Information providing apparatus and information providing method

Abstract

An information providing apparatus according to one embodiment of the present invention may comprise a processor that receives a search request signal from a user terminal, searches for product information on the basis of the search request signal, and provides the product information to the user terminal.

Description

Information providing device and information providing method

[0001] The present invention relates to an information providing device and an information providing method.

[0002] Recently, with the development of related technologies such as the Internet of Things (IoT) and Artificial Intelligence (AI), smart factories have become a hot topic. A smart factory is a general term for a manufacturing system operated by applying Information and Communications Technology (ICT) combined with digital automation solutions to production processes such as design, development, and manufacturing.

[0003] One of the key requirements in operating a smart factory is providing information that is closely related to the products or the company and possesses high importance and practicality. To this end, it is necessary to devise measures that enable stakeholders, including equipment managers, to quickly and accurately find the information they need.

[0004] Meanwhile, Generative Artificial Intelligence (GAI) is a type of artificial intelligence technology that generates or creates new data based on given input data. Chatbots, which are an example of applications for Generative AI models, are systems that provide necessary information through conversation with users and are utilized in various fields for purposes such as user support, information provision, and task automation. However, problems have been raised that the accuracy and usefulness of generated content cannot be guaranteed, as it is difficult to accurately understand and interpret all user inputs using only simple Natural Language Processing (NLP) technology, and a so-called hallucination phenomenon occurs where incorrect information is provided regarding unlearned content.

[0005] To address this, a new type of architecture called Retrieval-Augmented Generation (RAG) was developed to improve text generation performance by integrating the Large Language Model (LLM) of generative AI models with information retrieval models.

[0006] The purpose is to provide an information providing device and an information providing method that provide product information more conveniently and quickly.

[0007] An information providing device according to one embodiment of the present invention may include a processor that receives a search request signal from a user terminal, searches for product information based on the search request signal, and provides the product information to the user terminal.

[0008] The processor can receive a prompt regarding a product from the user terminal, input the prompt into a generative artificial intelligence model to obtain result information corresponding to the prompt among the product information provided to the user terminal, and transmit the result information to the user terminal.

[0009] The above search request signal may be generated by the user terminal recognizing identification information regarding the product.

[0010] The above search request signal may be generated through short-range wireless communication between the user terminal and the product.

[0011] The above search request signal may be generated based on user input selecting a product from a product list generated based on the location information of the user terminal.

[0012] The above processor can provide information regarding the real-time status of the product based on the search request signal.

[0013] A method for providing information performed by an information providing device according to an embodiment of the present invention comprises: receiving a search request signal from a user terminal; searching for product information based on the search request signal; and providing the product information to the user terminal. After the step of providing the product information, the method may include: receiving a prompt regarding a product from the user terminal; inputting the prompt into a generative artificial intelligence model to obtain result information corresponding to the prompt among the product information provided to the user terminal; and transmitting the result information to the user terminal.

[0014] The step of providing the above product information may include the step of providing information regarding the real-time status of the product based on the above search request signal.

[0015] According to one embodiment of the present invention, convenience for practitioners or customers can be increased by providing fast and accurate information.

[0016] According to one embodiment of the present invention, by digitizing product information, carbon reduction can be achieved through the minimization of paper usage, and maintenance and operational management can be facilitated.

[0017] According to one embodiment of the present invention, product purchase can be induced by improving accessibility to product information for customers and others, in addition to facility managers.

[0018] According to one embodiment of the present invention, product information provided for maintenance management purposes can also be usefully utilized in marketing, and customer convenience can be greatly improved.

[0019] According to one embodiment of the present invention, it is possible to clearly identify the user's intent within a short period of time to provide a more suitable response to the requirements, and faster task processing by relevant personnel and cost reduction effects regarding the operation of product-related consultation centers are expected.

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

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

[0022] FIG. 3 is a diagram illustrating the operation flowchart of an information providing device according to the first embodiment of the present invention.

[0023] FIG. 4 is a drawing illustrating the operation of a user terminal according to the first embodiment of the present invention.

[0024] FIG. 5 is a drawing illustrating the operation of a user terminal according to a second embodiment of the present invention.

[0025] FIG. 6 is a diagram illustrating the operation flowchart of an information providing device according to a second embodiment of the present invention.

[0026] FIG. 7 is a diagram illustrating the operation of an information providing device according to one embodiment of the present invention.

