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 one embodiment of the present invention, may comprise: a manual database that stores response plan information according to a state of equipment; an information provision device that receives a prompt including equipment information and equipment symptom information, collects equipment state information on the basis of the prompt so as to diagnose a state of the equipment, transmits notification information requesting re-inspection of the equipment to a user terminal if the state of the equipment is normal, searches for response plan information corresponding to equipment diagnosis information among the response plan information stored in the manual database if the state of the equipment is abnormal, inputs the prompt and the retrieved response plan information into a generative artificial intelligence model so as to obtain result information corresponding to the prompt, and transmits the result information to the 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 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 various fields for purposes such as user support, information provision, and task automation. However, simple Natural Language Processing (NLP) technology alone has difficulties accurately understanding and interpreting all user input. Furthermore, the so-called hallucination phenomenon, which provides incorrect information about unstudied content, has raised concerns about the accuracy and usefulness of generated content.

[0004] 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.

[0005] 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.

[0006] Smart factory technology eliminates the need for worker deployment, reducing labor costs. However, it also requires a fast and accurate response to abnormal situations such as equipment failures. In particular, in smart factory environments, failure consultations can vary depending on the situation and the consultant, even for the same equipment. Depending on the type of failure, safety issues can arise, making it essential to provide reliable 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 technical support staff, can quickly and accurately find the information they need.

[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 provides more reliable fault diagnosis and response measures, 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 manual database storing response measure information according to the status of equipment; an information providing device that receives a prompt including equipment information and equipment symptom information, collects equipment status information based on the prompt to diagnose the status of the equipment, transmits notification information requesting a re-inspection of the equipment to a user terminal when the status of the equipment is normal, and searches for response measure information corresponding to equipment diagnosis information among the response measure information stored in the manual database when the status of the equipment is not normal, inputs the prompt and the searched response measure information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmits the result information to the user terminal.

[0011] The above information providing device can receive feedback information on the result information and update the manual database.

[0012] The above information providing device can collect the equipment status information from at least one sensor connected to the equipment.

[0013] The above information providing device can predict the lifespan of the equipment based on the equipment diagnostic information and transmit information about the predicted lifespan of the equipment to the user terminal.

[0014] The above information providing device can build the manual database by storing response measure information including at least one of the first response measure information included in the equipment manufacturer's manual and the second response measure information built with user know-how.

[0015] The above information providing device can construct a vector database by vector-embedding the above response measure information.

[0016] 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.

[0017] In one embodiment of the present invention, a generative artificial intelligence-based information providing device may include a processor that receives a prompt including facility information and facility symptom information, collects facility status information based on the prompt to diagnose the facility status, transmits notification information requesting a re-inspection of the facility to a user terminal when the facility status is normal, and searches for response measure information corresponding to facility diagnosis information among response measure information according to the facility status stored in a manual database when the facility status is not normal, inputs the prompt and the searched response measure information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmits the result information to the user terminal.

[0018] A generative artificial intelligence-based information providing method performed by an information providing device according to one embodiment of the present invention may include the steps of: receiving a prompt including facility information and facility symptom information; collecting facility status information based on the prompt to diagnose the facility status; transmitting notification information requesting a re-inspection of the facility to a user terminal when the facility status is normal; searching for response measure information corresponding to facility diagnosis information among response measure information according to the facility status stored in a manual database when the facility status is not normal; inputting the prompt and the searched response measure information into a generative artificial intelligence model to obtain result information corresponding to the prompt; and transmitting the result information to the user terminal.

[0019] According to one embodiment of the present invention, by clearly identifying the equipment status through information related to on-site equipment in response to equipment failure reports, the reliability of equipment status diagnosis can be improved and unnecessary situations such as equipment shutdowns can be prevented.

[0020] It is expected that the information provision system according to one embodiment of the present invention will reduce the cost of operating consultants, and based on the equipment status information, the equipment status can be more clearly identified and the optimal response plan can be suggested.

[0021] According to one embodiment of the present invention, an independent database of response measure information within a smart factory can be constructed to provide information that is closely related to inspection of target equipment and has high importance and practicality.

[0022] 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.

