Electronic device and method for assessing value of product

Abstract

An electronic device for assessing the value of a product, according to one embodiment of the present invention, may comprise a processor which: collects first control data according to the start of a first product; predicts the performance of each part of the first product corresponding to the first control data by using at least one first artificial intelligence model trained to predict the performance of each of a plurality of parts constituting a product on the basis of control data of the product; and predicts the price of the first product by using at least one second artificial intelligence model trained to predict the price of the product on the basis of performance data of each part of the product.

Description

Electronic device and method for evaluating the value of a product

[0001] The present invention relates to an electronic device and method for evaluating the value of a product.

[0002] The trading of second-hand products is increasing to improve operational efficiency and reduce costs for industrial equipment. High-value industrial equipment has a long lifespan and retains high value even in a used state if properly maintained. Therefore, second-hand trading can maximize resource utilization and reduce unnecessary waste.

[0003] However, currently, sellers present prices along with simple conditions such as usage time, making it difficult to objectively evaluate the product's condition and performance. Consequently, it is difficult to verify the product's lifespan or whether the stated price is reasonable.

[0004] In particular, for products such as motors and drives, it is difficult to verify their condition before actual operation, and a proper value assessment is only possible by comprehensively considering factors such as the degree of wear on each component. For instance, the extent of wear on the internal coils of the motor and the driving performance of the bearings must be checked. However, it is difficult for buyers to verify these details individually, and assessing the value is even more challenging when they lack knowledge about the product.

[0005] The objective of the present invention is to provide an electronic device and method for evaluating the value of a product more accurately and efficiently.

[0006] An electronic device for evaluating the value of a product according to one embodiment of the present invention may include a processor that collects first control data according to the operation of a first product, predicts the performance of each component of a first product corresponding to the first control data using at least one first artificial intelligence model trained to predict the performance of each component constituting a product based on the product control data, and predicts the price of the first product using at least one second artificial intelligence model trained to predict the price of the product based on the performance data of each component of the product.

[0007] The above at least one second artificial intelligence model can be trained to predict the price of a product by assigning weights according to the importance of each component of the product.

[0008] The above at least one second artificial intelligence model can be trained to predict the price of a product by considering repair costs based on the performance of each component.

[0009] The above at least one second artificial intelligence model can be trained to predict the price of a product by considering the transaction data of the product.

[0010] The above processor can generate notification information regarding the replacement of a part for which performance is predicted to be below a predefined value.

[0011] The transaction data of the above product may include the product transaction price for the same product and information regarding the product provided by the seller.

[0012] A method for evaluating the value of a product performed by an electronic device according to an embodiment of the present invention may include: a step of collecting first control data according to the activation of a first product; a step of predicting the performance of each component of a first product corresponding to the first control data using at least one first artificial intelligence model trained to predict the performance of each component constituting a product based on the product control data; and a step of predicting the price of the first product using at least one second artificial intelligence model trained to predict the price of the product based on the performance data of each component of the product and the transaction data of the product.

[0013] The above method may further include the step of generating notification information regarding the replacement of a part for a part whose performance is predicted to be below a predefined value.

[0014] According to one embodiment of the present invention, the value of a product can be accurately evaluated through objective indicators.

[0015] According to one embodiment of the present invention, by accurately predicting the performance of the product and the price therefrom, the recycling of the product is made easier.

[0016] According to one embodiment of the present invention, a seller can facilitate sales by accurately evaluating the value of a product to be sold.

[0017] According to one embodiment of the present invention, a buyer can ensure reliability regarding the quality of the product they wish to purchase and can purchase it at a reasonable price.

[0018] FIG. 1 is a schematic diagram illustrating a product value evaluation system according to one embodiment of the present invention.

[0019] FIG. 2 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present invention.

[0020] FIG. 3 is a diagram illustrating the operation flowchart of an electronic device according to one embodiment of the present invention.

[0021] FIG. 4 is a diagram illustrating the learning process of a first artificial intelligence model according to an embodiment of the present invention.

[0022] FIG. 5 is a diagram illustrating the learning process of a second artificial intelligence model according to one embodiment of the present invention.

[0023] 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.

[0024] FIG. 1 is a schematic diagram illustrating a product value evaluation system according to one embodiment of the present invention.

