A data interaction method and system for translation process

Through the preset return body library and dynamic update of translation features, the problem of insufficient accuracy of machine translation tools in translation is solved, the translation efficiency and accuracy are improved, and the adaptive update of auxiliary libraries is realized.

CN113988091BActive Publication Date: 2024-11-22IOL WUHAN INFORMATION TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202111303181.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-05
Publication Date
2024-11-22
Estimated Expiration
2041-11-05

AI Technical Summary

Technical Problem

The existing machine translation tools are insufficient in the translation process, which leads to the translator need to repeatedly and manually confirm the candidate translation results, which reduces the translation efficiency, and the auxiliary library is static and cannot adaptively change, limiting the translator's active usage rate.

Method used

The preset return library is used to assist in the translation process. By identifying the keywords in the document to be translated, the control box is displayed and the return library is updated, and the return library is dynamically generated and updated using the translation features to improve the response speed and accuracy.

Benefits of technology

It improves the response speed and accuracy of the translation process, dynamic updates and return to the body library, enhances the real-time and effectiveness of auxiliary tools, and improves the translation efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113988091B_ABST
    Figure CN113988091B_ABST
Patent Text Reader

Abstract

The present invention proposes a data interaction method and system for a translation process. The method comprises: S101 importing a document to be translated, S102 displaying a first control box, S103 popping up a fill box in the first control box based on a translator's selection of at least one character to be translated in the document to be translated, S104 displaying at least one translation result corresponding to the character to be translated and its context on the first control box based on the translator's response operation to the fill box, and updating the first return body. The data interaction system comprises a human-computer interaction interface, the human-computer interaction interface comprises a first display area and a second display area, and the data interaction system comprises a preset return body library. The present invention also proposes a data interaction device and a storage medium for implementing the method. The present invention realizes human-computer interaction for the translation process and can dynamically update the auxiliary library.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of human-computer interactive translation, and in particular relates to a data interaction method and system for a translation process, a data interaction device for implementing the method, and a storage medium. Background Art

[0002] Machine translation, also known as automatic translation, is the process of using computers to convert one natural language (source language) into another natural language (target language). It is a branch of computational linguistics, one of the ultimate goals of artificial intelligence, and has important scientific research value.

[0003] At present, translation work can be divided into written translation and oral interpretation. In order to improve work efficiency, both written translation and oral interpretation can be assisted by machine translation tools. However, compared with the real-time nature of oral interpretation, written translation pays more attention to the accuracy of translation. However, the accuracy of current machine translation tools needs to be improved. Translators cannot rely entirely on auxiliary tools, otherwise the accuracy will be reduced.

[0004] After searching, the US patent publication US20160378748A1 proposes to ensure the quality of translation by using multiple reviewers to score each translation, while detecting and eliminating incompetent reviewers. The quality level is also controlled by increasing (higher quality) and reducing (lower quality) the types and number of errors that reviewers are to detect. Therefore, the computerized system can ensure the quality of translation into any language without knowing the language, the translator who translates the language, or the auditor who scores the translator.

[0005] In actual applications, if the auxiliary library of the auxiliary tool (machine translation tool) itself is inaccurate, it usually causes the translator to manually confirm or select repeatedly from multiple candidate libraries or candidate translation results, so that the use of the auxiliary tool actually reduces the translation efficiency; at the same time, the elements of the auxiliary library itself in the prior art are static and cannot adapt to changes, resulting in a low active usage rate by translators. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes a data interaction method and system for a translation process, a data interaction device and a storage medium for implementing the method.

[0007] In a first aspect of the present invention, a data interaction method is proposed, which is used in a translation process and can be implemented as follows:

[0008] S101: Import the document to be translated;

[0009] S102: displaying a first control box based on a first number of first keywords at a first target position in the document to be translated; the first control box corresponds to a first return body;

[0010] S103: Based on the translator's selection of at least one character to be translated in the document to be translated, the first control box pops up a filling box;

[0011] S104: Based on the translator's response operation to the filling box, display the to-be-translated character and at least one translation result corresponding to its context on the first control box, and update the first return body.

