system

Abstract

We provide the system. [Solution] A detection means for detecting weight, An evaluation means for evaluating inventory status based on detected weight data, An ordering method that automatically places an order when inventory falls below a set threshold, Analytical means for identifying products whose demand is expected to increase by analyzing social trends, A planning means that provides a plan for securing inventory of specified products in advance, A means of communication for users to check inventory information in real time and make inquiries, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern distribution and retail industries, inefficiency in inventory management has become an important issue. In particular, due to fluctuations in demand and unpredictable purchasing behavior of consumers, opportunity losses due to overstocking or shortage of inventory are likely to occur. These problems can reduce the efficiency of business processes and may lead to a decrease in revenue. The purpose of this invention is to solve such inefficiencies in inventory management and the difficulty of demand forecasting.

Means for Solving the Problems

[0005] This invention provides a detection means for detecting weight, and continuously monitors the weight of products using sensors installed on the shelf floor. It includes an ordering means that evaluates the inventory status based on the detected weight data and automatically places an order if it falls below a set threshold. Furthermore, by using a prediction means that analyzes past sales information and social trend information, it identifies products that are expected to have high demand and plans to secure inventory accordingly. In addition, by obtaining and analyzing user feedback, it is possible to improve the product lineup and services. This enables efficient and dynamic inventory management.

[0006] "Detection means" refers to a device or group of devices that detects the weight of a product using sensors installed on the floor of the shelf.

[0007] "Evaluation means" refers to a device or program that has the function of analyzing and evaluating the current inventory status based on weight data obtained by the detection means.

[0008] An "ordering device" refers to a device or system that has the function of automatically placing an order for replenishment when the evaluation device detects a decrease in inventory.

[0009] A "predictive tool" refers to a device or program that analyzes past sales data and social trend information to identify products that are expected to see increased demand in the future.

[0010] A "planning device" refers to a device or system that has the function of creating a plan to secure inventory in advance for products identified by a "prediction device."

[0011] "Means of acquisition" refers to methods, devices, or systems for obtaining opinions from users.

[0012] "Analysis tools" refer to devices or programs that have the function of effectively analyzing acquired user opinions and utilizing that information to improve product lineups and services. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is designed to provide an efficient inventory management system for retail stores. Key elements of the inventory management system include weight sensors, a data analysis server, user terminals, and an AI chatbot.

[0035] Specifically, the terminal periodically detects the weight of products using weight sensors installed on the shelf floor. This weight data is transmitted to a server via a communication method. The server analyzes the received data and evaluates the inventory level. Based on this evaluation, if the inventory level falls below a set threshold, the system automatically generates an order. The order is then electronically transmitted to the supplier.

[0036] Furthermore, the server utilizes generational AI to analyze past sales data and information on social trends. This analysis allows it to identify products that are predicted to see increased demand in the future. Based on this, the server can formulate a pre-inventory plan and automatically link it to placing orders.

[0037] Furthermore, store employees, who are also users, can check inventory information in real time via the AI ​​chatbot. For example, if a user asks the AI ​​chatbot, "What is the inventory status of a specific model?", the server retrieves the current status from the inventory database and immediately provides information such as, "There are 7 units left." Also, when a user changes models, the user's terminal collects feedback through a questionnaire, and the server can analyze this feedback to help improve the product.

[0038] Thus, this system highly automates inventory management, has the ability to flexibly respond to market demand trends, and supports efficient operations.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The terminal collects weight data in real time from weight sensors installed on the shelf floor. The terminal periodically updates this data and prepares it to be sent to the server.

[0042] Step 2:

[0043] The server receives weight data sent from the terminal. After receiving the data, it calculates the inventory quantity based on the weight of each product unit. This calculation is programmed to reflect the exact inventory quantity of each product.

[0044] Step 3:

[0045] The server compares the calculated inventory quantity with a pre-set threshold. If the inventory falls below the threshold, the server automatically creates an order.

[0046] Step 4:

[0047] The server sends the generated order instructions to the supplier. Digital communication methods such as email or APIs are used for transmission.

[0048] Step 5:

[0049] The server uses generative AI to analyze historical sales data and current social trend data. This analysis identifies products that are expected to see increased demand in the future.

[0050] Step 6:

[0051] The server creates an inventory pre-order plan based on demand forecast information. Based on this plan, it places additional orders to meet the predicted demand.

[0052] Step 7:

[0053] If a user wants to obtain inventory information via an AI chatbot, they will make a natural language inquiry from their device. This inquiry might take the form of, for example, "What is the inventory status of a specific model?"

[0054] Step 8:

[0055] The server receives a user inquiry, consults the current inventory database, and retrieves the appropriate information. After collecting the information, the server sends the results to the user's terminal via an AI chatbot to provide an answer.

[0056] Step 9:

[0057] The device collects survey responses from users when they switch to a new model. The collected opinions are sent from the device to a server and used to improve the product lineup and services.

[0058] Step 10:

[0059] The server analyzes the received survey results and extracts trends and areas for improvement. Based on this data, it provides reports to the product development team and marketing department to be used in product strategy.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Traditional inventory management systems struggled to respond flexibly to fluctuations in product demand, leading to risks of stockouts and increased costs due to excess inventory. Furthermore, there was a lack of effective means to utilize collected customer feedback for product improvement. Additionally, real-time inventory monitoring was difficult, hindering the efficiency of store operations.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes measuring means for detecting product weight, analysis means for evaluating inventory based on the measured data, and learning means for analyzing past transaction history and market trends. This enables appropriate inventory management based on demand forecasts and reduces the risk of stockouts through automated ordering. Furthermore, by analyzing collected feedback and reflecting it in product improvements, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0065] "Measuring means" refers to devices or methods for accurately detecting the weight of a product.

[0066] "Analysis means" refers to a system for processing measured data and evaluating inventory status.

[0067] "Control means" refers to a mechanism that automatically replenishes products when inventory falls below a set threshold.

[0068] "Learning tools" refer to algorithms and programs used to analyze past trading history and market trends.

[0069] "Identification means" refers to a method for identifying products whose demand will increase based on the results of learning means.

[0070] "Planning measures" refer to strategies and methods for securing advance inventory for identified goods.

[0071] "Opinion gathering means" refers to technology for obtaining user opinions based on generated prompts.

[0072] "Analysis tools" refer to a system that processes collected user feedback to identify areas for improvement in a product or service.

[0073] "Information provision means" refers to a method of obtaining inventory information in real time using communication technology and providing information necessary for store operations.

[0074] "Communication methods" refer to technologies used to transmit necessary instructions to store operators and systems based on acquired inventory information.

[0075] This system is designed to provide advanced inventory management, primarily for use in retail stores. The equipment necessary for implementing this invention includes a terminal equipped with a weight-measuring sensor, a server for data analysis and management, and a terminal to support information exchange with users.

[0076] The terminal uses weight sensors installed on the shelves to detect the weight of products in real time. This data is transmitted to a server using wireless communication technology. Wi-Fi modules and Bluetooth are commonly used for this purpose.

[0077] The server utilizes a database management system and data analysis software to calculate the inventory quantity of products using the received weight data. Big data analysis tools such as Hadoop and Spark are expected to be used. When the calculated inventory quantity falls below a pre-set threshold, the server automatically places a replenishment order with the supplier using EDI (Electronic Data Interchange System).

[0078] Furthermore, the server utilizes a generative AI model to analyze historical sales data and current social trend data. This analysis is crucial for predicting demand and securing inventory in advance. Specifically, a deep learning model using the TENSORFLOW® library in Python is employed.

[0079] Store employees, acting as users, can check inventory information via an AI chatbot using a dedicated terminal or PC. For example, if they enter a question such as "What is the stock of the NX100 model?" as a text prompt into the chatbot, the server will retrieve the information from the database and return an answer immediately.

[0080] As a concrete example of its use, the server can proactively identify products whose demand is expected to increase during the Christmas season and facilitate additional replenishment. This enables proper inventory management and prevents lost sales opportunities due to stockouts. Furthermore, users can review survey results based on collected customer feedback and see how that feedback can be used in future product development.

[0081] Thus, the system of the present invention utilizes the latest technology to improve the efficiency and accuracy of inventory management and enable rapid response to fluctuations in market demand.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The terminal detects the weight of the products using weight sensors installed on the shelves. It receives the current weight data of the products as input, and the sensors convert it into a digital value. The converted weight data is then transmitted to the server via a wireless communication module. This process captures the latest status of the products on the shelves in data format.

[0085] Step 2:

[0086] The server calculates the inventory quantity based on the received weight data. The input is weight data sent from the terminal, and the output generates calculated inventory quantity data. The database management system calculates the total inventory quantity using the unit weight of the products. This data is stored in the inventory database, contributing to accurate inventory management.

