Data translation method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a data translation method which comprises the following steps: receiving a translation processing request sent by a specified interface, and detecting whether the specified interface contains a translation annotation or not based on an interceptor; if yes, intercepting a return result of the specified interface, and analyzing the translation processing request to obtain text data and target language information; searching a local cache based on the text data, and judging whether the text data belongs to high-frequency terms or not; if not, searching a cache database based on the text data and the target language information; if the search result is that the matched translation result does not exist in the cache database, matching the target language information with the text data by using a term library to obtain a matching result; if the matching result is successful matching, generating a first translation result based on the matching result; and outputting the first translation result. The method can be applied to a translation scene of an insurance interaction service in the financial field, and the processing efficiency and accuracy of data translation are improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology and can be applied to the financial technology field, particularly to data translation methods, devices, computer equipment, and storage media. Background Technology

[0002] Traditional multilingual translation solutions primarily rely on general-purpose translation engines and standard language libraries, which suffer from significant shortcomings in supporting minority languages, hindering fast and accurate translation. Specifically, general-purpose translation engines focus on common languages, lacking in-depth research into the vocabulary, grammar, and semantics of minority languages, and thus lacking targeted optimization and adaptation. Furthermore, the updating and maintenance of standard language libraries struggle to keep pace with the changes and developments in minority languages, resulting in low accuracy and timeliness in data translation. This situation not only affects the timeliness and accuracy of information access for users but also increases the barrier to entry for minority users in rural and remote areas, lowering the user experience.

[0003] For example, in the agricultural insurance sector within the financial field, ethnic minority farmers need accurate translation of relevant texts when understanding insurance terms and applying for claims. Traditional translation methods may fail to accurately translate ethnic minority language expressions involved in insurance terminology, such as the names of specific crops in ethnic minority languages ​​or distinctive vocabulary related to local agricultural disasters. This can lead to farmers misunderstanding the insurance terms, encountering difficulties in applying for claims due to inaccurate translations, and affecting the protection of farmers' rights and the effective implementation of insurance services.

[0004] Therefore, there is an urgent need to provide a fast and accurate translation solution suitable for minority languages ​​in order to improve translation quality, lower the barrier to entry for minority users, and enhance user experience. Summary of the Invention

[0005] The purpose of this application is to provide a data translation method, apparatus, computer device, and storage medium to solve the technical problems of low accuracy and timeliness in existing data translation methods that rely on general translation engines and conventional language libraries.

[0006] Firstly, a data translation method is provided, including:

[0007] The system receives a translation processing request from a specified interface and detects whether the specified interface contains a preset translation annotation based on an interceptor; wherein the translation processing request carries the text data to be translated and the target language information.

[0008] If so, the return result of the specified interface is intercepted, and the translation processing request is parsed to obtain the corresponding text data and the target language information;

[0009] Based on the text data, a search is performed on the preset local cache to determine whether the text data belongs to high-frequency terms;

[0010] If the text data does not belong to high-frequency terms, then a search is performed on the preset cache database based on the text data and target language information to obtain the corresponding search results;

[0011] If the search result is that there is no translation result matching the text data in the cache database, then based on the preset priority matching strategy, the target language information and the text data are matched using a pre-built terminology database to obtain the corresponding matching result;

[0012] If the matching result is successful, a first translation result corresponding to the text data is generated based on the matching result;

[0013] The first translation result is output to complete the response processing for the translation processing request.

[0014] Secondly, a data translation device is provided, comprising:

[0015] The first processing module is used to receive a translation processing request sent by a specified interface, and to detect whether the specified interface contains a preset translation annotation based on an interceptor; wherein the translation processing request carries the text data to be translated and the target language information;

[0016] The second processing module is used to intercept the return result of the specified interface if the condition is met, and to parse the translation processing request to obtain the corresponding text data and the target language information.

[0017] The first judgment module is used to perform a search process on the preset local cache based on the text data to determine whether the text data belongs to high-frequency terms;

[0018] The search module is used to perform a search on a preset cache database based on the text data and target language information if the text data does not belong to high-frequency terms, and obtain the corresponding search results.

[0019] The matching module is used to, if the search result is that there is no translation result matching the text data in the cache database, then based on a preset priority matching strategy, use a pre-built terminology database to perform matching processing on the target language information and the text data to obtain the corresponding matching result.

[0020] A generation module is used to generate a first translation result corresponding to the text data based on the matching result if the matching result is a successful match.

[0021] The first output module is used to output the first translation result to complete the response processing of the translation processing request.

[0022] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described data translation method.

[0023] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described data translation method.

