of each word in the second word set appearing in the specified book is counted, and the word frequency is identified for words with a word frequency exceeding 10, and the words with a part of speech of nouns, the words with a part of speech of verbs and the words with a part of speech of adjectives are searched therefrom, and the words found are added to the word set to be detected as words to be detected; or, the words with a word frequency exceeding 10 can be identified by part of speech, and the words with adverbs, prepositions and other parts of speech are removed therefrom, and the remaining words of noun part of speech, verb part of speech and adjective part of speech are added to the word set to be detected as words to be detected.
[0049] After completing the establishment of the set of words to be detected for the specified book, the original text content is segmented to obtain the first word set, and then the first word set is searched for words that match the pre-established set of words to be detected to obtain the words to be detected in the original text content. In other words, the matching words found are used as the words to be detected in the original text content.
[0050] Step S202, searching the database for the target word translation corresponding to the word to be detected.
[0051] The database includes a pre-established keyword library and a translation database corresponding to a preset translation tool. The keyword library records the word translations corresponding to each named entity word, and can also record the word translations corresponding to each word of a specified part of speech. Specifically, the keyword library is searched to see whether it contains the word translation corresponding to the word to be detected; if the word translation corresponding to the word to be detected can be found in the keyword library, the word translation found is used as the target word translation corresponding to the word to be detected; if the word translation corresponding to the word to be detected is not found in the keyword library, at least two preset translation tools are used to search in the corresponding translation database, that is, the word translation corresponding to the word to be detected is searched in at least two translation databases, and the word translation with a higher word frequency appearing in the search result is used as the target word translation corresponding to the word to be detected, that is, the word translation with a higher degree of repetition is used as the target word translation corresponding to the word to be detected. Among them, at least two preset translation tools can be online translation tools or local translation tools operated and managed by different translation operators. For example, a word translation corresponding to a word to be detected is searched in two translation databases, where the word translations found in the first translation database include "translation 1 and translation 2", and the word translations found in the second translation database include "translation 1, translation 3 and translation 4". Then the word frequency of translation 1 in the search results of the two translation databases is 2, and the word frequencies of translation 2, translation 3 and translation 4 in the search results of the two translation databases are all 1. Then the word frequency of translation 1 is higher, indicating that translation 1 is more commonly used, and then translation 1 is used as the target word translation corresponding to the word to be detected.
[0052] Step S203, determining whether the translation text content contains the target word translation; if so, executing step S204; if not, executing step S205.
[0053] In this embodiment, a fuzzy detection method is adopted. As long as the translated text content contains the target word translation corresponding to the to-be-detected word determined in step S202, it can be considered that the user's translation of the to-be-detected word is correct. Specifically, a string matching can be performed on the translated text content to determine whether the translated text content contains the target word translation; if so, step S204 is executed; if not, step S205 is executed.
[0054] Step S204: taking the translated text content as the target translated text content.
[0055] Step S205, generating correction prompt information including the translation of the target word, and presenting the correction prompt information in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0056] When it is determined in step S203 that the translated text content does not contain the translation of the target word, it can be considered that the user's translation of the word to be detected is biased, and the translated text content needs to be edited and corrected. In step S205, correction prompt information containing the translation of the target word can be generated, and the correction prompt information can be presented in the translation interface so that the user can easily edit and correct the translated text content according to the correction prompt information. For example, if the word to be detected is "Shanghai" and the target word translation corresponding to the word to be detected is "Shanghai", the specific content of the generated correction prompt information can be "The correct translation of the word "Shanghai" should be "Shanghai", please modify the corresponding content in the translated text content".
[0057] Step S206, determining whether the edited and corrected translation text content is received within a preset time period; if so, executing step S207; if not, executing step S210.
[0058] Those skilled in the art may set the preset time period according to actual needs, for example, the preset time period may be set to 5 minutes.
[0059] Step S207, detecting whether the translated text after editing and correction contains the target word translation; if so, executing step S208; if not, executing step S209.
