Text translation management method, device and equipment and readable storage medium

Abstract

The invention provides a text translation management method and device, equipment and a readable storage medium. The method comprises the steps that a to-be-translated original text set is determined; each original text set comprises a plurality of original texts; distributing different access information for each original text set, and receiving an access request of translation service equipment; the access request carries target access information; determining a target original text set indicated by the target access information, and sending the target original text set to the translation service equipment; the translation service equipment is used for returning a translation text set corresponding to the target original text set; receiving the translation text set returned by the translation service equipment; and according to the identifier of each translated text, determining an original text carrying the identifier in the target original text set, and associating the translated text with the original text. The text translation management efficiency can be improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of text management, and in particular, to a text translation management method, apparatus, electronic device, and computer-readable storage medium. Background Art

[0002] In some business scenarios, due to the existence of a large amount of text materials, and at the same time, due to the need to expand the international market or conduct cross-border business cooperation, it is necessary to translate the original text involved in business such as product descriptions and function interfaces into translation texts in other languages.

[0003] In the related art, the original text is exported to the translation device, and then after the translation is completed by the translation device, the corresponding translation text is returned through the translation device.

[0004] However, in the related art, the original text and the translation text are not properly managed, and the processes such as the export of the original text and the return of the translation text are relatively chaotic, and the management efficiency of text translation is low. Summary of the Invention

[0005] In view of the above problems, embodiments of the present disclosure are proposed to provide a text translation management method, apparatus, electronic device, and computer-readable storage medium that overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect, embodiments of the present disclosure disclose a text translation management method, including:

[0007] Determine a set of original texts to be translated; each set of original texts includes multiple original texts; different original texts carry different identifiers;

[0008] Allocate different access information to each set of original texts, and receive an access request from a translation service device; the access request carries target access information;

[0009] Determine the target set of original texts indicated by the target access information, and send the target set of original texts to the translation service device; the translation service device is used to return a set of translation texts corresponding to the target set of original texts;

[0010] Receive the set of translation texts returned by the translation service device; the set of translation texts includes multiple translation texts; different translation texts carry different identifiers;

[0011] According to the identifier of each translation text, in the target set of original texts, determine the original text carrying the identifier, and associate the translation text with the original text.

[0012] In a second aspect, embodiments of the present disclosure disclose a text translation management device, including:

[0013] An original set determination module, configured to determine an original text set to be translated; each original text set includes multiple original texts; different original texts carry different identifiers;

[0014] An access information allocation module, configured to allocate different access information to each original text set and receive an access request from a translation service device; the access request carries target access information;

[0015] An original set sending module, configured to determine a target original text set indicated by the target access information and send the target original text set to the translation service device; the translation service device is configured to return a translation text set corresponding to the target original text set;

[0016] A translation file receiving module, configured to receive the translation text set returned by the translation service device; the translation text set includes multiple translation texts; different translation texts carry different identifiers;

[0017] A corresponding text association module, configured to determine, in the target original text set, an original text carrying the identifier according to the identifier of each translation text, and associate the translation text with the original text.

[0018] In a third aspect, embodiments of the present disclosure further disclose an electronic device, including a processor and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the text translation management method described in the first aspect are implemented.

[0019] In a fourth aspect, embodiments of the present disclosure further disclose a computer-readable storage medium, where a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the text translation management method described in the first aspect are implemented.

[0020] In the embodiments of the present disclosure, by determining a set of original texts to be translated, different access information is assigned to each set of original texts, and an access request from a translation service device is received. The target set of original texts indicated by the target access information in the access request is determined, and the target set of original texts is sent to the translation service device. The set of translated texts returned by the translation service device is received. According to the identifier of each translated text, the original text carrying the identifier is determined in the target set of original texts, and the translated text and the original text are associated. It is possible to manage multiple original texts in batches. Different sets of original texts have different access information, and the translation service device can accurately obtain different sets of original texts. After translation is completed, text association is performed based on the identifiers of the original text and the translated text, avoiding text confusion problems in large-scale translation scenarios, improving the orderliness in the text translation process, and ultimately improving the management efficiency of text translation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flowchart of a method for text translation management provided by an embodiment of the present disclosure;

[0022] Figure 2 is a flowchart of another method for text translation management provided by an embodiment of the present disclosure;

[0023] Figure 3 is a schematic diagram of a multilingual setting interface provided by an embodiment of the present disclosure;

[0024] Figure 4 is a logic diagram of a text translation management service provided by an embodiment of the present disclosure;

[0025] Figure 5 is a schematic diagram of a text translation management architecture provided by an embodiment of the present disclosure;

[0026] Figure 6 is a schematic diagram of a text retrieval interface provided by an embodiment of the present disclosure;

[0027] Figure 7 is a block diagram of a text translation management device provided by an embodiment of the present disclosure;

[0028] Figure 8 is a block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Hereinafter, exemplary embodiments of the present application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0030] Figure 1 The figure shows a step diagram of a text translation management method provided by an embodiment of the present disclosure. The method includes:

[0031] Step 101, determining a set of original texts to be translated; each set of original texts includes multiple original texts; different original texts carry different identifiers.

