Text modification method and device, electronic equipment and storage medium

Abstract

The application provides a text modification method and device, electronic equipment and storage medium, and relates to the technical field of computers, and comprises the following steps: obtaining translated text in a task library; receiving a first input instruction, calling a detection engine to detect the translated text; in the case that any field in the translated text contains suspicious words, calling an editing engine and displaying at least one candidate word in the interface box of the field containing the suspicious words; determining a word to be replaced, and replacing the suspicious word with the word to be replaced in the translated text; the word to be replaced is selected from multiple candidate words according to a second input instruction, or is determined according to input information indicated by a third input instruction in the editing box. The application can improve translation efficiency, avoid the behavior of inputting words in the editing box by a large number of people, and solve the problems of low calibration efficiency and high error rate caused by the factors of a small terminal screen or unresponsive touch screen.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a text editing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of mobile internet, text translation is usually done by machine translation and then sent to translators for approval. However, during the process of translators approving the translated text, they often overlook various translation errors. Furthermore, when performing translation correction on smart terminals, factors such as small screen size or unresponsive touch screens can greatly reduce calibration efficiency, and there is a high error rate during editing and calibration. Summary of the Invention

[0003] This invention provides a text modification method, apparatus, electronic device, and storage medium to solve the technical problems of low efficiency and high error rate of existing approved translated text, and provides a technical solution that combines a detection engine and an editing engine to replace suspicious words.

[0004] In a first aspect, the present invention provides a text modification method, comprising:

[0005] Retrieve translated text from the task library;

[0006] Upon receiving the first input instruction, the detection engine is invoked to detect the translated text.

[0007] If any suspicious word is detected in any field of the translated text, the editing engine is invoked, and at least one candidate word is displayed in the interface box of the field where the suspicious word is located.

[0008] Identify the words to be replaced, and replace the suspicious words with the words to be replaced in the translated text;

[0009] The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction;

[0010] The candidate words are determined based on the analysis of the suspicious words by the detection engine.

[0011] According to the text modification method provided by the present invention, obtaining the translated text in the task library includes:

[0012] Based on the first text features corresponding to all task texts in the task library, the first task text cluster is selected from the task library.

[0013] Each task text in the first task text cluster is received sequentially, and upon receiving a fourth input instruction, the task text indicated by the fourth input instruction is determined as the translated text.

[0014] The first text feature includes at least one of the following: language category, text subject category, translation difficulty level, or text word count.

[0015] According to the text modification method provided by the present invention, the step of invoking the editing engine and displaying at least one candidate word in the interface box of the field where the suspected word is located includes:

[0016] Locate the field containing the suspicious word in the translated text;

[0017] The detection engine is invoked to process the suspicious words, and at least one candidate word returned by the detection engine is received;

[0018] The editing engine is invoked to set an interface box in any blank area outside the field where the suspected word is located, so as to display at least one candidate word within the interface box.

[0019] According to the text modification method provided by the present invention, after locating the field where the suspicious word is located, the method further includes:

[0020] The suspicious words are processed using annotation methods;

[0021] The annotation format includes at least one of the following: adding a tilde, adding an underline, bolding the font, and changing the color of suspicious words.

[0022] According to the text modification method provided by the present invention, after replacing the suspicious word with the word to be replaced in the translated text, the method further includes:

[0023] Iterate through all fields in the translated text until all suspicious words are replaced.

[0024] According to the text modification method provided by the present invention, before obtaining the translated text in the task library, the method further includes:

[0025] Segment long texts in the task library to obtain multiple related task texts that have contextual semantic relationships;

[0026] Store the multiple associated task texts in the task library.

[0027] According to the text modification method provided by the present invention, after storing the plurality of associated task texts to the task library, the method further includes:

[0028] Obtain any associated task text from the task library, and identify the associated task text as the translated text;

[0029] Identify the words to be replaced that are associated with the suspicious words in the associated task text;

[0030] When processing the remaining associated task texts in the task library that are associated with the associated task text, the word to be replaced is selected as a candidate word and displayed in the first position within the interface box of the field where the suspected word is located.

[0031] Secondly, a text editing device is provided, comprising:

[0032] Acquisition Unit: Used to retrieve translated text from the task library;

[0033] Calling unit: Used to receive the first input instruction and call the detection engine to detect the translated text;

[0034] Display unit: When a suspicious word is detected in any field of the translated text, the editing engine is invoked and at least one candidate word is displayed in the interface box of the field where the suspicious word is located.