[0024] In the above-described data translation method, apparatus, computer equipment, and storage medium, a translation processing request is first received from a designated interface, and an interceptor is used to detect whether the designated interface contains a preset translation annotation. The translation processing request carries text data to be translated and target language information. If so, the return result of the designated interface is intercepted, and the translation processing request is parsed to obtain the corresponding text data and target language information. Then, a search is performed on a preset local cache based on the text data to determine whether the text data belongs to high-frequency terms. If the text data does not belong to high-frequency terms, a search is performed on a preset cache database based on the text data and target language information to obtain a corresponding search result. If the search result indicates that no translation result matching the text data exists in the cache database, a pre-built terminology database is used to match the target language information with the text data based on a preset priority matching strategy to obtain a corresponding matching result. If the matching result is successful, a first translation result corresponding to the text data is generated based on the matching result. Finally, the first translation result is output to complete the response processing to the translation processing request. Based on the above automated processing flow, this application, through the combined use of local caching, cache database, and terminology database, can automatically and accurately translate the text data to be translated according to the target speech information, and output a matching and accurate first translation result, effectively improving the processing efficiency and accuracy of data translation. Attached Figure Description

[0025] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0027] Figure 2 This is a flowchart of an embodiment of the data translation method according to this application;

[0028] Figure 3 This is a schematic diagram of one embodiment of the data translation apparatus according to this application;

[0029] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0031] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0032] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0033] like Figure 1 As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0034] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0035] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0036] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0037] It should be noted that the data translation method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the data translation device is generally set in the server / terminal device.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0039] Continue to refer to Figure 2 A flowchart illustrating an embodiment of the data translation method according to this application is shown. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different needs. The data translation method provided in this application embodiment can be applied to any scenario requiring data translation, and thus can be applied to products in these scenarios, such as data translation in the financial and insurance fields. The data translation method includes the following steps:

[0040] Step S201: Receive a translation processing request sent from a specified interface, and detect whether the specified interface contains a preset translation annotation based on the interceptor; wherein, the translation processing request carries the text data to be translated and the target language information.

[0041] In this embodiment, the data translation method operates on an electronic device (e.g., Figure 1The server / terminal device shown can acquire the text data to be translated and the target language information via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future wireless connection methods. The executing entity of this application is specifically a data translation system, which can be simply referred to as the system. This application can be applied to translation scenarios in insurance interaction business (such as agricultural insurance interaction business) in the financial field. The aforementioned translation processing request can be a request triggered by a user with text translation needs through the specified interface. The system interface provides a language selection function for the user. The user can input the corresponding language information (specifically, a minority language) and the text data to be translated according to the actual translation needs. When the user selects a minority language version, the front-end code will encapsulate the user-selected target language information into the request header when sending an HTTP request (translation processing request), with the parameter name being Accept-Language. For example, if a user selects Mongolian, the frontend will add `Accept-Language:mn` (where `mn` is the ISO 639 language code for Mongolian) to the request header and send it to the backend server. This method of using HTTP request headers to transmit language version information is a standard and efficient approach. It provides additional contextual information to the backend without altering the request body. This allows the system to determine the user's desired translation language based on the language parameter in the request header, thus providing accurate target language information for subsequent translation processing.

[0042] During the system design phase, the development team defined a custom annotation called `@Translate` (or translation annotation). This annotation can include optional attributes, such as translation priority. When writing API code, for APIs that return content that needs to be translated into minority languages, this annotation is added to the API method or API class. For example, adding the `@Translate` annotation to an API method that displays sales information for agricultural products from minority areas allows the system to recognize that this API requires translation. In this way, by using custom annotations, translation requirements are tightly integrated with API code, enabling developers to clearly mark APIs that need translation. This approach improves code readability and maintainability and facilitates unified management and processing of translated APIs later on.

[0043] Furthermore, after receiving a translation processing request, the system will use interceptors or aspect-oriented programming (such as Spring AOP) to check whether the interface methods of the specified interface have the @Translate annotation (translation annotation), and generate corresponding check results, including whether the specified interface contains the translation annotation or not.

[0044] Step S202: If yes, intercept the return result of the specified interface and parse the translation processing request to obtain the corresponding text data and target language information.

[0045] In this embodiment, when the specified interface is identified to contain a translation annotation, the system intercepts the return result of that interface using an interceptor. For example, in a Spring Boot project, AOP is used to intercept methods annotated with `@Translate`. After the method execution is complete, the return value is obtained and guided to the translation processing flow. Thus, through interceptors or aspect-oriented programming, the interception and processing of interfaces requiring translation can be achieved without modifying the original business logic code. This approach offers excellent decoupling, making the translation processing logic independent of the business logic, facilitating development and maintenance. It also facilitates unified management and optimization of the translation processing flow.

[0046] Furthermore, the system will automatically parse the above translation processing requests to extract the text data to be translated and the target language information carried in the translation processing requests.

[0047] Step S203: Based on the text data, perform a search on the preset local cache to determine whether the text data belongs to high-frequency terms.

[0048] In this embodiment, after entering the translation process, the system extracts key terms from the text data to be translated. Simultaneously, the system maintains a record table of high-frequency terms, recording the access frequency of each term. After extracting the key terms from the text data, the system queries this record table to determine if the access frequency of the current term exceeds 1000 QPS. If it does, the term is marked as a high-frequency term. Local caching offers extremely high access speed, enabling rapid result return. By recording the access frequency of terms and marking high-frequency terms, high-frequency terms can be prioritized for caching, further improving the system's response speed. This is significant for improving user experience and reducing the pressure on the backend server. Furthermore, the criterion for determining high-frequency terms (1000 QPS) can be adjusted according to actual business needs to adapt to different application scenarios.

[0049] Furthermore, if the above text data is determined to be a high-frequency term, the system will directly return the corresponding translation result from the local cache and output the translation result. The local cache can be implemented using an in-memory data structure (such as a HashMap).