[0032] In an embodiment of the present disclosure, the text translation management method may be executed by a server. Terminal devices, such as diagnostic devices that submit translation requirements and terminal devices of the translation party, may interact with the server through a management platform program or a web page.

[0033] The number of original texts to be translated may be relatively large. The set of original texts may be one or more. Each set of original texts may include multiple original texts. Different original texts have different identifiers, that is, unique identifiers. The identifier of the original text may exist when the original text is generated, or may be added to the original text by the server after receiving the original text, and there is no specific limitation.

[0034] Step 102, allocating different access information to each set of original texts, and receiving an access request from a translation service device; the access request carries target access information.

[0035] In an embodiment of the present disclosure, after determining at least one set of original texts based on multiple original texts, different access information may be allocated to each set of original texts. The access information can be used to distinguish different sets of original texts.

[0036] The translation party device, such as a translation service device, may generate an access request carrying target access information according to the set of original texts it wants to obtain. The target access information is used to indicate the set of original texts that the translation service device needs to obtain. For example, the access information may be different access keys. The translation service device may use the access key to obtain different sets of original texts through a specific application programming interface (API, Application Programming Interface).

[0037] Step 103, determining the target set of original texts indicated by the target access information, and sending the target set of original texts to the translation service device; the translation service device is used to return a set of translation texts corresponding to the target set of original texts.

[0038] In an embodiment of the present disclosure, when receiving an access request sent by a translation service device, according to the target access information in the access request, a corresponding target original text set is determined, and the target original text set is sent to the translation service device.

[0039] It can be understood that the translation service device may refer to a device for data interaction with a translation party (such as a third - party translator or company). The text translation work may be performed by this translation service device or other devices, or may be manual translation. After the texts in the target original text set are translated, the translation service device uploads the obtained translation text set to the server.

[0040] Step 104, receive the translation text set returned by the translation service device; the translation text set includes multiple translation texts; different translation texts carry different identifiers.

[0041] In an embodiment of the present disclosure, the server receives a translation text set returned by a translation service device. The translation text set includes multiple translation texts, and different translation texts carry different identifiers.

[0042] Among them, the identifier of the translation text may be that the translation service device reads the identifier of the original text before translation and adds the identifier to the corresponding translation text after the original text is translated. Therefore, for any original text, the identifier of the original text is the same as the identifier of the corresponding translation text.

[0043] Step 105, according to the identifier of each translation text, in the target original text set, determine the original text carrying the identifier, and associate the translation text with the original text.

[0044] In an embodiment of the present disclosure, since the identifier of each translation text is the same as the identifier of the corresponding original text. Therefore, based on the identifier of the translation text, in the target original text set, the original text having the same identifier as the current translation text can be determined one by one.

[0045] Based on the identifiers of each translation text in the translation text set, each translation text and the corresponding original text are respectively determined. After determining each translation text and the corresponding original text, an association relationship between the translation text and the original text can be established. For example, the corresponding translation text and the original text can be used as a group of text data and stored in a table, or can be achieved by constructing an index, or can be adding a value in the translation text and this value exists in the corresponding original text. There is no specific limitation on how to associate the translation text and the original text here.

[0046] In summary, in the embodiments of the present disclosure, by determining the set of original texts to be translated, assigning different access information to each set of original texts, receiving an access request from a translation service device, determining the target set of original texts indicated by the target access information in the access request, and sending the target set of original texts to the translation service device, receiving the set of translated texts returned by the translation service device, and based on the identifier of each translated text, determining the original text carrying the identifier in the target set of original texts, and associating the translated text with the original text. It is possible to manage multiple original texts in batches. Different sets of original texts have different access information, and the translation service device can accurately obtain different sets of original texts. After translation, text association is performed based on the identifiers of the original text and the translated text, avoiding text confusion in large-scale translation scenarios, improving the orderliness in the text translation process, and ultimately improving the management efficiency of text translation.

