Generative artificial intelligence-based information provision device, information provision system including same, and information provision method

Abstract

A generative artificial intelligence-based information provision system according to an embodiment of the present invention comprises: a user database for storing a collection request item for each user; a source database for storing source information collected on the basis of the collection request item; and an information provision device for retrieving source information including a variable keyword from pieces of source information collected in the source database on the basis of a prepared prompt, inputting the prompt and the retrieved source information to a generative artificial intelligence model to acquire result information corresponding to the prompt, and transmitting the result information corresponding to the collection request item to a user terminal.

Description

A generative artificial intelligence-based information providing device, an information providing system including the same, and an information providing method

[0001] The present invention relates to a generative artificial intelligence-based information providing device, an information providing system including the same, and an information providing 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 are applicable to a wide range of fields, including document writing, artistic creation, voice synthesis, game character creation, and engineering design. However, generative AI models exhibit hallucinations, which can provide incorrect information about unstudied content, making it difficult to guarantee the accuracy and usefulness of generated data.

[0003] To address this, a new architecture called Retrieval-Augmented Generation (RAG) was developed that integrates the Large Language Model (LLM) of a generative AI model with an information retrieval model to improve the performance of text generation.

[0004] Meanwhile, with the recent advancements in related technologies like the Internet of Things (IoT) and Artificial Intelligence (AI), smart factories are becoming a hot topic. A smart factory is a manufacturing system that operates by applying Information and Communications Technology (ICT) combined with digital automation solutions throughout the production process, from design and development to manufacturing.

[0005] One of the key requirements in operating a smart factory is to understand information that is closely related to products or businesses and is highly important and practical.

[0006] For example, when an issue arises, such as the discontinuation of equipment parts in the field, the bankruptcy of an equipment manufacturer, or the release of new equipment, it is important to respond quickly and appropriately by ensuring the level of information is aligned between the equipment managers and support department managers, and preventing the omission of key information.

[0007] To this end, it is necessary to establish an information provision system utilizing the RAG architecture so that relevant parties, including smart factory operations managers and production planners, can provide or receive necessary information at the appropriate time.

[0008] The purpose of the present invention is to provide a generative artificial intelligence-based information providing device that provides information that is closely related to a target product or company and has high importance and practicality, an information providing system including the same, and an information providing method.

[0009] The purpose of the present invention is to provide a generative artificial intelligence-based information providing device that automatically provides information for trend identification, an information providing system including the same, and an information providing method.

[0010] In one embodiment of the present invention, a generative artificial intelligence-based information providing system may include: a user database storing collection request items for each user; a source database storing source information collected based on the collection request items; and an information providing device searching for source information including a variable keyword among source information collected in the source database based on a pre-prompt, inputting the prompt and the searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmitting the result information corresponding to the collection request items to a user terminal.

[0011] The above information providing device can transmit alarm information together when the result information includes a caution keyword.

[0012] The above information providing device can receive the collection request item including at least one of a product type, a product manufacturer, and a product model name, and store the collection request item and user information corresponding to the collection request item to build the user database.

[0013] The above information providing device can collect the source information based on the collection request item through a web server and store the source information to build the source database.

[0014] The above information providing device can construct a vector database by vector embedding the source information.

[0015] The above information providing device can generate the result information based on the similarity between the embedding vector of the prompt and the embedding vector in the vector database using a generative artificial intelligence model.

[0016] In a generative artificial intelligence-based information providing device according to one embodiment of the present invention, a processor may be included that searches for source information including a variable keyword among source information collected according to a user-specific collection request item based on a pre-provisioned prompt, inputs the prompt and the searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmits the result information corresponding to the collection request item to a user terminal.

[0017] A method for providing information based on generative artificial intelligence, performed by an information providing device according to one embodiment of the present invention, may include: a step of searching for source information including a variable keyword among source information collected according to a collection request item for each user based on a pre-provided prompt; a step of inputting the prompt and the searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt; and a step of transmitting the result information corresponding to the collection request item to a user terminal.