[0025] The product valuation system (1) of FIG. 1 may include an electronic device (100), a seller terminal (200), and a buyer terminal (300).

[0026] The electronic device (100) is a device for evaluating the value of a product and can be implemented as a computer, PLC (Programmable Logic Controller), server, smartphone, tablet PC, smart pad, laptop, etc. The electronic device (100) can mediate a transaction between a seller terminal (200) and a buyer terminal (300), and can separately operate and manage a used goods trading platform for mediating the transaction.

[0027] The seller terminal (200) and the buyer terminal (300) are devices for selling or buying products, and can be implemented as a computer, server, smartphone, tablet PC, smart pad, laptop, etc.

[0028] Meanwhile, the electronic device (100) may be implemented as a seller terminal (200) and / or a buyer terminal (300), and the method of implementation of the electronic device (100) is not limited to any one. However, for the convenience of the following explanation, the electronic device (100), the seller terminal (200), and the buyer terminal (300) are assumed to be separate devices.

[0029] The present invention proposes a method for objectively evaluating the value of a product based on its performance, whereas the value of a product was previously evaluated based on the seller's subjective criteria.

[0030] Hereinafter, the configuration and operation of an electronic device (100) according to one embodiment of the present invention will be described in detail with reference to the drawings.

[0031] FIG. 2 is a block diagram illustrating the configuration of an electronic device according to one embodiment of the present invention.

[0032] An electronic 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).

[0033] The input unit (110) generates input data in response to user input of the electronic device (100). For example, user input may be a user input requesting the operation of a program for evaluating the value of a product, a user input for preprocessing control data, etc., and may also be applied without limitation if it is a user input necessary to evaluate the value of a product.

[0034] 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.

[0035] The communication unit (120) can perform communication with external devices such as a server, product, seller terminal (200) and buyer terminal (300) to transmit and receive control data, performance data by component, product transaction data, first artificial intelligence model, second artificial intelligence model, etc.

[0036] 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.

[0037] The display unit (130) displays display data according to the operation of the electronic device (100). The display unit (130) can display a screen displaying performance data by product component, a screen displaying the price of the product, and other screens receiving user input.

[0038] 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) can be combined with the input unit (110) to be implemented as a touch screen.

[0039] The storage unit (140) stores operation programs of the electronic 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, hard-disc drive (HDD), solid-state drive (SSD), and ROM (Read Only Memory), and memory includes buffer and RAM (Random Access Memory).

[0040] The storage unit (140) can store control data, performance data by component, product transaction data, a first artificial intelligence model, a second artificial intelligence model, etc. The storage unit (140) can store computation programs, etc., that are necessary in the process of collecting control data, learning models, predicting performance by component, predicting product prices, etc.

[0041] The processor (150) can control at least one other component (e.g., hardware or software component) of the electronic device (100) by executing software such as a program, and can perform various data processing or operations.

[0042] A processor (150) according to one embodiment of the present invention collects first control data according to the operation of a first product, predicts the performance of each component of the first product corresponding to the first control data using at least one first artificial intelligence model trained to measure the performance of each component constituting the product based on the product's control data, and predicts the price of the first product using at least one second artificial intelligence model trained to measure the price of the product based on the performance data of each component of the product and the product's transaction data.

[0043] At this time, the processor (150) may train at least one first artificial intelligence model trained to measure performance by component and / or at least one second artificial intelligence model trained to measure the price of a product, or receive and store an artificial intelligence model that has been trained and built from the outside and use it, and is not limited to either one.

[0044] 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), and RNN (Recurrent Neural Network).

[0045] FIG. 3 is a diagram illustrating the operation flowchart of an electronic device according to one embodiment of the present invention.

[0046] According to one embodiment of the present invention, the processor (150) can collect first control data according to the activation of the first product (S10).

[0047] The product of the present invention is composed of a plurality of parts and can be applied without limitation as long as performance can be measured using control data measured according to the operation of the product. The product may be, for example, a motor, an inverter, etc., and the motor may be a motor used in robot vacuum cleaners, Automated Guided Vehicles (AGVs), etc., in addition to industrial motors. It may also be applied to electric vehicles. For convenience of explanation, a motor will be described below as an example.

[0048] Control data may be, for example, data received from sensors attached to the product in response to the product's operation. Sensors may include, for example, current sensors, voltage sensors, temperature sensors, vibration sensors, rotational speed / position sensors, etc. Additionally, control data may be time-series data, but is not limited thereto, and may be image data generated using time-series data. The types of control data required to diagnose the performance of each component may differ.