[0027] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present invention and is not intended to represent the only embodiment in which the present invention can be practiced. In order to clearly explain the present invention in the drawings, parts unrelated to the description may be omitted, and the same reference numerals may be used for identical or similar components throughout the specification.

[0028] FIG. 1 is a schematic diagram illustrating an information providing system according to one embodiment of the present invention.

[0029] An information providing system (1) (hereinafter referred to as the system (1)) according to one embodiment of the present invention may include a database (10), an information providing device (100), and a user terminal (200).

[0030] The database (10) is a device that stores information necessary during the process of the information providing device (100) providing information. The database (10) may be implemented by dividing it into two or more databases as needed, and the method of implementation is not limited to any one, such as being implemented as a separate device from the information providing device (100) or being implemented within the information providing device (100).

[0031] The information providing device (100) is a device that provides information in response to a search request from a user terminal (200) and can be implemented as a computer, server, smartphone, tablet PC, smart pad, laptop, etc. The information providing device (100) can provide information about a product through a separately implemented interface, such as a product search application or a web page.

[0032] The user terminal (200) is a device that requests product search from the information providing device (100) in various ways, uses a chatbot program, and receives product information and result information from the information providing device (100), and can be implemented as a mobile terminal such as a smartphone, tablet PC, smart pad, or laptop.

[0033] In the present invention, an information provision system (1) is proposed that can supply necessary information more quickly and accurately to personnel, including facility managers of a smart factory.

[0034] Hereinafter, the configuration and operation of an information providing device (100) according to an embodiment of the present invention will be described in detail with reference to the drawings.

[0035] FIG. 2 is a block diagram illustrating the configuration of an information providing device according to one embodiment of the present invention.

[0036] 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).

[0037] 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 required to build a generative artificial intelligence model / database, etc. In addition to this, it may be applied without limitation if it is a user input required to transmit product information and result information to the user terminal (200).

[0038] 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.

[0039] The communication unit (120) can communicate with external devices such as a user terminal (200) and a server to transmit and receive search request signals, product information, prompts, result information, etc.

[0040] 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.

[0041] 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 product information, a screen displaying result information, a screen receiving user input, etc.

[0042] The display unit (130) includes a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, an Organic LED (OLED) display, a Micro Electro Mechanical Systems (MEMS) display, and an electronic paper display. The display unit (130) can be combined with the input unit (110) to be implemented as a touch screen.

[0043] The storage unit (140) stores operation programs of the information providing device (100). The storage unit (140) includes storage with non-volatile properties that can preserve data (information) regardless of whether power is provided, and memory with volatile properties in which data to be processed by the processor (150) is loaded and data cannot be preserved if power is not provided. Storage includes flash memory, HDD (Hard-Disc Drive), SSD (Solid-State Drive), ROM (Read Only Memory), etc., and memory includes buffer, RAM (Random Access Memory, RAM), etc.

[0044] As previously described, the storage unit (140) may be implemented by including any one of the databases (10). The storage unit (140) may store search request signals, product information, prompts, generative artificial intelligence models, etc., and may store computation programs, etc., required in the process of collecting and searching product information, vector embedding, building and running generative artificial intelligence models, receiving search request signals, obtaining result information, etc.

[0045] The processor (150) can execute software, such as a program, to control at least one other component (e.g., hardware or software component) of the information providing device (100) and can perform various data processing or operations.

[0046] A processor (150) according to one embodiment of the present invention receives a search request signal from a user terminal, searches for product information based on the search request signal, and can provide the product information to the user terminal.

[0047] The processor (150) receives a prompt regarding a product from the user terminal, inputs the prompt into a generative artificial intelligence model to obtain result information corresponding to the prompt among the product information provided to the user terminal, and can transmit the result information to the user terminal.

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

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

[0050] FIG. 3 is a diagram illustrating the operation flowchart of an information providing device according to the first embodiment of the present invention.

[0051] According to one embodiment of the present invention, the processor (150) can receive a search request signal from a user terminal (200) (S10).

[0052] As described above, it is assumed that the user terminal (200) communicates with the information providing device (100) through a digital channel such as an application or a web page.

[0053] The search request signal is a signal for specifying product information requested by the user terminal (200). The product information includes all information regarding the product and may include user manuals, product guidelines, maintenance manuals, test reports, data sheets, certificates, Digital Product Passports (DPP), product introduction videos, drawings (circuit diagrams, wiring diagrams, product disassembly perspective views, etc.), catalogs, user manual videos, product guideline videos, test data, accessory replacement manual videos, etc. At this time, the product information is not limited to any specific type or format, such as audio files, video files, or image files, in addition to documents.