[0023] According to one embodiment of the present invention, more efficient and accurate response measure information can be provided by reflecting response measure information utilized in an actual failure situation.

[0024] FIG. 1 is a schematic diagram illustrating an information provision system according to one embodiment of the present invention.

[0025] FIG. 2 is a block diagram illustrating the configuration of an information providing device according to one embodiment of the present invention.

[0026] FIG. 3 is a diagram illustrating an operation flow chart of an information providing device according to a first embodiment of the present invention.

[0027] FIG. 4 is a diagram illustrating an operation flow chart of an information providing device according to a second embodiment of the present invention.

[0028] FIG. 5 is a diagram illustrating the operation of an information provision system according to one embodiment of the present invention.

[0029] FIG. 6 is a drawing illustrating a result information generation process of an information providing device according to one embodiment of the present invention.

[0030] FIG. 7 is a drawing illustrating the operation of an information providing device according to one embodiment of the present invention.

[0031] 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.

[0032] FIG. 1 is a schematic diagram illustrating an information provision system according to one embodiment of the present invention.

[0033] 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), and a user terminal (200).

[0034] 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).

[0035] The information providing device (100) is a device that provides information required during the operation of a smart factory, and can be implemented as a computer, server, smart phone, tablet PC, smart pad, laptop, etc.

[0036] The user terminal (200) is a device that inputs a prompt including facility information and facility symptom information through a chatbot program and receives result information 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.

[0037] In addition, although not shown, the system (1) may further include a web server for collecting information required by the information providing device (100). The information providing device (100) may perform crawling to collect information from the web server.

[0038] 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 technical support managers, can more quickly and accurately provide necessary information.

[0039] 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.

[0040] FIG. 2 is a block diagram illustrating the configuration of an information providing device according to one embodiment of the present invention.

[0041] 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).

[0042] The input unit (110) generates input data in response to 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 stores information on response measures according to the status of the equipment, a user input required to build a database, etc. In addition, if it is a user input required to transmit result information corresponding to equipment symptom information to the user terminal (200), it may be applied without limitation.

[0043] 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.

[0044] The communication unit (120) can perform communication with external devices such as a user terminal (200) and a web server to transmit and receive equipment information, equipment symptom information, equipment status information, equipment diagnosis information, response plan information, result information, etc.

[0045] 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.

[0046] 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 that displays facility information and facility symptom information, a screen that displays facility status information, a screen that displays facility diagnosis information, a screen that displays searched response plan information, a screen that displays result information, a screen that receives user input, etc.

[0047] 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).

[0048] 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.

[0049] The storage unit (140) may be implemented by including any one of the databases (10) as described above. The storage unit (140) may store facility information, facility symptom information, facility status information, facility diagnosis information, response plan information, result information, generative artificial intelligence models, etc., and may store computational programs required in the process of performing facility status diagnosis, generating notification information, searching for response plan information, vector embedding, operating generative artificial intelligence models, obtaining result information, etc.

[0050] 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.

[0051] A processor (150) according to one embodiment of the present invention receives a prompt including facility information and facility symptom information, collects facility status information based on the prompt to diagnose the facility status, and if the facility status is normal, transmits notification information requesting a re-inspection of the facility to a user terminal, and if the facility status is not normal, searches for response measure information corresponding to facility diagnosis information among response measure information stored in the manual database, inputs the prompt and the searched response measure information into a generative artificial intelligence model to obtain result information corresponding to the prompt, and transmits the result information to the user terminal.

[0052] 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.

[0053] 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.

[0054] FIG. 3 is a diagram illustrating an operation flow chart of an information providing device according to a first embodiment of the present invention.

[0055] A processor (150) according to one embodiment of the present invention can receive a prompt including equipment information and equipment symptom information (S10).

[0056] Equipment information refers to information about equipment operating within a smart factory, and may include information such as equipment type, model name, and manufacturer. Equipment symptom information describes symptoms that occurred during the operation of the equipment. Users can input identified equipment symptoms as prompts into the chatbot program. Prompts are queries entered into a generative AI model. Prompts can be entered in text or voice, and there is no single format for the prompts.

[0057] A processor (150) according to one embodiment of the present invention can collect equipment status information based on a prompt and diagnose the status of the equipment (S20).