[0060] After receiving the translated text content that has been edited and corrected, it is checked whether it contains the translation of the target word, thus realizing a secondary check of the translated text content and effectively ensuring the consistency of the translated text.
[0061] Step S208: taking the edited and corrected translated text content as the target translated text content.
[0062] If the edited and corrected translated text content detected in step S207 contains the target word translation, it can be considered that the user's translation of the word to be detected is correct after editing and correction, and the edited and corrected translated text content is used as the target translated text content.
[0063] Step S209, searching for the word translation corresponding to the word to be detected in the edited and corrected translated text content, and replacing the word translation with the target word translation to obtain the target translated text content.
[0064] If it is detected in step S207 that the translation text content after editing and correction does not contain the translation of the target word, it can be considered that there is still a deviation in the translation of the word to be detected after editing and correction by the user, and the word translation corresponding to the word to be detected in the translation text content after editing and correction can be automatically replaced with the target word translation.
[0065] In step S209, the detection range of the translated text content processed by editing and correction can be determined according to the position information such as the number of lines and the number of sentences of the words to be detected in the original text content. Specifically, the number of lines of the words to be detected in the original text content can be based on the number of lines, and N redundant lines are extended up and down, and the extended range is used as the detection range. For example, when N is set to 1, if the number of lines of a certain word to be detected in the original text content is the 2nd line, then based on the 2nd line, 1 redundant line is extended up and down, and the extended range is the range from the 1st line to the 3rd line of the translated text content processed by editing and correction, and this range is used as the detection range. After determining the detection range, the translation of the named entity words and / or the translation of the words of the specified part of speech are searched in the detection range of the translated text content processed by editing and correction, and the first translation set is obtained. When the translated text content is English, considering that the word translation of the name usually has the feature of capitalized first letters, the word translation with the feature of capitalized first letters can also be found in the detection range to be added to the first translation set.
[0066] In order to accurately find the word translation corresponding to the word to be detected from the detection range, it is also necessary to obtain all the word translations corresponding to the word to be detected from the database to obtain a second translation set. For example, all the word translations corresponding to the word to be detected can be obtained from a pre-established keyword library and a translation database corresponding to a preset translation tool to obtain as many word translations as possible to form a second translation set. Then, the word translation matching the second translation set is searched in the first translation set, and the matching word translation is used as the word translation corresponding to the word to be detected in the edited and corrected translation text content, and the word translation is replaced with the target word translation to obtain the target translation text content.
[0067] Step S210, searching the translation text content for the word translation corresponding to the word to be detected, and replacing the word translation with the target word translation to obtain the target translation text content.
[0068] If the translated text content that has been edited and corrected is not received within a preset time period, the word translation corresponding to the word to be detected is searched in the translated text content, and the word translation is automatically replaced with the target word translation. Specifically, according to the position information of the word to be detected in the original text content, the detection range of the translated text content is determined, and the named entity word translation and / or the word translation of the specified part of speech are searched in the detection range to obtain a first translation set; all word translations corresponding to the word to be detected are obtained from the database to obtain a second translation set; the word translation matching the second translation set is searched in the first translation set, and the matching word translation is used as the word translation corresponding to the word to be detected in the translated text content. This method of searching for the word translation corresponding to the word to be detected in the translated text content is the same as the method of searching for the word translation corresponding to the word to be detected in the translated text content that has been edited and corrected, and will not be repeated here.
[0069] Optionally, the present embodiment also provides a full-text translation search function, and the translation interface also includes a search portal. If the user cannot accurately grasp the translation of a certain word during the translation of a certain text block, the full-text translation search function can be used to view the translation results of the word by other users in their corresponding contracted chapters for reference. Specifically, the user can enter a search term in the search portal and generate a translation search request through triggering. Then, in response to the translation search request carrying the search term triggered by the search portal, the search term is used to search for the word translation corresponding to the search term in the target translation text content corresponding to at least one chapter of the specified book, generate a translation search result containing the found word translation, and then present the translation search result in the translation interface. Optionally, the translation search result can be presented through a pop-up page.