[0050] Step S204: If the text data does not belong to high-frequency terms, then a search process is performed on the preset cache database based on the text data and target language information to obtain the corresponding search results.

[0051] In this embodiment, the specific implementation process of searching the preset cache database based on the text data and target language information to obtain the corresponding search results will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0052] Step S205: If the search result is that there is no translation result matching the text data in the cache database, then based on the preset priority matching strategy, the target language information and the text data are matched using a pre-built terminology database to obtain the corresponding matching result.

[0053] In this embodiment, the terminology database is a three-layer terminology database consisting of a core database, a regional database, and a scenario database. The three-layer terminology database architecture includes: (1) constructing a three-level dictionary of “basic terminology database + regional dialect database + professional agricultural terminology database”. ① Core layer (standardized terminology database / core database): integrates international standards (such as ISO 639 language codes) and national agricultural terminology standards (such as the “Standard for Agricultural Terminology of Ethnic Minorities”), covering the core vocabulary of four languages ​​including Tibetan and Uyghur. By using semantic type annotation (basic words / professional words / cultural words) and grammatical constraints (such as Mongolian verb suffix rules), the authority and compatibility of terms are ensured; and knowledge graph technology is used to construct the genus-species relationship between terms (such as "pests and diseases → yak dung biological pesticide control scheme") to improve the accuracy of semantic association; ② Regional layer (dialect dynamic adaptation library / regional library): includes dialect variants and regional expression differences, combined with user UGC (user-submitted dialect use cases + GPS positioning) and AI confidence screening (>95%), and is entered into the library after cross-verification by local experts; ③ Scenario layer (business semantic library / scenario library): binds the terminology weight model of business scenarios, for example, in the insurance scenario, the weight of "Blizzard" associated with "compensation standard" is increased by 47%. (2) Database architecture and collaboration mechanism include: using different databases to store data at different levels, which effectively improves the translation speed in different scenarios, as follows. The core library uses a relational database (MySQL) to ensure ACID transactions; the regional library uses a document database (MongoDB) to flexibly store dialects; and the scenario library uses a graph database (Neo4j) to efficiently handle terminology associations.

[0054] The aforementioned priority matching strategy refers to matching the text data based on the target language information, in the order of priority of the core library, regional library, and scene library. Correspondingly, if a match is found in any of the libraries (core library, regional library, scene library), a comprehensive successful matching result is generated; conversely, if no match is found in any of the libraries (core library, regional library, scene library), a comprehensive failed matching result is generated.

[0055] Step S206: If the matching result is successful, then a first translation result corresponding to the text data is generated based on the matching result.

[0056] In this embodiment, the specific implementation process of generating the first translation result corresponding to the text data based on the matching result will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0057] Step S207: Output the first translation result to complete the response processing for the translation processing request.

[0058] In this embodiment, the response to the translation processing request is completed by returning the generated first translation result to the relevant user who triggered the above translation processing request.

[0059] This application first receives a translation processing request from a designated interface and detects whether the designated interface contains preset translation annotations based on an interceptor. The translation processing request carries text data to be translated and target language information. If so, the return result of the designated interface is intercepted, and the translation processing request is parsed to obtain the corresponding text data and target language information. Then, based on the text data, a preset local cache is searched to determine whether the text data belongs to high-frequency terms. If the text data does not belong to high-frequency terms, a preset cache database is searched based on the text data and target language information to obtain the corresponding search result. If the search result indicates that no translation result matching the text data exists in the cache database, a pre-built terminology database is used to match the target language information with the text data based on a preset priority matching strategy to obtain the corresponding matching result. If the matching result is successful, a first translation result corresponding to the text data is generated based on the matching result. Finally, the first translation result is output to complete the response processing for the translation processing request. Based on the above automated processing flow, this application, through the combined use of local caching, cache database, and terminology database, can automatically and accurately translate the text data to be translated according to the target speech information, and output a matching and accurate first translation result, effectively improving the processing efficiency and accuracy of data translation.

[0060] In some alternative implementations, step S204 includes the following steps:

[0061] Construct a corresponding target key based on the text data and the target language information.

[0062] In this embodiment, the aforementioned cache database can specifically be Redis, a high-performance key-value store database with rich data structures and fast read / write capabilities. By storing recent translation results in Redis, the cache scope can be expanded, improving the efficiency of retrieving translation results. Simultaneously, Redis's distributed nature facilitates system expansion and maintenance. Compared to local caching, Redis can store more data and can share cached data across multiple servers, improving the overall system performance and reliability. Specifically, if the text data to be translated is not found in the local cache, or if the text data is not a high-frequency term, the system will automatically forward the request to the cache database, i.e., the Redis cache. The system will construct a unique key to identify the text data to be translated and the target language information, such as text_mn (indicating the text to be translated into Mongolian).

[0063] Perform a value lookup process corresponding to the target key in the cache database.

[0064] In this embodiment, the above-mentioned value lookup process refers to: finding the value corresponding to the target key in the cache database Redis, i.e., the translation result.

[0065] If a target value corresponding to the target key is found in the cache database, a first search result is generated in the cache database that contains a translation result corresponding to the text data.

