System and device for realizing system platform language conversion based on AI large model

Abstract

The invention relates to a system and method for achieving system platform language conversion based on an AI large model, electronic equipment, a computer readable medium and a computer program product. The method comprises the following steps: performing language data matching in a cache of a user side according to a language selection instruction; when the language data matching of the user side fails, obtaining a language attribute and a system version according to the language selection instruction; performing language data matching in a cache of a server side through the language attribute and the system version; when the language data matching of the server side fails, generating a prompt problem through language attributes and system configuration data, and inputting the prompt problem into an A I large model to generate language conversion data; and performing language visualization processing on the language conversion data and displaying the language conversion data in a system platform of a user side. The multilingual implementation process of the system can be greatly simplified, the manpower and resource cost can be reduced, the accuracy and efficiency of language conversion can be improved, and the system performance and the user experience can be improved.

Description

Technical Field

[0001] This application relates to the field of computer information processing. Specifically, it relates to a system, method, electronic device, computer-readable medium, and computer program product for implementing language conversion on a system platform based on an AI large model. Background Art

[0002] System multilingualism refers to designing a software system or business platform to support multiple languages, so as to be used globally and meet the needs of users with different cultural and language backgrounds. This technical background stems from the accelerating development of economic globalization. In order to expand market share, improve user experience, and enhance competitiveness, enterprises have turned their attention to the international market. Therefore, system multilingualism has become an inevitable prerequisite for conducting international business.

[0003] In the process of implementing traditional business system multilingual technologies, enterprises face many challenges. This process is not only complex and cumbersome, but also consumes a large amount of manpower and resources. Whenever a character in the system language needs to be changed, developers may need to manually modify dozens or more system language files, resulting in low efficiency. Moreover, multilingual projects require the participation of professional translation teams, developers, and testers, which is costly. When manually modifying language files, spelling mistakes, grammar mistakes, or inaccurate translations are likely to occur. As the business develops and the system is upgraded, the language files may need to be changed frequently, increasing the maintenance difficulty.

[0004] To overcome these challenges, a more efficient, accurate, and easy-to-maintain system multilingual solution is needed. Therefore, a new system, method, electronic device, computer-readable medium, and computer program product for implementing language conversion on a system platform based on an AI large model are needed.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of this application. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] In view of this, this application provides a system, method, electronic device, computer-readable medium, and computer program product for implementing language conversion on a system platform based on an AI large model, which can greatly simplify the implementation process of system multilingualism, reduce manpower and resource costs, and can also improve the accuracy and efficiency of language conversion, and enhance system performance and user experience.

[0007] Other features and advantages of this application will become apparent through the following detailed description, or will be partially learned through the practice of this application.

[0008] According to one aspect of the present application, a method for implementing language conversion on a system platform based on an AI large model is proposed. The method includes: performing language data matching in the cache of the user side according to a language selection instruction; when the language data matching on the user side fails, obtaining a language attribute and a system version according to the language selection instruction; performing language data matching in the cache of the server side through the language attribute and the system version; when the language data matching on the server side fails, generating a prompt question through the language attribute and system configuration data, and inputting the prompt question into the AI large model to generate language conversion data; performing language visualization processing on the language conversion data and displaying it in the system platform of the user side.

[0009] Optionally, before performing language data matching in the cache of the user side according to the language selection instruction, it further includes: displaying the system platform on the user side through default language data; providing a language switching window and an operation area in the system platform; generating a language selection instruction based on the operations of the user in the language window and the operation area.

[0010] Optionally, performing language data matching in the cache of the user side according to the language selection instruction includes: obtaining a language attribute through the language selection instruction; performing a first language data matching on the user side based on a data reading program and the language attribute.

[0011] Optionally, when the language data matching on the user side fails, obtaining a language attribute and a system version according to the language selection instruction includes: when there is no language data corresponding to the language attribute in the cache unit of the user side, determining that the first language data matching fails; obtaining the language attribute and the system version currently logged in by the user according to the language selection instruction.

[0012] Optionally, performing language data matching in the cache of the server side through the language attribute and the system version includes: generating a pass-through request in JSON format through the language attribute and the system version; performing a second language data matching on the server side according to the pass-through request.