[0087] Step 3:

[0088] The server uses analytical tools to analyze past sales data and market trends to predict demand fluctuations. Inputs are historical transaction history and external data, and output is a predicted list of products with potentially increasing demand. The analysis is performed using a generative AI model, such as the TensorFlow library, and the results are used to inform future sales strategies.

[0089] Step 4:

[0090] The server uses forecast information to develop a plan for securing advance stock of specific products. The input is the demand forecast list obtained in step 3, and the output is a specific ordering plan. The automated ordering system is activated and requests the supplier to replenish the necessary products via the EDI system. This action is taken as a preventative measure to prevent stockouts.

[0091] Step 5:

[0092] A user (store employee) inquires about inventory status via a terminal using an AI chatbot. The input is a prompt such as "How much stock do you have of the NX100 model?", and the output is inventory information. The server refers to a database and provides the user with specific inventory figures in real time via the chatbot.

[0093] Step 6:

[0094] Users send opinions and feedback collected from customers to a server, which analyzes the data to improve products. Inputs are customer survey data and feedback, and output is suggested improvements. The analysis is performed using natural language processing technology and provided to the product team. This enables product development that meets customer needs.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] Traditional inventory management systems struggled to track product inventory levels in real time and create flexible inventory plans based on demand fluctuations. In particular, when demand for a product surged due to social trends or other factors, it was difficult to replenish inventory at the appropriate time, leading to missed sales opportunities. Furthermore, the inability for users to quickly access inventory information created a need for increased efficiency in store operations.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes detection means for detecting weight, analysis means for analyzing social trends to identify products expected to see increased demand, and dialogue means for users to check inventory information in real time and make inquiries. This enables accurate understanding of product inventory status and rapid, flexible inventory management in response to fluctuations in demand.

[0100] "Detection means" refers to equipment or a mechanism for continuously measuring the weight of goods and understanding their inventory status.

[0101] "Evaluation means" refers to a system or algorithm for analyzing and determining the current inventory status based on weight data obtained from detection means.

[0102] An "ordering mechanism" is a function or process that automatically places an additional order when inventory falls below a predetermined threshold.

[0103] "Analysis means" refers to a function or system that analyzes social trends and past data to identify products that are predicted to see increased demand in the future.

[0104] "Planning means" refers to a function or system for formulating strategies to secure inventory in advance of products for which demand is expected to increase, as identified by analytical means.

[0105] A "dialogue mechanism" is a user interface that allows users to easily check inventory information in real time and make inquiries to the automated system as needed.

[0106] This invention's system combines multiple technological elements to streamline inventory management. First, a terminal periodically measures the weight of each product through weight sensors installed on the shelves. The measured weight data is transmitted to a server via a communication means. The server uses this data to evaluate the inventory status and identify which products are below a certain level.

[0107] Regarding the ordering process, the server automatically generates order instructions for products whose inventory levels fall below a certain threshold and sends them to suppliers. This enables timely inventory replenishment. In addition, the server analyzes social trends and past sales data to identify products for which demand is expected to increase in the future. AI-powered analysis is used, and based on this, a planning system develops a pre-emptive inventory securing plan.

[0108] Furthermore, users can obtain real-time inventory information through an AI chatbot. By entering prompts such as "Tell me the inventory status of a specific model" into the chatbot, the server will quickly provide the information. In addition, when users provide feedback, the system acquires and analyzes that feedback to help improve the product lineup and services.

[0109] As a concrete example, this can function as a smart assistant for inventory management used in physical stores, allowing store employees to easily check the status of products using their smartphones and manage inventory in anticipation of future demand. Furthermore, by using generative AI models, it becomes possible to perform data analysis that reflects social trends.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The terminal periodically acquires product weight data from weight sensors installed on the shelves. The input is an analog signal from the weight sensor, which is converted into digital data and sent to the server as a data packet along with product identification information.

[0113] Step 2:

[0114] The server receives weight data transmitted from the terminal. The input is a data packet, which is then compared with product information stored in the database to calculate the inventory quantity. For data processing, the server compares the standard weight of each product with the data from the sensor to evaluate the current inventory quantity.

[0115] Step 3:

[0116] The server automatically generates an order instruction when the calculated inventory level falls below a threshold. The output of the ordering process is order information sent to the supplier. This information includes product identification, required quantity, delivery date, etc., and is sent via email or electronic data interchange (EDI).

[0117] Step 4:

[0118] The server uses a generative AI model to analyze historical sales data and social trend information to identify products that will see increased demand in the future. Its inputs are sales history and trend data, which it analyzes to output predictive data. Data calculations include time series analysis and machine learning algorithms.

[0119] Step 5:

[0120] The server creates an inventory pre-ordering plan based on identified demand forecasts. The input is forecast data, and the output plan takes into account the store's current inventory status and supply-demand balance. Specifically, it determines the timing of inventory adjustments and new orders.

[0121] Step 6:

[0122] Users can inquire about inventory information in real time via an AI chatbot. The prompts sent by users are such as "Tell me the inventory status of a specific model," and the server responds by outputting the current inventory number as a text message.

[0123] Step 7:

[0124] User feedback is sent to the server via the terminal. The server receives the input feedback and analyzes it using text analysis techniques. The resulting analysis results are used as feedback to improve the product lineup and services.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention is a system designed to streamline inventory management in stores and improve the user experience. The system includes weight sensors, a data analysis server, a user terminal, an AI chatbot, and an emotion engine.

[0127] Specifically, the terminal continuously detects the weight of products using weight sensors installed on the shelf floor. The collected weight data is sent to a server, which then evaluates the inventory status based on it. If the evaluation indicates that inventory falls below a set threshold, the server automatically generates an order and sends it electronically to the supplier. This entire process prevents inventory shortages and enables appropriate product replenishment.

[0128] Furthermore, the server uses generative AI technology to analyze past sales data and trend information to predict which products will see increased demand in the future. Based on these predictions, a plan is created to secure inventory in advance, thereby ensuring that sales opportunities are not missed.

[0129] A unique feature of this invention is the incorporation of an emotion engine into the system. The terminal analyzes the user's voice and facial expressions using the emotion engine and sends the data to the server. Based on the obtained emotion data, the server adaptively adjusts the user experience to improve satisfaction. For example, if the user shows a dissatisfied expression, the system detects this and immediately provides a special support message.

[0130] For example, when a user asks an AI chatbot a question about a product, the emotion engine analyzes the user's tone of voice and facial expressions. If the server detects that the user is confused, it provides more detailed explanations or extra support.

[0131] This system not only improves inventory management but also significantly enhances the quality of in-store interactions, increasing customer satisfaction and the likelihood of repeat visits.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The device acquires weight data in real time from weight sensors installed on the shelf floor. The data is set to be updated at regular time intervals.

[0135] Step 2:

[0136] The device transmits the acquired weight data to the server using a communication method. The transmitted data is encrypted and transferred securely.

[0137] Step 3:

[0138] The server analyzes the weight data it receives and calculates the inventory quantity. The calculation results are designed to accurately reflect the current inventory status.

[0139] Step 4:

[0140] The server compares the inventory level to a set threshold. If the inventory falls below the threshold, the server automatically generates an order.

[0141] Step 5:

[0142] The server electronically sends order instructions to suppliers. This transmission is done via email or API.

[0143] Step 6:

[0144] The server uses generated AI to analyze historical sales data and trend information. This analysis identifies products that are likely to see increased demand in the future.

[0145] Step 7:

[0146] The server develops a plan to systematically secure inventory based on predicted demand. Additional orders are placed based on this plan.

[0147] Step 8:

[0148] The device acquires emotional data from the user's voice and facial expressions. The acquired data is then analyzed by an emotion engine.

[0149] Step 9:

[0150] The server receives emotion data and adjusts the user experience accordingly. For example, if a negative emotion is detected, it provides a special support message.

[0151] Step 10:

[0152] When a user inquires about information via an AI chatbot, communication takes place in natural language. While the emotion engine analyzes the user's emotions, the server generates and provides an appropriate response to the user.

[0153] (Example 2)

[0154] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0155] The challenges lie in improving the efficiency of inventory management and enhancing the consumer experience. Traditional systems failed to adequately track inventory levels and forecast future demand, resulting in lost opportunities due to excess or insufficient stock. Furthermore, providing services that reflected user emotions and opinions was difficult, hindering improvements in consumer satisfaction.

[0156] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0157] In this invention, the server includes a sensor means for detecting weight, an evaluation means for evaluating the inventory status based on the detected weight information, an ordering means for automatically placing an order when the inventory falls below a set threshold, an analysis means using a generative AI model for analyzing past sales information and trend information, an emotion analysis means for analyzing the emotional state of the user, and an improvement means for adjusting the user experience based on the analysis results. This enables improved accuracy in inventory management, appropriate product supply, and optimization of the consumer experience.

[0158] "Sensing means" is a general term for devices and technologies used to detect the weight of a product.