[0066] In this embodiment, if a corresponding translation result is found in the Redis cache database, a first lookup result will be generated indicating that a translation result corresponding to the text data exists in the cache database, and the system will directly return the translation result to the corresponding user. Simultaneously, the system will record the access time of the translation result for subsequent cache management and expiration handling. For example, the system can set an expiration time; when the translation result exceeds the expiration time, it will be automatically deleted from Redis to ensure data timeliness.

[0067] By directly returning translation results from the Redis cache, complex translation calculations are avoided, significantly improving system response speed. Furthermore, recording access times provides a basis for cache invalidation strategies, ensuring users receive the latest translation results. Simultaneously, Redis's caching mechanism also reduces the pressure on the backend translation service, improving overall system performance.

[0068] If no target value corresponding to the target key is found in the cache database, a second search result is generated in which no translation result corresponding to the text data exists in the cache database.

[0069] In this embodiment, if the corresponding translation result is not found in the cache database Redis, a second search result will be generated in which the translation result corresponding to the text data does not exist in the cache database.

[0070] This application constructs a corresponding target key based on the text data and the target language information; then, it performs a value lookup process corresponding to the target key in the cache database; if a target value corresponding to the target key is found in the cache database, a first lookup result is generated indicating that a translation result corresponding to the text data exists in the cache database; otherwise, if a target value corresponding to the target key is not found in the cache database, a second lookup result is generated indicating that a translation result corresponding to the text data does not exist in the cache database. Based on the above processing flow, this application constructs a corresponding target key based on the text data and the target language information, then performs a value lookup process corresponding to the target key in the cache database, and automatically and accurately generates the corresponding lookup result based on the obtained value lookup result, ensuring the accuracy of the obtained lookup result.

[0071] In some optional implementations of this embodiment, the terminology database is a three-layer terminology database comprising a core database, a regional database, and a scenario database; step S206 includes the following steps:

[0072] Obtain the result analysis strategy corresponding to the three-layer terminology database.

[0073] In this embodiment, when a translation result matching the text data cannot be found in the cache database, the system will match according to the priority of the core database, the regional database, and the scenario database in sequence, and use these three layers of terminology databases to obtain the most suitable translation result corresponding to the above text data.

[0074] Specifically, the result analysis strategy corresponding to the above three-layer terminology database includes the following steps: Step 1, Core Database Matching. 1. Terminology Retrieval. Determining the retrieval scope: The system first determines the text to be translated, using it as the key information for retrieval. Based on the content and type of the text, the scope of retrieval in the core database is clarified. The core database integrates international standards (such as ISO 639 language codes) and national-level agricultural terminology standards (such as the "Standard for Agricultural Terminology of Ethnic Minorities"), covering core vocabulary in four languages ​​including Tibetan and Uyghur. Semantic type and grammatical constraint matching: In the core database, terms are labeled with semantic types (basic words / professional words / cultural words) and grammatical constraints (such as Mongolian verb suffix rules). The system will filter out potentially matching terms in the core database based on the semantic features and grammatical rules of the text to be translated. For example, if the text to be translated is a professional agricultural term, the system will prioritize searching among terms labeled as professional words and check whether they conform to the corresponding grammatical constraints. Knowledge graph-assisted matching: The core database uses knowledge graph technology to construct genus-species relationships between terms (such as "pests and diseases → yak dung biological pesticide control program"). The system can leverage knowledge graphs to expand its search scope and find terms related to the text to be translated. For example, if the text to be translated is "yak dung biopesticide," the system can use the knowledge graph to find related terms such as "pests and diseases," thereby more comprehensively matching the translation results.

[0075] 2. Matching Result Processing. Exact Match: If a term that perfectly matches the text to be translated is found in the core library, the system will directly obtain the translation result for that term. Similar Match: If no term perfectly matches, the system will calculate the similarity between the text to be translated and the terms in the core library. Similarity can be determined using semantic similarity algorithms (such as word vector-based similarity calculation). The system will select the term with the highest similarity as the candidate translation result. Result Validation: For candidate translation results, the system will perform further validation. For example, it will check whether the translation result conforms to the grammatical rules and semantic conventions of the target language. If the validation passes, the translation result will be used as the matching result in the core library.

[0076] Step 2, Regional Database Matching (if no suitable translation result is found in the core database). 1. Terminology Retrieval. Determine Regional Features: The system will determine the regional dialect features to be matched based on the user's geographical location information (such as GPS positioning) or the language version selected by the user. The regional database includes dialect variants and regional expression differences. It combines user UGC (user-submitted dialect examples and GPS positioning) with AI confidence screening (>95%), and is added to the database after cross-validation by local experts. Dialect Variant Matching: In the regional database, the system will match the corresponding dialect variants based on the semantic and grammatical features of the text to be translated. For example, if the text to be translated is a general agricultural term, but has a special dialect expression in a certain ethnic minority area, the system will search for that dialect expression in the regional database. Handling Regional Expression Differences: The regional database also considers regional expression differences, and the system will adjust the translation results according to regional features. For example, ethnic minority languages ​​in different regions may have different expressions for the same concept, and the system will select the most appropriate expression based on the information in the regional database.