[0012] The above method steps are implemented based on a preset return body library, which pre-stores multiple return bodies, each return body corresponding to at least one keyword;

[0013] Specifically, the return body may be a template to be filled. When there is a corresponding keyword that can be filled into the template to be filled, the keyword has a corresponding return body.

[0014] On this basis, the step S102 specifically includes:

[0015] Based on the first number of first keywords, searching for a first return body from a preset return body library;

[0016] Based on the first return body, the first control box is generated and displayed.

[0017] More specifically, if the first return body corresponding to the first keyword is not found, a translation feature corresponding to the first keyword is obtained; and a corresponding target return body is searched from a preset return body library as the first return body according to the translation feature;

[0018] The first control box is generated and displayed according to the target return body.

[0019] In a second aspect of the present invention, a data interaction system is provided, the data interaction system comprising a human-computer interaction interface, the human-computer interaction interface comprising a first display area and a second display area, the data interaction system comprising a preset return body library.

[0020] In terms of system structure, the data interaction system includes a document processing subsystem, a return body search subsystem, a control box generation subsystem and a return body library update subsystem.

[0021] Specifically, the functions of each subsystem are implemented as follows:

[0022] A document processing subsystem, used for importing a document to be translated, and identifying a first number of first keywords at a first target position in the document to be translated;

[0023] A return body search subsystem searches for a corresponding first return body in the preset return body library based on the first keyword;

[0024] A control box generation subsystem generates a first control box based on the first return body;

[0025] The return body library updating subsystem updates the preset return body library based on the response operation received by the filling box popped up by the first control box.

[0026] The document to be translated is displayed in the first display area, and the first control box and a filling box popped up from the first control box are displayed in the second display area.

[0027] As a specific application, the system is used in the translation process of the document to be translated, that is, used to execute the data interaction method for the translation process described in the first aspect.

[0028] Corresponding to the method, in the data interaction system, the return body search subsystem searches for the corresponding first return body in the preset return body library based on the first keyword, specifically including:

[0029] Based on the first number of first keywords, searching for a first return body from a preset return body library;

[0030] If the first return body corresponding to the first keyword is not found, obtaining the translation feature corresponding to the first keyword; searching for the corresponding target return body from a preset return body library as the first return body according to the translation feature;

[0031] The first control box is generated according to the target return body and displayed in the second display area.

[0032] In the third aspect of the present invention, a terminal device is provided, which may be, for example, a data interaction device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program may be a data interaction program. When the processor executes the computer program, the steps of the above-mentioned data interaction method are implemented.

[0033] In a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data interaction method are implemented.

[0034] The technical solution of the present invention utilizes a preset return body library (auxiliary library) to assist the translation process, which can improve the response speed; at the same time, when a corresponding return body exists, a corresponding control box is displayed in real time, and when a corresponding return body does not exist, a target return body is determined based on translation features and a corresponding control box can be generated and updated to the preset return body library (auxiliary library), thereby making the update of the preset return body library (auxiliary library) dynamic.

[0035] Further advantages of the present invention will be further reflected in detail in the specific embodiments section in conjunction with the drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a main flow chart of a data interaction method for a translation process according to an embodiment of the present invention;

[0038] Figure 2 yes Figure 1 A partial logic control flow chart of the data interaction method;

[0039] Figure 3 It is a schematic diagram of an interface of a data interaction system according to an embodiment of the present invention;

[0040] Figure 4 yes Figure 3 A partial subsystem architecture diagram of the data interaction system;

[0041] Figure 5 is realized Figure 1 A schematic diagram of the structure of a computer device for the method. DETAILED DESCRIPTION

[0042] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0043] First of all, it should be pointed out that the technical solutions of various embodiments of the present invention are all aimed at the translation process, rather than the interpretation or other forms of translation process.