[0058] The processor (150) can collect equipment status information from at least one sensor connected to the equipment. The at least one sensor may be an IoT sensor and can measure the equipment's operating current, operating voltage, etc.

[0059] Equipment status information encompasses all sensor values ​​and information acquired during equipment operation. These sensor values ​​can be comprehensively considered, encompassing not only real-time measurements but also previously measured values.

[0060] The processor (150) can receive equipment status information from at least one sensor connected to the equipment, as well as a Manufacturing Execution System (MES), an Employee Assistance Program (EAP), a Recipe Parameter Management System (RPMS), etc.

[0061] The processor (150) can diagnose the condition of the equipment using a generative artificial intelligence model or another artificial intelligence model built to diagnose the condition of the equipment. In addition, the condition of the equipment can be diagnosed using various methods, and the equipment diagnosis method is not limited to any one method. Hereinafter, information obtained by diagnosing the equipment based on the equipment condition information is referred to as equipment diagnosis information.

[0062] The processor (150) can predict the lifespan of the equipment based on equipment diagnostic information and transmit information regarding the predicted lifespan of the equipment to the user terminal (200). The equipment diagnostic information can be utilized not only to respond to current failure situations, but also to identify future equipment operation conditions, thereby increasing the usability of the information.

[0063] According to one embodiment of the present invention, the processor (150) can transmit notification information requesting a re-inspection of the equipment to the user terminal (200) when the equipment is in a normal state (S30).

[0064] Based on the prompt received from the user terminal (200), the diagnosis of the equipment status may reveal that there is no abnormality in the equipment. In this case, the processor (150) may transmit notification information requesting a re-inspection of the equipment.

[0065] According to one embodiment of the present invention, by clearly identifying the equipment status through information related to on-site equipment in response to equipment failure reports, the reliability of equipment status diagnosis can be improved and unnecessary situations such as equipment shutdowns can be prevented.

[0066] FIG. 4 is a diagram illustrating an operation flow chart of an information providing device according to a second embodiment of the present invention.

[0067] While FIG. 3 previously showed a case in which the diagnosis of the equipment's status revealed no abnormalities, FIG. 4 describes an operation flowchart of the information provision device (100) in the case of an abnormality in the equipment. Any content that overlaps with the content described with reference to FIG. 3 will be omitted for brevity.

[0068] According to one embodiment of the present invention, if the condition of the equipment is not normal, the processor (150) can search for response measure information corresponding to the equipment diagnosis information among the response measure information stored in the manual database (S410).

[0069] As previously described with respect to S20 of FIG. 3, the processor (150) can identify whether the equipment status is normal based on equipment diagnostic information.

[0070] The processor (150) can build a manual database that stores information on response measures according to the status of the equipment.

[0071] The processor (150) can extract and collect response plan information from a prepared equipment catalog or internal documents, and can collect response plan information based on equipment information through a web server. For example, response plan information can be collected by searching for the equipment name or equipment manufacturer in a search portal, or response plan information can be collected within the equipment manufacturer's corporate site.

[0072] At this time, the processor (150) can collect response measure information 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 response measure information. Alternatively, the processor (150) can call an Open API (Rest API) to a service that provides an Open API to extract the necessary response measure information. In addition, any technology that collects response measure information can be applied without limitation.

[0073] In addition to these, there are various ways to collect response plan information, and the format or method of collecting response plan information is not limited to any one.

[0074] 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.

[0075] 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 response plan information or information retrieved from response plan information based on a prompt. This will be described in detail with reference to Figure 6.

[0076] A processor (150) according to one embodiment of the present invention can input a prompt and searched response method information into a generative artificial intelligence model to obtain result information corresponding to the prompt (S420).

[0077] The processor (150) can store the searched response method 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.

[0078] A processor (150) according to one embodiment of the present invention can transmit result information to a user terminal (200) (S430).

[0079] The processor (150) can display result information on the user terminal (200) through a chatbot program.

[0080] The result information may include a summary of at least one response measure information, the original text of the retrieved response measure information, feedback information, etc.

[0081] The processor (150) can provide a plurality of result information listed according to the similarity between embedding vectors to the user terminal (200), and can receive a user input for selecting one result information from the user terminal (200).