[0013] Optionally, when the language data matching on the server side fails, generating a prompt question through the language attribute and system configuration data, and inputting the prompt question into the AI large model to generate language conversion data includes: when there is no language data corresponding to the language attribute and the system version in the language data cache unit of the server side, determining that the second language data matching fails; determining system configuration data through the system version; generating the language conversion data through the language attribute, system configuration data, and the AI large model.

[0014] Optionally, generating a prompt question based on the language attribute and the system configuration data includes: pre-generating a prompt template; obtaining the system configuration data by the front end of the system platform; and combining the prompt template and the system configuration data to generate the prompt question.

[0015] Optionally, inputting the prompt question into the AI large model to generate the language conversion data includes: inputting the prompt question into the AI large model; the AI large model generating return data according to the prompt question; and converting the format of the return data to generate the language conversion data.

[0016] Optionally, after performing language visualization processing on the language conversion data and displaying it in the system platform of the user side, it further includes: storing the language conversion data in the language data cache unit of the server side according to its corresponding language attribute and system version.

[0017] According to one aspect of the present application, a system for implementing language conversion of a system platform based on an AI large model is proposed. The system includes: a first matching module for performing language data matching in the cache of the user side according to a language selection instruction; an attribute module for obtaining a language attribute and a system version according to the language selection instruction when the language data matching in the user side fails; a second matching module for performing language data matching in the cache of the server side through the language attribute and the system version; a conversion module for generating a prompt question through a language attribute and system configuration data and inputting the prompt question into the AI large model to generate language conversion data when the language data matching in the server side fails; and a display module for performing language visualization processing on the language conversion data and displaying it in the system platform of the user side.

[0018] According to one aspect of the present application, an electronic device is proposed. The electronic device includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0019] According to one aspect of the present application, a computer-readable medium is proposed, on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0020] According to one aspect of the present application, a computer program product is proposed, including: a computer program / instructions, and when the computer program / instructions are executed by a processor, the method as described above is implemented.

[0021] A system, method, electronic device, computer-readable medium, and computer program product for implementing language conversion on a system platform based on an AI large model according to the present application perform language data matching in a cache at a user end according to a language selection instruction; when the language data matching at the user end fails, obtain a language attribute and a system version according to the language selection instruction; perform language data matching in a cache at a server end through the language attribute and the system version; when the language data matching at the server end fails, generate a prompt question through a language attribute and system configuration data, and input the prompt question into the AI large model to generate language conversion data; and perform language visualization processing on the language conversion data and display it on a system platform at the user end, which can greatly simplify the implementation process of system multilingualism, reduce labor and resource costs, and can also improve the accuracy and efficiency of language conversion, and enhance system performance and user experience.

[0022] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present application. Brief Description of the Drawings

[0023] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other objectives, features, and advantages of the present application will become more apparent. The following described drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 is a flowchart of a method for implementing language conversion on a system platform based on an AI large model shown according to an exemplary embodiment.

[0025] Figure 2 is a flowchart of a method for implementing language conversion on a system platform based on an AI large model shown according to another exemplary embodiment.

[0026] Figure 3 is a schematic diagram of a method for implementing language conversion on a system platform based on an AI large model shown according to another exemplary embodiment.

[0027] Figure 4 is a block diagram of a system for implementing language conversion on a system platform based on an AI large model shown according to an exemplary embodiment.

[0028] Figure 5 is a block diagram of an electronic device shown according to an exemplary embodiment. Detailed Description of the Embodiments

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0030] The technical terms related to this application are explained as follows:

[0031] AI: Refers to the development of computer systems capable of performing tasks similar to human intelligence, such as learning, problem-solving, decision-making, and perception. AI systems can analyze data, identify patterns, and make predictions or decisions without human intervention.

[0032] Large model: Refers to a complex artificial neural network trained with a large amount of data to perform specific tasks, such as language translation, image recognition, or text generation. Large models are typically characterized by their large scale, complexity, and computational requirements.

[0033] Multilingual system: Refers to a system that implements multiple sets of language displays, mainly for local language systems in different international regions.

[0034] Storage unit: The data memory of the web or the client.

[0035] Cache unit: The data cache of the server.

[0036] Figure 1 It is a flowchart of a method for implementing language conversion on a system platform based on an AI large model according to an exemplary embodiment. The method 10 for implementing language conversion on a system platform based on an AI large model includes at least steps S102 to S110.