[0049] In the case of a motor, the starting section may consist of an acceleration section, a constant speed section, and a deceleration section, and the control data may be data for the constant speed section, but is not limited thereto and may include data for the acceleration / deceleration section.

[0050] The processor (150) can receive control data for a product from a seller terminal (200), and the collection path is not limited to any one of the following: collecting control data from a product or a separate device controlling the product, or receiving it through a server. For example, if the first product is a motor, the processor (150) can collect control data from an inverter connected to the motor, or obtain it through a server.

[0051] According to one embodiment of the present invention, the processor (150) can predict the performance of each component of a first product corresponding to the first control data using at least one first artificial intelligence model trained to predict the performance of each component of a product based on the control data of the product (S20).

[0052] At this time, the first artificial intelligence model can be trained to predict the performance of multiple parts through a single model, or multiple first artificial intelligence models can be trained to predict the performance of each part.

[0053] The first artificial intelligence model can implement various output data, such as representing the performance of each product component as durability (consumption) or lifespan. For example, if the first product is a motor, the motor may be composed of components such as a bearing, coil, fan, rotor, stator, and frame. The first artificial intelligence model may output performance data such as a bearing (65%) (wherein the initial performance is assumed to be 100%), a coil (40%), etc., or output performance data such as a fan (predicted lifespan: 50 hours), a rotor (predicted lifespan: 170 hours), etc. The process of training the first artificial intelligence model is described with reference to Fig. 4.

[0054] According to one embodiment of the present invention, the processor (150) can predict the price of the first product using at least one second artificial intelligence model trained to predict the price of the product based on the product's component performance data and the product's transaction data (S30).

[0055] The performance data by product component may be the result data of the aforementioned first artificial intelligence model. However, it is not limited thereto and may be performance data by component obtained through other methods. The product transaction data may include the product transaction price for the same product and information regarding the product provided by the seller.

[0056] At this time, the second artificial intelligence model can be trained to predict the prices of multiple products through a single model, or multiple second artificial intelligence models can be trained to predict the prices of each product. The process of training the second artificial intelligence model is described with reference to Fig. 5.

[0057] The second AI model can be trained to predict the price of a product by assigning weights based on the importance of each component. For example, if the rotor is given a high weight among the motor components, the rotor's wear rate can significantly affect the motor's price.

[0058] In addition, the second AI model can be trained to predict the price of a product by considering repair costs based on the performance of each component. For example, if the performance of a bearing among the motor components is below a predefined value, the product price can be predicted by considering the repair cost of the bearing.

[0059] The processor (150) can generate notification information regarding the replacement of a part for which performance is predicted to be below a predefined value. The implementation form of the notification information can vary; for example, it may be implemented as text or a photo on a product detail page on a used goods trading platform indicating that the product requires replacement of a part. Additionally, the notification information may include information regarding the cost of replacing the part, the replacement location, etc.

[0060] According to one embodiment of the present invention, the value of a product can be accurately evaluated through objective indicators.

[0061] According to one embodiment of the present invention, by accurately predicting the performance of the product and the price therefrom, the recycling of the product is made easier.

[0062] According to one embodiment of the present invention, a seller can facilitate sales by accurately evaluating the value of a product to be sold.

[0063] According to one embodiment of the present invention, a buyer can ensure reliability regarding the quality of the product they wish to purchase and can purchase it at a reasonable price.

[0064] The following describes the process of learning the first artificial intelligence model and the second artificial intelligence model by the processor (150).

[0065] FIG. 4 is a diagram illustrating the learning process of a first artificial intelligence model according to an embodiment of the present invention.

[0066] The processor (150) can train at least one first artificial intelligence model (400) based on control data (410) and performance data (420).

[0067] Control data (410) is data obtained according to the operation of the product, and performance data (420) is labeling data, which may be data regarding the durability (wear and tear) and lifespan of a part corresponding to the control data.

[0068] The first artificial intelligence model is an artificial intelligence model trained to predict the performance of components forming a product based on control data, and may include various types of artificial intelligence models such as CNN (Convolutional Neural Network), Resnet, AlexNet, DNN (Deep Neural Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based Deep Neural Network), DBN (Deep Belief Network), RBM (Restricted Boltzmann Machine), LSTM (Long Short-Term Memory), and Transformer.

