Generative artificial intelligence-based multilingual manual synchronization device, synchronization system including same and synchronization method thereof

Abstract

A generative artificial intelligence-based multilingual manual synchronization system according to an embodiment of the present invention may comprise: a term database for storing a reference term and a translation term of the reference term; a manual database for storing a reference manual written in a reference language and at least one translation manual written in a language different from the reference language; and a manual synchronization device for receiving a prompt including translation request information and change information of the reference manual, inputting the prompt to a generative artificial intelligence model to translate the change information into another language, and updating the translation manual on the basis of the translation content of the change information.

Description

A generative artificial intelligence-based multilingual manual synchronization device, a synchronization system including the same, and a synchronization method thereof

[0001] The present invention relates to a generative artificial intelligence-based multilingual manual synchronization device, a synchronization system including the same, and a synchronization method.

[0002] Generative artificial intelligence (GAI) is a type of AI technology that generates or creates new data based on given input data. Because generative AI models generate new data based on their understanding of training data, they can be used in a variety of fields, including document writing, art creation, voice synthesis, game character creation, and engineering design.

[0003] In particular, chatbots, a key application of generative AI models, are systems that provide users with necessary information through conversation. They are being utilized in a variety of fields for purposes such as user support, information provision, and task automation. Generative AI models can also be used to understand input text or sentences and translate and output the content in other languages.

[0004] In this way, the translation technology of generative AI models can be used to translate documents that require multilingualization. However, this can lead to problems such as a decrease in the consistency of the translation results due to the need to consider contextual and cultural differences, and especially in the case of technical documents, specific technical knowledge.

[0005] To this end, it is necessary to establish a synchronization system that can automate document updates and manage history through multilingual translation and review requests when changes occur in documents.

[0006] The purpose of the present invention is to provide a generative artificial intelligence-based multilingual manual synchronization device that automatically synchronizes country-specific manual information, a synchronization system including the same, and a synchronization method.

[0007] The purpose of the present invention is to provide a generative artificial intelligence-based multilingual manual synchronization device that provides information that is closely related to a target facility or product and has high importance and practicality, and a synchronization system and synchronization method including the same.

[0008] A generative artificial intelligence-based multilingual manual synchronization system according to one embodiment of the present invention may include: a term database storing reference terms and translation terms of the reference terms; a manual database storing a reference manual written in a reference language and at least one translation manual written in a language different from the reference language; and a manual synchronization device receiving a prompt including change information and translation request information of the reference manual, inputting the prompt into a generative artificial intelligence model to translate the change information into another language, and updating the translation manual based on the translated content of the change information.

[0009] The manual synchronization device can translate the change information into another language based on the translation terms stored in the term database.

[0010] The manual synchronization device can update the translation manual based on receiving a confirmation signal confirming the translation content of the change information from the administrator terminal.

[0011] The manual synchronization device can receive a modification request signal for modifying the translation content of the change information from the administrator terminal, and update the translation manual based on the modified translation content.

[0012] The above manual synchronization device can restrict access to the translation manual of the user terminal while updating the translation manual.

[0013] The above manual synchronization device can provide information indicating the translation manual and the part being updated to the user terminal while updating the translation manual.

[0014] The above manual synchronization device can generate a translation manual by translating the reference manual including the change information into another language.

[0015] In one embodiment of the present invention, a generative artificial intelligence-based multilingual manual synchronization device may include a processor that receives a prompt including change information and translation request information of a reference manual written in a reference language, inputs the prompt into a generative artificial intelligence model to translate the change information into another language, and updates a translation manual written in another language based on the translated content of the change information.

[0016] A method for synchronizing a multilingual manual based on generative artificial intelligence, performed by a multilingual manual synchronization device according to one embodiment of the present invention, may include: receiving a prompt including change information and translation request information of a reference manual written in a reference language; inputting the prompt into a generative artificial intelligence model to translate the change information into another language; and updating a translation manual written in another language based on the translated content of the change information.

[0017] According to one embodiment of the present invention, the consistency of the translation result can be improved by multilingual translation that takes into account national contexts or cultural differences for technical documents that require consideration of specific technical knowledge.

[0018] According to one embodiment of the present invention, the application of changes to the manual can be automated to prevent differences in manuals for each country and increase the work efficiency of managers.