[0077] 2. Matching Result Processing. Exact Match: If a dialect variant or regional expression that perfectly matches the text to be translated is found in the regional database, the system will directly obtain the translation result. Similar Match: If no term is found that perfectly matches, the system will calculate the similarity between the text to be translated and the terms in the regional database, and select the term with the highest similarity as the candidate translation result. Result Validation: The system will validate the candidate translation results. Since the terms in the regional database have undergone cross-validation by local experts, the validation process mainly checks whether the translation result conforms to the regional expression habits of the target language. If the validation passes, the translation result will be used as the matching result of the regional database.

[0078] Step 3: Scene Library Matching (if no suitable translation result is found in the regional library). 1. Terminology Retrieval. Determine the Business Scene: The system will determine the scene library to be matched based on the business scene to which the text to be translated belongs. The scene library is bound to a terminology weight model of the business scene. For example, in an insurance scene, the weight of "Blizzard" associated with "compensation standard" increases by 47%. Terminology Weight Matching: In the scene library, the system will match related terms based on the semantics and business scene of the text to be translated, and consider the weight of the terms. For example, in an insurance scene, if the text to be translated is "Blizzard," the system will prioritize terms with a higher weight associated with "compensation standard" as the translation result. Terminology Association Processing: The scene library is stored using a graph database (Neo4j), which can efficiently process terminology associations. The system can utilize the associations between terms to find other terms related to the text to be translated, thereby more comprehensively matching the translation result. For example, if the text to be translated is an agricultural insurance term, the system can find related agricultural and insurance terms through terminology association, thereby translating more accurately.

[0079] 2. Matching Result Processing. Exact Match: If a term that perfectly matches the text to be translated is found in the scenario library, and the weight of that term meets the requirements of the business scenario, the system will directly obtain the translation result. Similar Match: If no term perfectly matches, the system will calculate the similarity between the text to be translated and the terms in the scenario library, and select the term with the highest similarity and weight that meets the requirements of the business scenario as the candidate translation result. Result Validation: The system will validate the candidate translation results. The validation process mainly checks whether the translation result meets the needs of the business scenario and the semantic habits of the target language. If the validation passes, the translation result will be used as the matching result in the scenario library.

[0080] Step 4: Comprehensive Result Selection. Priority Judgment: The system will judge the matching results according to the priority of the core library, regional library, and scene library. If a suitable translation result is matched in the core library, the translation result of the core library will be used directly; if a suitable translation result is not matched in the core library, but a suitable translation result is matched in the regional library, the translation result of the regional library will be used; if no suitable translation result is matched in the first two layers, the translation result of the scene library will be used.

[0081] The matching results are analyzed based on the aforementioned result analysis strategy to generate corresponding initial translation results.

[0082] In this embodiment, the matching results can be analyzed based on the strategy content of the above result analysis strategy to generate an initial translation result corresponding to the above text data.

[0083] The initial translation result is optimized to obtain the corresponding target translation result.

[0084] In this embodiment, the quality and accuracy of the translation results can be ensured by performing grammatical checks and semantic adjustments on the initial translation results, and the corresponding target translation results can be obtained.

[0085] The target translation result is used as the first translation result corresponding to the text data.

[0086] In this embodiment, the three-tiered terminology database, matched according to priority, fully utilizes terminology resources at different levels. The core database ensures the authority and universality of the translation, the regional database handles dialect differences, and the scenario database incorporates business scenarios, making the translation results more accurate and in line with actual needs.

[0087] This application acquires a result analysis strategy corresponding to the three-layer terminology database; then analyzes the matching results based on the result analysis strategy to generate a corresponding initial translation result; subsequently, it optimizes the initial translation result to obtain a corresponding target translation result; and finally, it uses the target translation result as the first translation result corresponding to the text data. Based on the above processing flow, this application analyzes the matching results using the acquired result analysis strategy corresponding to the three-layer terminology database to generate a corresponding initial translation result, then optimizes the initial translation result to obtain a target translation result, which is then used as the first translation result corresponding to the text data. This achieves intelligent and accurate translation processing of text data based on a hierarchical matching method using a three-layer terminology database, effectively improving the accuracy and efficiency of data translation and reducing unnecessary translation calculations.

[0088] In some alternative implementations, after step S205, the electronic device may further perform the following steps:

[0089] If the matching result is a failure, the text data is preprocessed to obtain the corresponding processed data.

[0090] In this embodiment, the preprocessing described above may include at least word segmentation and part-of-speech tagging.

[0091] Call the preset translation model.

[0092] In this embodiment, the translation model specifically adopts a Bi-LSTM (Bidirectional Long Short-Term Memory) + attention mechanism model.

[0093] The data is translated based on the translation model to obtain the corresponding second translation result.

[0094] In this embodiment, the text data is encoded using a Bi-LSTM model to capture its contextual information. Then, an attention mechanism is used to assign different weights to words at different positions, highlighting important information. Finally, based on the encoding and attention weights, a translation result corresponding to the text data is output, i.e., the second translation result.

[0095] The second translation result is then processed for output.

[0096] In this embodiment, the response to the translation processing request is completed by returning the generated second translation result to the relevant user who triggered the above-mentioned translation processing request.

[0097] When a terminology database cannot provide translation results, AI translation can leverage the powerful language understanding and generation capabilities of deep learning models to analyze contextual information and resolve issues such as professional ambiguity. The combination of a Bi-LSTM model and an attention mechanism can better capture the semantic information of text data, improving translation accuracy. AI translation can supplement terminology database matching, further enhancing the coverage and accuracy of translations.

