Product information providing apparatus, product information providing system including the same, and information providing method

Abstract

The present invention relates to a product information providing apparatus, a product information providing system including the same, and an information providing method. A product information providing system according to an embodiment of the present invention can include a first product database storing first product information according to a first model system and weight information of each model item corresponding to the first product information, and an information providing apparatus receiving search request information including second product information according to a second model system, and measuring similarity between the second product information and the first product information stored in the first product database by reflecting the weight information, and identifying at least one target product information corresponding to the search request information among the first product information based on the similarity.

Description

Technical Field

[0001] This invention relates to a product information providing device, a product information providing system including the same, and a method for providing information. Background Technology

[0002] In recent years, with the development of 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 that operates by applying information and communications technology (ICT) combined with digital automation solutions in the design, development, and manufacturing processes.

[0003] One of the key requirements for operating a smart factory is to have access to information that is closely related to the product or business and is of high importance and practicality.

[0004] For example, it is necessary to know the company's products or components that have the same or similar rated conditions as a specific product or component and are price-competitive or have high product stability.

[0005] On the other hand, all products are named according to the product model system, which makes it easy to understand the product's characteristics, such as rated conditions and options, simply by looking at the product model.

[0006] Therefore, the current reality is that there is a need for a solution to establish an information provision system that utilizes product modeling, enabling relevant personnel, including smart factory operations managers and production planning managers, to quickly and accurately find the information they need.

[0007] However, the above content merely provides background information for the present invention and is not the disclosed technology. Summary of the Invention

[0008] The problem to be solved

[0009] The purpose of this invention is to provide a product information providing device that recommends products with a high degree of matching with the user's request, a product information providing system including the product information providing device, and a product information providing method.

[0010] The purpose of this invention is not limited to the purposes mentioned above, and those skilled in the art will clearly understand other purposes not mentioned from the following description.

[0011] Technical solutions to the problem

[0012] A product information providing system according to an embodiment of the present invention may include: a first product database storing first product information according to a first model system and weight information of each model item corresponding to the first product information; and an information providing device receiving search request information containing second product information according to a second model system, measuring the similarity between the second product information and the first product information stored in the first product database by reflecting the weight information, and identifying at least one target product information in the first product information corresponding to the search request information based on the similarity.

[0013] The information providing device can use the first embedding vector of each model item in the first product information and the second embedding vector of each model item in the second product information to calculate the distance reflecting the weight information and measure the similarity based on the distance.

[0014] In the case of a predefined model item in the model item, the information providing device may assign additional weights to the rated conditions that are higher than the rated conditions of the second product information.

[0015] When the first model system and the second model system are different, the information providing device can use information about the model systems of each manufacturer to decompose the second product information by model item.

[0016] The information providing system can establish a second product database that stores information about the second product; the information providing device can use the information about the second product to decompose the second product information according to each model item.

[0017] The information providing device can convert the second product information, which is decomposed according to each of the model items, into information corresponding to the first model system.

[0018] The information providing system may further include a source database storing source information about product collection; the information providing device may provide source information corresponding to the target product information together with at least one of the target product information.

[0019] The information providing system may further include a user terminal that transmits the search request information; the user terminal can obtain the second product information by recognizing the product's identification information.

[0020] The user terminal can obtain the second product information based on user input.

[0021] A product information providing device according to an embodiment of the present invention may include a processor; the processor establishes a first product database storing first product information according to a first model system and weight information of each model item corresponding to the first product information; the processor receives search request information containing second product information according to a second model system; the processor measures the similarity between the second product information and the first product information stored in the first product database by reflecting the weight information; the processor identifies at least one target product information in the first product information corresponding to the search request information based on the similarity.

[0022] A product information providing method performed by an information providing device according to an embodiment of the present invention may include the following steps: establishing a first product database storing first product information according to a first model system and weight information of each model item corresponding to the first product information; receiving search request information containing second product information according to a second model system; measuring the similarity between the second product information and the first product information stored in the first product database by reflecting the weight information; and identifying at least one target product information in the first product information corresponding to the search request information based on the similarity.