[0019] According to one embodiment of the present invention, an independent database for manuals within a smart factory can be built to provide information that is closely related to the management of target equipment or products and is highly important and practical.

[0020] FIG. 1 is a schematic diagram illustrating a manual synchronization system according to one embodiment of the present invention.

[0021] FIG. 2 is a block diagram illustrating the configuration of a manual synchronization device according to one embodiment of the present invention.

[0022] FIG. 3 is a diagram illustrating an operation flow chart of a manual synchronization device according to one embodiment of the present invention.

[0023] FIG. 4 is a drawing illustrating the operation of a manual synchronization system according to one embodiment of the present invention.

[0024] FIG. 5 is a drawing illustrating a result information generation process of a manual synchronization device according to one embodiment of the present invention.

[0025] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The detailed description set forth below, together with the accompanying drawings, is intended to explain exemplary embodiments of the present invention and is not intended to represent the only embodiments in which the present invention may be practiced. In the drawings, portions irrelevant to the description may be omitted for clarity in describing the present invention, and the same reference numerals may be used throughout the specification for identical or similar components.

[0026] FIG. 1 is a schematic diagram illustrating a manual synchronization system according to one embodiment of the present invention.

[0027] A manual synchronization system (1) (hereinafter referred to as system (1)) according to one embodiment of the present invention may include a database (10), a multilingual manual synchronization device (100) (hereinafter also referred to as manual synchronization device (100) or synchronization device (100)), an administrator terminal (200), and a user terminal (300).

[0028] The database (10) is a device that stores information required in the process of providing information by the manual synchronization device (100). The database (10) may be implemented by dividing into two or more databases as needed, and the implementation method is not limited to either being implemented as a separate device from the manual synchronization device (100) or being implemented within the manual synchronization device (100).

[0029] The manual synchronization device (100) is a device that updates and synchronizes translation manuals when the contents of the standard manual are changed, and can be implemented as a computer, server, smart phone, tablet PC, smart pad, laptop, etc.

[0030] The administrator terminal (200) is a device that inputs a prompt containing information on changes to the standard manual and translation request information through a chatbot program and confirms the updated translation manual through a manual synchronization device (100). The administrator terminal (200) can be implemented as a computer, a PLC (Programmable Logic Controller), a server, a smartphone, a tablet PC, a smart pad, a laptop, etc.

[0031] The user terminal (300) is a device that receives a standard manual or a translated manual translated into the language of each country on a website or intranet, and can be implemented as a computer, PLC (Programmable Logic Controller), server, smart phone, tablet PC, smart pad, laptop, etc.

[0032] At this time, the user terminal (300) may be a terminal of a person in charge of a smart factory, a smart factory server, or equipment within a smart factory. The user terminal (300) may be a device that has a built-in manufacturing execution system (MES), an employee assistance program (EAP), a recipe parameter management system (RPMS), etc.

[0033] In addition, although not shown, the system (1) may further include a web server for collecting information required by the manual synchronization device (100). The manual synchronization device (100) may perform crawling to collect information from the web server.

[0034] In the present invention, a manual synchronization system (1) utilizing a generative artificial intelligence model is proposed to provide a manual translated by country more quickly and accurately when the manual is changed.

[0035] Hereinafter, the configuration and operation of a manual synchronization device (100) according to one embodiment of the present invention will be specifically described with reference to the drawings.

[0036] FIG. 2 is a block diagram illustrating the configuration of a manual synchronization device according to one embodiment of the present invention.

[0037] A manual synchronization device (100) according to one embodiment of the present invention may include an input unit (110), a communication unit (120), a display unit (130), a storage unit (140), and a processor (150).

[0038] The input unit (110) generates input data in response to user input of the manual synchronization device (100). For example, the user input may be a user input that initiates the operation of the manual synchronization device (100), a user input that stores a reference term and a translation term of the reference term, a user input required to build a database, etc. In addition, if it is a user input required to update change information of the reference manual to the translation manual, it can be applied without limitation.

[0039] The input unit (110) includes at least one input means. The input unit (110) may include a keyboard, a key pad, a dome switch, a touch panel, a touch key, a mouse, a menu button, etc.