[0054] The search request signal can be received in various ways, for example, by the user terminal (200) recognizing identification information regarding the product, by short-range wireless communication between the user terminal (200) and the product, or by receiving user input selecting a product from a product list generated based on the location information of the user terminal (200). This will be explained with reference to FIGS. 4 and 5.

[0055] According to one embodiment of the present invention, the processor (150) can search for product information based on a search request signal (S20).

[0056] When a search request signal is generated by the user terminal (200) recognizing identification information regarding a product, the processor (150) can search for product information using the identification information. The identification information regarding a product may include unique product information such as a product model name, product serial number (LOT ID), and item code, or identification codes such as a QR code (Quick Response code), barcode, or data matrix. In addition, any format of connection information that allows for the rapid recognition of product information may be adopted as identification information.

[0057] Meanwhile, in the process of the user terminal (200) recognizing identification information, object detection technology may be utilized. For example, when the user terminal (200) photographs a nameplate or user manual attached to a product through a built-in camera, identification codes or product description information can be identified through an object detection model. The object detection model may be implemented as a model such as YOLO (You Only Look Once), R-CNN (Region-based Convolutional Neural Networks), SSD (Single Shot MultiBox Detector), etc., but is not limited to any one of them.

[0058] When an identification code is detected as a result of object detection, the information providing device (100) or user terminal (200) can analyze the pattern of the identification code through a decoding program to identify unique product information corresponding to the identification code.

[0059] When product description information is detected as a result of object detection, the user terminal (200) can recognize text included in the product description information through character recognition technology. The information providing device (100) or the user terminal (200) can identify unique product information containing text similar to the recognized text based on a similarity algorithm. The character recognition technology may be, for example, Optical Character Recognition (OCR) technology, but is not limited thereto.

[0060] A similarity algorithm is an algorithm trained to evaluate how similar two strings (character-recognized text and pre-stored product unique information) are by calculating their similarity, and similarity can be expressed as a numerical value (e.g., between 0 and 1). In this case, the similarity algorithm can be trained by considering the importance of the components of the product unique information. For example, the product unique information can be divided into main parts and accessories, and the algorithm can be trained to identify higher similarity as the product unique information corresponding to the main parts is more similar. Naturally, the criteria for dividing the product unique information into various components and weights based on importance can be set in various ways. The similarity algorithm can be implemented using, for example, cosine similarity, Euclidean distance, or BERT (Bidirectional Encoder Representations from Transformers), but is not limited to any one of them.

[0061] The processor (150) can search for product information in the database (10) using product unique information.

[0062] According to one embodiment of the present invention, the processor (150) can provide product information to the user terminal (200) (S30).

[0063] There may be various ways to provide product information, and product information can be displayed on a user terminal (200) through digital channels such as applications and web pages.

[0064] At this time, the processor (150) may additionally provide information regarding the real-time status of the product in addition to product information. The information regarding the real-time status of the product includes real-time measurement data of the product obtained through sensors connected to the product, and may also include the lifespan of the product identified based on the measurement data, or the current status of the product (whether there is an abnormality, etc.).

[0065] According to one embodiment of the present invention, convenience for practitioners or customers can be increased by providing fast and accurate information.

[0066] According to one embodiment of the present invention, by digitizing product information, carbon reduction can be achieved through the minimization of paper usage, and maintenance and operational management can be facilitated.

[0067] According to one embodiment of the present invention, product purchase can be induced by improving accessibility to product information for customers and others, in addition to facility managers.

[0068] FIG. 4 is a drawing illustrating the operation of a user terminal according to the first embodiment of the present invention.

[0069] As previously described in relation to S10 of FIG. 3, the search request signal can be received in various ways.

[0070] For example, a search request signal may be generated when a user terminal (200) recognizes identification information regarding a product. The user terminal (200) may recognize identification information regarding a product (420) by photographing a product catalog (410) using a built-in camera or by photographing a nameplate attached to a product (420).

[0071] As another example, a search request signal may be generated via short-range wireless communication between the user terminal (200) and the product (430).

[0072] Short-range wireless communication includes various communication methods depending on the application, transmission distance, speed, power consumption, etc. Examples include Near-field Communication (NFC), Bluetooth, Wi-Fi, UWB (Ultra-Wideband), RFID (Radio-Frequency Identification), and Zigbee.