[0023] Invention Effects

[0024] According to one embodiment of the present invention, it is possible to grasp the user's intent in a short time and recommend products that are more suitable for the requirements, which is expected to reduce the operating costs of product-related consultation centers.

[0025] According to one embodiment of the present invention, similar products can be searched efficiently using only the model number system, thereby easily providing users with the product information they need.

[0026] According to one embodiment of the present invention, an independent database for product information within a smart factory is established, thereby providing information that is closely related to the target product or the enterprise and is of high importance and practicality.

[0027] According to one embodiment of the present invention, while recommending products similar to the requested product, various information related to the product is also provided, thereby further improving user convenience.

[0028] The effects achievable by this invention are not limited to those mentioned above. Those skilled in the art can clearly understand other effects not mentioned through the following description. Attached Figure Description

[0029] Figure 1 This is a schematic diagram illustrating an information providing system according to an embodiment of the present invention.

[0030] Figure 2 This is a block diagram illustrating the configuration of an information providing device according to an embodiment of the present invention.

[0031] Figure 3 This is a flowchart illustrating the operation of an information providing device according to an embodiment of the present invention.

[0032] Figure 4 This is a diagram illustrating a product model system according to an embodiment of the present invention.

[0033] Figure 5 This is a diagram illustrating the similarity measurement status of an information providing device according to an embodiment of the present invention.

[0034] Figure 6 This is a diagram illustrating the transition state of a product model system according to an embodiment of the present invention.

[0035] Figure 7 This is a diagram illustrating the operating state of the information providing system according to the first embodiment of the present invention.

[0036] Figure 8 This is a flowchart of the operation of the information providing system according to the second embodiment of the present invention. Detailed Implementation

[0037] Hereinafter, specific embodiments of the present invention will be described with reference to the accompanying drawings. The following detailed description is provided to provide a thorough understanding of the methods, apparatus, and / or systems described herein. However, these are merely examples, and the present invention is not limited thereto.

[0038] In describing embodiments of the present invention, detailed descriptions of well-known technologies related to the present invention will be omitted if they are deemed to obscure the essence of the invention. Furthermore, the terms used below are defined in consideration of the functionality of the present invention and may vary depending on the intent or practice of the user or operator. Therefore, their definitions should be derived from the entirety of this specification. The terms used in the detailed description are for illustrative purposes only and are not intended to be limiting. Unless explicitly used differently, the singular includes the plural. In this specification, expressions such as "comprising" or "having" are used to indicate certain characteristics, numbers, steps, operations, elements, parts thereof, or combinations thereof, and should not be construed as excluding the presence or possibility of one or more other characteristics, numbers, steps, operations, elements, parts thereof, or combinations thereof besides those stated. Additionally, terms such as "...part," "...device," "...module," and "block" used in the specification indicate at least one unit of function or processing operation, which may be implemented by hardware or software, or a combination of hardware and software.

[0039] Figure 1 This is a schematic diagram illustrating an information providing system according to an embodiment of the present invention.

[0040] An information providing system 1 (hereinafter referred to as system 1) according to an embodiment of the present invention may include a database 10, an information providing device 100, and a user terminal 200.

[0041] Database 10 is a device for storing required information during the process of information provision by information providing device 100. Database 10 can be implemented as two or more databases as needed. Database 10 can be implemented by a device independent of information providing device 100, or it can be implemented within information providing device 100, but is not limited thereto.

[0042] The information providing device 100 is a device that provides the necessary information during the operation of a smart factory. As an example, the information providing device 100 can be implemented by a computer, server, smartphone, tablet PC, smart tablet, laptop, etc., but is not limited to these.

[0043] User terminal 200 is a device that transmits search request information to information providing device 100 and receives target product information corresponding to the search request information from information providing device 100. As an example, user terminal 200 can be implemented using a computer, PLC (Programmable Logic Controller), server, smartphone, tablet PC, smart tablet, laptop, etc., but is not limited to these. In this case, user terminal 200 can be a smart factory server or equipment within the smart factory, in addition to being the terminal of the person in charge of the smart factory.