[0044] It is understandable that the technical solution of the present invention does not emphasize real-time performance, and is therefore not suitable for use in interpretation processes that require high real-time performance (although the technical solution can be implemented, i.e., the technical solution of the present invention can be used exclusively for interpretation). Similarly, the related auxiliary methods used in interpretation in the prior art are not suitable for the translation process.

[0045] Compared with interpretation or other forms of translation, an important concern of translation is the high requirement for accuracy. Precision must be ensured during the translation process, but timeliness is not a rush. Usually, a translation document to be translated will be delivered to the translator a long time in advance.

[0046] Nevertheless, written translation is not a completely manual translation process, but can be carried out with the assistance of various machine translation tools. Of course, the final result needs to be determined by the translator.

[0047] However, there are many machine translation tools at present, and different machine translation engines have different focuses and even different fields of accuracy. How to reasonably refer to the most accurate machine-assisted translation results in the translation process has become an important factor restricting the efficiency of translation.

[0048] Based on the above application background, the specific implementation of each embodiment of the present application is introduced below.

[0049] See also Figure 1 , Figure 1 The main flow chart of the data interaction method for the translation process according to one embodiment of the present invention is shown. Figure 1 The method includes steps S101-S104, and each step is specifically implemented as follows:

[0050] S101: Import the document to be translated;

[0051] S102: displaying a first control box based on a first number of first keywords at a first target position in the document to be translated; the first control box corresponds to a first return body;

[0052] S103: Based on the translator's selection of at least one character to be translated in the document to be translated, the first control box pops up a filling box;

[0053] S104: Based on the translator's response operation to the filling box, display the to-be-translated character and at least one translation result corresponding to its context on the first control box, and update the first return body.

[0054] Next, we briefly introduce some details of further implementation of each step.

[0055] In step S101 , the translator may import the document to be translated through various methods, including manual import or automatic import.

[0056] In step S102, after the document to be translated is imported, the method can automatically perform structural analysis on the document to be translated, including title, abstract, keyword, paragraph and even sentence analysis.

[0057] Specifically, in step S102,

[0058] Identify a first target position of the document to be translated, where the first target position includes one of the following positions or a combination thereof:

[0059] Title, abstract, keywords, opening paragraph, closing paragraph;

[0060] identifying domain attributes of a first number of first keywords of the first target location;

[0061] Displaying a first control box corresponding to the domain attribute;

[0062] Furthermore, the control boxes corresponding to different domain attributes contain different return bodies.

[0063] Specifically, the above method further includes step S100 before step S101:

[0064] S100: Establishing a preset return body library, wherein the preset return body library stores a plurality of return bodies in advance, and each return body corresponds to at least one keyword;

[0065] Specifically, the return body may be a template to be filled. When there is a corresponding keyword that can be filled into the template to be filled, the keyword has a corresponding return body.

[0066] As a more specific example, the template to be filled may be a template including a plurality of fillable positions, between which a plurality of domain keyword contexts have been pre-positioned;

[0067] When the corresponding keyword is filled into the fillable position, it can be associated with the domain keyword context, which means that the corresponding keyword can be filled into the template to be filled;

[0068] If the corresponding keyword cannot be associated with the domain keyword context no matter which fillable position it is filled in, it is said that there is no corresponding keyword that can be filled in the template to be filled.

[0069] The corresponding keywords can be contextually associated with the domain keywords, which can be measured in a variety of ways, such as contextual relevance, prefix word relevance, suffix word relevance, etc., and the present invention does not impose specific restrictions on this. There are also many existing technologies in the field of word relevance algorithms, which are not specifically introduced here.

[0070] When there is a corresponding return body, the corresponding control box can be generated.

[0071] A control box is one of the conventional concepts in this field, and usually refers to a movable sub-area / interface button that can be displayed on a human-computer interaction interface. It is only displayed in the currently visible area. A control box can also have more sub-control boxes. The current user clicks the response button of the current control box to perform the corresponding operation, or performs the corresponding operation based on the input signal of the input device, etc. The control box can also include an input area, etc.