[0159] "Evaluation methods" refer to the process of analyzing inventory status based on detected weight information and implementing appropriate management.

[0160] An "ordering method" refers to a method or system for automatically generating an order instruction and notifying the supplier when inventory falls below a set threshold.

[0161] A "generative AI model" is an artificial intelligence technology that uses past sales and trend information to analyze and predict future demand.

[0162] "Analysis methods" refer to techniques and technologies that utilize generative AI models to perform data analysis and obtain useful information.

[0163] "Emotional analysis methods" refer to technologies and systems that read and analyze a user's emotional state from their voice and facial expressions.

[0164] "Improvement measures" refer to strategies and measures to optimize the user experience and improve the service based on the analyzed data.

[0165] This invention is a system that improves the efficiency of inventory management in stores and optimizes the user experience. The specific system configuration includes sensors for detecting weight, a server for collecting and analyzing data, and a terminal for user use. Furthermore, it is equipped with a generative AI model and an emotion analysis engine, which are used in conjunction with each other.

[0166] The terminal continuously detects the weight of the product via weight sensors installed on the shelf floor. This weight data is first collected by the terminal and then transmitted in real time to a server via the internet.

[0167] The server evaluates the inventory status based on the received data. This evaluation includes an algorithm that determines if inventory is insufficient when it falls below a set threshold, and automatically places an order. The server also utilizes a generative AI model to analyze past sales data and social trend information. This analysis predicts future demand, and a plan is created to secure inventory in advance based on the results.

[0168] Furthermore, this system is equipped with an emotion analysis engine. The terminal detects the user's voice and facial expressions and sends this as emotion data to the server. The server then analyzes this data and provides adaptive user services tailored to the user's emotions. For example, if the system detects that the user is feeling dissatisfied, it immediately generates and presents a special support message.

[0169] As a concrete example, consider a scenario where a user asks an AI chatbot a question about a product. In this case, the user can input a prompt into the generative AI model such as, "Predict which products are likely to see increased demand in the next month. Specify the necessary historical dataset and explain your reasoning."

[0170] By adopting this system, the accuracy of inventory management will improve, and high-quality customer service will be provided along with the appropriate supply of goods, thereby improving both the operational efficiency of stores and customer satisfaction.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The device uses a weight sensor to detect the weight of the product.

[0174] Input: The physical weight of the product on the shelf.

[0175] Processing: A weight sensor measures the weight of the product and records the value as digital data.

[0176] Output: Detected weight data.

[0177] Step 2:

[0178] The device sends the collected weight data to the server.

[0179] Input: Detected weight data.

[0180] Processing: The terminal uses network protocols to packetize the data and send it to the server over the internet.

[0181] Output: Weight data sent to the server.

[0182] Step 3:

[0183] The server evaluates the inventory status based on the weight data it receives.

[0184] Input: Weight data sent to the server.

[0185] Processing: The server queries the database, calculates the current inventory level, and compares it to the set baseline value.

[0186] Output: Current inventory status report.

[0187] Step 4:

[0188] The server generates an order instruction when inventory falls below a certain threshold.

[0189] Input: Inventory status report.

[0190] Processing: The automated ordering algorithm determines the required order quantity based on the inventory shortage and generates an order instruction.

[0191] Output: Order instructions to suppliers.

[0192] Step 5:

[0193] The server uses a generated AI model to perform demand forecasting.

[0194] Input: Past sales data and trend information.

[0195] Processing: The generative AI model analyzes the input data and predicts future demand.

[0196] Output: Forecasted demand data.

[0197] Step 6:

[0198] The server creates an inventory management plan based on demand forecasts.

[0199] Input: Forecasted demand data.

[0200] Processing: The server analyzes the prediction results and develops a future inventory replenishment plan.

[0201] Output: Inventory securing plan.

[0202] Step 7:

[0203] The device uses an emotion analysis engine to analyze the user's voice and facial expressions.

[0204] Input: User's voice and facial expression data.

[0205] Processing: The device uses its camera and microphone to capture data and performs analysis to determine the emotional state.

[0206] Output: User sentiment data.

[0207] Step 8:

[0208] The server optimizes the user experience based on sentiment data.

[0209] Input: User sentiment data.

[0210] Processing: The server analyzes sentiment data and generates personalized services and support messages for the user.

[0211] Output: Optimized user experience information.

[0212] (Application Example 2)

[0213] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0214] A system is needed that balances efficient inventory management with an improved consumer experience. Insufficient inventory and a lack of accurate supply and demand forecasting can lead to missed sales opportunities. Furthermore, the in-store user experience often lacks emotionally responsiveness, resulting in decreased customer satisfaction and reduced willingness to return.

[0215] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0216] In this invention, the server includes detection means for detecting weight, emotion analysis means, and forecasting means for predicting demand based on past sales information and social trend information. This enables more efficient inventory management and an improved consumer experience through the provision of services adapted to the user's emotions.

[0217] A "detection means" is a mechanism for measuring weight and making that information available within the system.

[0218] "Evaluation method" refers to the process of analyzing detected weight data to determine the inventory status.

[0219] An "ordering system" is a system that automatically places orders for necessary products when inventory levels fall below a set threshold.

[0220] An "emotion analysis tool" is a mechanism that analyzes emotions from users' voices, facial expressions, etc., and supports the provision of adaptive services.

[0221] "Predictive methods" refer to the process of forecasting future demand based on past sales data and social trend information, and formulating appropriate inventory plans.

[0222] A "planning tool" is a system that provides strategies for efficiently managing inventory based on demand identified by a forecasting tool.

[0223] "Methods of acquisition" refers to the process of collecting feedback and opinions from users.

[0224] "Analysis methods" refer to techniques used to analyze user feedback and identify areas for improvement in products and services.

[0225] "Information provision methods" refer to the process of providing information optimized according to the user's emotional state in order to improve the customer experience.

[0226] This application is implemented in a system aimed at improving inventory management and user experience in physical stores. The system includes weight sensors, an emotion analysis engine, a data analysis server, and a user terminal.

[0227] The server collects data from weight sensors installed on product shelves and uses this information to evaluate inventory levels. If inventory levels fall below a set threshold, the server activates a program that automatically issues reorders via the cloud system. Weight data analysis utilizes a common database management system and scripting language running on a cloud platform.

[0228] Furthermore, the server utilizes the smartphone's camera and microphone, as well as an AI-powered emotion analysis engine, to perform advanced analysis of the user's emotions. When the user uses their smartphone, voice and facial expression data are captured and processed by the emotion analysis model. Once the emotion data is sent to the server, generative AI technology provides information and support tailored to the user.

[0229] As a concrete example, when a user makes a product inquiry in a store, a smartphone AI chatbot provides relevant information. In this case, the chatbot analyzes the user's emotions from their voice tone and facial expressions, and if anxiety is detected, it provides more detailed explanations or similar products.

[0230] The following are examples of prompts to input into a generative AI model:

[0231] Dissatisfaction was detected from the user's facial expression. Please provide the following supplementary product information: Product name. Customer inquiry: Inquiry details. Please suggest additional information and similar products.

[0232] By combining these technologies, it becomes possible to improve the accuracy of inventory management in physical stores and to individually optimize the customer experience.

[0233] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0234] Step 1:

[0235] The terminal acquires data in real time from weight sensors placed on product shelves. The input is weight data obtained from the sensors. This data is periodically sent to a server, providing raw data to understand the current inventory status.

[0236] Step 2:

[0237] The server analyzes weight data and evaluates inventory levels. The evaluation uses an analysis algorithm running on a database system. Input is weight data sent from the terminal, and output is numerical information about inventory levels. A purchase order is generated when the inventory level falls below a set threshold.

[0238] Step 3:

[0239] The server incorporates historical sales data and trend information to perform demand forecasting. Using a data analysis-based algorithm, it forecasts demand for a specific period based on the input data. The output is a list of products predicted to experience increased demand. This information is used as a planning tool to create a plan for securing inventory in advance.

[0240] Step 4:

[0241] The terminal uses the user's smartphone camera and microphone to acquire the user's voice and facial expression data. The input is voice and video data. After pre-processing for emotion analysis, this data is sent to the server.

[0242] Step 5:

[0243] The server processes the received voice and facial expression data using an emotion analysis engine to determine the user's emotions. Input consists of voice and facial expression data acquired from the terminal, and output is fed back to the system as emotion data. This data is used to improve real-time services.

[0244] Step 6:

[0245] The server uses a generative AI model to provide users with optimal information based on analyzed sentiment data. Inputs are analyzed sentiment data and product information. It generates prompts, and the output is personalized information presented to the user via an AI chatbot.

[0246] Throughout the system, efficient data processing and analysis are performed to optimize inventory management and user experience.