[0047] Reference Figure 2 , which shows a flowchart of the steps of a text translation management method provided by an embodiment of the present disclosure. The method includes:

[0048] Step 201, determining a set of original texts to be translated; each set of original texts includes multiple original texts; different original texts carry different identifiers;

[0049] Step 202, assigning different access information to each set of original texts and receiving an access request from a translation service device; the access request carries target access information;

[0050] Step 203, determining the target set of original texts indicated by the target access information and sending the target set of original texts to the translation service device; the translation service device is used to return a set of translated texts corresponding to the target set of original texts;

[0051] Step 204, receiving the set of translated texts returned by the translation service device; the set of translated texts includes multiple translated texts; different translated texts carry different identifiers;

[0052] Step 205, based on the identifier of each translated text, determining the original text carrying the identifier in the target set of original texts and associating the translated text with the original text.

[0053] The above steps 201-205 can refer to the content of the above Figure 1 embodiment and will not be elaborated here.

[0054] In the case where the number of original texts is large, if multiple original texts are managed as a whole, it is likely to result in insufficient accuracy, while managing each original text separately will cause excessive management pressure.

[0055] Optionally, step 201 of determining the set of original texts to be translated includes:

[0056] Sub-step 2011, determining the time information of each original text among multiple original texts;

[0057] Sub-step 2012, dividing the multiple original texts into at least one set of original texts according to the time information of each original text and a preset time interval; the time information of the original texts in each set of original texts is within the same preset time interval.

[0058] In the embodiments of the present disclosure, the time information of the original text can be determined based on the generation time of the original text, the time of uploading to the server, or other times. The multiple original texts can be divided according to the time information of each original text and the preset time interval.

[0059] For example, the preset time interval can be one hour, and the duration of each hour can correspond to a set of original texts. The time information of the original texts in this set of original texts is within the same preset time interval. For example, if there are twenty-four hours in a day, the multiple original texts uploaded within a day can be divided into twenty-four sets of original texts.

[0060] Implementing the embodiments of the present disclosure, by determining the time information of each original text among multiple original texts and dividing the multiple original texts into at least one set of original texts according to the time information of each original text and the preset time interval, a large number of original texts can be divided based on time, enabling the processed set of original texts to be processed, and reducing the text processing pressure.

[0061] Optionally, step 203 of determining the set of target original texts indicated by the target access information and sending the set of target original texts to the translation service device includes:

[0062] Sub-step 2031, determining the target access information carried in the access request and matching the target access information with the access information of each set of original texts;

[0063] Sub-step 2032, when the access information of any set of original texts among the multiple sets of original texts is consistent with the target access information, using the set of original texts as the set of target original texts;

[0064] Sub-step 2033, sending the set of target original texts to the translation service device.

[0065] In an embodiment of the present disclosure, after receiving an access request from a translation service device, the target access information carried in the access request may be determined first, and then the access information of each original text set is compared and matched with the target access information.

[0066] When the access information of the original text set is consistent with the target access information, it indicates that the access information corresponding to the original text set is the target access information, and the original text set is the target original text set. The server may send the target original text set to the translation service device.

[0067] For example, the access information of the original text set 1 is A, the access information of the original text set 2 is B, the access information of the original text set 3 is C, and the target access information carried in the access request is B. Then, the access information in each original text set can be compared and matched with the target access information B in turn, so that the original text set 2 can be used as the target original text set and sent to the translation service device.

[0068] By implementing the embodiments of the present disclosure, the target access information carried in the access request can be determined, the target access information is matched with the access information of each original text set, and when the access information of any original text set in multiple original text sets is consistent with the target access information, the original text set is used as the target original text set, and the target original text set is sent to the translation service device, which can accurately determine the original text required by the translation service device, thereby improving the accuracy of text translation management.

[0069] When the business goes international, it usually involves multiple countries around the world, and the languages of multiple countries may be different. Therefore, it is necessary to translate the original text in a specific language into translation texts in multiple other languages, which doubles the difficulty and workload of text translation management.

[0070] Optionally, the target original text set corresponds to multiple translation text sets; different translation text sets are composed of translation texts in different languages;

[0071] The step of determining the original text carrying the identifier in the target original text set according to the identifier of each translation text and associating the translation text with the original text includes:

[0072] For each translation text set, according to the identifier of each translation text in the translation text set, determine the original text carrying the identifier in the target original text set, and associate the translation text with the original text;

[0073] Construct a multilingual text set corresponding to the original text according to the translation texts respectively associated with each original text in multiple translation text sets.

[0074] In the embodiments of the present disclosure, for the same target original text set, the translation parties can perform translations in different languages, obtaining multiple translation text sets, and the difference between each translation text set lies in the different languages. In fact, each translation text set has translation texts corresponding to each original text in the target original text set.