[0018] According to one embodiment of the present invention, by continuously receiving information in a desired field, it is possible to prevent the omission of important information and respond quickly when an issue arises.

[0019] According to one embodiment of the present invention, by automating the provision of highly reliable and accurate information, resources required for identifying industry trends can be minimized, and efficient production can be supported.

[0020] According to one embodiment of the present invention, by ensuring that the level of information between the business equipment manager and the support department manager is aligned, issues can be appropriately addressed and unexpected costs can be prevented.

[0021] An information processing system according to one embodiment of the present invention can significantly reduce the amount of data processed compared to when implemented in the form of a chatbot, thereby providing economical, accurate and reliable information and enabling stable service provision.

[0022] According to one embodiment of the present invention, an independent database for a smart factory can be built to provide information that is closely related to a target product or company and has high importance and practicality.

[0023] FIG. 1 is a schematic diagram illustrating an information provision system according to one embodiment of the present invention.

[0024] FIG. 2 is a block diagram illustrating the configuration of an information providing device according to one embodiment of the present invention.

[0025] FIG. 3 is a diagram illustrating an operation flow chart of an information providing device according to one embodiment of the present invention.

[0026] FIG. 4 is a diagram illustrating the operation of an information provision system according to one embodiment of the present invention.

[0027] FIG. 5 is a drawing illustrating a result information generation process of an information providing device according to one embodiment of the present invention.

[0028] FIG. 6 is a drawing illustrating the operation of an information providing device according to one embodiment of the present invention.

[0029] 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.

[0030] FIG. 1 is a schematic diagram illustrating an information provision system according to one embodiment of the present invention.

[0031] An information provision system (1) (hereinafter referred to as system (1)) according to one embodiment of the present invention may include a database (10), an information provision device (100), a user terminal (200), and a web server (300).

[0032] A database (10) is a device that stores information required in the process of providing information by an information providing 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 information providing device (100) or being implemented within the information providing device (100).

[0033] The information providing device (100) provides information necessary for the operation of a smart factory, and may be implemented as a computer, server, smart phone, tablet PC, smart pad, laptop, etc. In this case, the information providing device (100) may not only provide information, but also provide notification information when major changes occur, such as the release or update of a product or technology, the bankruptcy of a manufacturer, or the discontinuation of a product / component.

[0034] The user terminal (200) is a device that receives information provided from the information providing device (100), and can be implemented as a computer, a PLC (Programmable Logic Controller), a server, a smart phone, a tablet PC, a smart pad, a laptop, etc. In this case, the user terminal (200) 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 (200) may be a device that has a manufacturing execution system (MES), an employee assistance program (EAP), a recipe parameter management system (RPMS), etc. built in.

[0035] The web server (300) is a source for collecting information required by the information providing device (100), and the information providing device (100) can collect information from the web server (300) by performing crawling.

[0036] In the present invention, an information provision system (1) utilizing the RAG architecture is proposed so that relevant parties, including smart factory operation managers and production planners, can provide or receive necessary information at an appropriate time.

[0037] Hereinafter, the configuration and operation of an information providing device (100) according to one embodiment of the present invention will be specifically described with reference to the drawings.

[0038] FIG. 2 is a block diagram illustrating the configuration of an information providing device according to one embodiment of the present invention.

[0039] An information providing 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).

[0040] The input unit (110) generates input data in response to a user input of the information providing device (100). For example, the user input may be a user input that initiates the operation of the information providing device (100), a user input that sets a collection request item, a user input that sets a variable keyword or a caution keyword, a user input that inputs a prompt, a user input for collecting source information, a user input required for building a database, etc. In addition, if it is a user input required for transmitting result information corresponding to a collection request item to a user terminal, it can be applied without limitation.

[0041] 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.

[0042] The communication unit (120) can perform communication with external devices such as a user terminal (200) and a web server (300) to transmit and receive collection request items, user information, source information, result information, etc.