[0037] As Figure 1 shown, in S102, language data matching is performed in the cache at the user side according to the language selection instruction. For example, the language attribute can be obtained through the language selection instruction; the first language data matching is performed at the user side based on the data reading program and the language attribute.

[0038] More specifically, after the user side receives the language selection instruction generated by the user's operation, tools such as regular expressions, JSON parsers, or XML parsers can be used to extract the specific language attribute from the instruction. The language attribute can be represented in the form of a string, such as "zh-CN" (Simplified Chinese), "en-US" (American English), etc.

[0039] For example, according to the language attribute, the client can call the built-in data reading program to try to retrieve language data that matches the language attribute through a query statement or a file path. After retrieving the language data, the matching logic will check the version of the data and the degree of match with the language attribute. If all the data meet the requirements, it is regarded as the first successful language data match, and the language data corresponding to the language attribute will be provided to the client for display; otherwise, the subsequent process will continue.

[0040] In one embodiment, before performing language data matching in the cache of the client according to the language selection instruction, it further includes: displaying the system platform on the client through default language data; providing a language switching window and an operation area in the system platform; generating a language selection instruction based on the operations of the user in the language window and the operation area.

[0041] More specifically, when the system platform is started or the user accesses it for the first time, the client will automatically load a set of preset default language data. This data usually contains the most basic and commonly used text information in the system platform, such as button labels, menu items, error prompts, etc., and is presented in a widely supported language (such as Chinese, English).

[0042] Design a window dedicated to language switching at a preset position in the system platform (such as the top navigation bar, sidebar, or settings page). This window should contain all available language options and be presented to the user in an intuitive way (such as a drop-down menu, a radio button group, etc.).

[0043] When the user interacts with the language switching window or the operation area (such as clicking on a language option, pressing a button, etc.), the client will detect these operations and record them, generating a language selection instruction that includes the language attribute.

[0044] In a specific application, the user selects French in the selection window of the system platform. The client queries the language data corresponding to French in the memory. If there is corresponding language data, the system platform will be switched to French display; otherwise, the subsequent steps will be performed.

[0045] In S104, when the language data matching in the client fails, obtain the language attribute and the system version according to the language selection instruction. For example, when the language data corresponding to the language attribute does not exist in the cache unit of the client, it is determined that the first language data match fails; obtain the language attribute and the system version currently logged in by the user according to the language selection instruction.

[0046] After confirming the failure of the first match, subsequent processing can be continued. For example, the language attribute and system version can be obtained from the language selection instruction. The system version can also be obtained in various ways such as user session (Session), Cookie, HTTP request header, or system configuration file. The client parses this information to determine the system version logged in by the current user and ensures the accuracy and timeliness of the version information.

[0047] In S106, language data matching is performed in the cache on the server side through the language attribute and the system version. For example, a pass-through request in JSON format can be generated through the language attribute and the system version; a second language data matching is performed on the server side according to the pass-through request.

[0048] The client can, for example, serialize the language attribute and system version information into a pass-through request in JSON format.

[0049] More specifically, the storage form of the language in the storage unit in this application can be, for example:

[0050] [Language]_v[Version].json

[0051] Parameters: language, version

[0052] Storage instance:

[0053] en_v1.0.0.json

[0054] zh_v1.0.0.json

[0055] In a specific application: A user in France uses the system platform with a version number of 1.1.3. The user switches the system language to French display. If the first language data matching on the client side fails, the parameters of the generated pass-through request are:

[0056] Parameters:

[0057] - Language - key: lang, value: fr

[0058] - Version - key: version, value: 1.1.3

[0059] In S108, when the language data matching on the server side fails, a prompt question is generated through the language attribute and system configuration data, and the prompt question is input into the AI large model to generate language conversion data. For example, when the language data corresponding to the language attribute and the system version does not exist in the language data cache unit on the server side, it is determined that the second language data matching fails; the system configuration data is determined through the system version; the language conversion data is generated through the language attribute, system configuration data, and the AI large model.

[0060] When the second language data matching fails, the server side can select a suitable large AI model for language conversion according to the specific requirements of the language attribute and system version. The model selection may be based on factors such as the performance of the model, accuracy, training data set, etc. The selected model can also be loaded from the model repository into a specific server cache for calculation.