[0075] For each translation text set, the original text carrying the same identifier can be determined in the target original text set one by one according to the identifier of each translation text in the translation text set, and the translation text and the original text are associated. The specific comparison and matching process will not be elaborated here.

[0076] In the case where there are multiple translation text sets for the same target original text set, any original text can have multiple corresponding translation texts. For example, for the target original text set in Chinese, there can be a first translation text set in Hebrew, a second translation text set in English, and a third translation text set in Spanish. The original text A can correspond to the first translation text A1, the second translation text A2, and the third translation text A3.

[0077] A multilingual text set corresponding to the original text can be constructed according to multiple translation texts of each original text. Thus, based on different original texts, multiple translation text sets are split and integrated to obtain a multilingual text set closely corresponding to each original text.

[0078] Figure 3 It is a schematic diagram of the multilingual setting interface provided by the embodiments of the present disclosure; Figure 3 It can be the web page 30 of the text translation management platform. Triggering the attribute maintenance control 301 in the web page 30 can enter the language maintenance interface for setting multiple languages. The language maintenance interface can include French, Korean, Spanish, etc. There can be editing and deletion controls corresponding to each language on the right side. Triggering the editing and deletion controls can adjust the language. The user of the translation text can set the languages to be translated through this multilingual setting interface, and the translation party can also perform translations in the corresponding languages based on the languages set in the multilingual setting interface, thereby obtaining translation texts in different languages.

[0079] Implementing the embodiments of the present disclosure, for each set of translation texts, according to the identifiers of each translation text in the set of translation texts, in the set of target original texts, determine the original texts carrying the identifiers, associate the translation texts with the original texts, and construct a multilingual text set corresponding to the original texts according to the translation texts respectively associated with each original text in multiple sets of translation texts. It is possible to extract multiple translation texts corresponding to each original text based on the set of target original texts and multiple sets of translation texts according to different original texts, and construct the corresponding multilingual text set, which can improve the management efficiency of the translation texts corresponding to each original text.

[0080] In text translation, there are various links such as creation, editing, translation, proofreading, etc. Each link can be operated by multiple users, which easily leads to chaotic operations on the original texts and translation texts, resulting in incorrect text content or other problems.

[0081] Optionally, the method further includes:

[0082] Associate each original text with a corresponding project label, and configure the description information of each project label; the description information includes project member information and member permission information;

[0083] When receiving an operation request sent by a terminal device, determine the target project label and operating user information carried in the operation request;

[0084] According to the operating user information carried in the operation request, the project member information and member permission information corresponding to the target project label, respond to the operation request.

[0085] In the embodiments of the present disclosure, each original text can be associated with different project labels, where each project can represent a certain specific business scenario. For example, when translating the relevant original texts of an application, the weather application and the settings application can be used as different projects. The original texts in the weather project can be texts such as "The weather is nice", "The weather is cold", "Windy weather", etc., and the original texts in the settings project can be texts such as "Color mode", "Charging mode", etc. Through different project labels, different original texts can be distinguished.

[0086] It can be understood that multiple projects can also form a project group. Each original text can be associated with one or more projects and project groups, and at the same time, each project group and project can contain multiple original texts. Through this relationship model, flexible classification and accurate positioning of the original texts in the organizational structure can be achieved.

[0087] Each project label is correspondingly configured with description information, which at least includes project member information and member permission information. The project member information can include information such as member names and member accounts for differentiating different members. The project member information is used to determine which users have operation permissions for the original text within the project.

[0088] The member permission information can record the operation permissions of each member. For example, it can be the operation types that each member can perform. For instance, Member A - Operation type: Add, Member B - Operation type: Add and Delete, which means Member A can edit the original text to add content, and Member B can edit the original text to add or delete content.

[0089] For example, it can be to use the Role - Based Access Control (RBAC) model, define different roles and corresponding permission sets, and then assign users to specific roles. When a user logs in to the translation management platform and performs an operation, verify the role to which the user belongs to determine whether the user has the corresponding permissions.

[0090] Users can interact with the server through an application or a web page on a terminal device. When a user needs to operate on the original text, for example, for the function controls "Edit" and "Review" corresponding to specific original text, when the user triggers the "Edit" control, the terminal device can generate an edit operation request.

[0091] The operation request carries the target project label and the operating user information. After receiving the operation request, the server can determine the project that the user needs to operate on according to the target project label.