[0070] By using the translation text consistency verification method provided in this embodiment, a translation interface including four areas is provided, which is convenient for users to translate by comparing the original text content and the initial translation text content, effectively improving the translation efficiency and translation accuracy; and the original text content and the translation text content corresponding to the text block translated by the user are verified. By querying the keyword library and the translation database, the target word translation corresponding to the to-be-detected word in the original text content can be accurately determined. By judging whether the original text content contains the target word translation, it is determined whether the user's translation of the to-be-detected word is correct. If the user's translation of the to-be-detected word has deviations, a correction containing the target word translation can be automatically generated and presented. Prompt information is provided so that the user can conveniently edit and correct the translated text content according to the correction prompt information; if the user does not edit and correct the translated text content or there is still a deviation in the translation of the to-be-detected word after editing and correction, the word translation corresponding to the to-be-detected word in the translated text content can be automatically replaced with the target word translation, effectively ensuring the consistency of the translation of the same to-be-detected word in each chapter of the same book, effectively improving the translation quality, and facilitating user reading; in addition, a full-text translation search function is also provided, allowing users to view other users' translation results of words in their corresponding contracted chapters through search for reference, thereby further improving translation efficiency and translation accuracy, and facilitating user translation.
[0071] Embodiment 3
[0072] Embodiment 3 of the present invention provides a non-volatile storage medium, wherein the storage medium stores at least one executable instruction, and the executable instruction can execute the translation text consistency verification method in any of the above method embodiments.
[0073] The executable instructions can be specifically used to enable the processor to perform the following operations: obtain the original text content and the translated text content to be verified, and determine the words to be detected in the original text content; search the database for the target word translation corresponding to the words to be detected; determine whether the translated text content contains the target word translation; if not, generate correction prompt information containing the target word translation, and present the correction prompt information in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0074] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: segment the original text content to obtain a first word set, search the first word set for words that match a pre-established word set to be detected, and obtain the words to be detected in the original text content.
[0075] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: obtain the text content of a specified book, segment the text content to obtain a second word set; search the second word set for named entity words and / or words of a specified part of speech whose frequency exceeds a preset threshold, and establish a word set to be detected that includes multiple words to be detected.
[0076] In an optional embodiment, the database includes a pre-established keyword library and a translation database corresponding to a preset translation tool; the executable instructions further cause the processor to perform the following operations: search the keyword library to see whether it contains a word translation corresponding to the word to be detected; if so, use the found word translation as the target word translation corresponding to the word to be detected; if not, search for the word translation corresponding to the word to be detected in at least two translation databases, and use the word translation with a higher word frequency as the target word translation corresponding to the word to be detected.
[0077] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: determine whether the edited and corrected translation text content is received within a preset time period; if not, search the translation text content for the word translation corresponding to the word to be detected, and replace the word translation with the target word translation to obtain the target translation text content.
[0078] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: determine the detection scope of the translated text content based on the position information of the words to be detected in the original text content, and search for the translation of named entity words and / or the translation of words of specified parts of speech in the detection scope to obtain a first translation set; obtain all word translations corresponding to the words to be detected from the database to obtain a second translation set; search for word translations that match the second translation set in the first translation set, and use the matching word translations as the word translations corresponding to the words to be detected in the translated text content.
[0079] In an optional embodiment, the translation interface includes a first area, a second area, a third area and a fourth area; wherein the first area is used to display at least one chapter label element corresponding to at least one chapter of a specified book, the second area is used to display the original text content of each text block corresponding to any chapter label element, the third area is used to display the initial translated text content corresponding to each text block, and the fourth area is used to display the initial translated text content corresponding to each text block or the translated text content after editing the initial translated text content.
[0080] In an optional embodiment, the executable instructions further cause the processor to perform the following operations: in response to a submission operation performed by a user for the initial translated text content or the edited translated text content corresponding to at least one text block, obtain the original text content of the at least one text block as the original text content to be verified, and obtain the initial translated text content or the edited translated text content corresponding to the at least one text block in the fourth area as the translated text content to be verified.