[0247] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0248] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0249] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0250] [Second Embodiment]

[0251] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0252] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0253] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0254] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0255] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0256] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0257] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0258] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0259] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0260] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0261] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0262] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0263] This invention is designed to provide an efficient inventory management system for retail stores. Key elements of the inventory management system include weight sensors, a data analysis server, user terminals, and an AI chatbot.

[0264] Specifically, the terminal periodically detects the weight of products using weight sensors installed on the shelf floor. This weight data is transmitted to a server via a communication method. The server analyzes the received data and evaluates the inventory level. Based on this evaluation, if the inventory level falls below a set threshold, the system automatically generates an order. The order is then electronically transmitted to the supplier.

[0265] Furthermore, the server utilizes generational AI to analyze past sales data and information on social trends. This analysis allows it to identify products that are predicted to see increased demand in the future. Based on this, the server can formulate a pre-inventory plan and automatically link it to placing orders.

[0266] Furthermore, store employees, who are also users, can check inventory information in real time via the AI ​​chatbot. For example, if a user asks the AI ​​chatbot, "What is the inventory status of a specific model?", the server retrieves the current status from the inventory database and immediately provides information such as, "There are 7 units left." Also, when a user changes models, the user's terminal collects feedback through a questionnaire, and the server can analyze this feedback to help improve the product.

[0267] Thus, this system highly automates inventory management, has the ability to flexibly respond to market demand trends, and supports efficient operations.

[0268] The following describes the processing flow.

[0269] Step 1:

[0270] The terminal collects weight data in real time from weight sensors installed on the shelf floor. The terminal periodically updates this data and prepares it to be sent to the server.

[0271] Step 2:

[0272] The server receives weight data sent from the terminal. After receiving the data, it calculates the inventory quantity based on the weight of each product unit. This calculation is programmed to reflect the exact inventory quantity of each product.

[0273] Step 3:

[0274] The server compares the calculated inventory quantity with a preset threshold. If the inventory is below the threshold as a result of the comparison, the server automatically creates a purchase order instruction.

[0275] Step 4:

[0276] The server sends the generated purchase order instruction to the supplier. Digital communication means such as email or API are used as the transmission method.

[0277] Step 5:

[0278] The server uses generative AI to analyze past sales data and current social trend data. This analysis identifies products whose demand is expected to increase in the future.

[0279] Step 6:

[0280] Based on the demand prediction information, the server creates a pre-arrangement plan for inventory. Additional purchase orders are placed based on this plan to meet the predicted demand.

[0281] Step 7:

[0282] If the user wants to obtain inventory information via the AI chatbot, the user makes a natural language inquiry from the user terminal. This inquiry is made in the form of, for example, "What is the inventory status of a specific model?"

[0283] Step 8:

[0284] The server receives the inquiry from the user, retrieves appropriate information by referring to the current inventory database. After collecting the information, the server sends the result to the terminal via the AI chatbot to answer the user.

[0285] Step 9:

[0286] The terminal collects questionnaires from users when the device model is changed. The collected opinions are sent from the terminal to the server and used to improve the product lineup and services.

[0287] Step 10:

[0288] The server analyzes the received questionnaire results and extracts trends and improvement points. Based on this data, it provides a report to the product development team and the marketing department and utilizes it for product strategies.

[0289] (Example 1)

[0290] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0291] In the conventional inventory management system, it was difficult to flexibly respond to changes in demand for products, and there were problems such as the risk of out-of-stock of necessary products and an increase in costs due to excessive inventory. In addition, there was a lack of effective means to utilize the opinions of users collected for product improvement. Furthermore, it was difficult to grasp the inventory status in real time, which sometimes hindered the efficiency of store operations.

[0292] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0293] In this invention, the server includes a measurement means for detecting the weight of a product, an analysis means for evaluating the inventory based on the measured data, and a learning means for analyzing past transaction histories and market trends. As a result, appropriate inventory management based on demand prediction and reduction of the risk of out-of-stock due to automatic ordering become possible. In addition, by analyzing the collected opinions and reflecting them in product improvement, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0294] The "measurement means" refers to a device or method for accurately detecting the weight of a product.

[0295] "Analysis means" refers to a system for processing measured data and evaluating inventory status.

[0296] "Control means" refers to a mechanism that automatically replenishes products when inventory falls below a set threshold.

[0297] "Learning tools" refer to algorithms and programs used to analyze past trading history and market trends.

[0298] "Identification means" refers to a method for identifying products whose demand will increase based on the results of learning means.

[0299] "Planning measures" refer to strategies and methods for securing advance inventory for identified goods.

[0300] "Opinion gathering means" refers to technology for obtaining user opinions based on generated prompts.

[0301] "Analysis tools" refer to a system that processes collected user feedback to identify areas for improvement in a product or service.

[0302] "Information provision means" refers to a method of obtaining inventory information in real time using communication technology and providing information necessary for store operations.

[0303] "Communication methods" refer to technologies used to transmit necessary instructions to store operators and systems based on acquired inventory information.

[0304] This system is designed to provide advanced inventory management, primarily for use in retail stores. The equipment necessary for implementing this invention includes a terminal equipped with a weight-measuring sensor, a server for data analysis and management, and a terminal to support information exchange with users.

[0305] The terminal uses a weight sensor installed on the shelf to detect the weight of the product in real time. This data is transmitted to the server using wireless communication technology. Here, Wi-Fi modules and Bluetooth are often used.

[0306] The server utilizes a database management system and data analysis software to calculate the inventory quantity of the product using the received weight data. Big data analysis tools such as Hadoop and Spark are expected to be used. When the calculated inventory quantity falls below a pre-set standard, the server automatically places a replenishment order to the supplier using EDI (Electronic Data Interchange System).

[0307] Furthermore, the server utilizes a generative AI model to analyze past sales data and current social trend data. This analysis is important for predicting demand and securing inventory in advance. Specifically, a deep learning model using the TensorFlow library in Python is utilized.

[0308] The store clerk, who is the user, can use a dedicated terminal or PC to check the inventory information via an AI chatbot. For example, when a question like "What is the inventory of the NX100 model?" is entered as a text prompt into the chatbot, the server retrieves information from the database and returns an answer immediately.

[0309] As a specific example of utilization, the server can identify in advance products whose demand is predicted to increase towards the Christmas season and promote additional replenishment. This enables appropriate inventory management and prevents opportunity losses due to out-of-stock situations. Also, the user can review the questionnaire results based on the collected customer opinions and check how those feedbacks can be utilized for the next product development.

[0310] In this way, the system of the present invention utilizes the latest technologies, enabling efficient inventory management, improved accuracy, and rapid response to market demand fluctuations.

[0311] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0312] Step 1:

[0313] The terminal detects the weight of the products using weight sensors installed on the shelves. It receives the current weight data of the products as input, and the sensors convert it into a digital value. The converted weight data is then transmitted to the server via a wireless communication module. This process captures the latest status of the products on the shelves in data format.

[0314] Step 2:

[0315] The server calculates the inventory quantity based on the received weight data. The input is weight data sent from the terminal, and the output generates calculated inventory quantity data. The database management system calculates the total inventory quantity using the unit weight of the products. This data is stored in the inventory database, contributing to accurate inventory management.

[0316] Step 3:

[0317] The server uses analytical tools to analyze past sales data and market trends to predict demand fluctuations. Inputs are historical transaction history and external data, and output is a predicted list of products with potentially increasing demand. The analysis is performed using a generative AI model, such as the TensorFlow library, and the results are used to inform future sales strategies.

[0318] Step 4:

[0319] The server uses forecast information to develop a plan for securing advance stock of specific products. The input is the demand forecast list obtained in step 3, and the output is a specific ordering plan. The automated ordering system is activated and requests the supplier to replenish the necessary products via the EDI system. This action is taken as a preventative measure to prevent stockouts.

[0320] Step 5:

[0321] A user (store employee) inquires about inventory status via a terminal using an AI chatbot. The input is a prompt such as "How much stock do you have of the NX100 model?", and the output is inventory information. The server refers to a database and provides the user with specific inventory figures in real time via the chatbot.

[0322] Step 6:

[0323] Users send opinions and feedback collected from customers to a server, which analyzes the data to improve products. Inputs are customer survey data and feedback, and output is suggested improvements. The analysis is performed using natural language processing technology and provided to the product team. This enables product development that meets customer needs.

[0324] (Application Example 1)

[0325] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0326] Traditional inventory management systems struggled to track product inventory levels in real time and create flexible inventory plans based on demand fluctuations. In particular, when demand for a product surged due to social trends or other factors, it was difficult to replenish inventory at the appropriate time, leading to missed sales opportunities. Furthermore, the inability for users to quickly access inventory information created a need for increased efficiency in store operations.

[0327] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0328] In this invention, the server includes detection means for detecting weight, analysis means for analyzing social trends to identify products expected to see increased demand, and dialogue means for users to check inventory information in real time and make inquiries. This enables accurate understanding of product inventory status and rapid, flexible inventory management in response to fluctuations in demand.