[0092] Furthermore, according to the operating user information carried in the operation request, as well as the project member information and member permission information of the target project label, determine whether the user who needs to perform the operation currently is a user with operation permissions corresponding to the target project label, and the content of the current user's operation permissions.

[0093] When the current user is a user with operation permissions and the current operation request, such as an edit operation request, conforms to the current user's operation permissions, the operation request of the terminal device can be responded to, enabling the terminal device to edit the text.

[0094] In implementing the embodiments of the present disclosure, by associating each original text with a corresponding project tag and configuring the description information of each project tag, when an operation request sent by a terminal device is received, according to the operator information carried in the operation request, the project member information corresponding to the target project tag, and the member permission information, the operation request is responded to, and the user's permissions can be accurately restricted, preventing different users from performing arbitrary operations on the text and improving the orderliness of text management.

[0095] Since the original text involves links such as creation, editing, review, and proofreading, different users in different links will make multiple adjustments to the original text. After multiple adjustments, each user can only obtain the original text after the last adjustment, which results in the loss of the content adjusted previously and affects the precise management of the original text.

[0096] Optionally, when the terminal device operates on the original text, the operated original text, the operator information, and the operation type are stored as a set of operation information to construct the operation record of the original text;

[0097] In response to a trigger operation on any operation information in the operation record, the original text, the operator information, and the operation type corresponding to the operation information are displayed.

[0098] In the embodiments of the present disclosure, when any terminal device operates on the original text, for example, performs addition or deletion, the server can store the operated original text, the operator information, and the operation type as a set of operation information, and multiple sets of operation information can constitute the operation record of the original text.

[0099] It can be understood that the operated original text refers to the text in the original language, that is, the text not translated into other languages, rather than the text content being fixed and unchangeable.

[0100] After constructing the operation record for the original text, the terminal device can view the operation record of any original text through an application or a web page. The operation record can include the serial numbers or other identifiers of multiple sets of operation information. The user can trigger the serial number or other identifier of any operation information through the terminal device, and the server can send the original text, the operator information, and the operation type corresponding to the operation information to the terminal device, and the terminal device can display this information.

[0101] For example, the terminal device can display that user 1 performed an edit operation, and the edited original text is abbab; the terminal device can display that user 2 performed a review operation, and the reviewed original text is abaab.

[0102] In the embodiments of the present disclosure, when the original text is operated on a terminal device, the operated original text, the operating user information, and the operation type are stored as a set of operation information to construct an operation record of the original text. In response to a trigger operation on any operation information in the operation record by the terminal device, the original text, the operating user information, and the operation type of the operation information are sent to the terminal device, which can track the entire life cycle of a single original text from creation, editing, translation, proofreading to final release or archiving, record the operation records at each stage, enable the user to trace back the historical state of the original text at any time, so that the user can conveniently query the information of the original text at different stages, and improve the integrity of text management.

[0103] The number of original texts and translated texts may be large, and there may be problems in both the original texts and the translated texts, such as unsmooth sentences, incorrect use of punctuation marks, or other problems. In order to improve the usability of the texts so that the texts can correctly convey the corresponding meanings, it is necessary to correct the texts. However, for a large number of original texts and translated texts, the data volume is large, and due to the involvement of different languages, the difficulty is also great.

[0104] Optionally, the method further includes:

[0105] Input the initial texts in the original text set and the translated text set into a preset error correction model; the preset error correction model is used to modify the error content of the initial texts;

[0106] When there is error content in the initial texts, obtain the updated texts output by the preset error correction model, and replace the initial texts with the updated texts.

[0107] In the embodiments of the present disclosure, a model capable of correcting texts in multiple languages can be pre-trained, which may include the following processes:

[0108] I. Data collection

[0109] Construct a multilingual corpus, and high-quality text data in multiple languages can be collected. For each language, obtain texts from different sources with correct grammar, spelling, and semantics, such as news articles, academic works, official documents, etc. In addition, an error corpus can be constructed, and error texts can be artificially constructed to generate error text samples based on common error types. The error types can include spelling mistakes, grammar mistakes, and punctuation mistakes, etc. Error texts can also be generated by changing some characters in the correct texts, adjusting the word order, etc.

[0110] II. Data preprocessing

[0111] For all the collected texts, remove unnecessary formatting tags, unify texts in different formats into a format suitable for model processing, for example, convert all texts into plain text format, and perform encoding conversion as needed. Tokenization, which splits the text into smaller units such as words or characters.

[0112] III. Model Selection and Construction

[0113] One can select a natural language processing (NLP) model in deep learning, such as a pre-trained model based on the Transformer architecture, like the multilingual version of BERT (mBERT) or other similar multilingual pre-trained models. The model can be one that has been pre-trained on a large amount of multilingual data and has the generalization ability for multiple languages. Adjust the model structure. According to the specific requirements of the errata task, the structure of the pre-trained model can be fine-tuned.