[0035] Replacement unit: used to determine the word to be replaced, and replace the suspicious word with the word to be replaced in the translated text;

[0036] The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction;

[0037] The candidate words are determined based on the analysis of the suspicious words by the detection engine.

[0038] Thirdly, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the text modification method.

[0039] Fourthly, a non-transitory computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the text modification method described above.

[0040] This invention provides a text modification method, apparatus, electronic device, and storage medium. It obtains translated text from a task library, calls a detection engine to detect the translated text, calls an editing engine, and displays at least one candidate word in the interface box of the field containing the suspicious word to determine the word to be replaced. Finally, it replaces the suspicious word with the word to be replaced to achieve translation approval of the translated text. This invention can quickly locate suspicious words by checking the translated text with the detection engine and quickly select the word to be replaced from the candidate words by calling the editing engine, thereby improving translation efficiency, avoiding a large amount of manual input of words in the editing box, and solving the problems of low calibration efficiency and high error rate caused by small terminal screens or unresponsive touch screens. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is one of the flowcharts illustrating the text modification method provided by the present invention;

[0043] Figure 2 This is a flowchart illustrating the process of obtaining translated text from a task library provided by the present invention;

[0044] Figure 3 This is a flowchart illustrating the process of displaying at least one candidate word provided by the present invention;

[0045] Figure 4 This is the second flowchart illustrating the text modification method provided by the present invention;

[0046] Figure 5 This is the third flowchart illustrating the text modification method provided by the present invention;

[0047] Figure 6 This is the fourth flowchart of the text modification method provided by the present invention;

[0048] Figure 7 This is a schematic diagram of the text editing device provided by the present invention;

[0049] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0051] Figure 1 This is one of the flowcharts illustrating the text modification method provided by this invention. This invention offers a text modification method because machine translation cannot incorporate contextual semantics and may contain translation flaws. Furthermore, text translated by novice translators often contains numerous translation errors. Therefore, this invention aims to detect the accuracy of already translated text and to modify and adjust it accordingly. Optionally, this invention is applicable to mobile devices, providing translation approval personnel with a convenient, efficient solution to reduce editing error rates, including:

[0052] Retrieve translated text from the task library;

[0053] Upon receiving the first input instruction, the detection engine is invoked to detect the translated text.

[0054] If any suspicious word is detected in any field of the translated text, the editing engine is invoked, and at least one candidate word is displayed in the interface box of the field where the suspicious word is located.

[0055] Identify the words to be replaced, and replace the suspicious words with the words to be replaced in the translated text;

[0056] The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction;

[0057] The candidate words are determined based on the analysis of the suspicious words by the detection engine.

[0058] In step 101, the translated text in the task library is obtained. The task library stores task texts with various text features. The task texts can be independent text information or independent fields after segmenting long articles. In this invention, multiple task texts can be randomly assigned for translators to choose from. The translators select the most suitable task text as the translated text. In other embodiments, task texts can be pushed to translators one by one in a certain order. The translators can then choose to accept or reject them. After receiving the corresponding instructions from the translators, the translated text in the task library is obtained.

[0059] In step 102, a first input instruction is received, and a detection engine is invoked to detect the translated text. After receiving the translated text, the translator performs a preliminary check on it. If it is determined that there are no errors in the translated text, the task ends. However, if the translator determines that it is necessary to perform detection, an input action is executed to generate a first input instruction, which is received and confirmed to invoke the detection engine to detect the translated text. The detection engine is an intelligent text translation detection system in a remote server, which is capable of detecting errors in the translated text.

[0060] In step 103, if any suspicious word is detected in any field of the translated text, the editing engine is invoked, and at least one candidate word is displayed in the interface box of the field containing the suspicious word. The suspicious word may be a word with a translation error, such as "good" being written as "go0d", or "apple" being written as "aople". The suspicious word may also be a question of the reasonable applicability of a word in combination with the context. For example, "want", "wish", and "desire" all have the meaning of "want", but in a certain context, there may be the most appropriate collocation. Therefore, when a suspicious word is detected in any field of the translated text, the present invention needs to call the editing engine. The editing engine is used to edit and modify the suspicious word based on the translated text. However, the present invention does not use the editing engine to allow translators to manually input words to modify the suspicious word. Instead, it displays at least one candidate word in the display interface of the smart terminal, especially in the interface box of the field where the suspicious word is located. For example, in the above embodiment, if the suspicious word is "want", the candidate words can be "wish" and "desire".