[0329] "Detection means" refers to equipment or a mechanism for continuously measuring the weight of goods and understanding their inventory status.

[0330] "Evaluation means" refers to a system or algorithm for analyzing and determining the current inventory status based on weight data obtained from detection means.

[0331] An "ordering mechanism" is a function or process that automatically places an additional order when inventory falls below a predetermined threshold.

[0332] "Analysis means" refers to a function or system that analyzes social trends and past data to identify products that are predicted to see increased demand in the future.

[0333] "Planning means" refers to a function or system for formulating strategies to secure inventory in advance of products for which demand is expected to increase, as identified by analytical means.

[0334] A "dialogue mechanism" is a user interface that allows users to easily check inventory information in real time and make inquiries to the automated system as needed.

[0335] This invention's system combines multiple technological elements to streamline inventory management. First, a terminal periodically measures the weight of each product through weight sensors installed on the shelves. The measured weight data is transmitted to a server via a communication means. The server uses this data to evaluate the inventory status and identify which products are below a certain level.

[0336] Regarding the ordering process, the server automatically generates order instructions for products whose inventory levels fall below a certain threshold and sends them to suppliers. This enables timely inventory replenishment. In addition, the server analyzes social trends and past sales data to identify products for which demand is expected to increase in the future. AI-powered analysis is used, and based on this, a planning system develops a pre-emptive inventory securing plan.

[0337] Furthermore, users can obtain real-time inventory information through an AI chatbot. By entering prompts such as "Tell me the inventory status of a specific model" into the chatbot, the server will quickly provide the information. In addition, when users provide feedback, the system acquires and analyzes that feedback to help improve the product lineup and services.

[0338] As a concrete example, this can function as a smart assistant for inventory management used in physical stores, allowing store employees to easily check the status of products using their smartphones and manage inventory in anticipation of future demand. Furthermore, by using generative AI models, it becomes possible to perform data analysis that reflects social trends.

[0339] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0340] Step 1:

[0341] The terminal periodically acquires product weight data from weight sensors installed on the shelves. The input is an analog signal from the weight sensor, which is converted into digital data and sent to the server as a data packet along with product identification information.

[0342] Step 2:

[0343] The server receives weight data transmitted from the terminal. The input is a data packet, which is then compared with product information stored in the database to calculate the inventory quantity. For data processing, the server compares the standard weight of each product with the data from the sensor to evaluate the current inventory quantity.

[0344] Step 3:

[0345] The server automatically generates an order instruction when the calculated inventory level falls below a threshold. The output of the ordering process is order information sent to the supplier. This information includes product identification, required quantity, delivery date, etc., and is sent via email or electronic data interchange (EDI).

[0346] Step 4:

[0347] The server uses a generative AI model to analyze historical sales data and social trend information to identify products that will see increased demand in the future. Its inputs are sales history and trend data, which it analyzes to output predictive data. Data calculations include time series analysis and machine learning algorithms.

[0348] Step 5:

[0349] The server creates an inventory pre-ordering plan based on identified demand forecasts. The input is forecast data, and the output plan takes into account the store's current inventory status and supply-demand balance. Specifically, it determines the timing of inventory adjustments and new orders.

[0350] Step 6:

[0351] Users can inquire about inventory information in real time via an AI chatbot. The prompts sent by users are such as "Tell me the inventory status of a specific model," and the server responds by outputting the current inventory number as a text message.

[0352] Step 7:

[0353] User feedback is sent to the server via the terminal. The server receives the input feedback and analyzes it using text analysis techniques. The resulting analysis results are used as feedback to improve the product lineup and services.

[0354] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0355] This invention is a system designed to streamline inventory management in stores and improve the user experience. The system includes weight sensors, a data analysis server, a user terminal, an AI chatbot, and an emotion engine.

[0356] Specifically, the terminal continuously detects the weight of products using weight sensors installed on the shelf floor. The collected weight data is sent to a server, which then evaluates the inventory status based on it. If the evaluation indicates that inventory falls below a set threshold, the server automatically generates an order and sends it electronically to the supplier. This entire process prevents inventory shortages and enables appropriate product replenishment.

[0357] Furthermore, the server uses generative AI technology to analyze past sales data and trend information to predict which products will see increased demand in the future. Based on these predictions, a plan is created to secure inventory in advance, thereby ensuring that sales opportunities are not missed.

[0358] A unique feature of this invention is the incorporation of an emotion engine into the system. The terminal analyzes the user's voice and facial expressions using the emotion engine and sends the data to the server. Based on the obtained emotion data, the server adaptively adjusts the user experience to improve satisfaction. For example, if the user shows a dissatisfied expression, the system detects this and immediately provides a special support message.

[0359] For example, when a user asks an AI chatbot a question about a product, the emotion engine analyzes the user's tone of voice and facial expressions. If the server detects that the user is confused, it provides more detailed explanations or extra support.

[0360] This system not only improves inventory management but also significantly enhances the quality of in-store interactions, increasing customer satisfaction and the likelihood of repeat visits.

[0361] The following describes the processing flow.

[0362] Step 1:

[0363] The device acquires weight data in real time from weight sensors installed on the shelf floor. The data is set to be updated at regular time intervals.

[0364] Step 2:

[0365] The device transmits the acquired weight data to the server using a communication method. The transmitted data is encrypted and transferred securely.

[0366] Step 3:

[0367] The server analyzes the weight data it receives and calculates the inventory quantity. The calculation results are designed to accurately reflect the current inventory status.

[0368] Step 4:

[0369] The server compares the inventory level to a set threshold. If the inventory falls below the threshold, the server automatically generates an order.

[0370] Step 5:

[0371] The server electronically sends order instructions to suppliers. This transmission is done via email or API.

[0372] Step 6:

[0373] The server uses generated AI to analyze historical sales data and trend information. This analysis identifies products that are likely to see increased demand in the future.

[0374] Step 7:

[0375] The server develops a plan to systematically secure inventory based on predicted demand. Additional orders are placed based on this plan.

[0376] Step 8:

[0377] The device acquires emotional data from the user's voice and facial expressions. The acquired data is then analyzed by an emotion engine.

[0378] Step 9:

[0379] The server receives emotion data and adjusts the user experience accordingly. For example, if a negative emotion is detected, it provides a special support message.

[0380] Step 10:

[0381] When a user inquires about information via an AI chatbot, communication takes place in natural language. While the emotion engine analyzes the user's emotions, the server generates and provides an appropriate response to the user.

[0382] (Example 2)

[0383] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0384] The challenges lie in improving the efficiency of inventory management and enhancing the consumer experience. Traditional systems failed to adequately track inventory levels and forecast future demand, resulting in lost opportunities due to excess or insufficient stock. Furthermore, providing services that reflected user emotions and opinions was difficult, hindering improvements in consumer satisfaction.

[0385] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0386] In this invention, the server includes a sensor means for detecting weight, an evaluation means for evaluating the inventory status based on the detected weight information, an ordering means for automatically placing an order when the inventory falls below a set threshold, an analysis means using a generative AI model for analyzing past sales information and trend information, an emotion analysis means for analyzing the emotional state of the user, and an improvement means for adjusting the user experience based on the analysis results. This enables improved accuracy in inventory management, appropriate product supply, and optimization of the consumer experience.

[0387] "Sensing means" is a general term for devices and technologies used to detect the weight of a product.

[0388] "Evaluation methods" refer to the process of analyzing inventory status based on detected weight information and implementing appropriate management.

[0389] An "ordering method" refers to a method or system for automatically generating an order instruction and notifying the supplier when inventory falls below a set threshold.

[0390] A "generative AI model" is an artificial intelligence technology that uses past sales and trend information to analyze and predict future demand.

[0391] "Analysis methods" refer to techniques and technologies that utilize generative AI models to perform data analysis and obtain useful information.

[0392] "Emotional analysis methods" refer to technologies and systems that read and analyze a user's emotional state from their voice and facial expressions.

[0393] "Improvement measures" refer to strategies and measures to optimize the user experience and improve the service based on the analyzed data.

[0394] This invention is a system that improves the efficiency of inventory management in stores and optimizes the user experience. The specific system configuration includes sensors for detecting weight, a server for collecting and analyzing data, and a terminal for user use. Furthermore, it is equipped with a generative AI model and an emotion analysis engine, which are used in conjunction with each other.

[0395] The terminal continuously detects the weight of the product via weight sensors installed on the shelf floor. This weight data is first collected by the terminal and then transmitted in real time to a server via the internet.

[0396] The server evaluates the inventory status based on the received data. This evaluation includes an algorithm that determines if inventory is insufficient when it falls below a set threshold, and automatically places an order. The server also utilizes a generative AI model to analyze past sales data and social trend information. This analysis predicts future demand, and a plan is created to secure inventory in advance based on the results.