[0044] The information providing device 100 and / or user terminal 200 may have built-in production execution system (MES), employee assistance program (EAP), recipe parameter management system (RPMS), etc.

[0045] On the other hand, the information providing device 100 and the user terminal 200 can, as Figure 1 The information providing device 100 and the user terminal 200 can be implemented separately, but are not limited to this; they can be implemented by a single electronic device.

[0046] In addition, although not shown, system 1 may also include a web server for collecting information required by information providing device 100. Information providing device 100 can collect information from the web server by performing crawling.

[0047] This invention proposes an information provision system 1 based on the product model system, enabling relevant personnel, including the operation manager, sales staff, and production planning manager of a smart factory, to quickly and accurately provide or receive the required information.

[0048] Hereinafter, with reference to the accompanying drawings, the configuration and operation of an information providing device 100 according to an embodiment of the present invention will be specifically described.

[0049] Figure 2 This is a block diagram illustrating the configuration of an information providing device according to an embodiment of the present invention.

[0050] An information providing device 100 according to an embodiment of the present invention may include a storage unit 140 and a processor 150. Of course, the information providing device 100 may also include an input unit 110, a communication unit 120, or a display unit 130.

[0051] The input unit 110 generates input data in correspondence with the user input of the information providing device 100. For example, the user input may be user input to start the operation of the information providing device 100, user input to set weights for each model item, user input required to build a database, etc. In addition, the user input may also be various inputs required to identify and search for product information corresponding to the requested information.

[0052] The input unit 110 includes at least one input component. For example, the input unit 110 may include a keyboard, keypad, dome switch, touch panel, touch key, mouse, or menu button. In addition, the input unit 110 may also include a camera or other imaging device and a microphone for voice input.

[0053] The communication unit 120 is configured to communicate with other devices. That is, the communication unit 120 can perform communication with external devices such as the user terminal 200 and the web server in order to send and receive search request information, weight information, distance information, similarity information, product information, source information, etc.

[0054] As an example, the Communications Department 120 can perform wireless communications such as 5G (5th generation communication), LTE-A (Long Term Evolution-Advanced), LTE (Long Term Evolution), Wi-Fi (Wireless Fidelity), and Bluetooth, or wired communications such as LAN (Local Area Network), WAN (Wide Area Network), and power line communication.

[0055] The display unit 130 displays display data based on the operation of the information providing device 100. That is, the display unit 130 can display screens showing search request information, product information, source information, and screens for receiving user input, etc.

[0056] As an example, 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, or an electronic paper display. The display unit 130 can be combined with the input unit 110 and implemented as a touch screen.

[0057] Storage unit 140 stores various information for the operation of information providing device 100. That is, storage unit 140 can store programs for the operation of information providing device 100. Storage unit 140 includes non-volatile memory capable of storing data (information) regardless of power supply, and volatile memory loaded with data to be processed by processor 150 and which cannot be stored without power. Memory includes flash memory, HDD (Hard-Disc Drive), SSD (Solid-State Drive), ROM (Read Only Memory), etc., and storage devices include buffers, random access memory (RAM), etc.

[0058] As mentioned above, the storage unit 140 includes any one of the databases 10. The storage unit 140 can store search request information, weight information, distance information, similarity information, product information, source information, etc., and can also store the computational programs required for performing processes such as collecting product information and weight information of each model item, vector embedding, similarity measurement, target product information identification, product information decomposition and transformation.

[0059] The processor 150 can control at least one other component (e.g., hardware or software component) of the information providing device 100 by running software such as programs, and perform various data processing or operations.

[0060] A processor 150 according to one embodiment of the present invention can receive search request information containing second product information according to a second model system, measure the similarity between the second product information and first product information stored in the first product database by reflecting the weight information, and identify at least one target product information in the first product information corresponding to the search request information based on the similarity.

[0061] At this time, the processor 150 can establish a database and / or a similarity measurement algorithm, or receive, store and use an established database and / or similarity measurement algorithm from an external source, without being limited to any one of these methods.