[0114] IV. Model Training

[0115] One can define a loss function, such as the cross-entropy loss function, to measure the difference between the model's prediction results and the true labels. Input the preprocessed correct and incorrect text data into the model and train it according to the defined objective function. During the training process, the model can learn the grammar, spelling, and semantic rules of different languages so as to be able to identify errors and correct them. Optimization algorithms such as mini-batch gradient descent can be used to update the model's parameters, making the loss of the model on the training data gradually decrease.

[0116] V. Model Evaluation and Optimization

[0117] One can use accuracy (the proportion of correct predictions by the model), recall (the proportion of incorrectly written texts correctly predicted by the model among all actual incorrectly written texts), etc. as indicators to evaluate the performance of the model. An independent validation dataset can be used to evaluate the performance of the model. Optimize the model according to the evaluation results, including adjusting the model's hyperparameters (such as learning rate, hidden layer size, etc.), increasing the training data, improving the data preprocessing method, or adjusting the model structure, etc.

[0118] After obtaining the trained errata model, input the texts in the original text set and the translated text set as the initial texts into the errata model. The errata model performs grammar, vocabulary, and semantic analysis on the original text and the translated text, identifies grammar and vocabulary errors in the multilingual text, and automatically corrects the original text and the translated text, correcting issues such as incorrect usage of idiomatic expressions and improper punctuation in different languages.

[0119] In the case where there are error contents in the initial text, the errata model adjusts the error contents, and the server can obtain the updated text output by the errata model and replace the initial text with the updated text.

[0120] Implementing the embodiments of the present disclosure, by inputting the initial texts in the original text set and the translation text set into a preset errata model, the preset errata model modifies the error contents of the initial texts, obtains the updated text output by the preset errata model, and replaces the initial text with the updated text, which can conveniently correct a large number of multi-language texts, thereby improving the accuracy of the texts.

[0121] Figure 4 It is a logic diagram of the text translation management service provided by the embodiments of the present disclosure;

[0122] Step 401, the translation requester enters the translation requirement into the multi-language collaborative translation management platform to upload the original text to the server;

[0123] Step 402, the translation party exports the translation requirement from the multi-language collaborative translation management platform, that is, obtains the target original text set;

[0124] Step 403, the translation party imports the translation text set into the multi-language collaborative translation management platform, that is, returns to the server;

[0125] Step 404, the translation user extracts the translation text.

[0126] Among them, the multi-language collaborative translation management platform can implement functions such as translation process management, operation record of the original text, multi-language text set (translation corpus), and model errata.

[0127] Figure 5 It is a schematic diagram of the text translation management architecture provided by the embodiments of the present disclosure; when the business scenario to be translated is an intelligent vehicle, the original text source 501 may include the application (APP, APPlication) end, the cockpit end, and the platform end. By collecting the original texts from different sources, they can be divided into different batches of original text sets based on the time information of the original texts and uploaded to the translation management platform 502.

[0128] The translation management platform 502 can implement business functions such as batch management, duplicate check verification, intelligent retrieval, intelligent errata, and version management. The translation party 503 can obtain the original text set and return the translation text set to the translation management platform 502.

[0129] The business middle platform 504 can implement functions such as file management, permission management, role management, and account management for the translation management platform 502, which are not specifically limited herein.

[0130] Figure 6 It is a schematic diagram of a text retrieval interface provided by an embodiment of the present disclosure; Figure 6 The shown retrieval interface 60 can be obtained by triggering the classical Chinese library control 601 in the translation management platform. Information such as access information (e.g., batch number) belonging to the original text set to which the original text belongs, the original text, and the language type can be input in the retrieval interface 60 for retrieval. The retrieved results can include the original text, batch number, project label, language of the translation text, translation text, etc., and the translation text status of other languages corresponding to the original text can also be displayed.

[0131] Based on the above embodiments, the following effects can be achieved:

[0132] 1. Improvement in organizational management efficiency: By effectively associating the organizational structure of the project with the original text, the orderliness of content management is realized, and the text management efficiency is improved;

[0133] 2. Significant platform interoperability effect: Different users on different terminal devices can achieve full-platform real-time synchronization and consistency, eliminate information silos, and shorten the project cycle of multi-platform collaboration;

[0134] 3. Optimization of the translation process: Batch management and data matching technologies improve translation efficiency and reduce translation quality problems;

[0135] 4. Improvement in original text management: Lifecycle management and search functions improve the depth and breadth of content management and reduce decision-making errors;

[0136] 5. High accuracy of intelligent error correction: The intelligent error correction module improves the correction accuracy, reduces the workload of manual proofreading, and improves the text quality;

[0137] 6. Clear role management: Role management based on the RBAC model improves the standardization and security of the work process and ensures the stable operation of the platform.