[0081] In an optional embodiment, the translation interface also includes a search portal; the executable instructions further cause the processor to perform the following operations: in response to a translation search request carrying a search term triggered by the search portal, search for a term translation corresponding to the search term in the target translation text content corresponding to at least one chapter of the specified book; generate a translation search result including the found term translation, and present the translation search result in the translation interface.
[0082] Embodiment 4
[0083] Figure 3 A schematic diagram of the structure of a computing device according to Embodiment 4 of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.
[0084] like Figure 3 As shown, the computing device may include: a processor (processor) 302 , a communication interface (Communications Interface) 304 , a memory (memory) 306 , and a communication bus 308 .
[0085] in:
[0086] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via the communication bus 308 .
[0087] The communication interface 304 is used to communicate with other devices such as clients or other servers.
[0088] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above-mentioned translation text consistency verification method embodiment.
[0089] Specifically, the program 310 may include program codes, which include computer operation instructions.
[0090] The processor 302 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0091] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0092] Program 310 can be specifically used to enable processor 302 to perform the following operations: obtain the original text content and translated text content to be verified, and determine the words to be detected in the original text content; search the database for the target word translation corresponding to the words to be detected; determine whether the translated text content contains the target word translation; if not, generate correction prompt information containing the target word translation, and present the correction prompt information in the translation interface, so that the user can edit and correct the translated text content according to the correction prompt information.
[0093] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: segment the original text content to obtain a first word set, search the first word set for words that match a pre-established word set to be detected, and obtain the words to be detected in the original text content.
[0094] In an optional embodiment, the program 310 further enables the processor 302 to perform the following operations: obtain the text content of the specified book, segment the text content to obtain a second word set; search the second word set for named entity words and / or words of a specified part of speech whose frequency exceeds a preset threshold, and establish a word set to be detected that includes multiple words to be detected.
[0095] In an optional embodiment, the database includes a pre-established keyword library and a translation database corresponding to a preset translation tool; the program 310 further enables the processor 302 to perform the following operations: search the keyword library to see whether it contains a word translation corresponding to the word to be detected; if so, use the found word translation as the target word translation corresponding to the word to be detected; if not, search for the word translation corresponding to the word to be detected in at least two translation databases, and use the word translation with a higher word frequency as the target word translation corresponding to the word to be detected.
[0096] In an optional embodiment, the program 310 further enables the processor 302 to perform the following operations: determine whether the edited and corrected translation text content is received within a preset time period; if not, search the translation text content for the word translation corresponding to the word to be detected, and replace the word translation with the target word translation to obtain the target translation text content.
[0097] In an optional implementation, the program 310 further enables the processor 302 to perform the following operations: determine the detection scope of the translated text content based on the position information of the words to be detected in the original text content, and search for the translation of named entity words and / or the translation of words of specified parts of speech in the detection scope to obtain a first translation set; obtain all word translations corresponding to the words to be detected from the database to obtain a second translation set; search for word translations that match the second translation set in the first translation set, and use the matching word translations as the word translations corresponding to the words to be detected in the translated text content.
[0098] In an optional embodiment, the translation interface includes a first area, a second area, a third area and a fourth area; wherein the first area is used to display at least one chapter label element corresponding to at least one chapter of a specified book, the second area is used to display the original text content of each text block corresponding to any chapter label element, the third area is used to display the initial translated text content corresponding to each text block, and the fourth area is used to display the initial translated text content corresponding to each text block or the translated text content after editing the initial translated text content.
[0099] In an optional embodiment, the program 310 further enables the processor 302 to perform the following operations: in response to a user's submission operation for the initial translated text content or the edited translated text content corresponding to at least one text block, obtain the original text content of the at least one text block as the original text content to be verified, and obtain the initial translated text content or the edited translated text content corresponding to the at least one text block in the fourth area as the translated text content to be verified.
[0100] In an optional embodiment, the translation interface also includes a search portal; the program 310 further causes the processor 302 to perform the following operations: in response to a translation search request carrying a search term triggered by the search portal, search for a word translation corresponding to the search term in the target translation text content corresponding to at least one chapter of the specified book; generate a translation search result including the found word translation, and present the translation search result in the translation interface.