[0073] For example, in the case of NFC communication, the user terminal (200) and the product (430) can be connected by performing a handshake (tagging) according to the NFC communication protocol of the product (430) at a very close distance. At this time, product information can be packaged as an NDEF message and transmitted directly via NFC communication, or configuration data for exchanging high-speed transmission protocols (e.g., Bluetooth, Wi-Fi Direct) to be used for file transfer between devices can be shared.

[0074] According to one embodiment of the present invention, a search request signal for searching product information can be transmitted in various ways, so product information can be easily provided even in various situations for relevant parties (situations where there is no product nearby, situations where the camera cannot be operated for security reasons, situations where internet connection is difficult, etc.).

[0075] FIG. 5 is a drawing illustrating the operation of a user terminal according to a second embodiment of the present invention.

[0076] Similar to Figure 4, another example of receiving a search request signal is described.

[0077] In this embodiment, the search request signal may be generated based on user input selecting a product from a product list generated based on location information of the user terminal (200).

[0078] The user terminal (200) can identify location information and identify products (510, 520, 530) located in close proximity to the user terminal (200) and capable of communicating. At this time, as described above, there are various communication methods for short-range wireless communication depending on the purpose, transmission distance, speed, power consumption, etc., and may be, for example, Near-field Communication (NFC), Bluetooth, Wi-Fi, UWB (Ultra-Wideband), RFID (Radio-Frequency Identification), Zigbee, etc.

[0079] The location information of the user terminal (200) can be identified by utilizing technologies such as GPS (Global Positioning System) and IPS (indoor positioning system).

[0080] The user terminal (200) can receive user input selecting a product from a generated product list. At this time, the product list may be composed of text containing unique product information of the identified products (510, 520, 530), or implemented as icons indicating the location of the products (510, 520, 530) on a 2D / 3D map that reconstructs the site. The user terminal (200) can display the product list and receive user input selecting one of them, and thereby transmit a signal requesting product information to the information providing device (100).

[0081] Meanwhile, surrounding products of the user terminal (200) can also be identified based on the location of the product. For example, the exact location where a product, such as power equipment, is installed can be determined by utilizing GPS, IPS, etc. Since the installation location of individual equipment / products can be determined even indoors, such as in a factory or electrical room, a map of the location of individual equipment / products can be created and saved and then utilized.

[0082] Under this premise, when a user terminal moves near a product within a factory or electrical room, the user terminal can identify the product by using GPS and IPS functions to display a list of products near the user terminal and receiving user input to select the product. It is expected that using this method will allow for immediate entry into the stage of identifying and selecting the product to be verified without using direct methods such as product tags, and will also enable easy wireless communication connection with the product.

[0083] According to one embodiment of the present invention, information about products located nearby can be easily obtained without taking separate measures, thereby maximizing convenience.

[0084] FIG. 6 is a diagram illustrating the operation flowchart of an information providing device according to a second embodiment of the present invention.

[0085] Figure 6 illustrates the process of asking and answering questions through a chatbot program regarding product information provided through the process of Figure 3.

[0086] According to one embodiment of the present invention, the processor (150) can receive a prompt regarding a product from a user terminal (200) (S610).

[0087] A prompt is a query input into a generative artificial intelligence model, and it may relate to products for which information is provided based on a search request signal. The prompt may be voice input in addition to text input, and the prompt format is not limited to any one type.

[0088] According to one embodiment of the present invention, the processor (150) can input a prompt into a generative artificial intelligence model to obtain result information corresponding to the prompt among the product information provided to the user terminal (200) (S620).

[0089] Meanwhile, as described above, the present invention adopts a RAG architecture to improve the answer accuracy of a generative artificial intelligence model, and the RAG architecture is largely composed of a generative artificial intelligence model and a database.

[0090] The generative AI model may be a large language model, and the database may consist of a product database storing product information that serves as a reference for the large language model to provide answers corresponding to queries, and a vector database constructed by vector embedding the product information.

[0091] The processor (150) can store the entire product information by vector embedding it into 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 within the vector database. Similarity can be determined by distance measures such as Euclidean distance or cosine similarity, and similarity can also be measured in various other known ways.

[0092] 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 a generative artificial intelligence model.

[0093] The processor (150) can build a product database by adding metadata (e.g., tags, filenames, descriptions, etc.) for text or images of all product information. The processor (150) can search for necessary information in the product database based on the metadata.

[0094] According to one embodiment of the present invention, the processor (150) can transmit result information to the user terminal (200) (S630).