[0138] Figure 7 It is a text translation management device provided by an embodiment of the present disclosure. The device 40 includes:

[0139] An original set determination module 701, configured to determine a set of original texts to be translated; each set of original texts includes multiple original texts; different original texts carry different identifiers;

[0140] An access information allocation module 702, configured to allocate different access information to each set of original texts and receive an access request from a translation service device; the access request carries target access information;

[0141] The original set sending module 703 is configured to determine a target original text set indicated by the target access information and send the target original text set to the translation service device; the translation service device is configured to return a translation text set corresponding to the target original text set;

[0142] The translation file receiving module 704 is configured to receive the translation text set returned by the translation service device; the translation text set includes multiple translation texts; different translation texts carry different identifiers;

[0143] The corresponding text association module 705 is configured to determine, in the target original text set, an original text carrying the identifier according to the identifier of each translation text, and associate the translation text with the original text.

[0144] Optionally, the diagnostic database stores repair information corresponding to fault codes; the apparatus further includes:

[0145] The repair information module is configured to determine target repair information corresponding to the target fault code in the diagnostic database;

[0146] The repair diagnosis module is configured to add the target repair information to the fault diagnosis result.

[0147] Optionally, the original set determination module includes:

[0148] The original time sub-module is configured to determine the time information of each original text in multiple original texts;

[0149] The time division sub-module is configured to divide multiple original texts into at least one original text set according to the time information of each original text and a preset time interval; the time information of the original texts in each original text set is within the same preset time interval.

[0150] Optionally, the original set sending module includes:

[0151] The access information matching sub-module is configured to determine the target access information carried in the access request and match the target access information with the access information of each original text set;

[0152] The original text sending sub-module is configured to use the original text set as the target original text set when the access information of any original text set in multiple original text sets is consistent with the target access information;

[0153] Send the target original text set to the translation service device.

[0154] Optionally, the target original text set corresponds to multiple translated text sets; different translated text sets are composed of translated texts in different languages;

[0155] The corresponding text association module includes:

[0156] The respective association sub-modules are used to, for each translated text set, determine, in the target original text set, the original text carrying the identifier according to the identifier of each translated text in the translated text set, and associate the translated text with the original text;

[0157] The multi-language construction sub-module is used to construct a multi-language text set corresponding to the original text according to the translated texts respectively associated with each original text in multiple translated text sets.

[0158] Optionally, the device further includes:

[0159] The project association module is used to associate each original text with a corresponding project label and configure the description information of each project label; the description information includes project member information and member permission information;

[0160] The request information module is used to determine the target project label and the operating user information carried in the operation request when receiving the operation request sent by the terminal device;

[0161] The operation response module is used to respond to the operation request according to the operating user information carried in the operation request, the project member information and the member permission information corresponding to the target project label.

[0162] Optionally, the device further includes:

[0163] The operation record module is used to store the original text after operation, the operating user information and the operation type as a set of operation information when the terminal device operates on the original text, so as to construct the operation record of the original text;

[0164] The historical viewing module is used to send the original text, the operating user information and the operation type corresponding to the operation information to the terminal device in response to the trigger operation of the terminal device on any operation information in the operation record.

[0165] Optionally, the device further includes:

[0166] The text errata module is used to input the initial texts in the original text set and the translated text set into a preset errata model; the preset errata model is used to modify the error content of the initial texts;

[0167] A text update module, configured to obtain an updated text output by the preset errata model when there is incorrect content in the initial text, and replace the initial text with the updated text.

[0168] In summary, in the embodiments of the present disclosure, by determining a set of original texts to be translated, assigning different access information to each set of original texts, receiving an access request from a translation service device, determining the target set of original texts indicated by the target access information in the access request, and sending the target set of original texts to the translation service device, receiving the set of translated texts returned by the translation service device, and determining, according to the identifier of each translated text, the original text carrying the identifier in the target set of original texts, the translated text and the original text are associated. It is possible to manage multiple original texts in batches. Different sets of original texts have different access information, and the translation service device can accurately obtain different sets of original texts. After translation is completed, text association is performed based on the identifiers of the original text and the translated text, avoiding text confusion problems in large-scale translation scenarios, improving the orderliness in the text translation process, and ultimately improving the management efficiency of text translation.