[0062] On the other hand, the processor 150 can perform at least a portion of data analysis, processing, and result information generation for performing the operation, based on rules or utilizing at least one of machine learning, neural network, or deep learning algorithms as artificial intelligence algorithms. Examples of neural networks may include models such as CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), and transformer.

[0063] Figure 3 This is a flowchart illustrating the operation of an information providing device according to an embodiment of the present invention.

[0064] According to one embodiment of the present invention, the processor 150 may receive search request information containing second product information according to a second model system (S10).

[0065] Processor 150 can store product information and establish a product database according to a model system. A model system is a system defined to allow easy understanding of product characteristics such as specifications and options using model numbers. A model system consists of multiple model items, each of which may include at least one specification and / or option. Figure 4 An example of a model system is shown.

[0066] Search request information is the basic information required to perform a search based on a request from an internal manager or a client company, and it may include second product information. This invention proposes a technical solution that utilizes at least one product database storing product information to recommend first product information (hereinafter also referred to as target product information) with specifications similar to second product information according to a second model system. In this case, the first model system and the second model system can be the same, or they can be different model systems followed by different manufacturers. The case of different model systems will be referred to later. Figure 6 Please provide an explanation.

[0067] In addition, the first product information can be the company's product information, and the second product information can be the product information of other companies, but it is not limited to this. Various settings can be made. For example, the first product information and the second product information can both be the company's products.

[0068] The processor 150 can receive search request information via the input unit 110. For example, the processor 150 can use a camera or similar device in the input unit 110 to identify product identification information, thereby obtaining second product information. For example, the identification information may be a product serial number, QR (Quick Response) code, barcode, product catalog, etc., attached to the product. The processor 150 can use Optical Character Recognition (OCR) technology to transcribe the identification information into text.

[0069] Alternatively, the processor 150 can obtain the second product information based on user input received through the input unit 110. The user input can be text input, voice input, etc., and the input method is not limited to any one of these. When receiving voice input, the processor 150 can recognize the search request information through STT (Speech to Text) conversion.

[0070] In addition, the processor 150 can receive search request information from the user terminal 200, and the user terminal 200 can transmit the search request information to the information providing device 100 in various ways.

[0071] For example, user terminal 200 can obtain second product information by recognizing the product's identification information. Similarly, identification information can be recognized using a camera or similar device in user terminal 200.

[0072] Alternatively, user terminal 200 can obtain second product information based on user input. User input can be text input, voice input, etc., and the input method is not limited to any one of them. When receiving voice input, user terminal 200 can convert it to STT (Speech to Text) and transmit the search request information to information providing device 100.

[0073] According to one embodiment of the present invention, the processor 150 can reflect weight information to measure the similarity between the second product information and the first product information stored in the first product database (S20).

[0074] The product database may include a first product database that stores information about a first product according to a first model system and a second product database that stores information about a second product according to a second model system.

[0075] In the first product database, in addition to the first product information, weight information for each model item corresponding to the first product information can also be stored. Weight information assigns weights to each model item. When there are multiple model items in the model system, a priority order can be set among the model items, thereby enabling more effective product information recommendations.

[0076] Weighting information can be determined by experts specializing in the product, and can be tailored to the model items within each product information item. In this case, the weighting information can be assigned different values ​​based on the priority of each model item; however, depending on the circumstances, all model items can certainly be assigned the same weight. An example regarding weighting information will be provided later. Figure 6 Please provide an explanation.

[0077] The processor 150 can establish a first product database by performing vector embedding on the first product information. At this time, the processor 150 can perform vector embedding on the first product information according to each model item.

[0078] The processor 150 can establish a second product database that stores information about the second product according to a second model system. The information about the second product is used to confirm the model system of the second product information received via the input unit 110 or the user terminal 200. For example, the information about the second product may include a catalog of the second product, information available from the manufacturer's website, etc.

[0079] As another example, information about the second product may include information about the model systems of each manufacturer.

[0080] At this time, as Figure 4 As shown, the processor 150 can match detailed information (i.e., specific rated conditions) for each model item in the product model system, thereby establishing a second product database. For example, for the model "VH-06-H-25-B-13" of product A, the detailed specifications of each model item can be matched as follows: [VH-06-H-25-B-13: Rated voltage 7.2kV, H-type lead-out, circuit breaking current 25kA, phase-to-phase distance 210mm, rated current 1250A].