[0397] Furthermore, this system is equipped with an emotion analysis engine. The terminal detects the user's voice and facial expressions and sends this as emotion data to the server. The server then analyzes this data and provides adaptive user services tailored to the user's emotions. For example, if the system detects that the user is feeling dissatisfied, it immediately generates and presents a special support message.

[0398] As a concrete example, consider a scenario where a user asks an AI chatbot a question about a product. In this case, the user can input a prompt into the generative AI model such as, "Predict which products are likely to see increased demand in the next month. Specify the necessary historical dataset and explain your reasoning."

[0399] By adopting this system, the accuracy of inventory management will improve, and high-quality customer service will be provided along with the appropriate supply of goods, thereby improving both the operational efficiency of stores and customer satisfaction.

[0400] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0401] Step 1:

[0402] The device uses a weight sensor to detect the weight of the product.

[0403] Input: The physical weight of the product on the shelf.

[0404] Processing: A weight sensor measures the weight of the product and records the value as digital data.

[0405] Output: Detected weight data.

[0406] Step 2:

[0407] The device sends the collected weight data to the server.

[0408] Input: Detected weight data.

[0409] Processing: The terminal uses network protocols to packetize the data and send it to the server over the internet.

[0410] Output: Weight data sent to the server.

[0411] Step 3:

[0412] The server evaluates the inventory status based on the weight data it receives.

[0413] Input: Weight data sent to the server.

[0414] Processing: The server queries the database, calculates the current inventory level, and compares it to the set baseline value.

[0415] Output: Current inventory status report.

[0416] Step 4:

[0417] The server generates an order instruction when inventory falls below a certain threshold.

[0418] Input: Inventory status report.

[0419] Processing: The automated ordering algorithm determines the required order quantity based on the inventory shortage and generates an order instruction.

[0420] Output: Order instructions to suppliers.

[0421] Step 5:

[0422] The server uses a generated AI model to perform demand forecasting.

[0423] Input: Past sales data and trend information.

[0424] Processing: The generative AI model analyzes the input data and predicts future demand.

[0425] Output: Forecasted demand data.

[0426] Step 6:

[0427] The server creates an inventory management plan based on demand forecasts.

[0428] Input: Forecasted demand data.

[0429] Processing: The server analyzes the prediction results and develops a future inventory replenishment plan.

[0430] Output: Inventory securing plan.

[0431] Step 7:

[0432] The device uses an emotion analysis engine to analyze the user's voice and facial expressions.

[0433] Input: User's voice and facial expression data.

[0434] Processing: The device uses its camera and microphone to capture data and performs analysis to determine the emotional state.

[0435] Output: User sentiment data.

[0436] Step 8:

[0437] The server optimizes the user experience based on sentiment data.

[0438] Input: User sentiment data.

[0439] Processing: The server analyzes sentiment data and generates personalized services and support messages for the user.

[0440] Output: Optimized user experience information.

[0441] (Application Example 2)

[0442] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0443] A system is needed that balances efficient inventory management with an improved consumer experience. Insufficient inventory and a lack of accurate supply and demand forecasting can lead to missed sales opportunities. Furthermore, the in-store user experience often lacks emotionally responsiveness, resulting in decreased customer satisfaction and reduced willingness to return.

[0444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0445] In this invention, the server includes detection means for detecting weight, emotion analysis means, and forecasting means for predicting demand based on past sales information and social trend information. This enables more efficient inventory management and an improved consumer experience through the provision of services adapted to the user's emotions.

[0446] A "detection means" is a mechanism for measuring weight and making that information available within the system.

[0447] "Evaluation method" refers to the process of analyzing detected weight data to determine the inventory status.

[0448] An "ordering system" is a system that automatically places orders for necessary products when inventory levels fall below a set threshold.

[0449] An "emotion analysis tool" is a mechanism that analyzes emotions from users' voices, facial expressions, etc., and supports the provision of adaptive services.

[0450] "Predictive methods" refer to the process of forecasting future demand based on past sales data and social trend information, and formulating appropriate inventory plans.

[0451] A "planning tool" is a system that provides strategies for efficiently managing inventory based on demand identified by a forecasting tool.

[0452] "Methods of acquisition" refers to the process of collecting feedback and opinions from users.

[0453] "Analysis methods" refer to techniques used to analyze user feedback and identify areas for improvement in products and services.

[0454] "Information provision methods" refer to the process of providing information optimized according to the user's emotional state in order to improve the customer experience.

[0455] This application is implemented in a system aimed at improving inventory management and user experience in physical stores. The system includes weight sensors, an emotion analysis engine, a data analysis server, and a user terminal.

[0456] The server collects data from weight sensors installed on product shelves and uses this information to evaluate inventory levels. If inventory levels fall below a set threshold, the server activates a program that automatically issues reorders via the cloud system. Weight data analysis utilizes a common database management system and scripting language running on a cloud platform.

[0457] Furthermore, the server utilizes the smartphone's camera and microphone, as well as an AI-powered emotion analysis engine, to perform advanced analysis of the user's emotions. When the user uses their smartphone, voice and facial expression data are captured and processed by the emotion analysis model. Once the emotion data is sent to the server, generative AI technology provides information and support tailored to the user.

[0458] As a concrete example, when a user makes a product inquiry in a store, a smartphone AI chatbot provides relevant information. In this case, the chatbot analyzes the user's emotions from their voice tone and facial expressions, and if anxiety is detected, it provides more detailed explanations or similar products.

[0459] The following are examples of prompts to input into a generative AI model:

[0460] Dissatisfaction was detected from the user's facial expression. Please provide the following supplementary product information: Product name. Customer inquiry: Inquiry details. Please suggest additional information and similar products.

[0461] By combining these technologies, it becomes possible to improve the accuracy of inventory management in physical stores and to individually optimize the customer experience.

[0462] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0463] Step 1:

[0464] The terminal acquires data in real time from weight sensors placed on product shelves. The input is weight data obtained from the sensors. This data is periodically sent to a server, providing raw data to understand the current inventory status.

[0465] Step 2:

[0466] The server analyzes weight data and evaluates inventory levels. The evaluation uses an analysis algorithm running on a database system. Input is weight data sent from the terminal, and output is numerical information about inventory levels. A purchase order is generated when the inventory level falls below a set threshold.

[0467] Step 3:

[0468] The server incorporates historical sales data and trend information to perform demand forecasting. Using a data analysis-based algorithm, it forecasts demand for a specific period based on the input data. The output is a list of products predicted to experience increased demand. This information is used as a planning tool to create a plan for securing inventory in advance.

[0469] Step 4:

[0470] The terminal uses the user's smartphone camera and microphone to acquire the user's voice and facial expression data. The input is voice and video data. After pre-processing for emotion analysis, this data is sent to the server.

[0471] Step 5:

[0472] The server processes the received voice and facial expression data using an emotion analysis engine to determine the user's emotions. Input consists of voice and facial expression data acquired from the terminal, and output is fed back to the system as emotion data. This data is used to improve real-time services.

[0473] Step 6:

[0474] The server uses a generative AI model to provide users with optimal information based on analyzed sentiment data. Inputs are analyzed sentiment data and product information. It generates prompts, and the output is personalized information presented to the user via an AI chatbot.

[0475] Throughout the system, efficient data processing and analysis are performed to optimize inventory management and user experience.

[0476] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0477] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0478] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0479] [Third Embodiment]

[0480] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0481] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0482] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0483] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0484] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0485] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0486] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0487] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0488] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0489] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0490] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0491] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0492] This invention is designed to provide an efficient inventory management system for retail stores. Key elements of the inventory management system include weight sensors, a data analysis server, user terminals, and an AI chatbot.

[0493] Specifically, the terminal periodically detects the weight of products using weight sensors installed on the shelf floor. This weight data is transmitted to a server via a communication method. The server analyzes the received data and evaluates the inventory level. Based on this evaluation, if the inventory level falls below a set threshold, the system automatically generates an order. The order is then electronically transmitted to the supplier.

[0494] Furthermore, the server utilizes generational AI to analyze past sales data and information on social trends. This analysis allows it to identify products that are predicted to see increased demand in the future. Based on this, the server can formulate a pre-inventory plan and automatically link it to placing orders.

[0495] Furthermore, store employees, who are also users, can check inventory information in real time via the AI ​​chatbot. For example, if a user asks the AI ​​chatbot, "What is the inventory status of a specific model?", the server retrieves the current status from the inventory database and immediately provides information such as, "There are 7 units left." Also, when a user changes models, the user's terminal collects feedback through a questionnaire, and the server can analyze this feedback to help improve the product.

[0496] Thus, this system highly automates inventory management, has the ability to flexibly respond to market demand trends, and supports efficient operations.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The terminal collects weight data in real time from weight sensors installed on the shelf floor. The terminal periodically updates this data and prepares it to be sent to the server.