[0040] The communication unit (120) can perform communication with external devices such as an administrator terminal (200), a user terminal (300), and a web server to transmit and receive standard terms, translation terms, standard manuals, translation manuals, change information, translation request information, confirmation signals, modification request signals, etc.

[0041] To this end, the communication unit (120) can perform wireless communication such as 5G (5th generation communication), LTE-A (Long Term Evolution-Advanced), LTE (Long Term Evolution), Wi-Fi (Wireless Fidelity), Bluetooth, or wired communication such as LAN (Local Area Network), WAN (Wide Area Network), and power line communication.

[0042] The display unit (130) displays display data according to the operation of the manual synchronization device (100). The display unit (130) can display a screen displaying reference terms and translation terms, a screen displaying change information and translation request information, a screen displaying the translated contents of the change information, a screen displaying an updated translation manual, a screen receiving user input, etc.

[0043] The display unit (130) includes a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, and an electronic paper display. The display unit (130) may be implemented as a touch screen by being combined with the input unit (110).

[0044] The storage unit (140) stores the operation programs of the manual synchronization device (100). The storage unit (140) includes a non-volatile storage that can preserve data (information) regardless of whether power is supplied, and a volatile memory that loads data to be processed by the processor (150) and cannot preserve data if power is not supplied. The storage includes a flash memory, a hard-disc drive (HDD), a solid-state drive (SSD), a read-only memory (ROM), etc., and the memory includes a buffer, a random access memory (RAM), etc.

[0045] The storage unit (140) may be implemented by including any one of the databases (10), as described above. The storage unit (140) may store reference terms, translation terms, reference manuals, translation manuals, change information, translation request information, modification request content, generative artificial intelligence models, etc., and may store computational programs required in the process of performing translation, translation manual creation and update, vector embedding, generative artificial intelligence model operation, and result information acquisition.

[0046] The processor (150) can control at least one other component (e.g., hardware or software component) of the manual synchronization device (100) by executing software such as a program, and can perform various data processing or operations.

[0047] A processor (150) according to one embodiment of the present invention may receive a prompt including change information and translation request information of the reference manual, input the prompt into a generative artificial intelligence model to translate the change information into another language, and update the translation manual based on the translated content of the change information.

[0048] At this time, the processor (150) may build a database and / or a generative artificial intelligence model, or may receive and store a previously built database and / or a generative artificial intelligence model from the outside and use it, but is not limited to either one.

[0049] Meanwhile, the processor (150) may perform at least a portion of the data analysis, processing, and result information generation for performing the above operations using at least one of a machine learning, neural network, or deep learning algorithm as a rule-based or artificial intelligence (AI) algorithm. Examples of the neural network may include models such as a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), and a transformer.

[0050] FIG. 3 is a diagram illustrating an operation flow chart of a synchronization device according to one embodiment of the present invention.

[0051] A processor (150) according to one embodiment of the present invention can receive a prompt including change information and translation request information of a reference manual (S10).

[0052] Manuals can be instructions for equipment within a smart factory or products manufactured through a smart factory, and can include catalogs. A reference manual is a manual written in a reference language, which can be the language of the country that manages the equipment or product.

[0053] For example, the base language can be Korean, and can be set to two or more languages, such as Korean and English, as needed.

[0054] Change information in the standard manual refers to information regarding changes to the manual, such as typos, changes to equipment operation, changes to the type designation system, or the acquisition of new certifications. Change information can consist of various components, and its format and content are not limited to any one specific category.

[0055] As another example, the processor (150) may receive a reference manual including change information and identify changed portions by comparing them with a previously stored reference manual.

[0056] Translation request information requests translation into a specific language or into all languages ​​of the countries where the manual is available. Additionally, translation request information may include information that may consider contextual or cultural differences, particularly in technical documents, and specific technical knowledge. For example, it may request a translation that closely resembles the tone and sentence structure of a sample manual. Alternatively, it may include information regarding notational differences between the target languages.

[0057] The administrator terminal (200) can input prompts containing information about changes to the standard manual and translation requests via a chatbot program. Prompts are queries input to a generative artificial intelligence model. Prompts can be input in voice as well as text, and the prompt format is not limited to any one format.

[0058] A processor (150) according to one embodiment of the present invention can input a prompt to a generative artificial intelligence model to translate change information into another language (S20).