[0081] Alternatively, processor 150 can store information about each manufacturer's model system in a prescribed format. For example, for product group A, it can be stored in the format "(where 'a' is a letter and '0' is a number). Here, the first two letters represent the model number, the next two numbers represent the rated voltage, the next letter represents the configuration, the next two numbers represent the circuit breaking current, the next letter represents the phase-to-phase distance, and the next two numbers represent the rated current information. Processor 150 can decompose text recognized by OCR based on this format.

[0082] The processor 150 can match the second product information contained in the search request information with the information stored in the second product database to obtain information about each model item.

[0083] The processor 150 can use the first embedding vector of each model item in the first product information and the second embedding vector of each model item in the second product information to calculate the distance reflecting the weight information.

[0084] Processor 150 can measure similarity based on distance. Processor 150 can determine that the closer the distance between the first embedding vector and the second embedding vector, the higher the similarity.

[0085] According to one embodiment of the present invention, the processor 150 can identify at least one target product information in the first product information that corresponds to the search request information based on similarity (S30).

[0086] There can be more than one target product information. The processor 150 can display at least one target product information on the display unit 130 or transmit it to the user terminal 200.

[0087] According to one embodiment of the present invention, it is possible to clearly understand the user's intent in a short time and recommend products that are more suitable for the requirements, and it is expected to reduce the operating costs of product-related consultation centers.

[0088] According to one embodiment of the present invention, similar products can be searched efficiently using only the model number system, thereby easily providing users with the product information they need.

[0089] As an additional embodiment, refer to Figure 3 The process described above involves matching and storing the selected target product information with the second product information. The matched information can then be stored in either the first or second product database. Alternatively, the first and second product databases can be connected to directly output the target product information corresponding to the input second product information. Furthermore, different matching methods or storage paths can be applied, and are not limited to any one of them.

[0090] In this case, the processor 150 can directly provide target product information matching the second product information upon receiving a search request containing the second product information. This has the advantage of reducing the data usage burden on the information providing device 100 and providing target product information to the user more quickly.

[0091] Figure 4 This is a diagram illustrating a product model system according to an embodiment of the present invention.

[0092] The product model system is a system designed to allow users to easily understand the characteristics of a product, such as its specifications and options, simply by looking at its model number.

[0093] For example, Figure 4 This diagram illustrates the product model system for vacuum circuit breakers (VCBs). The model system for vacuum circuit breakers can be composed of model number, rated voltage, type, breaking current, phase-to-phase distance, shape classification, and rated current.

[0094] Product model VH-06-H-25-B-13 is a vacuum circuit breaker product, indicating a rated voltage of 7.2kV, an H-type lead-out configuration, a breaking current of 25kA, a phase-to-phase distance of 210mm, and a rated current of 1250A.

[0095] The information providing device 100 can store the first product information based on the first model system and the weight information of each model item corresponding to the first product information in the first product database.

[0096] For example, a weight can be assigned to represent model number 5, phase-to-phase distance / shape classification 4, form distinction 3, and rated voltage / rated current / breaking current 2. This weight information can be used when calculating the distance between the embedding vector of the first product information and the embedding vector of the second product information.

[0097] Figure 5 is a diagram showing the similarity measurement state of the information providing apparatus according to an embodiment of the present invention.

[0098] As described above Figure 3 in the description of S20, the information providing apparatus 100 may calculate the distance reflecting the weight information using the first embedding vector of each model item of the first product information and the second embedding vector of each model item of the second product information.

[0099] The information providing apparatus 100 may calculate the distance d using Equation 1 below.

[0100] [Equation 1]

[0101] wherein , .

[0102] Here, d represents the distance between x and y, and x and y represent the embedding vectors of each model item. At this time, Equation 1 may be used to measure the similarity of each model item, and the similarity may be comprehensively determined by considering the distance and weight for all the model items.