[0072] As an illustrative but non-limiting example, the domain attribute may be a domain category such as mechanics, medicine, physics, chemistry, etc.;

[0073] According to the structural analysis of the manuscript to be translated, for example, randomly obtaining the first number of entity keywords in the title, abstract, keywords, opening paragraph, closing paragraph, etc. of the manuscript to be translated, the field attribute of the manuscript to be translated can be basically determined, for example, the current manuscript to be translated belongs to the mechanical field, or belongs to the comprehensive field of medicine-chemistry, etc.;

[0074] Then, a first control box corresponding to the domain attribute is displayed.

[0075] More specifically, in Figure 1 See also Figure 2 . Figure 2 Show Figure 1 Part of the logical control flow chart of the data interaction method.

[0076] exist Figure 2 In the method, based on the first number of first keywords, a first return body is searched from a preset return body library.

[0077] In a judgment logic branch, if the first return body corresponding to the first keyword is not found, the translation feature corresponding to the first keyword is obtained;

[0078] searching a corresponding target return body from a preset return body library according to the translation feature as the first return body;

[0079] The first control box is generated and displayed according to the target return body.

[0080] As a general example, the preset return body library can preset return bodies corresponding to multiple different field types.

[0081] However, no matter how it is preset, the preset return body library cannot cover all domain keywords.

[0082] In practical applications, it is often the case that based on the structural analysis of the document to be translated, for example, based on the first number of first keywords at the first target position in the document to be translated, it can be determined that the current document to be translated is in the medical field;

[0083] However, since the preset return body library has not yet included the first keyword, the to-be-filled templates of all return bodies in the medical field in the preset return body library cannot be filled with the first keyword (for example, the context relevance after filling is always lower than the threshold). At this time, it means that there is no corresponding return body for the first keyword.

[0084] If the first return body corresponding to the first keyword is not found, obtaining the translation feature corresponding to the first keyword;

[0085] The translation feature here usually refers to the feature of the first keyword related to translation, and the feature here is also related to the field.

[0086] As an example, it is assumed that the first keyword is the keyword to be translated "magazine".

[0087] Normally, the domain attribute of "magazine" is "literature" ("magazine" is translated as magazine in this case);

[0088] However, in translation applications, if "magazine" appears in multiple locations at the same time, its translation characteristics may suggest that the domain characteristics should be "military" or "mechanical", because when "magazine" appears in multiple typical locations of the document to be translated (title, abstract, keywords, opening paragraph, and closing paragraph), its meaning should be "magazine", "ammunition depot", or "film box".

[0089] At this time, the translation feature corresponding to the first keyword should be corrected to "military" or "machinery".

[0090] According to the translation feature, a corresponding target return body is searched from a preset return body library as the first return body,

[0091] That is, at this time, you need to search for the return body corresponding to "military" or "mechanical" from the preset return body library, instead of searching for the return body corresponding to "literature". Only the former can be found.

[0092] The first control box is generated and displayed according to the target return body.

[0093] Obviously, if the domain attribute of "magazine" is identified as "literature", when "magazine" is translated into magazine, since the original meaning of "magazine" is "magazine", "ammunition depot" or "film box", in the templates corresponding to all the return bodies in the "literature" field, it is impossible for the corresponding keyword ("magazine"-magazine) to fill in the template to be filled, that is, the keyword ("magazine"-magazine) does not have a corresponding return body, because the template context (related to the military) at this time has basically nothing to do with "magazine".

[0094] However, if it is corrected to "military" or "mechanical" based on the translation feature, the corresponding target return body can be searched from the preset return body library as the first return body according to the translation feature, because the template context (related to military) at this time has a high correlation with "magazine" and "ammunition depot".

[0095] As a further improvement, step S104 further includes:

[0096] If the translator does not respond within a predetermined time period, the target return body is used as the first return body corresponding to the first keyword and updated to the preset return body library;

[0097] If the translator's filling operation on the filling box within a predetermined time period is obtained, the filling element corresponding to the filling operation is obtained to correct the target return body as the first return body, and the first return body is saved in the preset return body library.