[0500] Step 2:

[0501] The server receives weight data sent from the terminal. After receiving the data, it calculates the inventory quantity based on the weight of each product unit. This calculation is programmed to reflect the exact inventory quantity of each product.

[0502] Step 3:

[0503] The server compares the calculated inventory quantity with a pre-set threshold. If the inventory falls below the threshold, the server automatically creates an order.

[0504] Step 4:

[0505] The server sends the generated order instructions to the supplier. Digital communication methods such as email or APIs are used for transmission.

[0506] Step 5:

[0507] The server uses generative AI to analyze historical sales data and current social trend data. This analysis identifies products that are expected to see increased demand in the future.

[0508] Step 6:

[0509] The server creates an inventory pre-order plan based on demand forecast information. Based on this plan, it places additional orders to meet the predicted demand.

[0510] Step 7:

[0511] If a user wants to obtain inventory information via an AI chatbot, they will make a natural language inquiry from their device. This inquiry might take the form of, for example, "What is the inventory status of a specific model?"

[0512] Step 8:

[0513] The server receives a user inquiry, consults the current inventory database, and retrieves the appropriate information. After collecting the information, the server sends the results to the user's terminal via an AI chatbot to provide an answer.

[0514] Step 9:

[0515] The device collects survey responses from users when they switch to a new model. The collected opinions are sent from the device to a server and used to improve the product lineup and services.

[0516] Step 10:

[0517] The server analyzes the received survey results and extracts trends and areas for improvement. Based on this data, it provides reports to the product development team and marketing department to be used in product strategy.

[0518] (Example 1)

[0519] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0520] Traditional inventory management systems struggled to respond flexibly to fluctuations in product demand, leading to risks of stockouts and increased costs due to excess inventory. Furthermore, there was a lack of effective means to utilize collected customer feedback for product improvement. Additionally, real-time inventory monitoring was difficult, hindering the efficiency of store operations.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0522] In this invention, the server includes measuring means for detecting product weight, analysis means for evaluating inventory based on the measured data, and learning means for analyzing past transaction history and market trends. This enables appropriate inventory management based on demand forecasts and reduces the risk of stockouts through automated ordering. Furthermore, by analyzing collected feedback and reflecting it in product improvements, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0523] "Measuring means" refers to devices or methods for accurately detecting the weight of a product.

[0524] "Analysis means" refers to a system for processing measured data and evaluating inventory status.

[0525] "Control means" refers to a mechanism that automatically replenishes products when inventory falls below a set threshold.

[0526] "Learning tools" refer to algorithms and programs used to analyze past trading history and market trends.

[0527] "Identification means" refers to a method for identifying products whose demand will increase based on the results of learning means.

[0528] "Planning measures" refer to strategies and methods for securing advance inventory for identified goods.

[0529] "Opinion gathering means" refers to technology for obtaining user opinions based on generated prompts.

[0530] "Analysis tools" refer to a system that processes collected user feedback to identify areas for improvement in a product or service.

[0531] "Information provision means" refers to a method of obtaining inventory information in real time using communication technology and providing information necessary for store operations.

[0532] "Communication methods" refer to technologies used to transmit necessary instructions to store operators and systems based on acquired inventory information.

[0533] This system is designed to provide advanced inventory management, primarily for use in retail stores. The equipment necessary for implementing this invention includes a terminal equipped with a weight-measuring sensor, a server for data analysis and management, and a terminal to support information exchange with users.

[0534] The terminal uses weight sensors installed on the shelves to detect the weight of products in real time. This data is transmitted to a server using wireless communication technology. Wi-Fi modules and Bluetooth are commonly used for this purpose.

[0535] The server utilizes a database management system and data analysis software to calculate the inventory quantity of products using the received weight data. Big data analysis tools such as Hadoop and Spark are expected to be used. When the calculated inventory quantity falls below a pre-set threshold, the server automatically places a replenishment order with the supplier using EDI (Electronic Data Interchange System).

[0536] Furthermore, the server utilizes generative AI models to analyze historical sales data and current social trend data. This analysis is crucial for predicting demand and securing inventory in advance. Specifically, a deep learning model using the TensorFlow library in Python is employed.

[0537] Store employees, acting as users, can check inventory information via an AI chatbot using a dedicated terminal or PC. For example, if they enter a question such as "What is the stock of the NX100 model?" as a text prompt into the chatbot, the server will retrieve the information from the database and return an answer immediately.

[0538] As a concrete example of its use, the server can proactively identify products whose demand is expected to increase during the Christmas season and facilitate additional replenishment. This enables proper inventory management and prevents lost sales opportunities due to stockouts. Furthermore, users can review survey results based on collected customer feedback and see how that feedback can be used in future product development.

[0539] Thus, the system of the present invention utilizes the latest technology to improve the efficiency and accuracy of inventory management and enable rapid response to fluctuations in market demand.

[0540] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0541] Step 1:

[0542] The terminal detects the weight of the products using weight sensors installed on the shelves. It receives the current weight data of the products as input, and the sensors convert it into a digital value. The converted weight data is then transmitted to the server via a wireless communication module. This process captures the latest status of the products on the shelves in data format.

[0543] Step 2:

[0544] The server calculates the inventory quantity based on the received weight data. The input is weight data sent from the terminal, and the output generates calculated inventory quantity data. The database management system calculates the total inventory quantity using the unit weight of the products. This data is stored in the inventory database, contributing to accurate inventory management.

[0545] Step 3:

[0546] The server uses analytical tools to analyze past sales data and market trends to predict demand fluctuations. Inputs are historical transaction history and external data, and output is a predicted list of products with potentially increasing demand. The analysis is performed using a generative AI model, such as the TensorFlow library, and the results are used to inform future sales strategies.

[0547] Step 4:

[0548] The server uses forecast information to develop a plan for securing advance stock of specific products. The input is the demand forecast list obtained in step 3, and the output is a specific ordering plan. The automated ordering system is activated and requests the supplier to replenish the necessary products via the EDI system. This action is taken as a preventative measure to prevent stockouts.

[0549] Step 5:

[0550] A user (store employee) inquires about inventory status via a terminal using an AI chatbot. The input is a prompt such as "How much stock do you have of the NX100 model?", and the output is inventory information. The server refers to a database and provides the user with specific inventory figures in real time via the chatbot.

[0551] Step 6:

[0552] Users send opinions and feedback collected from customers to a server, which analyzes the data to improve products. Inputs are customer survey data and feedback, and output is suggested improvements. The analysis is performed using natural language processing technology and provided to the product team. This enables product development that meets customer needs.

[0553] (Application Example 1)

[0554] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0555] Traditional inventory management systems struggled to track product inventory levels in real time and create flexible inventory plans based on demand fluctuations. In particular, when demand for a product surged due to social trends or other factors, it was difficult to replenish inventory at the appropriate time, leading to missed sales opportunities. Furthermore, the inability for users to quickly access inventory information created a need for increased efficiency in store operations.

[0556] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0557] In this invention, the server includes detection means for detecting weight, analysis means for analyzing social trends to identify products expected to see increased demand, and dialogue means for users to check inventory information in real time and make inquiries. This enables accurate understanding of product inventory status and rapid, flexible inventory management in response to fluctuations in demand.

[0558] "Detection means" refers to equipment or a mechanism for continuously measuring the weight of goods and understanding their inventory status.

[0559] "Evaluation means" refers to a system or algorithm for analyzing and determining the current inventory status based on weight data obtained from detection means.

[0560] An "ordering mechanism" is a function or process that automatically places an additional order when inventory falls below a predetermined threshold.

[0561] "Analysis means" refers to a function or system that analyzes social trends and past data to identify products that are predicted to see increased demand in the future.

[0562] "Planning means" refers to a function or system for formulating strategies to secure inventory in advance of products for which demand is expected to increase, as identified by analytical means.

[0563] A "dialogue mechanism" is a user interface that allows users to easily check inventory information in real time and make inquiries to the automated system as needed.

[0564] This invention's system combines multiple technological elements to streamline inventory management. First, a terminal periodically measures the weight of each product through weight sensors installed on the shelves. The measured weight data is transmitted to a server via a communication means. The server uses this data to evaluate the inventory status and identify which products are below a certain level.

[0565] Regarding the ordering process, the server automatically generates order instructions for products whose inventory levels fall below a certain threshold and sends them to suppliers. This enables timely inventory replenishment. In addition, the server analyzes social trends and past sales data to identify products for which demand is expected to increase in the future. AI-powered analysis is used, and based on this, a planning system develops a pre-emptive inventory securing plan.

[0566] Furthermore, users can obtain real-time inventory information through an AI chatbot. By entering prompts such as "Tell me the inventory status of a specific model" into the chatbot, the server will quickly provide the information. In addition, when users provide feedback, the system acquires and analyzes that feedback to help improve the product lineup and services.