[0101] The specific implementation of each step in program 310 can refer to the description of the corresponding steps in the above-mentioned translation text consistency verification embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.
[0102] Through the scheme provided in this embodiment, the words to be detected in the original text content and the target word translations corresponding to the words to be detected in the database are determined, and whether the user's translation of the words to be detected is correct is determined by judging whether the original text content contains the target word translation. If the user's translation of the words to be detected has deviations, correction prompt information containing the target word translation can be automatically generated and presented to prompt the user to make editing corrections, thereby effectively ensuring the consistency of the translation of the same words to be detected in the same book, effectively improving the translation quality, and facilitating user reading.
[0103] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages can be utilized to realize the content of the present invention described herein, and the description of the above specific languages is for disclosing the best mode of the present invention.
[0104] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0105] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.
[0106] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.
[0107] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.
[0108] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including a number of different elements and by means of a suitably programmed computer. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.
Claims
1. A translation text consistency verification method, comprising: Obtaining the original text content and the translated text content to be verified, and determining the words to be detected in the original text content; Searching the database for the target word translation corresponding to the word to be detected; Determining whether the translation text content contains the target word translation; If not, generating correction prompt information including the translation of the target word, and presenting the correction prompt information in the translation interface, so that the user can edit and correct the translation text content according to the correction prompt information; The translation interface includes a first area, a second area, a third area and a fourth area; wherein the first area is used to display at least one chapter label element corresponding to at least one chapter of the specified book, the second area is used to display the original text content of each text block corresponding to any chapter label element, the third area is used to display the initial translation text content corresponding to each text block, and the fourth area is used to display the initial translation text content corresponding to each text block or the translation text content after editing the initial translation text content; the initial translation text content corresponding to each text block is obtained by inputting each text block into a specified translation tool for translation processing, so as to be used as a reference for the user when translating, and the user undertakes the translation task of at least one chapter of the specified book; The obtaining of the original text content and the translated text content to be verified further includes: in response to a submission operation performed by a user on the initial translated text content or the edited translated text content corresponding to at least one text block, obtaining the original text content of the at least one text block as the original text content to be verified, and obtaining the initial translated text content or the edited translated text content corresponding to the at least one text block in the fourth area as the translated text content to be verified.
2. According to the method of claim 1, the step of determining the words to be detected in the original text content further comprises: The original text content is segmented to obtain a first word set, and words matching a pre-established word set to be detected are searched in the first word set to obtain the words to be detected in the original text content.
3. According to the method of claim 2, before determining the words to be detected in the original text content, the method further comprises: Acquire text content of a specified book, and segment the text content to obtain a second word set; Named entity words and / or words of a specified part of speech whose word frequency exceeds a preset threshold are searched in the second word set to establish a to-be-detected word set including a plurality of to-be-detected words.
4. The method according to claim 1, wherein the database comprises a pre-established keyword library and a translation database corresponding to a preset translation tool; The step of searching the database for the target word translation corresponding to the word to be detected further comprises: Searching the keyword library to see whether the word translation corresponding to the word to be detected is included; If yes, the found word translation is used as the target word translation corresponding to the word to be detected; If not, then search for the word translation corresponding to the word to be detected in at least two translation databases, and use the word translation with a higher word frequency as the target word translation corresponding to the word to be detected.
5. The method according to claim 1, further comprising: Determining whether the edited and corrected translated text content has been received within a preset time period; If not, then the word translation corresponding to the to-be-detected word is searched in the translation text content, and the word translation is replaced with the target word translation to obtain the target translation text content.
6. The method according to claim 5, wherein searching the translated text content for a word translation corresponding to the word to be detected further comprises: Determine the detection range of the translated text content according to the position information of the words to be detected in the original text content, and search for translations of named entity words and / or translations of words with specified parts of speech in the detection range to obtain a first translation set; Acquire all word translations corresponding to the to-be-detected word from the database to obtain a second translation set; The first translation set is searched for word translations that match the second translation set, and the matching word translations are used as word translations corresponding to the to-be-detected words in the translation text content.