[0061] In S110, the language conversion data is subjected to language visualization processing and displayed in the system platform of the user side. The generated language conversion data can, for example, be post-processed, such as format adjustment, encoding conversion, text cleaning, etc., to ensure the quality and readability of the output data.

[0062] In one embodiment, after the language conversion data is subjected to language visualization processing and displayed in the system platform of the user side, it further includes: storing the language conversion data in the language data cache unit of the server side according to its corresponding language attribute and system version.

[0063] More specifically, the server side can encapsulate the result into an appropriate response format (such as JSON, XML, etc.) and return it to the user side through an HTTP response. After processing the language selection instruction, the user side will update the interface of the system platform to reflect the newly selected language by the user. This includes reloading the language data matching the language attribute and applying this data to the corresponding positions in the interface. At the same time, the user side can, for example, display a confirmation message or prompt to the user to inform them that the language switch has been successfully completed.

[0064] According to the method for realizing language conversion of the system platform based on a large AI model of the present application, by performing language data matching in the cache of the user side according to the language selection instruction; when the language data matching in the user side fails, obtaining the language attribute and system version according to the language selection instruction; performing language data matching in the cache of the server side through the language attribute and the system version; when the language data matching in the server side fails, generating a prompt question through the language attribute and system configuration data, and inputting the prompt question into the large AI model to generate language conversion data; and subjecting the language conversion data to language visualization processing and displaying it in the system platform of the user side, the implementation process of system multilingualism can be greatly simplified, the human and resource costs can be reduced, and the accuracy and efficiency of language conversion can also be improved, enhancing the system performance and user experience.

[0065] It should be clearly understood that the present application describes how to form and use specific examples, but the principles of the present application are not limited to any details of these examples. On the contrary, based on the teachings of the content disclosed in the present application, these principles can be applied to many other embodiments.

[0066] Figure 2 It is a flowchart of a method for implementing language conversion on a system platform based on an AI large model shown according to another exemplary embodiment. Figure 2 The shown process 20 is for Figure 1 a detailed description of "generating language conversion data through an AI large model" in the shown process at S108.

[0067] As Figure 2 shown, in S202, system configuration data is determined through the system version.

[0068] For example, the received system version information can be parsed. This usually involves string processing to break down the version number into different parts (such as major version number, minor version number, revision number, etc.) for subsequent logical judgment or data retrieval. According to the parsed system version information, the system retrieves the corresponding system configuration data by querying a database, configuration file, or calling an API, etc. The configuration data may include various information such as hardware requirements, software dependencies, function switch states, interface layout settings, etc.

[0069] To improve efficiency, the system can, for example, store commonly used system configuration data through a caching mechanism. During the actual adaptation process, it can first check whether the required data exists in the cache. If it exists, the cached data is directly used; otherwise, real-time retrieval is performed.

[0070] In S204, prompt questions are generated through the language attributes and the system configuration data.

[0071] More specifically, for example, a prompt template can be pre-generated; the system configuration data is obtained by the front end of the system platform; and the prompt template and the system configuration data are combined to generate the prompt questions.

[0072] The prompt template defines the structure and format required for generating prompt questions. The template can contain placeholders for inserting specific language attributes and system configuration data when generating prompt questions.

[0073] In an actual application:

[0074] The template is: template

[0075] The parameter is: topic

[0076] The parameter will be determined by the input of the system user. Through this processing, the large language model can be formulated to provide proprietary services.

[0077] More specifically, the prompt template can be simply set as:

[0078] template = XXXXX

[0079] Please translate the value of the data {data} into {lang}

[0080] Among them, the data and lang parameters will be generated from the data passed in by the front end of the system.

[0081] The front end of the system platform can, for example, be responsible for obtaining system configuration data from the back end or local storage. The front end interacts with the back end through AJAX requests, WebSocket connections, or other communication mechanisms to obtain the latest system configuration data. After the front end obtains the system configuration data, according to the predefined prompt template, it inserts the system configuration data into the corresponding position of the template to generate a complete prompt question. This process may involve techniques such as string replacement and template engine rendering.

[0082] In S206, input the prompt question into the AI large model to generate the language conversion data.

[0083] More specifically, for example, input the prompt question into the AI large model; the AI large model generates return data according to the prompt question; format the return data to generate the language conversion data.