[0069] In particular, when the control data takes the form of image data, it can also be implemented using YOLO, R-CNN (Region with Convolutional Neural Network), Fully Convolutional Network, RPN (Region Proposal Network), etc.

[0070] FIG. 5 is a diagram illustrating the learning process of a second artificial intelligence model according to one embodiment of the present invention.

[0071] The processor (150) can train at least one second artificial intelligence model (500) based on the product's component performance data (510) and the product's price. The processor (150) can predict the overall product's performance based on the component performance data (510).

[0072] The performance data (510) for each part of the product may have the same format as the performance data (410) of FIG. 4.

[0073] The processor (150) can train at least one second artificial intelligence model (500) by additionally considering the product's transaction data (520) along with the product's component performance data (510).

[0074] The product transaction data (520) may include the actual product transaction price for the same product and information about the product provided by the seller. The information about the product provided by the seller may include the product name, manufacturer, year of purchase, cost, degree of aging of parts, and usage time of the product. For example, it may be "The bearing is somewhat worn out," or "It has been about 3 years with a usage time of 40 hours per week." These may be used to predict the wear of the bearing or the lifespan of the product. Information about the product may be collected from various sources, for example, the processor (150) may parse the product transaction data from a sales web page for the same product posted on a sales platform, etc.

[0075] The second artificial intelligence model is an artificial intelligence model trained to predict the price of a product based on the performance of multiple components, and may include various types of artificial intelligence models such as CNN (Convolutional Neural Network), Resnet, AlexNet, DNN (Deep Neural Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based Deep Neural Network), DBN (Deep Belief Network), RBM (Restricted Boltzmann Machine), LSTM (Long Short-Term Memory), and Transformer.

[0076] In particular, when the performance data takes the form of image data, it can also be implemented using YOLO, R-CNN (Region with Convolutional Neural Network), Fully Convolutional Network, RPN (Region Proposal Network), etc.

[0077] The processor (150) can train at least one second artificial intelligence model (500) to predict the price of a product by assigning weights according to the importance of each part of the product.

[0078] For example, a motor consists of various components, and the performance of each component can significantly impact the overall performance and price of the motor. Key motor components include, for instance, the rotor, bearings, coils, fan, stator, and frame. Each component has a different level of importance, and by assigning weights based on this significance, the performance and price of the product can be predicted.

[0079] First, the rotor is the central component of the motor and is directly responsible for rotational motion. Therefore, if the performance of the rotor deteriorates, the overall performance of the motor may drop significantly, so the weight can be set to 0.35.

[0080] Bearings support the rotational motion of the rotor and reduce friction. If the condition of the bearings is poor, the motor's efficiency decreases and noise and heat generation may increase, so the weight can be set to 0.25.

[0081] The coil receives current and forms a magnetic field to rotate the rotor. Since a decrease in coil performance can reduce current efficiency and cause overheating problems, the weight can be set to 0.2.

[0082] The stator maintains the magnetic field and works in conjunction with the rotor. Since the efficiency of electromagnetic induction may decrease if the performance of the stator deteriorates, the weight can be set to 0.1.

[0083] The fan serves to cool the motor. If the fan's performance deteriorates, the motor may overheat, but since it is less important compared to other major components, its weight can be set to 0.05.

[0084] The frame plays a structural role in supporting the motor, but since it does not have a significant impact on direct electrical performance, the weight can be set to 0.05.

[0085] The lifespan or wear rate of each motor component can be predicted based on performance data, and then weights can be applied to that data to evaluate the motor's overall performance. For example, let's assume the performance of each component is as follows.

[0086] Rotor: 70%, Bearing: 80%, Coil: 50%, Stator: 82%, Fan: 65%, Rotor: 85%, Frame: 70%

[0087] In this case, the total performance of the motor (70%*0.35+80%*0.25+50%*0.2+82%*0.1+65%*0.05+85%*0.05) is 70.2%. For example, if the base price of the motor is 1,000,000 won, the motor can be predicted to be 702,000 won.

[0088] In this way, by evaluating the overall performance of the motor by applying weights to the performance of each component, more accurate product performance evaluation and price prediction are possible. By assigning weights according to the importance of each component, a motor price prediction model based on component performance data can be developed and utilized.