[0082] According to one embodiment of the present invention, it is possible to respond quickly and accurately to equipment abnormalities, and to respond more safely by providing unified information according to the type of failure.

[0083] It is expected that the cost of operating a counselor can be reduced through the information provision system (1) according to one embodiment of the present invention, and the optimal response plan can be suggested by more clearly understanding the equipment status based on the equipment status information.

[0084] FIG. 5 is a diagram illustrating the operation of an information provision system according to one embodiment of the present invention.

[0085] Figure 5 specifically describes the operation process of the information provision device (100) described above with reference to Figure 3. Any content that overlaps with the content described with reference to Figure 3 will be omitted.

[0086] As described above, the database (10) of FIG. 1 may be implemented as two or more databases as needed. The database may include a manual database (11), a vector database (12), and a result database (13).

[0087] At this time, each database can be implemented separately, but two or more databases can be combined and implemented as needed. For example, the manual database (11) and the result database (13) can be implemented as a single database.

[0088] According to one embodiment of the present invention, the processor (150) may construct a manual database (11) by storing response measure information including at least one of first response measure information included in an equipment manufacturer's manual and second response measure information constructed using user know-how. The processor (150) may store the response measure information in the manual database (11) by matching it with equipment diagnostic information.

[0089] The manual database (11) can store response plan information, search conditions, and the source of the response plan information. The search conditions may be identical to the equipment diagnostic information, or may be separately processed conditions to reflect the equipment diagnostic information. The source of the response plan information may be the name of the manual document from which the response plan information was extracted, the extracted location information, or a Uniform Resource Locator (URL). The processor (150) can also record the source of the response plan information in various other ways.

[0090] The processor (150) can build a vector database (12) by vector-embedding response plan information, and can build a result database (13) by storing result information generated for each prompt.

[0091] The processor (150) can separately search for the first response measure information included in the equipment manufacturer's manual and the second response measure information built with user know-how in the manual database (11), and provide the first result information based on the first response measure information and the second result information based on the second response measure information together.

[0092] In addition, the processor (150) can match the equipment diagnostic information and user information that performed the fault report with the result information and store them in the result database (13).

[0093] After the result database (13) is sufficiently constructed, the processor (150) can first search for equipment diagnostic information matching the newly entered failure report in the result database (13).

[0094] According to one embodiment of the present invention, an independent database of response measure information within a smart factory can be constructed to provide information that is closely related to inspection of target equipment and has high importance and practicality.

[0095] According to one embodiment of the present invention, a more efficient and faster breakdown consultation service can be provided by constructing a result database (13).

[0096] FIG. 6 is a drawing illustrating a result information generation process of an information providing device according to one embodiment of the present invention.

[0097] The information providing device (100) can perform response measure information search-importance evaluation-final selection based on a generative artificial intelligence model (610) to select the response measure information most suitable for the equipment diagnosis information among the collected response measure information.

[0098] When the information providing device (100) receives a prompt (620), it can search for response measure information in the manual database (11) based on the equipment symptom information and / or equipment diagnosis information according to the equipment symptom information.

[0099] The information providing device (100) can generate result information based on the similarity between the embedding vector of the prompt (620) and the embedding vector of the vector database (12).

[0100] The information providing device (100) can compare similarities and provide the user terminal (200) with the top response plan information in descending order of similarity. The information providing device (100) can store the history of the final result information selected from among the plurality of result information provided to the user terminal (200) in the result database (13).

[0101] 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.

[0102] FIG. 7 is a drawing illustrating the operation of an information providing device according to one embodiment of the present invention.

[0103] Referring to FIG. 7, the information providing device (100) can transmit notification information requesting a re-inspection of the equipment to the user terminal (200) when the equipment is in a normal state, and can transmit result information to the user terminal (200) based on response measure information retrieved from the manual database (11) when the equipment is in a abnormal state.

[0104] For example, the information providing device (100) can diagnose that there is an abnormality in the equipment based on a prompt received from user terminal #1 and transmit result information including a response plan to user terminal #1.