[0043] 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.

[0044] The display unit (130) displays display data according to the operation of the information providing device (100). The display unit (130) can display a screen displaying collection request items and user information, a screen displaying source information, a screen displaying result information, a screen receiving user input, etc.

[0045] 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).

[0046] The storage unit (140) stores the operation programs of the information providing 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.

[0047] The storage unit (140) may be implemented by including any one of the databases (10), as described above. The storage unit (140) may store collection request items, user information, source information, result information, generative artificial intelligence models, etc., and may store computational programs required in the process of collecting and searching source information, vector embedding, operating a generative artificial intelligence model, obtaining result information, etc.

[0048] The processor (150) can control at least one other component (e.g., hardware or software component) of the information providing device (100) by executing software such as a program, and can perform various data processing or operations.

[0049] A processor (150) according to one embodiment of the present invention searches for source information including a variable keyword among source information collected according to a user-specific collection request item based on a pre-provided prompt, inputs the prompt and the searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmits the result information corresponding to the collection request item to a user terminal.

[0050] 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.

[0051] 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.

[0052] FIG. 3 is a diagram illustrating an operation flow chart of an information providing device according to one embodiment of the present invention.

[0053] A processor (150) according to one embodiment of the present invention can search for source information including a variable keyword among source information collected according to a user-specific collection request item based on a pre-provided prompt (S10).

[0054] Collection request items represent the user's desired information and alerts. These items may include at least one of the following: product type, product manufacturer, and product model name. Collection request items may also include additional information, such as the collection period and information provision cycle.

[0055] The processor (150) can receive a collection request item from the user terminal (200), and for example, the processor (150) can receive a collection request item requesting information about a circuit breaker and circuit breaker manufacturers, Company A and Company B, once every two weeks.

[0056] At this time, collection request items can be set not only for individual users but also for groups such as teams and departments. If collection request items are set for groups, the same information and alarms can be provided for the same group.

[0057] The processor (150) can receive a collection request item from a user terminal (200) and collect source information based on the collection request item through a web server (300).

[0058] Source information refers to raw data related to the collection request item. For example, source information may be original news articles about Company A, a circuit breaker manufacturer, or papers on circuit breaker technology.

[0059] The processor (150) may collect source information by searching for circuit breakers, companies A and B, for example, in a search portal, or may collect source information within the corporate sites of companies A and B.

[0060] At this time, the processor (150) can collect source information using a separate program that performs crawling and scraping. Specifically, the processor (150) can retrieve an HTML page, parse HTML / CSS, etc., and extract the necessary source information. Alternatively, the processor (150) can extract the necessary source information by calling an Open API (Rest API) to a service that provides an Open API. In addition, any technology that collects source information can be applied without limitation.

[0061] Meanwhile, as described above, the present invention adopts the RAG architecture to improve the performance of text generation of a generative artificial intelligence model, and the RAG architecture is largely composed of a generative artificial intelligence model and a vector database.

[0062] A generative AI model can be a large-scale language model, and a vector database is constructed by vector-embedding information that serves as a reference for the large-scale language model to provide answers to queries. This reference information can be collected source information or information retrieved from the collected source information based on a prompt. This will be described in detail with reference to Figure 5.

[0063] A prompt is a query input into a generative artificial intelligence model, which can be set up to periodically generate information to be provided to user terminals and to properly reflect the purpose of providing information according to the collection request items for each user.

[0064] The processor (150) can search for source information containing a variable keyword among the collected source information based on a provided prompt.

[0065] For example, if the prompt is "Please summarize in three sentences news articles about circuit breaker manufacturer A that contain variable keywords and provide up to five core keywords including the variable keywords," the processor (150) can search for news information about circuit breaker manufacturer A that contains variable keywords (update, new, launch, bankruptcy, discontinuation, etc.) among the collected source information. The processor (150) can receive a user input for setting a variable keyword or receive information about the variable keyword from the user terminal (200).