[0098] If the translator does not respond within the predetermined time period, it means that the translator finally decides to adopt the current result, and therefore, the result is directly updated and associated to the preset return body library;

[0099] Otherwise, if the translator's filling operation on the filling box within a predetermined time period is obtained, the translator has actively corrected it. At this time, the filling element corresponding to the filling operation is obtained to correct the target return body as the first return body, and the first return body is saved in the preset return body library.

[0100] It can be seen that no matter in which case, dynamic updating of the preset return body library can be achieved.

[0101] exist Figure 1-Figure 2 Based on the principle of Figure 3 A schematic diagram of an interface of a data interaction system according to an embodiment of the present invention is provided.

[0102] exist Figure 3In the embodiment, the data interaction system includes a human-computer interaction interface, the human-computer interaction interface includes a first display area and a second display area, and the data interaction system includes a preset return body library.

[0103] The preset return body library stores a plurality of return bodies in advance, each return body corresponds to at least one keyword;

[0104] Specifically, the return body may be a template to be filled. When there is a corresponding keyword that can be filled into the template to be filled, the keyword has a corresponding return body.

[0105] As a more specific example, the template to be filled may be a template including a plurality of fillable positions, between which a plurality of domain keyword contexts have been pre-positioned;

[0106] When the corresponding keyword is filled into the fillable position, it can be associated with the domain keyword context, which means that the corresponding keyword can be filled into the template to be filled;

[0107] If the corresponding keyword cannot be associated with the domain keyword context no matter which fillable position it is filled in, it is said that there is no corresponding keyword that can be filled in the template to be filled.

[0108] Figure 4 yes Figure 3 Subsystem architecture diagram of the data interaction system.

[0109] The data interaction system includes the following subsystems:

[0110] A document processing subsystem, the document processing subsystem is used to import a document to be translated and identify a first number of first keywords at a first target position in the document to be translated;

[0111] A return body search subsystem, wherein the return body search subsystem searches for a corresponding first return body in the preset return body library based on the first keyword;

[0112] A control box generation subsystem, wherein the control box generation subsystem generates a first control box based on the first return body;

[0113] A return body library updating subsystem, wherein the return body library updating subsystem updates the preset return body library based on a response operation received by a filling box popped up by the first control box;

[0114] The document to be translated is displayed in the first display area, and the first control box and a filling box popped up from the first control box are displayed in the second display area.

[0115] Specifically, the system is used for the translation process of the document to be translated.

[0116] The return body search subsystem searches for the corresponding first return body in the preset return body library based on the first keyword, specifically including:

[0117] Based on the first number of first keywords, searching for a first return body from a preset return body library;

[0118] If the first return body corresponding to the first keyword is not found, obtaining the translation feature corresponding to the first keyword; searching for the corresponding target return body from a preset return body library as the first return body according to the translation feature;

[0119] The first control box is generated according to the target return body and displayed in the second display area.

[0120] Figure 4 The system can achieve Figure 1-Figure 2 The corresponding steps of the method, Figure 4 The system technical solution may include Figure 1 or Figure 2 All or part of the steps of the method, or one-to-one correspondence, will not be repeated in this embodiment.

[0121] It should be pointed out that Figure 1 The steps or methods and processes can be automatically implemented by computer program instructions. Figure 5 , provides an electronic computer device, which may be a data interaction device, comprising a bus, a processor and a memory, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is used to execute the program instructions stored in the computer storage medium.