[0061] Optionally, after replacing the suspicious words with the words to be replaced in the translated text, the method further includes: traversing all fields in the translated text until all suspicious words are replaced. Steps 101 to 103 of this invention are merely one implementation means, disclosing how to detect one or more suspicious words in specific fields of the translated text, how to determine candidate words for suspicious words, and how to replace the suspicious words with words to be replaced, etc. However, since the translated text may have multiple fields, this invention can adopt a traversal approach to determine all suspicious words field by field, and then edit and modify each suspicious word to finally complete the modification process of all suspicious words in the translated text.

[0062] This invention provides a text modification method, apparatus, electronic device, and storage medium. It obtains translated text from a task library, calls a detection engine to detect the translated text, calls an editing engine, and displays at least one candidate word in the interface box of the field containing the suspicious word to determine the word to be replaced. Finally, it replaces the suspicious word with the word to be replaced to achieve translation approval of the translated text. This invention can quickly locate suspicious words by checking the translated text with the detection engine and quickly select the word to be replaced from the candidate words by calling the editing engine, thereby improving translation efficiency, avoiding a large amount of manual input of words in the editing box, and solving the problems of low calibration efficiency and high error rate caused by small terminal screens or unresponsive touch screens.

[0063] Figure 2 This is a flowchart illustrating the process of obtaining translated text from a task library provided by the present invention. The process of obtaining translated text from a task library includes:

[0064] Based on the first text features corresponding to all task texts in the task library, the first task text cluster is selected from the task library.

[0065] Each task text in the first task text cluster is received sequentially, and upon receiving a fourth input instruction, the task text indicated by the fourth input instruction is determined as the translated text.

[0066] The first text feature includes at least one of the following: language category, text subject category, translation difficulty level, or text word count.

[0067] In step 1011, a first task text cluster is selected from the task library based on the first text features corresponding to all task texts in the task library. Those skilled in the art will understand that translators can optionally log in and enter the task library list through an application on a smart terminal. Each translator has different translation abilities, different languages ​​they are good at translating, and different types of articles they are good at translating, such as argumentative essays, expository texts, popular science articles, etc. They are also good at translating articles from different industry fields, such as chemistry, mechanics, physics, etc. Therefore, it is necessary to match task texts that are appropriate to each translator's professional expertise based on their abilities. That is, this invention performs preliminary screening of all task texts in the task library based on at least one of the following: language category, text professional category, translation difficulty level, or text word count, and then selects the first task text cluster from the task library.

[0068] In step 1012, each task text in the first task text cluster is received sequentially. Upon receiving a fourth input instruction, the task text indicated by the fourth input instruction is determined as translated text. After obtaining the first task text cluster that matches the translator, each task text in the first task text cluster is displayed on the smart terminal. For the translator, each task text in the first task text cluster can be received sequentially. If the translator does not have the ability to translate or does not wish to receive the current task text, they can receive and display the next task text by swiping up or down or clicking the indicator box, until a task that matches their ability to translate or that they wish to receive occurs. At this time, an input action is executed to generate a fourth input instruction. Upon receiving the fourth input instruction, the smart terminal determines the task text indicated by the fourth input instruction as translated text.

[0069] Figure 3 This is a flowchart illustrating the process of displaying at least one candidate word provided by the present invention. The step of calling the editing engine and displaying at least one candidate word within the interface box of the field containing the suspected word includes:

[0070] Locate the field containing the suspicious word in the translated text;

[0071] The detection engine is invoked to process the suspicious words, and at least one candidate word returned by the detection engine is received;

[0072] The editing engine is invoked to set an interface box in any blank area outside the field where the suspected word is located, so as to display at least one candidate word within the interface box.

[0073] In step 1031, the field containing the suspicious word is located in the translated text. This invention can quickly lock the suspicious word in the current field and find all suspicious words appearing in the current field through the quick search function.

[0074] In step 1032, the detection engine is invoked to process the suspicious words, and at least one candidate word returned by the detection engine is received. This invention can not only detect suspicious words, but also provide corresponding candidate words based on the semantics of the suspicious words in the context, for translators to choose from. The detection performed by the detection engine is a detection operation completed on a remote server. After the detection engine determines at least one candidate word, the candidate word is sent to the application of the smart terminal to receive at least one candidate word returned by the detection engine.