[0059] At this time, the other language may be the language specified in the translation request information, or it may be the language of any country that provides the manual.

[0060] Meanwhile, since the manual may contain terms for specific technologies, a terminology database can be built by storing translated terms for reference terms to ensure proper translation of the terms.

[0061] The processor (150) can translate the change information into another language based on the translation terms stored in the terminology database.

[0062] If the term database does not contain a translation term corresponding to the reference term, the processor (150) may use a translation program to translate the reference term into another language. Alternatively, the processor (150) may search for a translation term corresponding to the reference term via a web server. For example, the processor may collect translation terms by searching for the equipment name or equipment manufacturer on a search portal, or may collect translation terms from the equipment manufacturer's corporate website.

[0063] At this time, the processor (150) can collect translation terms using a separate program that performs crawling and scraping. Specifically, the processor (150) can retrieve an HTML page, parse the HTML / CSS, etc., and extract the necessary translation terms. Alternatively, the processor (150) can call an Open API (Rest API) to a service that provides an Open API to extract the necessary translation terms. In addition, any technology that collects translation terms can be applied without limitation. In addition, translation terms can be collected in various ways, and the method of collecting translation terms is not limited to any one.

[0064] A processor (150) according to one embodiment of the present invention can update a translation manual based on the translation content of the change information (S30).

[0065] In the present invention, when a change occurs in the standard manual, the consistency of the translation content can be verified through review by an administrator.

[0066] Specifically, the processor (150) can update the translation manual based on receiving a confirmation signal confirming the translation of the change information from the administrator terminal (200). If there is an error in the translation or additional modifications are required, the processor (150) can receive a modification request signal for modifying the translation of the change information from the administrator terminal and update the translation manual based on the modified translation.

[0067] Alternatively, the processor (150) may verify the consistency of the translation using a separate artificial intelligence model, etc., designed to verify the consistency of the translation. In addition, the consistency of the translation can be verified using various methods, and the method of verifying the consistency is not limited to any one.

[0068] According to one embodiment of the present invention, the application of changes can be automated to prevent differences in country-specific documents and increase the work efficiency of administrators.

[0069] According to one embodiment of the present invention, the consistency of the translation result can be improved by multilingual translation that takes into account national contexts or cultural differences for technical documents that require consideration of specific technical knowledge.

[0070] FIG. 4 is a drawing illustrating the operation of a manual synchronization system according to one embodiment of the present invention.

[0071] Fig. 4 specifically describes the operation process of the manual synchronization device (100) described above with reference to Fig. 3. Any content that overlaps with the content described with reference to Fig. 3 will be omitted.

[0072] As described above, the database (10) of Fig. 1 may be implemented with two or more databases as needed. The database may include a terminology database (11) and a manual database (12).

[0073] At this time, each database can be implemented separately, but if necessary, the terminology database (11) and the manual database (12) can be implemented as one database.

[0074] The manual synchronization device (100) can build a terminology database (11) that stores reference terms and translation terms of the reference terms, and can build a manual database (12) by storing reference manuals written in a reference language and at least one translation manual written in a language different from the reference language. In addition, the manual synchronization device (100) can store the change history of the manual in the manual database (12).

[0075] The manual synchronization device (100) can generate a translation manual by translating a reference manual containing change information into another language. For example, if the manual database (12) does not contain a translation manual written in the language to be translated, or if the changes are so numerous that it is deemed efficient to generate a new translation manual, the manual synchronization device (100) can generate a translation manual by translating the reference manual itself into another language.

[0076] According to one embodiment of the present invention, an independent database for manuals within a smart factory can be built to provide information that is closely related to the management of target equipment or products and is highly important and practical.

[0077] FIG. 5 is a drawing illustrating a result information generation process of a synchronization device according to one embodiment of the present invention.

[0078] The manual synchronization device (100) can perform translation of changed contents and verification of consistency based on a generative artificial intelligence model (510) to synchronize the contents of the remaining translation manuals when the contents of the standard manual are changed.

[0079] When the manual synchronization device (100) receives a prompt (520) including change information and translation request information of a reference manual, it can translate the change information into another language based on the change information and translation request information and generate a translation manual.