[0084] In practical applications, the data output by the AI large model is generally of text type and may also contain other impurities or data formats that do not conform to those used by the system platform. For example, the data output by the large model can be assembled into json format:

[0085] For example: when the model translates a language and outputs 'hello', the above data can be processed into:

[0086] {greet:'hello'}

[0087] Then it can be assigned to a variable to use this data value.

[0088] More specifically, the AI large model can be called through an API or other interface, and the encoded prompt question is passed as input to the model. During the call, specific request formats, parameter settings, etc. can also be set. After receiving the return data from the AI large model, format conversion is required to convert the model output into language conversion data that the system platform can understand and use. This may include steps such as parsing JSON or XML format data, converting data types, and adjusting data structures.

[0089] Figure 3 It is a schematic diagram of a method for implementing language conversion of a system platform based on an AI large model shown according to another exemplary embodiment. Figure 3 For the basic process architecture of an internationalized system platform that supports multiple types of languages, through Figure 3The processing steps shown can ensure a good user experience and achieve the most complex language series at the lowest cost.

[0090] As Figure 3 shown, in [1.1], when the user logs in to the system platform, the system pulls the default language data for display and can also provide a language switching window and an operation area;

[0091] In [1.2], the user can select the language of the system platform to be displayed through the language switching window and the operation area;

[0092] In [1.3], after the system platform obtains the switching instruction, it starts the language data reading program.

[0093] When the language data is successfully read, that is, when the language data corresponding to the user's switched language exists locally, it is displayed to the user; more specifically, [1.3.2] can be executed. If the system data stores the data of this language, the system language data is selected in the data storage unit, and [1.3.2.1] can also be executed.

[0094] Language data is obtained, and "language processing program visualization" is started.

[0095] When the language data is not successfully read, follow-up steps are carried out.

[0096] In [1.3.1], if the data storage unit cannot find the data of this language, the parameters such as the language and version are transparently transmitted to trigger the data requester;

[0097] In [1.3.1.1], the requester communicates with the server with parameters such as the language and version. The server receives the data and searches the cache unit according to the language and version number;

[0098] In [1.3.1.2], cache retrieval is performed in the language cache data; the language cache area can also classify and back up the language data by version and cache it in the language data cache unit;

[0099] In [1.3.1.3], it is found that there is no data of this language and the corresponding version;

[0100] In [1.3.1.4], the data that the system needs to translate is transmitted to the AI large model service through the prompt template parameter;

[0101] In [1.3.1.5], the AI large model service calls the large model engine;

[0102] In [2.1.1], after the AI large model uses the language configuration data as parameters for the large model engine, it executes the AIGC response data for the AI large model service. Here, AIGC is the abbreviation of "AI Generated Content", which means "Artificial Intelligence Generated Content" in Chinese. This concept refers to the automatic generation of various forms of content such as text, images, videos, and audio through artificial intelligence technology.

[0103] The large model receives the previously processed prompt template parameters, such as: translate the value of data XXX into French, and then output data of xxx format through xxx. The large model will output specific content data according to this prompt.

[0104] After the large model engine generates the data, the service undertaken by the large model performs data processing and data return.

[0105] In [2.1.2], the translated and formatted data is returned to the system for language processing visualization;

[0106] In [2.2], the large model service converts the data format and transmits it to the cache simultaneously;

[0107] In [2.2.1], after the server returns the translation language data to the system, the data is classified and stored by version;

[0108] In [2.2.3], the data is persistently stored by the system data storage unit for the user to select and use.

[0109] The solution of this application can build an efficient, scalable and cost-effective international system platform. By combining configuration data management, AI large model translation, visualization control program and cache strategy, it realizes the comprehensive optimization of multi-language support. The solution of this application has the following advantages:

[0110] High scalability: Through the translation ability of the AI large model, the system can easily support a large number of language types without developing and maintaining code separately for each language version.

[0111] Low cost and high benefit: The cache strategy and the reusability of the AI model significantly reduce the computing and storage costs of the server, while improving the translation efficiency.

[0112] Simplify development and maintenance: Configuration data management and visualization control program reduce the use of hard-coded text, making it easier to update and maintain language content.

[0113] Enhance user experience: Through the cache and efficient request processing mechanism, the system can quickly respond to user requests and provide a smooth multi-language interface experience.