[0103] Referring to Figure 5 , a state of measuring the similarity between products having two model items of current and pole is shown. Here, Figure 5 the distance is measured using the rated condition value of each model item for intuitive illustration, but it is different from this that the distance is regarded as being measured using the embedding vector.

[0104] 0 is the second product information, 1, 2, and 3 represent the first product information, the distance between 0 and 1 is d1, the distance between 0 and 2 is d2, and the distance between 0 and 3 is d3. The closer the distance is to 0, the more similar the products are considered to be.

[0105] Referring to Figure 5 the first curve 510, when the same weight is assigned to all model items, the distance between the embedding vectors of the products satisfies d1=d2<d3. Accordingly, the information providing apparatus 100 may determine that the products similar to 0 are 1 and 2.

[0106] However, when determining the similarity by considering a plurality of model items, it is very important to determine the priority order between the model items. For example, since the same number of poles is more important than matching the rated current, a higher weight may be assigned to the number of poles.

[0107] Referring to Figure 5the second curve 520, the result of measuring the similarity after reflecting different weights between the model items is that the distance between the embedding vectors of the products satisfies d2<d1<d3. Accordingly, the information providing apparatus 100 can determine that the product similar to 0 is 2.

[0108] On the other hand, in addition to determining the distance based on absolute values for all model items, it is also necessary to assign weights to distances in specific directions for reasons such as product size and compatibility. For example, when the rated current of 0 is 200A, the rated current of 2 is 175A, and the rated current of 3 is 250A, 2 is closer than 3 in terms of distance. However, from the perspective of the characteristics of the rated current, it is preferable to recommend a product having a rated current larger than the rated current of 0 as the comparison target, so it is necessary to assign a weight reflecting this point.

[0109] As described above, for the predefined model items among the model items, the information providing apparatus 100 may assign an additional weight to a rated condition higher than the rated condition of the second product information. The additional weight may be included in the weight information and stored in advance.

[0110] Reference Figure 5 the third curve 530, as a result of assigning different weights between the model items and assigning the additional weight according to the direction, the distance between the embedding vectors of the products satisfies d3<d2<d1. Accordingly, the information providing apparatus 100 can determine that the product similar to 0 is 3.

[0111] According to an embodiment of the present invention, weights and additional weights can be appropriately assigned according to the requirements of each product, so that target product information similar to the second product information can be flexibly identified.

[0112] Figure 6 is a diagram showing a conversion state of a product model system according to an embodiment of the present invention.

[0113] As described above in relation to Figure 3 the description of S10, the model systems of the product information may be different from each other. In order to measure the similarity between product information, the second model system may be transformed to be the same as the first model system before use.

[0114] According to an embodiment of the present invention, when the first model system and the second model system are different, the information providing apparatus 100 may decompose the second product information based on the model items.

[0115] Reference Figure 6 the second product information 610 according to the second model system is shown.

[0116] The second product information 610 consists of the following items: frame, circuit breaking capacity, bracket, pole, voltage, rated current, voltage level, and model of the trip unit.

[0117] The information providing device 100 can break down the second product information 610 into frame / break capacity / bracket / pole / voltage / rated current / voltage level / trip unit based on the model item.

[0118] The information providing device 100 can calculate the model items with high similarity based on the model items after decomposing the second product information 610, and select the first product information (target product information) that matches it from the first product database.

[0119] As another example, the information providing device 100 can convert the second product information 610 based on the decomposed model items so that the second product information corresponds to the first model system (converted product information 620). The information providing device 100 can measure the similarity between the converted second product information and the first product information stored in the first product database by reflecting weight information, and select the target product information with a high similarity to the converted second product information.

[0120] At this time, there can be multiple target product information items, and the information providing device 100 can arrange the first product information items in order of similarity.

[0121] On the other hand, in order to convert the second product information 610 to correspond to the first model system, the information providing device 100 can utilize the second product database that stores information about the second product.

[0122] First, the information providing device 100 can identify the second product information from the search request information received through the input unit 110 or the user terminal 200.

[0123] The information providing device 100 can utilize the information about the second product stored in the second product database, decompose the second product information based on the model item, and convert the second product information into one that corresponds to the first model system.