[0098] If this application detects that the matching result is a failure, it preprocesses the text data to obtain corresponding processed data; then it calls a preset translation model; subsequently, it translates the processed data based on the translation model to obtain a corresponding second translation result; and then it outputs the second translation result. Based on the above processing flow, this application automatically utilizes the language understanding and generation capabilities of the translation model to translate the text data when a matching result is detected as a failure, i.e., the terminology database cannot provide a translation result, thereby improving the coverage and accuracy of the generated second translation result.

[0099] In some alternative implementations, after the step of outputting the first translation result, the electronic device may further perform the following steps:

[0100] Obtain the preset target structure.

[0101] In this embodiment, the target structure described above can specifically adopt a "scene label + semantic weight" structure.

[0102] Based on the target structure, the text data is processed to generate information, thereby obtaining the corresponding target information.

[0103] In this embodiment, after the new term is translated by the translation model, the system generates scene labels and semantic weight information corresponding to the text data according to the target structure described above, i.e., the target information. Specifically, for text data, such as a newly emerging agricultural insurance term, the system adds scene labels according to its business scenario (such as claims scenario, insurance scenario, etc.), and assigns semantic weights according to the importance and relevance of the term in the scenario.

[0104] Get the preset storage policy.

[0105] In this embodiment, the storage strategy includes storing new terms into the scene library of the terminology library according to the structure of "scene tag + semantic weight".

[0106] Based on the storage strategy, the target information and the second translation result are stored in the terminology database.

[0107] In this embodiment, based on the strategy content of the above storage strategy, the target information including scene tags and semantic weights can be stored together with the second translation result in the scene library of the terminology library.

[0108] This application obtains a preset target structure; then, based on the target structure, it performs information generation processing on the text data to obtain corresponding target information; subsequently, it obtains a preset storage strategy; and then, based on the storage strategy, it stores the target information and the second translation result in the terminology database. Based on the above processing flow, this application obtains corresponding target information by performing information generation processing on text data based on the use of the target structure, and then stores the target information and the second translation result in the terminology database based on the use of the storage strategy. Thus, by storing text data belonging to new terms according to the "scene tag + semantic weight" structure, new terms can be closely integrated with business scenarios. Scene tags help to quickly locate and retrieve relevant terms, while semantic weights reflect the importance of terms in the scenario, improving the accuracy and relevance of terms in subsequent translations. Through this processing method, the terminology database can be continuously enriched and improved, thereby enhancing the system's translation capabilities and adaptability.

[0109] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0110] Determine whether the input error correction information corresponding to the first translation result has been received.

[0111] In this embodiment, a pre-built function entry point for providing translation error correction to users is constructed within the system. When a user finds the translation result inaccurate, they can click the error correction button, input what they believe to be the correct translation, and submit the corresponding error correction information. The front-end code then sends the user's error correction information (including the original text, incorrect translation, correct translation, etc.) to the system. By providing translation error correction functionality, the system fully leverages user initiative, allowing them to participate in optimizing translation quality. User feedback is the most direct and valuable, enabling the timely identification of problems in the translation. In this way, user opinions and suggestions can be continuously collected, providing data support for improving translation quality.

[0112] If so, obtain the preset verification strategy.

[0113] In this embodiment, the aforementioned verification strategy includes the following: After receiving the user's error correction information, the system sends it to local experts for review. Local experts are typically professionals familiar with the local language and culture. They evaluate and verify the user's corrections and generate corresponding verification results. This local expert review ensures the accuracy and reasonableness of the user's error correction information. Because local experts have a deep understanding of local language habits and practical needs, their review can prevent erroneous or inappropriate error correction information from being included in the system, thereby improving translation quality. Through this mechanism of user feedback and expert review, errors in translation can be continuously corrected, making the translation results more in line with local language habits and practical needs, and continuously improving the accuracy of the translation.

[0114] The error correction information is verified based on the verification strategy.

[0115] In this embodiment, the error correction information can be verified according to the content of the verification strategy, and a corresponding verification result can be generated. The verification result includes whether the error correction information passes verification or fails verification.

[0116] If the error correction information passes the verification, the first translation result in the terminology database is updated based on the error correction information.

[0117] In this embodiment, if the above-mentioned error correction information is detected to pass the verification, the correct translation contained in the above-mentioned error correction information will be automatically used to replace the above-mentioned first translation result in the terminology database to complete the data update process.

[0118] This application determines whether it has received error correction information corresponding to the first translation result; if so, it obtains a preset verification strategy; subsequently, it verifies the error correction information based on the verification strategy; if the error correction information passes verification, it updates the data of the first translation result in the terminology database based on the error correction information. Based on this processing flow, after receiving the error correction information corresponding to the first translation result, this application intelligently uses the verification strategy to verify the error correction information, and automatically updates the data of the first translation result in the terminology database based on the use of the error correction information after detecting that the error correction information has passed verification. Thus, by combining user feedback and verification processing mechanisms, errors in the translation process can be continuously corrected, making the translation results more consistent with local language habits and actual needs, and continuously improving the accuracy of the translation.