[0095] The processor (150) can display result information on the user terminal (200) through a chatbot program. The result information is detailed information about the product searched through the prompt. For example, if the prompt requests the product's rated conditions, a part of the product manual can be provided as result information. As another example, if the prompt requests a drawing of the product, the drawing can be provided as result information.

[0096] Meanwhile, the processor (150) can provide multiple result information to the user terminal (200) and can receive user input from the user terminal (200) to select one of the result information.

[0097] According to one embodiment of the present invention, it is possible to clearly identify the user's intent within a short period of time to provide a more suitable response to the requirements, and faster task processing by relevant personnel and cost reduction effects regarding the operation of product-related consultation centers are expected.

[0098] According to one embodiment of the present invention, customer satisfaction can be improved as the customer can quickly check the information they want to check without having to search for it one by one on the product information.

[0099] FIG. 7 is a diagram illustrating the operation of an information providing device according to one embodiment of the present invention.

[0100] As described above, the database (10) of FIG. 1 may be implemented as two or more databases as needed. The database may include a product database (11) and a vector database (12). At this time, each database may be implemented separately, but two or more databases may be combined as needed.

[0101] The information providing device (100) can collect product information and build a product database (12). The product information includes all information regarding the product and may include user manuals, product guidelines, maintenance manuals, test reports, data sheets, certificates, Digital Product Passport (DPP), product introduction videos, drawings (circuit diagrams, wiring diagrams, product disassembly perspective views, etc.), catalogs, user manual videos, product guideline videos, test data, accessory replacement manual videos, etc. At this time, the product information is not limited to any specific type or format, such as audio files, video files, or image files, in addition to documents.

[0102] In addition to the product information mentioned above, the information providing device (100) can store metadata (e.g., tags, filenames, descriptions, etc.) for text, images, videos, etc. constituting each product information in the product database (12).

[0103] The information providing device (100) can build a vector database (13) by vector embedding product information.

[0104] When the information providing device (100) receives a prompt (720), it can identify result information based on information stored in the product database (11) and the vector database (12) through a generative artificial intelligence model (710). At this time, embedding vectors or metadata can be utilized to identify result information corresponding to the prompt (720).

[0105] According to one embodiment of the present invention, an independent database for product information within a smart factory can be established to provide information that is closely related to target products or companies and is of high importance and practicality.

Claims

1. In an information providing device, Receive a search request signal from a user terminal, and Search for product information based on the above search request signal, and An information providing device comprising a processor that provides the product information to the above user terminal.

2. In Paragraph 1, The above search request signal is, An information providing device characterized by the above-mentioned user terminal recognizing identification information regarding a product.

3. In Paragraph 1, The above search request signal is, An information providing device characterized by generating information through short-range wireless communication between the above-mentioned user terminal and the above-mentioned product.

4. In Paragraph 1, The above search request signal is, An information providing device characterized by generating based on user input selecting a product from a product list generated based on location information of the above-mentioned user terminal.

5. In Paragraph 1, The above processor is, An information providing device that provides information regarding the real-time status of a product based on the above search request signal.

6. In Paragraph 1, The above processor is, Receive a prompt regarding the product from the above user terminal, and Input the above prompt into a generative artificial intelligence model to obtain result information corresponding to the above prompt among the product information provided to the user terminal, and An information providing device that transmits the above result information to the above user terminal.

7. In a method of providing information performed by an information providing device, A step of receiving a search request signal from a user terminal; A step of searching for product information based on the above search request signal; The method includes the step of providing the product information to the user terminal, After the step of providing the above product information, A step of receiving a prompt regarding a product from the above user terminal; A step of inputting the above prompt into a generative artificial intelligence model to obtain result information corresponding to the above prompt among the product information provided to the user terminal; A method for providing information comprising the step of transmitting the above result information to the user terminal.

8. In Paragraph 7, The above search request signal is, A method for providing information characterized by the above-mentioned user terminal recognizing identification information regarding a product.

9. In Paragraph 7, The above search request signal is, A method for providing information characterized by generating short-range wireless communication between the above-mentioned user terminal and the above-mentioned product.

10. In Paragraph 7, The above search request signal is, A method for providing information characterized by generating based on user input selecting a product from a product list generated based on location information of the above-mentioned user terminal.

11. In Paragraph 7, The step of providing the above product information is, A method for providing information comprising the step of providing information regarding the real-time status of a product based on the above search request signal.

Images