[0066] A processor (150) according to one embodiment of the present invention can input a prompt and searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt (S20).

[0067] The processor (150) can store the searched source information by vector embedding it in a vector database. The processor (150) can generate result information based on the similarity between the embedding vector of the prompt and the embedding vector in the vector database. The similarity can be determined by a distance measurement method such as Euclidean distance or cosine similarity, and the similarity can also be measured in various other known ways. The processor (150) can generate result information by using the embedding vectors with the highest similarity through a generative artificial intelligence model. At this time, the processor (150) can obtain result information by forming an enhanced prompt that includes both the embedding vector of the prompt and the embedding vector in the vector database, and inputting the enhanced prompt into the generative artificial intelligence model.

[0068] A processor (150) according to one embodiment of the present invention can transmit result information corresponding to a collection request item to a user terminal (S30).

[0069] The resulting information may include information requested through the prompt, a summary of the information, or information indicating key changes.

[0070] The processor (150) may transmit alarm information together with the result information if the result information includes a caution keyword. The caution keyword refers to a keyword that requires special attention, such as bankruptcy or discontinuation of production. Similarly, the processor (150) may receive a user input setting a caution keyword or receive information regarding the caution keyword from the user terminal (200). The alarm information may be transmitted together with the result information or transmitted separately in the form of a pop-up window. In addition to text, it may also be transmitted with voice or a warning sound, and the alarm form is not limited to any one.

[0071] According to one embodiment of the present invention, by continuously receiving information in a desired field, it is possible to prevent the omission of important information and respond quickly when an issue arises.

[0072] According to one embodiment of the present invention, by automating the provision of highly reliable and accurate information, resources required for identifying industry trends can be minimized, and efficient production can be supported.

[0073] According to one embodiment of the present invention, by ensuring that the level of information between the business equipment manager and the support department manager is aligned, issues can be appropriately addressed and unexpected costs can be prevented.

[0074] FIG. 4 is a diagram illustrating the operation of an information provision system according to one embodiment of the present invention.

[0075] FIG. 4 specifically describes the collection request items and source information collection process during the operation of the information provision device (100) described with reference to FIG. 3 above. Any content that overlaps with the content described with reference to FIG. 3 will be omitted for brevity.

[0076] As described above, the database (10) of FIG. 1 may be implemented with two or more databases as needed. The database may include a user database (11), a source database (12), a vector database (13), and a result database (14).

[0077] At this time, each database can be implemented separately, but two or more databases can be combined and implemented as needed. For example, the user database (11), the source database (12), and the result database (14) can be implemented as a single database.

[0078] According to one embodiment of the present invention, the processor (150) may construct a user database (11) by storing collection request items and user information corresponding to the collection request items. The user information may include account information and affiliation information of the user who will receive information and alarms. The user account information may include an email account, team channel address, etc. As described above, when collection request items are set as a group unit, the processor (150) may transmit the same result information to multiple user accounts with the same affiliation information.

[0079] When the processor (150) receives an updated collection request item from the user terminal (200), it can modify the collection request item in the user database (11) and record the change history. At this time, a separate log database for recording the change history may be provided.

[0080] The processor (150) can collect source information based on collection request items through a web server (300) and store the source information to build a source database (12).

[0081] The source database (12) can store source information, search conditions, and the source of the source information together. The search conditions may be identical to the collection request items, or may be separately processed conditions to reflect the collection request items. The source of the source information may be the Uniform Resource Locator (URL) of the source information, and the processor (150) can record the source of the source information in various ways other than the URL.

[0082] The processor (150) can build a vector database (13) by vector-embedding source information, and can build a result database (14) by storing result information generated for each prompt.

[0083] An information processing system (1) according to one embodiment of the present invention can significantly reduce the amount of data processed compared to when implemented in the form of a chatbot, thereby providing economical, accurate and reliable information and enabling stable service provision.

[0084] According to one embodiment of the present invention, an independent database for a smart factory can be built to provide information that is closely related to a target product or company and has high importance and practicality.