[0080] As described above, the manual synchronization device (100) can receive a reference manual containing change information and identify changed portions by comparing it with a previously stored reference manual. At this time, the manual synchronization device (100) can compare the reference manual stored in the manual database (12) with the reference manual containing the change information received via the prompt (520).

[0081] Meanwhile, the manual synchronization device (100) can restrict access to the translation manual of the user terminal (300) while updating the translation manual.

[0082] Access restrictions can be implemented in a variety of ways. For example, for a manual being updated, a notification may be displayed indicating that the manual is currently being updated, or a warning may be displayed indicating that the manual is unavailable to prevent conflicts between the manual synchronization device (100) and the user terminal (300). Alternatively, the icon for selecting the manual being updated may be disabled.

[0083] The manual synchronization device (100) updates the translation manual based on receiving a confirmation signal confirming the translation content of the change information from the administrator terminal (200), and the confirmed translation manual can be displayed as available for use again.

[0084] Alternatively, the manual synchronization device (100) may provide the current translation manual to the user terminal (300) while updating the translation manual, while simultaneously displaying the portion being updated. This allows the user to access the translation manual without interruption if they need information other than change information, and even if the portion they are checking is related to change information, they can confirm in real time that the manual is being updated, thereby enhancing user convenience.

Claims

1. In a multilingual manual synchronization system based on generative artificial intelligence, A term database storing base terms and translation terms of said base terms; A manual database storing a reference manual written in a reference language and at least one translation manual written in a language other than the reference language; and Receive a prompt containing information on changes to the above reference manual and information on translation requests; By inputting the above prompt into the generative AI model, the above change information is translated into another language, A manual synchronization system including a manual synchronization device for updating the translation manual based on the translation contents of the above change information.

2. In paragraph 1, The above manual synchronization device is, A manual synchronization system that translates the change information into another language based on the translation terms stored in the above terminology database.

3. In paragraph 1, The above manual synchronization device is, A manual synchronization system that updates the translation manual based on receiving a confirmation signal confirming the translation contents of the change information from the administrator terminal.

4. In paragraph 3, The above manual synchronization device is, A manual synchronization system that receives a modification request signal for modifying the translation content of the change information from the above administrator terminal and updates the translation manual based on the modified translation content.

5. In paragraph 1, The above manual synchronization device is, A manual synchronization system that restricts access to the above translation manual from user terminals while updating the above translation manual.

6. In paragraph 1, The above manual synchronization device is, A manual synchronization system that provides information indicating the translation manual and the part being updated to the user terminal while updating the above translation manual.

7. In paragraph 1, The above manual synchronization device is, A manual synchronization system that generates a translation manual by translating a reference manual containing the above change information into another language.

8. In a multilingual manual synchronization device based on generative artificial intelligence, Receive a prompt containing information on changes to the reference manual written in the reference language and information on translation requests; By inputting the above prompt into the generative AI model, the above change information is translated into another language, A manual synchronization device including a processor for updating a translation manual written in another language based on the translation contents of the above change information.

9. In paragraph 8, The above processor, A manual synchronization device that translates the change information into another language based on a base term stored in a term database and a translation term of the base term.

10. In paragraph 8, The above processor, A manual synchronization device that updates the translation manual based on receiving a confirmation signal confirming the translation contents of the change information from the administrator terminal.

11. In paragraph 10, The above processor, A manual synchronization device that receives a modification request signal for modifying the translation content of the change information from the above administrator terminal and updates the translation manual based on the modified translation content.

12. In paragraph 8, The above processor, A manual synchronization device that restricts access to the above translation manual from user terminals while updating the above translation manual.

13. In paragraph 8, The above processor, A manual synchronization device that provides information indicating the translation manual and the part being updated to the user terminal while updating the above translation manual.

14. In paragraph 8, The above processor, A manual synchronization device that generates a translation manual by translating a reference manual containing the above change information into another language.

15. In a generative artificial intelligence-based multilingual manual synchronization method performed by a multilingual manual synchronization device, A step of receiving a prompt containing change information and translation request information of a reference manual written in a reference language; A step of inputting the above prompt into a generative artificial intelligence model to translate the above change information into another language; A method for synchronizing a manual, comprising: a step of updating a translation manual written in another language based on the translated contents of the above change information;

Images