[0105] The information providing device (100) can diagnose that there is no abnormality in the equipment based on the prompt received from the user terminal #2 and transmit notification information requesting a re-inspection of the equipment to the user terminal #2.

[0106] Additionally, the information providing device (100) can diagnose that there is an abnormality in the equipment based on a prompt received from the user terminal #3 and transmit result information including a response plan to the user terminal #3.

[0107] Meanwhile, the information providing device (100) can receive feedback information on the result information and update the manual database (11) and the result database (13).

[0108] Feedback information refers to feedback on the provided result information. It may include information regarding the appropriateness of the provided response plan, information on other response plans that can resolve the issue beyond the provided result information, or information on the response plans actually implemented for the issue. Feedback information may be in the form of text or voice prompts, or it may be implemented as user input selecting items on a user interface provided in a questionnaire format. Thus, the format and method of receiving feedback information are not limited to any one specific method.

[0109] According to one embodiment of the present invention, more efficient and accurate response measure information can be provided by reflecting response measure information utilized in an actual failure situation.

Claims

1. In the information provision system based on generative artificial intelligence, A manual database that stores information on response measures according to the status of the equipment; Receive prompts containing facility information and facility symptom information; Collect equipment status information based on the above prompts and diagnose the status of the equipment. If the above equipment is in normal condition, notification information requesting re-inspection of the above equipment is transmitted to the user terminal. If the condition of the above equipment is not normal, search for the countermeasure information corresponding to the equipment diagnosis information among the countermeasure information stored in the above manual database, By inputting the above prompt and the searched response method 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 the above result information to a user terminal.

2. In paragraph 1, The above information providing device, An information providing system that receives feedback information on the above result information and updates the manual database.

3. In paragraph 1, The above information providing device, An information providing system that collects equipment status information from at least one sensor connected to the equipment.

4. In paragraph 1, The above information providing device, Predict the life of the equipment based on the equipment diagnostic information, An information providing system that transmits information about the predicted lifespan of the equipment to the user terminal.

5. In paragraph 1, The above information providing device, An information provision system that constructs a manual database by storing response measure information including at least one of the first response measure information included in the equipment manufacturer's manual and the second response measure information constructed with user know-how.

6. In paragraph 1, The above information providing device, An information provision system that constructs a vector database by vector embedding the above response measure information.

7. In paragraph 6, 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.

8. In a generative artificial intelligence-based information providing device, Receive prompts containing facility information and facility symptom information; Collect equipment status information based on the above prompts and diagnose the status of the equipment. If the above equipment is in normal condition, notification information requesting re-inspection of the above equipment is transmitted to the user terminal. If the above equipment is not in a normal state, search for the countermeasure information corresponding to the equipment diagnosis information among the countermeasure information according to the equipment state stored in the manual database. By inputting the above prompt and the searched response method 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 the above result information to a user terminal.

9. In paragraph 8, The above processor, An information providing device that receives feedback information on the above result information and updates the manual database.

10. In paragraph 8, The above processor, An information providing device that collects equipment status information from at least one sensor connected to the equipment.

11. In paragraph 8, The above processor, Predict the life of the equipment based on the equipment diagnostic information, An information providing device that transmits information about the predicted lifespan of the equipment to the user terminal.

12. In paragraph 8, The above processor, An information providing device that constructs a manual database by storing response measure information including at least one of the first response measure information included in the equipment manufacturer's manual and the second response measure information constructed with user know-how.

13. In paragraph 8, The above processor, An information providing device that constructs a vector database by vector embedding the above response measure information.

14. In paragraph 13, 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.

15. In a method for providing information based on artificial intelligence, which is performed by an information providing device, A step of receiving a prompt including facility information and facility symptom information; A step of collecting equipment status information based on the above prompt and diagnosing the status of the equipment; If the status of the above equipment is normal, a step of transmitting notification information requesting re-inspection of the above equipment to the user terminal; If the status of the above equipment is not normal, a step of searching for response measure information corresponding to equipment diagnosis information among the response measure information according to the status of the equipment stored in the manual database; A step of inputting the above prompt and the searched response method information into a generative artificial intelligence model to obtain result information corresponding to the prompt; An information providing method comprising: a step of transmitting the above result information to a user terminal.

Images