[0122] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, the steps of the aforementioned method example are implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing power secondary device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions may also be loaded onto a computer or other programmable data processing power secondary device so that a series of operating steps are executed on the computer or other programmable power secondary device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable power secondary device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] The technical solution of the present invention utilizes a preset return body library (auxiliary library) to assist the translation process, which can improve the response speed; at the same time, when a corresponding return body exists, a corresponding control box is displayed in real time, and when a corresponding return body does not exist, a target return body is determined based on translation features and a corresponding control box can be generated and updated to the preset return body library (auxiliary library), thereby making the update of the preset return body library (auxiliary library) dynamic.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0127] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A data interaction method, which is used in a translation process, characterized in that: The method comprises the following steps: S100: Establishing a preset return body library, wherein the preset return body library pre-stores a plurality of return bodies, each return body corresponding to at least one keyword; the return body is a template to be filled, and when there is a corresponding keyword that can be filled into the template to be filled, the keyword has a corresponding return body; S101: Import the document to be translated; S102: searching for a first return body from a preset return body library based on a first number of first keywords at a first target position in the document to be translated; Based on the first return body, a first control box is generated and displayed; the first control box corresponds to the first return body; S103: Based on the translator's selection of at least one character to be translated in the document to be translated, the first control box pops up a filling box; S104: If the translator does not respond within a predetermined time period, the target return body is used as the first return body corresponding to the first keyword and updated to the preset return body library; If the translator's filling operation on the filling box within a predetermined time period is obtained, the filling element corresponding to the filling operation is obtained to correct the target return body as the first return body, and the first return body is saved in the preset return body library.

2. A data interaction method according to claim 1, characterized in that: The step S102 specifically includes: Identify a first target position of the document to be translated, where the first target position includes one of the following positions or a combination thereof: Title, abstract, keywords, opening paragraph, closing paragraph; identifying domain attributes of a first number of first keywords of the first target location; Displaying a first control box corresponding to the domain attribute; Furthermore, the control boxes corresponding to different domain attributes contain different return bodies.

3. A data interaction method according to claim 1, characterized in that: The step S102 further includes: If the first return body corresponding to the first keyword is not found, obtaining the translation feature corresponding to the first keyword; searching for the corresponding target return body from a preset return body library as the first return body according to the translation feature; The first control box is generated and displayed according to the target return body.

4. A data interaction system for implementing the data interaction method according to any one of claims 1 to 3, the data interaction system comprising a human-computer interaction interface, the human-computer interaction interface comprising a first display area and a second display area, the data interaction system comprising a preset return body library, characterized in that: The system further comprises: A document processing subsystem, the document processing subsystem is used to import a document to be translated and identify a first number of first keywords at a first target position in the document to be translated; A return body search subsystem, wherein the return body search subsystem searches for a corresponding first return body in the preset return body library based on the first keyword; A control box generation subsystem, wherein the control box generation subsystem generates a first control box based on the first return body; A return body library updating subsystem, wherein the return body library updating subsystem updates the preset return body library based on a response operation received by a filling box popped up by the first control box; The document to be translated is displayed in the first display area, and the first control box and a filling box popped up from the first control box are displayed in the second display area.

5. A data interaction system as claimed in claim 4, characterized in that: The system is used for the translation process of the document to be translated.

6. A data interaction system as claimed in claim 4, characterized in that: The return body search subsystem searches for the corresponding first return body in the preset return body library based on the first keyword, specifically including: Based on the first number of first keywords, searching for a first return body from a preset return body library; If the first return body corresponding to the first keyword is not found, obtaining the translation feature corresponding to the first keyword; searching for the corresponding target return body from a preset return body library as the first return body according to the translation feature; The first control box is generated according to the target return body and displayed in the second display area.

7. A data interaction device, characterized in that: The device comprises: A memory, a processor, and a data interaction program stored in the memory and executable on the processor; The data interaction program is configured to implement the steps of the data interaction method according to any one of claims 1 to 3.

8. A storage medium, characterized in that: The storage medium stores a data interaction program, and when the data interaction program is executed by the processor, the steps of the data interaction method according to any one of claims 1 to 3 are implemented.

Citation Information

Patent Citations

  • System and method for ensuring the quality of a human translation of content through real-time quality checks of reviewers

    US20160378748A1

  • Input method and device oriented at computer-assisting translation

    CN104462072A

  • Online translation system with full-original text reference

    CN107943797A

  • Machine translation system

    JP2009266042A

  • College readiness predictor and selection service using profile manager and translation validation

    US20170048340A1