[0124] As another example, even without a separate second product database, the information providing device 100 can use information about the model systems of various manufacturers to decompose and transform the second product information.

[0125] Figure 6 An example of the weighting information regarding product models is shown in Table 1 below.

[0126] [Table 1]

[0127] According to one embodiment of the present invention, similar products can be identified more accurately through a synchronized model system. Figure 7 This is a diagram illustrating the operating state of the information providing system according to the first embodiment of the present invention.

[0128] Figure 7 For detailed instructions, please refer to the foregoing. Figure 3 The description provides information on the operation of the device 100. Relatedly, omissions and references are omitted. Figure 3 The description contains repetitive content.

[0129] As mentioned above, Figure 1 Database 10 can be implemented as two or more databases as needed. The databases may include a first product database 11, a second product database 12, and a source database 13.

[0130] At this point, each database can be implemented independently, but two or more databases can also be merged as needed. For example, the first product database 11 and the source database 13 can be implemented as a single database.

[0131] According to an embodiment of the present invention, the information providing device 100 can establish a first product database 11 by storing first product information based on a first model system and weight information of each model item corresponding to the first product information.

[0132] In addition to the first product information and weight information, the first product database 11 can also store information about the first product, including product name, product rating, model system, and product diagram. At this time, the information providing device 100 can embed and store the product information according to each model item, and can also separately establish a vector database that only stores the embedded vectors.

[0133] The information providing device 100 can establish a second product database 12 that stores information about the second product according to the second model system.

[0134] Information providing device 100 can, according to Figure 4 The model system shown stores product information in the first product database 11. The information providing device 100 can extract and collect product information from pre-set product catalogs or internal documents, and can also collect product information through a web server based on search request information.

[0135] At this point, the collected product information can be transcribed into text using Optical Character Recognition (OCR) technology. In addition, product information can be collected in various other ways, and the form or method of collection is not limited to any one of these methods.

[0136] As another example, the first product database 11 and the second product database 12 can be connected to each other. That is, it can be implemented such that by matching at least one target information that matches each second product information, the target product information corresponding to the input second product information is directly output.

[0137] Information providing device 100 can collect and store source information via a web server to establish a source database 13. Source information can be additionally provided in relation to the target product, such as product catalogs, DPP (Digital Product Passport), carbon emissions, LCA (Life Cycle Assessment), product manufacturer websites, user menus, product images, cable diagrams, factory inspection reports, sales manager information, and product finders. For example, information providing device 100 can collect source information by searching for manufacturers, product names, etc., on a search portal, or by collecting source information within the manufacturer's corporate website.

[0138] When the information providing device 100 provides target product information, it can provide source information together with the target product information.

[0139] The information providing device 100 can collect source information using a separate program that performs web crawling or scraping. Specifically, the information providing device 100 can acquire HTML pages, parse HTML / CSS, and extract the required source information. Alternatively, the information providing device 100 can extract the required source information by calling an Open API (REST API) provided by a service. In addition, any technology can be applied, as long as it is a technology for collecting source information.

[0140] According to one embodiment of the present invention, an independent database for product information within a smart factory is established, thereby providing information that is closely related to the target product or enterprise and is of high importance and practicality.

[0141] Figure 8 This is a flowchart of the operation of the information providing system according to the second embodiment of the present invention.

[0142] The product recommendation service of this company, which is similar to other companies' products in one embodiment of the present invention, can be provided in the form of a webpage or implemented as an application.

[0143] Reference Figure 8 The first step 810 is to use the user terminal 200 to log in to the implemented webpage or application.

[0144] In the second step 820, the user terminal 200 can be used to identify identification information such as product nameplates or QR codes.

[0145] At this point, if the product is the first product, in the third step 830, the information providing device 100 can provide the corresponding first product information and the source information corresponding to the first product information based on the identified identification information.

[0146] Furthermore, when the product is a second product, the information providing device 100 can receive search request information based on the identified identification information. The information providing device 100 can identify the second product information and at least one target product information, and provide source information corresponding to the target product information together with the target product information.

[0147] In the fourth step 840, the catalog can be displayed based on user input that selects a product catalog from the list of source information provided in the third step 830.