[0075] In step 1033, the editing engine is invoked to set an interface frame in any blank area outside the field containing the suspected word, so as to display at least one candidate word within the interface frame. After obtaining the candidate word corresponding to the suspected word, the present invention needs to display the candidate word to the translator. Simultaneously, to facilitate the translator's understanding of the specific problems existing in the position of the field containing the suspected word, an interface frame is set in any blank area outside the field containing the suspected word, so as to display at least one candidate word within the interface frame, thereby achieving simultaneous display of the interface frame and the field containing the suspected word. Optionally, at least one candidate word can also be displayed in the form of a bottom pop-up window.

[0076] Optionally, after locating the field containing the suspicious word, the method further includes:

[0077] The suspicious words are processed using annotation methods;

[0078] The annotation format includes at least one of the following: adding a tilde, adding an underline, bolding the font, and changing the color of suspicious words.

[0079] In order to enable translators to quickly browse and locate the position of suspicious words in the field, thereby improving translation efficiency and saving translation time, this invention uses a labeling method to process the suspicious words, so as to highlight the position of the suspicious words in the field. Optionally, the labeling method includes at least one of the following: adding a tilde, adding an underline, bolding the font, and changing the color of the suspicious words.

[0080] Figure 4 This is the second flowchart of the text modification method provided by the present invention. Before obtaining the translated text in the task library, it also includes:

[0081] Segment long texts in the task library to obtain multiple related task texts that have contextual semantic relationships;

[0082] Store the multiple associated task texts in the task library.

[0083] In step 201, since the texts in the task library are of various types and have different words, it is impossible to distribute them evenly among translators when there are texts with significantly different word counts, which will cause uneven distribution. In order to solve this technical problem, the present invention defines texts with more than a first preset word count as long texts, and then segments the long texts in the task library. The segmentation can be based on fields as the dividing points, and a second preset word count can be used as the upper limit of the task text. Under the condition that the second preset word count is not exceeded and the field is used as the end, each independent field is determined in turn, thereby obtaining multiple related task texts with contextual semantic relationships.

[0084] In step 202, the multiple associated task texts are stored in the task library. In order to ensure that the texts in the task library are all translated texts that can be directly distributed, the long texts need to be segmented first using the segmentation module of the smart terminal or by calling the segmentation module of the remote server. Then, after obtaining multiple associated task texts that have contextual semantic relationships, the multiple associated task texts are stored in the task library.

[0085] Figure 5 This is a flowchart of the text modification method provided by the present invention, which, after storing the multiple associated task texts to the task library, further includes:

[0086] Obtain any associated task text from the task library, and identify the associated task text as the translated text;

[0087] Identify the words to be replaced that are associated with the suspicious words in the associated task text;

[0088] When processing the remaining associated task texts in the task library that are associated with the associated task text, the word to be replaced is selected as a candidate word and displayed in the first position within the interface box of the field where the suspected word is located.

[0089] In step 301, any associated task text from the task library is obtained, and this associated task text is identified as the translated text. The associated task text is one of multiple associated task texts with contextual semantic relationships. That is, if a translator is assigned to process multiple associated task texts with contextual semantic relationships, they need to ensure the consistency of suspicious words in these texts to avoid a situation where one meaning corresponds to multiple words in a long text. Figure 5 The aim is to address the need for consistency in the modification of suspicious words when multiple translators are detecting and correcting multiple related task texts with contextual semantic connections.

[0090] In step 302, words to be replaced associated with suspicious words are identified in the associated task text. After the associated task text is identified as the translated text, words to be replaced associated with suspicious words can be identified according to the specific workflow of steps 101 to 104.

[0091] In step 303, when processing the remaining associated task texts in the task library that are associated with the associated task text, the word to be replaced is taken as a candidate word and displayed in the first position in the interface box of the field where the suspected word is located. The remaining associated task texts associated with the associated task text are other associated task texts other than the currently processed associated task text, which can be understood as other fields in the long text corresponding to the associated task text other than the associated task text.

[0092] Those skilled in the art will understand that currently, large translation tasks in a complete translation project can take several days or even weeks to complete if only one translator is involved. Therefore, the task needs to be distributed among multiple translators. However, when multiple translators translate multiple related task texts with contextual semantic connections, inefficiency and inconsistent handling of suspicious words arise. The remaining related task texts in the task library can be processed by the same translator or by different translators. Regardless of whether they are processed by the same or different translators, once the words to be replaced associated with the suspicious words have been identified, to ensure consistency among all modified suspicious words in long texts, this invention presents the words to be replaced as candidate words and suggests them to the translators processing other remaining related task texts. To strengthen the suggestion, these words are displayed in the first position within the interface box of the field containing the suspicious word. In an optional embodiment, the words to be replaced can also be annotated in other ways to distinguish them from other candidate words.