[0114] High maintainability: The modular design and standardized interfaces enable each part of the system to be independently upgraded and maintained, reducing the complexity of the system.

[0115] Quick adaptation to market changes: When new languages need to be supported or language content updated, the system can respond quickly without long development and testing cycles.

[0116] Those skilled in the art can understand that all or part of the steps for implementing the above embodiments are realized as a computer program executed by a CPU. When this computer program is executed by the CPU, it performs the above functions defined by the above method provided in this application. The said program can be stored in a computer-readable storage medium, which can be a read-only memory, a magnetic disk, an optical disc, etc.

[0117] In addition, it should be noted that the above drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, rather than for limiting purposes. It is easy to understand that the processes shown in the above drawings do not indicate or limit the time sequence of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0118] The following is the device embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the device embodiment of the present application, please refer to the method embodiment of the present application.

[0119] Figure 4 is a block diagram of a system for implementing language conversion of a system platform based on an AI large model shown according to an exemplary embodiment. As Figure 4 shown, the system 40 for implementing language conversion of a system platform based on an AI large model includes: a first matching module 402, an attribute module 404, a second matching module 406, a conversion module 408, and a display module 410.

[0120] The first matching module 402 is used to perform language data matching in the cache of the user side according to the language selection instruction; the first matching module 402 is also used to obtain the language type attribute through the language selection instruction; and perform the first language data matching in the user side based on the data reading program and the language type attribute.

[0121] The attribute module 404 is used to obtain the language type attribute and the system version according to the language selection instruction when the language data matching in the user side fails; the attribute module 404 is also used to determine that the first language data matching fails when there is no language data corresponding to the language type attribute in the cache unit of the user side; and obtain the language type attribute and the system version of the currently logged-in user according to the language selection instruction.

[0122] The second matching module 406 is used to perform language data matching in the server-side cache through the language attribute and the system version; the second matching module 406 is also used to generate a pass-through request in JSON format through the language attribute and the system version; and perform a second language data matching on the server side according to the pass-through request.

[0123] The conversion module 408 is used to generate a prompt question through the language attribute and system configuration data when the language data matching on the server side fails, and input the prompt question into the AI large model to generate language conversion data; the conversion module 408 is also used to determine that the second language data matching fails when the language data corresponding to the language attribute and the system version does not exist in the language data cache unit on the server side; determine the system configuration data through the system version; and generate the language conversion data through the language attribute, system configuration data and the AI large model.

[0124] The display module 410 is used to perform language visualization processing on the language conversion data and display it in the system platform of the user side. The display module 410 is also used to store the language conversion data in the language data cache unit on the server side according to its corresponding language attribute and system version.

[0125] According to the system for realizing language conversion of the system platform based on the AI large model of the present application, language data matching is performed in the cache of the user side according to the language selection instruction; when the language data matching on the user side fails, the language attribute and the system version are obtained according to the language selection instruction; language data matching is performed in the cache of the server side through the language attribute and the system version; when the language data matching on the server side fails, a prompt question is generated through the language attribute and system configuration data, and the prompt question is input into the AI large model to generate language conversion data; and the language conversion data is subjected to language visualization processing and displayed in the system platform of the user side, which can greatly simplify the implementation process of system multilingualization, reduce labor and resource costs, and can also improve the accuracy and efficiency of language conversion, and enhance system performance and user experience.

[0126] As Figure 5 shown, an embodiment of the present application provides an electronic device, including a processor 510, a memory 520 and a bus. Among them, the processor 510 and the memory 520 complete mutual communication through the bus 540;

[0127] The memory 520 is used to store a computer program;

[0128] When the processor 510 is used to execute the program stored on the memory 520, it realizes the method for realizing language conversion of the system platform based on the AI large model in any of the above embodiments.

[0129] The communication interface 520 is used for communication between the above-mentioned electronic device and other devices.

[0130] The memory 520 may include a random access memory 520 (Random Access Memory, abbreviated as RAM), or may include a non-volatile memory 520 (non-volatile memory), such as at least one disk memory 520. Optionally, the memory 520 may also be at least one storage device located far from the aforementioned processor 510.

[0131] If the above method in this application is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc.