[0119] In some optional implementations of this embodiment, before step S203, the electronic device may further perform the following steps:

[0120] Invoke the preset target elimination algorithm.

[0121] In this embodiment, the target elimination algorithm described above can specifically adopt the LRU (Least Recently Used) elimination algorithm.

[0122] The local cache is managed based on the target eviction algorithm.

[0123] In this embodiment, the cache space of the local cache is managed using the LRU (Least Recently Used) eviction algorithm. When the cache space is insufficient, the least recently used high-frequency terms are evicted first, thereby ensuring that the local cache always retains the most frequently used terms and improving the cache hit rate.

[0124] Obtain the preset terminology change monitoring strategy.

[0125] In this embodiment, the strategy of the term change monitoring strategy includes: the system monitors changes in terms and updates the content in the local cache in a timely manner when a term changes.

[0126] The local cache is updated based on the terminology change monitoring strategy.

[0127] In this embodiment, the processing mechanism corresponding to the aforementioned terminology change monitoring strategy can be used to update the content of the local cache. The terminology change monitoring strategy ensures the timeliness of the cached data stored in the local cache, preventing users from obtaining outdated translation results.

[0128] This application manages the local cache by invoking a preset target eviction algorithm, then managing the cache space based on the target eviction algorithm, subsequently obtaining a preset terminology change monitoring strategy, and then updating the local cache content based on the terminology change monitoring strategy. Based on this process, this application manages the local cache by combining the target eviction algorithm with the terminology change monitoring strategy, ensuring both cache efficiency and data accuracy. This significantly reduces access to the backend database or other storage systems, thereby improving overall system performance.

[0129] In some alternative implementations, the user information obtained is subject to user consent and complies with relevant laws and policies.

[0130] Furthermore, any software tools or components not belonging to our company that appear in the embodiments of this application are merely illustrative examples and do not represent actual use.

[0131] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0132] It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned first translation result, the above-mentioned first translation result can also be stored in a node of a blockchain.

[0133] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0134] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0135] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0136] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0137] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0138] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a data translation device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0139] like Figure 3 As shown, the data translation device 300 described in this embodiment includes: a first processing module 301, a second processing module 302, a first judgment module 303, a search module 304, a matching module 305, a generation module 306, and a first output module 307. Wherein:

[0140] The first processing module 301 is used to receive a translation processing request sent by a specified interface, and to detect whether the specified interface contains a preset translation annotation based on an interceptor; wherein the translation processing request carries the text data to be translated and the target language information;

[0141] The second processing module 302 is used to intercept the return result of the specified interface if the condition is met, and to parse the translation processing request to obtain the corresponding text data and the target language information.

[0142] The first judgment module 303 is used to perform a search process on the preset local cache based on the text data to determine whether the text data belongs to high-frequency terms.

[0143] The search module 304 is used to perform a search on a preset cache database based on the text data and target language information if the text data does not belong to high-frequency terms, and obtain the corresponding search results.

[0144] The matching module 305 is used to, if the search result is that there is no translation result matching the text data in the cache database, then based on a preset priority matching strategy, use a pre-built terminology database to perform matching processing on the target language information and the text data to obtain the corresponding matching result.

[0145] The generation module 306 is used to generate a first translation result corresponding to the text data based on the matching result if the matching result is a successful match;

[0146] The first output module 307 is used to output the first translation result to complete the response processing of the translation processing request.

[0147] In some optional implementations of this embodiment, the lookup module 304 includes:

[0148] A submodule is constructed to build a corresponding target key based on the text data and the target language information;

[0149] An execution submodule is used to perform a value lookup process corresponding to the target key in the cache database;

[0150] The first generation submodule is used to generate a first search result in the cache database if a target value corresponding to the target key is found in the cache database;

[0151] The second generation submodule is used to generate a second search result if no target value corresponding to the target key is found in the cache database.

[0152] In some optional implementations of this embodiment, the terminology database is a three-layer terminology database comprising a core database, a regional database, and a scenario database; the generation module 306 includes:

[0153] The acquisition submodule is used to acquire the result analysis strategy corresponding to the three-layer terminology database;

[0154] The analysis submodule is used to analyze the matching results based on the result analysis strategy and generate corresponding initial translation results;

[0155] The optimization submodule is used to optimize the initial translation result to obtain the corresponding target translation result;

[0156] A determination submodule is used to take the target translation result as the first translation result corresponding to the text data.

[0157] In some optional implementations of this embodiment, the data translation device further includes:

[0158] The preprocessing module is used to preprocess the text data to obtain corresponding processed data if the matching result is a matching failure.

[0159] The first calling module is used to call the preset translation model;

[0160] The translation module is used to translate the processed data based on the translation model to obtain the corresponding second translation result;

[0161] The second output module is used to process the second translation result.

[0162] In some optional implementations of this embodiment, the data translation device further includes:

[0163] The first acquisition module is used to acquire a preset target structure;

[0164] The third processing module is used to perform information generation processing on the text data based on the target structure to obtain the corresponding target information;

[0165] The second acquisition module is used to acquire the preset storage strategy;

[0166] A storage module is used to store the target information and the second translation result into the terminology database based on the storage strategy.

[0167] In some optional implementations of this embodiment, the data translation device further includes:

[0168] The second judgment module is used to determine whether the error correction information corresponding to the first translation result has been received.