[0089] The processor (150) can train at least one second artificial intelligence model (500) to predict the price of a product by considering repair costs based on the performance of each component. The processor (150) can consider the repair cost of a component when the performance of each component is below a predefined standard.

[0090] For example, it is assumed that the base price of the motor is 1,000,000 won, and if the bearing performance is 50% or less, the bearing replacement cost is 100,000 won, and if the fan performance is 60% or less, the fan replacement cost is 50,000 won. When predicting the price of a motor with a bearing performance of 45% and a fan performance of 55%, the final price can be calculated by subtracting 150,000 from the predicted price.

[0091] According to one embodiment of the present invention, it is possible to accurately evaluate the actual condition of the motor based on performance data for each component. This is much more reliable than existing evaluation methods that rely on simple external condition or service life.

[0092] According to one embodiment of the present invention, both the buyer and the seller can clearly know the predicted performance of each part and the corresponding repair costs, thereby increasing the transparency of the transaction. This can enhance the reliability of the transaction and contribute to the revitalization of the used motor trading market.

[0093] According to one embodiment of the present invention, the buyer can predict and bear potential future repair costs, thereby reducing the occurrence of unexpected additional costs. The seller can secure market competitiveness by offering an appropriate price based on accurate performance evaluation.

[0094] According to one embodiment of the present invention, performance can be predicted in advance before a failure occurs and the product can be traded at an appropriate price, thereby reducing the disposal of substantially usable motors. This reduces resource waste and promotes recycling.

[0095] According to one embodiment of the present invention, the buyer can purchase a motor with guaranteed quality at a reasonable price, thereby increasing satisfaction, and the seller can conduct a fair transaction through accurate performance evaluation, thereby providing a satisfactory sales experience.

[0096] In this way, product price prediction considering component performance and repair costs through the first and second AI models can significantly improve the efficiency and reliability of transactions in the motor sector.

Claims

1. In an electronic device for evaluating the value of a product, Collecting first control data according to the activation of the first product, and Predicting the performance of each component of a first product corresponding to the first control data using at least one first artificial intelligence model trained to predict the performance of each component constituting a product based on the product's control data, and An electronic device comprising a processor that predicts the price of the first product using at least one second artificial intelligence model trained to predict the price of the product based on performance data of the product's components.

2. In Paragraph 1, The above-mentioned at least one second artificial intelligence model is, An electronic device characterized by being trained to predict the price of a product by assigning weights according to the importance of each component of the product.

3. In Paragraph 1, The above-mentioned at least one second artificial intelligence model is, An electronic device characterized by being trained to predict the price of a product by considering repair costs based on the performance of each component.

4. In Paragraph 1, The above-mentioned at least one second artificial intelligence model is, An electronic device characterized by being trained to predict the price of a product by considering transaction data of the above-mentioned product.

5. In Paragraph 1, The above processor is, An electronic device that generates notification information regarding the replacement of a part when the performance is predicted to be below a predefined value.

6. In Paragraph 1, The transaction data for the above product is, An electronic device containing product transaction prices for identical products and information regarding the products provided by the seller.

7. In a method for evaluating the value of a product performed by an electronic device, A step of collecting first control data according to the activation of the first product; A step of predicting the performance of each component of a first product corresponding to the first control data using at least one first artificial intelligence model trained to predict the performance of each component constituting the product based on the product's control data; A method comprising the step of predicting the price of the first product using at least one second artificial intelligence model trained to predict the price of the product based on performance data of the product's parts.

8. In Paragraph 7, The above-mentioned at least one second artificial intelligence model is, A method characterized by being trained to predict the price of a product by assigning weights according to the importance of each component of the product.

9. In Paragraph 7, The above-mentioned at least one second artificial intelligence model is, A method characterized by being trained to predict the price of a product by considering repair costs based on the performance of each component.

10. In Paragraph 7, The above-mentioned at least one second artificial intelligence model is, A method characterized by being trained to predict the price of a product by considering the transaction data of the above-mentioned product.

11. In Paragraph 7, A method further comprising the step of generating notification information regarding the replacement of a part for which performance is predicted to be below a predefined value.

12. In Paragraph 7, The transaction data for the above product is, A method including product transaction prices for identical products and information regarding products provided by the seller.

Images