[0148] According to one embodiment of the present invention, while recommending products similar to the requested product, various information related to the product is also provided, thereby further improving user convenience.

[0149] The present invention has been described in detail above through representative embodiments. However, those skilled in the art will understand that various modifications and equivalent embodiments can be implemented from the above embodiments. Therefore, the true scope of protection of the present invention should be determined by the technical concept of the appended claims.

[0150] Industrial applicability

[0151] This invention relates to product information provision technology, which can provide product information technology that recommends products with a high degree of matching with user requests, and therefore has industrial applicability.

Claims

1. An information providing system that provides product information, wherein, include: The first product database stores first product information based on the first model system and weight information of each model item corresponding to the first product information. as well as An information providing device receives search request information containing second product information according to a second model system, measures the similarity between the second product information and first product information stored in a first product database by reflecting the weight information, and identifies at least one target product information in the first product information that corresponds to the search request information based on the similarity.

2. The information providing system according to claim 1, wherein, The information providing device uses the first embedding vector of each model item in the first product information and the second embedding vector of each model item in the second product information to calculate the distance reflecting the weight information, and measures the similarity based on the distance.

3. The information providing system according to claim 2, wherein, In the case of a predefined model item in the model item, the information providing device assigns additional weights to the rated conditions that are higher than the rated conditions of the second product information.

4. The information providing system according to claim 1, wherein, When the first model system and the second model system are different, the information providing device uses information about the model systems of each manufacturer to decompose the second product information by model item.

5. The information providing system according to claim 1, wherein, The information providing system establishes a second product database that stores information about the second product. The information providing device uses information about the second product to break down the second product information into various model items.

6. The information providing system according to claim 4, wherein, The information providing device converts the second product information, which is decomposed according to each of the model items, into information corresponding to the first model system.

7. The information providing system according to claim 1, wherein, The information providing system also includes a source database that stores source information about the product collection; The information providing device provides source information corresponding to the target product information together with at least one of the target product information.

8. The information providing system according to claim 1, wherein, The information providing system also includes a user terminal that transmits the search request information; The user terminal obtains the second product information by recognizing the product's identification information.

9. The information providing system according to claim 8, wherein, The user terminal obtains the second product information based on user input.

10. An information providing device that provides product information, wherein, Including the processor; The processor establishes a first product database that stores first product information based on the first model system and weight information of each model item corresponding to the first product information; The processor receives search request information containing second product information according to the second model system; The processor measures the similarity between the second product information and the first product information stored in the first product database by reflecting the weight information; Based on the similarity, the processor identifies at least one target product information in the first product information that corresponds to the search request information.

11. The information providing apparatus according to claim 10, wherein, The processor uses the first embedding vector of each model item in the first product information and the second embedding vector of each model item in the second product information to calculate the distance reflecting the weight information and measure the similarity based on the distance.

12. The information providing apparatus according to claim 11, wherein, In the case of a predefined model item in the model item, the processor assigns additional weights to the rated conditions that are higher than the rated conditions of the second product information.

13. The information providing apparatus according to claim 10, wherein, When the first model system differs from the second model system, the processor uses information about the model systems of each manufacturer to decompose the second product information into model items.

14. The information providing apparatus according to claim 10, wherein, The processor uses a second product database that stores information about the second product to decompose the second product information by model item.

15. The information providing apparatus according to claim 13, wherein, The processor converts the second product information, which is decomposed according to each of the model items, into a form that corresponds to the first model system.

16. The information providing apparatus according to claim 10, wherein, The processor utilizes a source database storing source information about product collection to provide source information corresponding to the target product information, along with the at least one target product information.

17. An information providing method, comprising a product information providing method performed by an information providing device, wherein, include: The steps of establishing a first product database that stores first product information based on the first model system and weight information of each model item corresponding to the first product information; The step of receiving search request information containing second product information according to the second model system; The step of measuring the similarity between the second product information and the first product information stored in the first product database by reflecting the weight information; as well as The step of identifying at least one target product information in the first product information that corresponds to the search request information based on the similarity.

Images