[0093] In another optional embodiment, if a translator selects other candidate words besides the word to be replaced while processing the remaining related task text, the translator can notify the translator processing the related task text associated with the word to be replaced, or choose not to notify. Alternatively, the other candidate words and the word to be replaced can be used together as the candidate basis when processing the next suspicious word in other remaining related task text.

[0094] Figure 6 This is the fourth flowchart of the text modification method provided by the present invention, as shown below. Figure 6As shown, this invention first filters tasks from the task library, allowing translators to choose to accept or abandon the current task. After accepting the task, the translated text is obtained. Translators can use their experience to determine whether the translated document needs to be checked. If not, the task ends; if so, the check function is activated, and the check interface is called to obtain the check result. If the check result shows "pass," the task ends; if the check result shows "fail," it indicates the presence of suspicious words that need to be edited. The editing interface is then called to obtain modification suggestions from the server. The translator further determines whether to adopt the modification suggestions. If so, the suspicious words in the translated text are modified; if not, the suspicious words are manually modified. Thus, the entire text modification process is achieved according to the above method.

[0095] This invention leverages the development of mobile internet applications to facilitate translation tasks for a large number of online translators. It enables faster retrieval of translation errors and allows for intelligent one-click correction of these errors, eliminating the need for online translators to edit via mobile phone keyboards. This effectively solves the problem of small screen size and error-prone editing on mobile phones, significantly improving both the efficiency and quality of translation tasks.

[0096] Compared to the traditional built-in editing box functionality of smart terminals, this invention adds intelligent detection and intelligent modification functions. It also humanely allows translators to decide on the modification method without any coercion. This invention uses an AI engine to quickly identify translation task errors and provide reasonable modification suggestions. Its purpose is to provide reasonable modification suggestions based on the actual translation content, thereby improving the efficiency of translators in reviewing and modifying translation tasks.

[0097] Figure 7 This is a schematic diagram of the text editing device provided by the present invention. The present invention also provides a text editing device, including an acquisition unit 1: used to acquire translated text in a task library. The working principle of the acquisition unit 1 can be referred to the aforementioned step 101, and will not be repeated here.

[0098] The text modification device further includes a calling unit 2: used to receive a first input instruction and call the detection engine to detect the translated text. The working principle of the calling unit 2 can be referred to the aforementioned step 102, and will not be repeated here.

[0099] The text editing device further includes a display unit 3: when a suspicious word is detected in any field of the translated text, the editing engine is invoked and at least one candidate word is displayed in the interface box of the field where the suspicious word is located. The working principle of the display unit 3 can be referred to the aforementioned step 103, and will not be repeated here.

[0100] The text modification device further includes a replacement unit 4: used to determine the word to be replaced, and replace the suspicious word with the word to be replaced in the translated text. The working principle of the replacement unit 4 can be referred to the aforementioned step 104, and will not be repeated here.

[0101] The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction;

[0102] The candidate words are determined based on the analysis of the suspicious words by the detection engine.

[0103] This invention provides a text modification method, apparatus, electronic device, and storage medium. It obtains translated text from a task library, calls a detection engine to detect the translated text, calls an editing engine, and displays at least one candidate word in the interface box of the field containing the suspicious word to determine the word to be replaced. Finally, it replaces the suspicious word with the word to be replaced to achieve translation approval of the translated text. This invention can quickly locate suspicious words by checking the translated text with the detection engine and quickly select the word to be replaced from the candidate words by calling the editing engine, thereby improving translation efficiency, avoiding a large amount of manual input of words in the editing box, and solving the problems of low calibration efficiency and high error rate caused by small terminal screens or unresponsive touch screens.

[0104] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. For example... Figure 8 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a text modification method, which includes: acquiring translated text from a task library; receiving a first input instruction and calling a detection engine to detect the translated text; if a suspicious word is detected in any field of the translated text, calling an editing engine and displaying at least one candidate word in the interface box of the field containing the suspicious word; determining a word to be replaced and replacing the suspicious word with the word to be replaced in the translated text; the word to be replaced is selected from multiple candidate words according to a second input instruction, or determined in the editing box according to input information indicated by a third input instruction; the candidate words are determined after the detection engine analyzes the suspicious word.