[0085] FIG. 5 is a drawing illustrating a result information generation process of an information providing device according to one embodiment of the present invention.

[0086] The information providing device (100) can perform source information re-search-importance evaluation-final selection based on a generative artificial intelligence model (510) to select the source information most suitable for the collection request item among the collected source information.

[0087] First, the information providing device (100) can search for information including variable keywords in parallel based on prompts (520) prepared in various ways among the source information collected in the source database (12) by utilizing a generative artificial intelligence model (510).

[0088] The information providing device (100) evaluates the importance based on the similarity between the embedding vector that vectorizes the prompt (520) and the embedding vector of the vector database (13).

[0089] The information providing device (100) can finally select the information with the highest importance, and store the selected result information in the result database (14).

[0090] According to one embodiment of the present invention, the user's intention can be clearly identified through a chain structure with a large language model (LLM), thereby improving the reliability and validity of information.

[0091] FIG. 6 is a drawing illustrating the operation of an information providing device according to one embodiment of the present invention.

[0092] The information providing device (100) can match the collection request items stored in the user database (11), user information, and result information stored in the result database (14) and transmit the result information to the user terminal (200).

[0093] At this time, the information providing device (100) can transmit notification information together with the result information if the transmitted result information includes a caution keyword.

Claims

1. In the information provision system based on generative artificial intelligence, A user database that stores collection request items per user; A source database storing source information collected based on the above collection request items; and Search for source information containing variable keywords among the source information collected in the source database based on the provided prompt, By inputting the above prompt and the searched source information into the generative artificial intelligence model, the result information corresponding to the above prompt is obtained, An information providing system including an information providing device that transmits result information corresponding to the above collection request items to a user terminal.

2. In paragraph 1, The above information providing device, An information provision system that transmits alarm information together when the above result information includes a caution keyword.

3. In paragraph 1, The above information providing device, Receive the collection request item including at least one of the product type, product manufacturer and product model name, An information providing system that constructs a user database by storing the above collection request items and user information corresponding to the above collection request items.

4. In paragraph 1, The above information providing device, Collect the source information based on the collection request items through the web server, An information providing system that constructs a source database by storing the above source information.

5. In paragraph 1, The above information providing device, An information providing system that constructs a vector database by vector embedding the above source information.

6. In paragraph 5, The above information providing device, An information providing system that generates the result information based on the similarity between the embedding vector of the prompt and the embedding vector in the vector database using a generative artificial intelligence model.

7. In a generative artificial intelligence-based information providing device, Search for source information containing variable keywords among the collected source information according to the user-specific collection request items based on the provided prompts. By inputting the above prompt and the searched source information into the generative artificial intelligence model, the result information corresponding to the above prompt is obtained, An information providing device including a processor that transmits result information corresponding to the above collection request items to a user terminal.

8. In paragraph 7, The above processor, An information providing device that transmits alarm information together when the above result information includes a caution keyword.

9. In paragraph 7, The above processor, Receive the collection request item including at least one of the product type, product manufacturer and product model name, An information providing device that constructs a user database by storing the above collection request items and user information corresponding to the above collection request items.

10. In paragraph 7, The above processor, Collect the source information based on the collection request items through the web server, An information providing device that constructs a source database by storing the above source information.

11. In paragraph 7, The above processor, An information providing device that constructs a vector database by vector embedding the above source information.

12. In paragraph 11, The above processor, An information providing device that generates the result information based on the similarity between the embedding vector of the prompt and the embedding vector in the vector database using a generative artificial intelligence model.

13. In a method for providing information based on artificial intelligence, which is performed by an information providing device, A step of searching for source information containing variable keywords among the collected source information according to user-specific collection request items based on a provided prompt; A step of inputting the above prompt and the searched source information into a generative artificial intelligence model to obtain result information corresponding to the prompt; An information providing method comprising a step of transmitting result information corresponding to the above collection request item to a user terminal.

Images