[0169] An embodiment of the present application further provides an electronic device, as Figure 8 shown, including a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004. Among them, the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0170] The memory 1003 is used to store a computer program.

[0171] When the processor 1001 is used to execute the program stored in the memory 1003, it implements the steps in the above text translation management method, which will not be elaborated here.

[0172] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0173] The communication interface is used for communication between the above electronic device and other devices.

[0174] The memory may include a Random Access Memory (RAM), or may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0175] The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0176] In another embodiment provided by the present application, there is also provided a computer-readable storage medium, in which instructions are stored. When it runs on a computer, it causes the computer to execute the text translation management method described in the above embodiment.

[0177] In another embodiment provided by the present application, there is also provided a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the text translation management method described in the above embodiment.

[0178] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0179] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0180] Each embodiment in this specification is described in a related manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For the embodiments of the device, electronic device, computer-readable storage medium, and computer program product including instructions, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0181] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A text translation management method, characterized in that: The method comprises: Determine a set of original texts to be translated; each set of original texts includes multiple original texts; different original texts carry different identifiers; Assigning different access information to each original text set, and receiving an access request from a translation service device; the access request carries target access information; Determine the target original text set indicated by the target access information, and send the target original text set to the translation service device; the translation service device is used to return the translation text set corresponding to the target original text set; receiving the translation text set returned by the translation service device; the translation text set includes a plurality of translation texts; different translation texts carry different identifiers; According to the identifier of each translated text, the original text carrying the identifier is determined in the target original text set, and the translated text is associated with the original text.

2. The method according to claim 1, characterized in that The step of determining a set of original texts to be translated comprises: determining time information of each original text in the plurality of original texts; According to the time information of each original text and the preset time interval, the multiple original texts are divided into at least one original text set; the time information of the original texts in each original text set is within the same preset time interval.

3. The method according to claim 1, characterized in that The step of determining the target original text set indicated by the target access information and sending the target original text set to the translation service device includes: Determining target access information carried in the access request, and matching the target access information with access information of each original text set; When the access information of any original text set among the multiple original text sets is consistent with the target access information, taking the original text set as the target original text set; The target original text set is sent to the translation service device.

4. The method according to claim 1, characterized in that: The target original text set corresponds to a plurality of translation text sets; different translation text sets are composed of translation texts in different languages; The step of determining the original text carrying the identifier of each translated text in the target original text set and associating the translated text with the original text comprises: For each translation text set, according to the identifier of each translation text in the translation text set, in the target original text set, the original text carrying the identifier is determined, and the translation text is associated with the original text; According to the translation texts respectively associated with each original text in the plurality of translation text sets, a multilingual text set corresponding to the original text is constructed.

5. The method according to claim 1, characterized in that The method further comprises: Associating each original text with a corresponding project tag, and configuring description information for each project tag; the description information includes project member information and member authority information; When receiving an operation request sent by a terminal device, determining a target item label and operation user information carried in the operation request; The operation request is responded to according to the operation user information carried in the operation request, the project member information and the member authority information corresponding to the target project tag.

6. The method according to claim 5, characterized in that The method further comprises: In the case where the terminal device operates the original text, the original text after the operation, the operation user information and the operation type are stored as a set of operation information to construct an operation record of the original text; In response to a trigger operation of the terminal device on any operation information in the operation record, the original text, operation user information and operation type corresponding to the operation information are sent to the terminal device.

7. The method according to claim 1, characterized in that The method further comprises: Inputting the initial texts in the original text set and the translated text set into a preset errata model; the preset errata model is used to modify the erroneous content of the initial text; In the case that the initial text contains erroneous content, an updated text output by the preset errata model is obtained, and the initial text is replaced by the updated text.

8. A text translation management device, characterized in that: The device comprises: The original set determination module is used to determine the original text set to be translated; each original text set includes multiple original texts; different original texts carry different identifiers; An access information allocation module, used to allocate different access information to each original text set, and receive an access request from a translation service device; the access request carries target access information; An original set sending module, used to determine the target original text set indicated by the target access information, and send the target original text set to the translation service device; the translation service device is used to return the translation text set corresponding to the target original text set; A translation file receiving module, used for receiving the translation text set returned by the translation service device; the translation text set includes a plurality of translation texts; different translation texts carry different identifiers; The corresponding text association module is used to determine the original text carrying the identifier in the target original text set according to the identifier of each translated text, and associate the translated text with the original text.

9. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the text translation management method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the text translation management method according to any one of claims 1 to 7 are implemented.

Images