7. The method according to any one of claims 1 to 6, wherein the translation interface further comprises a search entry, and the method further comprises: In response to a translation search request carrying a search term triggered by the search entry, searching for a term translation corresponding to the search term in target translation text content corresponding to at least one chapter of a specified book; A translation search result including the translation of the searched term is generated, and the translation search result is presented in a translation interface.
8. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following operations: Obtaining the original text content and the translated text content to be verified, and determining the words to be detected in the original text content; Searching the database for the target word translation corresponding to the word to be detected; Determining whether the translation text content contains the target word translation; If not, generating correction prompt information including the translation of the target word, and presenting the correction prompt information in the translation interface, so that the user can edit and correct the translation text content according to the correction prompt information; The translation interface includes a first area, a second area, a third area and a fourth area; wherein the first area is used to display at least one chapter label element corresponding to at least one chapter of the specified book, the second area is used to display the original text content of each text block corresponding to any chapter label element, the third area is used to display the initial translation text content corresponding to each text block, and the fourth area is used to display the initial translation text content corresponding to each text block or the translation text content after editing the initial translation text content; the initial translation text content corresponding to each text block is obtained by inputting each text block into a specified translation tool for translation processing, so as to be used as a reference for the user when translating, and the user undertakes the translation task of at least one chapter of the specified book; The executable instructions further cause the processor to perform the following operations: in response to a submission operation performed by a user for an initial translated text content or an edited translated text content corresponding to at least one text block, obtain the original text content of the at least one text block as the original text content to be verified, and obtain the initial translated text content or the edited translated text content corresponding to the at least one text block in the fourth area as the translated text content to be verified.
9. The computing device of claim 8, wherein the executable instructions further cause the processor to: The original text content is segmented to obtain a first word set, and words matching a pre-established word set to be detected are searched in the first word set to obtain the words to be detected in the original text content.
10. The computing device of claim 9, wherein the executable instructions further cause the processor to: Acquire text content of a specified book, and segment the text content to obtain a second word set; Named entity words and / or words of a specified part of speech whose word frequency exceeds a preset threshold are searched in the second word set to establish a to-be-detected word set including a plurality of to-be-detected words.
11. The computing device according to claim 8, wherein the database comprises a pre-established keyword library and a translation database corresponding to a preset translation tool; and the executable instructions further cause the processor to perform the following operations: Searching the keyword library to see whether the word translation corresponding to the word to be detected is included; If yes, the found word translation is used as the target word translation corresponding to the word to be detected; If not, then search for the word translation corresponding to the word to be detected in at least two translation databases, and use the word translation with a higher word frequency as the target word translation corresponding to the word to be detected.
12. The computing device of claim 8, wherein the executable instructions further cause the processor to: Determining whether the edited and corrected translated text content has been received within a preset time period; If not, then the word translation corresponding to the to-be-detected word is searched in the translation text content, and the word translation is replaced with the target word translation to obtain the target translation text content.
13. The computing device of claim 12, wherein the executable instructions further cause the processor to: Determine the detection range of the translated text content according to the position information of the words to be detected in the original text content, and search for translations of named entity words and / or translations of words with specified parts of speech in the detection range to obtain a first translation set; Acquire all word translations corresponding to the to-be-detected word from the database to obtain a second translation set; The first translation set is searched for word translations that match the second translation set, and the matching word translations are used as word translations corresponding to the to-be-detected words in the translation text content.
14. The computing device according to any one of claims 8 to 13, wherein the translation interface further comprises a search entry; and the executable instructions further cause the processor to perform the following operations: In response to a translation search request carrying a search term triggered by the search entry, searching for a term translation corresponding to the search term in target translation text content corresponding to at least one chapter of a specified book; A translation search result including the translation of the searched term is generated, and the translation search result is presented in a translation interface.
15. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the translation text consistency verification method according to any one of claims 1 to 7.
Citation Information
Patent Citations
English-Chinese machine translation term consistency self-correction system and method
CN110807338A