[0132] The embodiment of this application provides a computer-readable storage medium. The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method for realizing system platform language conversion based on the AI large model in any of the above embodiments. For example, language data matching can be performed in the cache of the user terminal according to the language selection instruction; when the language data matching in the user terminal fails, the language type attribute and system version can be obtained according to the language selection instruction; language data matching can be performed in the cache of the server terminal through the language type attribute and the system version; when the language data matching in the server terminal fails, a prompt question can be generated through the language attribute and system configuration data, and the prompt question can be input into the AI large model to generate language conversion data; the language conversion data can be subjected to language visualization processing and displayed in the system platform of the user terminal.

[0133] The above specifically shows and describes the exemplary embodiments of this application. It should be understood that this application is not limited to the detailed structures, setting methods or implementation methods described here; on the contrary, this application is intended to cover various modifications and equivalent settings included within the spirit and scope of the appended claims.

Claims

1. A system for realizing system platform language conversion based on AI big model, characterized in that: include: A first matching module, used for matching language data in a cache of a user terminal according to a language selection instruction; An attribute module, used for obtaining language attributes and system version according to the language selection instruction when language data matching at the user end fails; A second matching module, used for matching language data in a cache on the server side according to the language attribute and the system version; A conversion module, used for generating prompt questions through language attributes and system configuration data when the language data on the server fails to match, and inputting the prompt questions into the AI ​​big model to generate language conversion data; The display module is used to perform language visualization processing on the language conversion data and display it on the system platform of the user end.

2. A method for realizing system platform language conversion based on AI big model, characterized in that: include: matching language data in the cache of the user terminal according to the language selection instruction; When the language data of the user terminal fails to match, the language attribute and the system version are obtained according to the language selection instruction; Matching language data in the server-side cache using the language attribute and the system version; When the language data on the server fails to match, prompt questions are generated through language attributes and system configuration data, and the prompt questions are input into the AI ​​big model to generate language conversion data; The language conversion data is processed by language visualization and displayed on the system platform at the user end.

3. The method according to claim 2, characterized in that Before matching the language data in the user's cache according to the language selection instruction, it also includes: Display the system platform on the user side through the default language data; Providing a language switching window and an operation area in the system platform; A language selection instruction is generated based on user operations in the language window and the operation area.

4. The method according to claim 2, characterized in that According to the language selection instruction, language data is matched in the user's cache, including: Acquiring language attributes through the language selection instruction; Language data matching is performed in the cache of the user terminal based on the data reading program and the language attribute.

5. The method according to claim 2, characterized in that When the language data of the user terminal fails to match, obtaining the language attribute and the system version according to the language selection instruction includes: When the language data corresponding to the language attribute does not exist in the cache unit of the user terminal, determining that the language data of the user terminal fails to match; The language attribute and the system version logged in by the current user are obtained according to the language selection instruction.

6. The method according to claim 2, characterized in that The language data is matched in the cache on the server side by the language attribute and the system version, including: Generate a transparent transmission request in JSON format according to the language attribute and the system version; Language data matching is performed in the cache of the server according to the transparent transmission request.

7. The method according to claim 2, characterized in that When the language data on the server fails to match, prompt questions are generated through language attributes and system configuration data, and the prompt questions are input into the AI ​​big model to generate language conversion data, including: When the language data corresponding to the language attribute and the system version does not exist in the language data cache unit of the server, determining that the language data matching of the server fails; Determining system configuration data through the system version; Generate prompt questions through language attributes and system configuration data; The prompt question is input into the AI ​​big model to generate the language conversion data.

8. The method according to claim 7, characterized in that Generate prompt questions based on language attributes and system configuration data, including: Pre-generated prompt templates; The system configuration data is obtained by the front end of the system platform; The prompt question is generated by combining the prompt template and the system configuration data.

9. The method according to claim 7, characterized in that Inputting the prompt question into the AI ​​big model to generate the language conversion data includes: Inputting the prompt question into the AI ​​big model; The AI ​​big model generates return data according to the prompt question; The returned data is format-converted to generate the language-converted data.

10. The method according to claim 2, characterized in that After the language conversion data is processed by language visualization and displayed on the system platform of the user end, it also includes: The language conversion data is stored in a language data cache unit at the server end according to its corresponding language attribute and system version.

11. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 2 to 10.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 2 to 10 is implemented.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 2 to 10 are implemented.

Images