[0169] The third acquisition module is used to acquire the preset verification strategy if the condition is met.

[0170] The verification module is used to verify the error correction information based on the verification strategy.

[0171] The first update module is used to update the first translation result in the terminology database based on the error correction information if the error correction information passes the verification.

[0172] In some optional implementations of this embodiment, the data translation device further includes:

[0173] The second calling module is used to invoke the preset target elimination algorithm;

[0174] The management module is used to manage the cache space of the local cache based on the target eviction algorithm.

[0175] The fourth acquisition module is used to acquire the preset terminology change monitoring strategy;

[0176] The second update module is used to update the content of the local cache based on the term change monitoring strategy.

[0177] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0178] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0179] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0180] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for data translation methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0181] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions for the data translation method.

[0182] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0183] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the data translation method described above.

[0184] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0185] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A data translation method, characterized in that, Includes the following steps: The system receives a translation processing request from a specified interface and detects whether the specified interface contains a preset translation annotation based on an interceptor; wherein the translation processing request carries the text data to be translated and the target language information. If so, the return result of the specified interface is intercepted, and the translation processing request is parsed to obtain the corresponding text data and the target language information; Based on the text data, a search is performed on the preset local cache to determine whether the text data belongs to high-frequency terms; If the text data does not belong to high-frequency terms, then a search is performed on the preset cache database based on the text data and target language information to obtain the corresponding search results; If the search result is that there is no translation result matching the text data in the cache database, then based on the preset priority matching strategy, the target language information and the text data are matched using a pre-built terminology database to obtain the corresponding matching result; If the matching result is successful, a first translation result corresponding to the text data is generated based on the matching result; The first translation result is output to complete the response processing for the translation processing request.

2. The data translation method according to claim 1, characterized in that, The step of searching the preset cache database based on the text data and target language information to obtain the corresponding search results specifically includes: Construct a corresponding target key based on the text data and the target language information; Perform a value lookup process corresponding to the target key in the cache database; If a target value corresponding to the target key is found in the cache database, a first search result is generated in the cache database that contains a translation result corresponding to the text data; If no target value corresponding to the target key is found in the cache database, a second search result is generated in which no translation result corresponding to the text data exists in the cache database.

3. The data translation method according to claim 1, characterized in that, The terminology database comprises a three-layer database consisting of a core database, a regional database, and a scenario database; the step of generating a first translation result corresponding to the text data based on the matching result specifically includes: A strategy for obtaining results corresponding to the three-layer terminology database; The matching results are analyzed based on the aforementioned result analysis strategy to generate corresponding initial translation results; The initial translation result is optimized to obtain the corresponding target translation result; The target translation result is used as the first translation result corresponding to the text data.

4. The data translation method according to claim 1, characterized in that, After the step of matching the target language information with the text data using a pre-built terminology database based on a preset priority matching strategy to obtain the corresponding matching result, the method further includes: If the matching result is a failure, the text data is preprocessed to obtain the corresponding processed data; Call the preset translation model; The data is translated based on the translation model to obtain the corresponding second translation result. The second translation result is then processed for output.

5. The data translation method according to claim 4, characterized in that, After the step of translating the processed data based on the translation model to obtain the corresponding second translation result, the method further includes: Obtain the preset target structure; Based on the target structure, the text data is processed to generate information, thereby obtaining the corresponding target information; Get the preset storage policy; Based on the storage strategy, the target information and the second translation result are stored in the terminology database.

6. The data translation method according to claim 1, characterized in that, After the step of outputting the first translation result, the method further includes: Determine whether error correction information corresponding to the first translation result has been received; If so, obtain the preset verification strategy; The error correction information is verified based on the verification strategy. If the error correction information passes the verification, the first translation result in the terminology database is updated based on the error correction information.

7. The data translation method according to claim 1, characterized in that, Before the step of performing a lookup process on a preset local cache based on the text data to determine whether the text data belongs to high-frequency terms, the method further includes: Invoke the preset target elimination algorithm; The local cache is managed based on the target eviction algorithm. Obtain the preset terminology change monitoring strategy; The local cache is updated based on the terminology change monitoring strategy.

8. A data translation device, characterized in that, include: The first processing module is used to receive a translation processing request sent by a specified interface, and to detect whether the specified interface contains a preset translation annotation based on an interceptor; wherein the translation processing request carries the text data to be translated and the target language information; The second processing module is used to intercept the return result of the specified interface if the condition is met, and to parse the translation processing request to obtain the corresponding text data and the target language information. The first judgment module is used to perform a search process on the preset local cache based on the text data to determine whether the text data belongs to high-frequency terms; The search module is used to perform a search on a preset cache database based on the text data and target language information if the text data does not belong to high-frequency terms, and obtain the corresponding search results. The matching module is used to, if the search result is that there is no translation result matching the text data in the cache database, then based on a preset priority matching strategy, use a pre-built terminology database to perform matching processing on the target language information and the text data to obtain the corresponding matching result. A generation module is used to generate a first translation result corresponding to the text data based on the matching result if the matching result is a successful match. The first output module is used to output the first translation result to complete the response processing of the translation processing request.

9. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the data translation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the data translation method as described in any one of claims 1 to 7.

Images