[0105] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute a text modification method provided by the above methods. The method includes: acquiring translated text in a task library; receiving a first input instruction and calling a detection engine to detect the translated text; if a suspicious word is detected in any field of the translated text, calling an editing engine and displaying at least one candidate word in the interface box of the field where the suspicious word is located; determining a word to be replaced and replacing the suspicious word with the word to be replaced in the translated text; the word to be replaced is selected from multiple candidate words according to a second input instruction, or determined in the editing box according to input information indicated by a third input instruction; the candidate word is determined after the detection engine analyzes the suspicious word.

[0107] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the above-described methods to provide a text modification method, the method comprising: acquiring translated text from a task library; receiving a first input instruction and invoking a detection engine to detect the translated text; if a suspicious word is detected in any field of the translated text, invoking an editing engine and displaying at least one candidate word in the interface box of the field containing the suspicious word; determining a word to be replaced and replacing the suspicious word with the word to be replaced in the translated text; the word to be replaced is selected from multiple candidate words according to a second input instruction, or determined in an editing box according to input information indicated by a third input instruction; the candidate word is determined after the detection engine analyzes the suspicious word.

[0108] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0109] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A text modification method, characterized in that, include: Segment long texts in the task library to obtain multiple related task texts that have contextual semantic relationships; Store the multiple associated task texts in the task library; Obtain any associated task text from the task library and identify the associated task text as translated text; Upon receiving the first input instruction, the detection engine is invoked to detect the translated text. If any suspicious word is detected in any field of the translated text, the editing engine is invoked, and at least one candidate word is displayed in the interface box of the field where the suspicious word is located. Identify the words to be replaced, and replace the suspicious words with the words to be replaced in the translated text; The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction; The candidate words are determined based on the analysis of the suspicious words by the detection engine; When processing the remaining associated task texts in the task library that are associated with the associated task text, the word to be replaced is selected as a candidate word and displayed in the first position within the interface box of the field where the suspected word is located.

2. The text modification method according to claim 1, characterized in that, The process of obtaining translated text from the task library includes: Based on the first text features corresponding to all task texts in the task library, the first task text cluster is selected from the task library. Each task text in the first task text cluster is received sequentially, and upon receiving a fourth input instruction, the task text indicated by the fourth input instruction is determined as the translated text. The first text feature includes at least one of the following: language category, text subject category, translation difficulty level, or text word count.

3. The text modification method according to claim 1, characterized in that, The step of invoking the editing engine and displaying at least one candidate word in the interface box of the field containing the suspected word includes: Locate the field containing the suspicious word in the translated text; The detection engine is invoked to process the suspicious words, and at least one candidate word returned by the detection engine is received; The editing engine is invoked to set an interface box in any blank area outside the field where the suspected word is located, so as to display at least one candidate word within the interface box.

4. The text modification method according to claim 3, characterized in that, After locating the field containing the suspicious words, the process also includes: The suspicious words are processed using annotation methods; The annotation format includes at least one of the following: adding a tilde, adding an underline, bolding the font, and changing the color of suspicious words.

5. The text modification method according to claim 1, characterized in that, After replacing the suspicious word with the word to be replaced in the translated text, the process further includes: Iterate through all fields in the translated text until all suspicious words are replaced.

6. A text editing device, characterized in that, include: Acquisition Unit: Used to segment long texts in the task library and acquire multiple related task texts that have contextual semantic relationships; Store the multiple associated task texts in the task library; Obtain any associated task text from the task library and identify the associated task text as translated text; Calling unit: Used to receive the first input instruction and call the detection engine to detect the translated text; Display unit: When a suspicious word is detected in any field of the translated text, the editing engine is invoked and at least one candidate word is displayed in the interface box of the field where the suspicious word is located. Replacement unit: used to determine the word to be replaced, and replace the suspicious word with the word to be replaced in the translated text; The word to be replaced is selected from multiple candidate words according to the second input instruction, or determined in the edit box according to the input information indicated by the third input instruction; The candidate words are determined based on the analysis of the suspicious words by the detection engine; When processing the remaining associated task texts in the task library that are associated with the associated task text, the word to be replaced is selected as a candidate word and displayed in the first position within the interface box of the field where the suspected word is located.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the text modification method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the text modification method as described in any one of claims 1 to 5.

Images