[0567] As a concrete example, this can function as a smart assistant for inventory management used in physical stores, allowing store employees to easily check the status of products using their smartphones and manage inventory in anticipation of future demand. Furthermore, by using generative AI models, it becomes possible to perform data analysis that reflects social trends.

[0568] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0569] Step 1:

[0570] The terminal periodically acquires product weight data from weight sensors installed on the shelves. The input is an analog signal from the weight sensor, which is converted into digital data and sent to the server as a data packet along with product identification information.

[0571] Step 2:

[0572] The server receives weight data transmitted from the terminal. The input is a data packet, which is then compared with product information stored in the database to calculate the inventory quantity. For data processing, the server compares the standard weight of each product with the data from the sensor to evaluate the current inventory quantity.

[0573] Step 3:

[0574] The server automatically generates an order instruction when the calculated inventory level falls below a threshold. The output of the ordering process is order information sent to the supplier. This information includes product identification, required quantity, delivery date, etc., and is sent via email or electronic data interchange (EDI).

[0575] Step 4:

[0576] The server uses a generative AI model to analyze historical sales data and social trend information to identify products that will see increased demand in the future. Its inputs are sales history and trend data, which it analyzes to output predictive data. Data calculations include time series analysis and machine learning algorithms.

[0577] Step 5:

[0578] The server creates an inventory pre-ordering plan based on identified demand forecasts. The input is forecast data, and the output plan takes into account the store's current inventory status and supply-demand balance. Specifically, it determines the timing of inventory adjustments and new orders.

[0579] Step 6:

[0580] Users can inquire about inventory information in real time via an AI chatbot. The prompts sent by users are such as "Tell me the inventory status of a specific model," and the server responds by outputting the current inventory number as a text message.

[0581] Step 7:

[0582] User feedback is sent to the server via the terminal. The server receives the input feedback and analyzes it using text analysis techniques. The resulting analysis results are used as feedback to improve the product lineup and services.

[0583] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0584] This invention is a system designed to streamline inventory management in stores and improve the user experience. The system includes weight sensors, a data analysis server, a user terminal, an AI chatbot, and an emotion engine.

[0585] Specifically, the terminal continuously detects the weight of products using weight sensors installed on the shelf floor. The collected weight data is sent to a server, which then evaluates the inventory status based on it. If the evaluation indicates that inventory falls below a set threshold, the server automatically generates an order and sends it electronically to the supplier. This entire process prevents inventory shortages and enables appropriate product replenishment.

[0586] Furthermore, the server uses generative AI technology to analyze past sales data and trend information to predict which products will see increased demand in the future. Based on these predictions, a plan is created to secure inventory in advance, thereby ensuring that sales opportunities are not missed.

[0587] A unique feature of this invention is the incorporation of an emotion engine into the system. The terminal analyzes the user's voice and facial expressions using the emotion engine and sends the data to the server. Based on the obtained emotion data, the server adaptively adjusts the user experience to improve satisfaction. For example, if the user shows a dissatisfied expression, the system detects this and immediately provides a special support message.

[0588] For example, when a user asks an AI chatbot a question about a product, the emotion engine analyzes the user's tone of voice and facial expressions. If the server detects that the user is confused, it provides more detailed explanations or extra support.

[0589] This system not only improves inventory management but also significantly enhances the quality of in-store interactions, increasing customer satisfaction and the likelihood of repeat visits.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The device acquires weight data in real time from weight sensors installed on the shelf floor. The data is set to be updated at regular time intervals.

[0593] Step 2:

[0594] The device transmits the acquired weight data to the server using a communication method. The transmitted data is encrypted and transferred securely.

[0595] Step 3:

[0596] The server analyzes the weight data it receives and calculates the inventory quantity. The calculation results are designed to accurately reflect the current inventory status.

[0597] Step 4:

[0598] The server compares the inventory level to a set threshold. If the inventory falls below the threshold, the server automatically generates an order.

[0599] Step 5:

[0600] The server electronically sends order instructions to suppliers. This transmission is done via email or API.

[0601] Step 6:

[0602] The server uses generated AI to analyze historical sales data and trend information. This analysis identifies products that are likely to see increased demand in the future.

[0603] Step 7:

[0604] The server develops a plan to systematically secure inventory based on predicted demand. Additional orders are placed based on this plan.

[0605] Step 8:

[0606] The device acquires emotional data from the user's voice and facial expressions. The acquired data is then analyzed by an emotion engine.

[0607] Step 9:

[0608] The server receives emotion data and adjusts the user experience accordingly. For example, if a negative emotion is detected, it provides a special support message.

[0609] Step 10:

[0610] When a user inquires about information via an AI chatbot, communication takes place in natural language. While the emotion engine analyzes the user's emotions, the server generates and provides an appropriate response to the user.

[0611] (Example 2)

[0612] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0613] The challenges lie in improving the efficiency of inventory management and enhancing the consumer experience. Traditional systems failed to adequately track inventory levels and forecast future demand, resulting in lost opportunities due to excess or insufficient stock. Furthermore, providing services that reflected user emotions and opinions was difficult, hindering improvements in consumer satisfaction.

[0614] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0615] In this invention, the server includes a sensor means for detecting weight, an evaluation means for evaluating the inventory status based on the detected weight information, an ordering means for automatically placing an order when the inventory falls below a set threshold, an analysis means using a generative AI model for analyzing past sales information and trend information, an emotion analysis means for analyzing the emotional state of the user, and an improvement means for adjusting the user experience based on the analysis results. This enables improved accuracy in inventory management, appropriate product supply, and optimization of the consumer experience.

[0616] "Sensing means" is a general term for devices and technologies used to detect the weight of a product.

[0617] "Evaluation methods" refer to the process of analyzing inventory status based on detected weight information and implementing appropriate management.

[0618] An "ordering method" refers to a method or system for automatically generating an order instruction and notifying the supplier when inventory falls below a set threshold.

[0619] A "generative AI model" is an artificial intelligence technology that uses past sales and trend information to analyze and predict future demand.

[0620] "Analysis methods" refer to techniques and technologies that utilize generative AI models to perform data analysis and obtain useful information.

[0621] "Emotional analysis methods" refer to technologies and systems that read and analyze a user's emotional state from their voice and facial expressions.

[0622] "Improvement measures" refer to strategies and measures to optimize the user experience and improve the service based on the analyzed data.

[0623] This invention is a system that improves the efficiency of inventory management in stores and optimizes the user experience. The specific system configuration includes sensors for detecting weight, a server for collecting and analyzing data, and a terminal for user use. Furthermore, it is equipped with a generative AI model and an emotion analysis engine, which are used in conjunction with each other.

[0624] The terminal continuously detects the weight of the product via weight sensors installed on the shelf floor. This weight data is first collected by the terminal and then transmitted in real time to a server via the internet.

[0625] The server evaluates the inventory status based on the received data. This evaluation includes an algorithm that determines if inventory is insufficient when it falls below a set threshold, and automatically places an order. The server also utilizes a generative AI model to analyze past sales data and social trend information. This analysis predicts future demand, and a plan is created to secure inventory in advance based on the results.

[0626] Furthermore, this system is equipped with an emotion analysis engine. The terminal detects the user's voice and facial expressions and sends this as emotion data to the server. The server then analyzes this data and provides adaptive user services tailored to the user's emotions. For example, if the system detects that the user is feeling dissatisfied, it immediately generates and presents a special support message.

[0627] As a concrete example, consider a scenario where a user asks an AI chatbot a question about a product. In this case, the user can input a prompt into the generative AI model such as, "Predict which products are likely to see increased demand in the next month. Specify the necessary historical dataset and explain your reasoning."

[0628] By adopting this system, the accuracy of inventory management will improve, and high-quality customer service will be provided along with the appropriate supply of goods, thereby improving both the operational efficiency of stores and customer satisfaction.

[0629] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0630] Step 1:

[0631] The device uses a weight sensor to detect the weight of the product.

[0632] Input: The physical weight of the product on the shelf.

[0633] Processing: A weight sensor measures the weight of the product and records the value as digital data.

[0634] Output: Detected weight data.

[0635] Step 2:

[0636] The device sends the collected weight data to the server.

[0637] Input: Detected weight data.

[0638] Processing: The terminal uses network protocols to packetize the data and send it to the server over the internet.

[0639] Output: Weight data sent to the server.

[0640] Step 3:

[0641] The server evaluates the inventory status based on the weight data it receives.

[0642] Input: Weight data sent to the server.

[0643] Processing: The server queries the database, calculates the current inventory level, and compares it to the set baseline value.

[0644] Output: Current inventory status report.

[0645] Step 4:

[0646] The server generates an order instruction when inventory falls below a certain threshold.

[0647] Input: Inventory status report.

[0648] Processing: The automated ordering algorithm determines the required order quantity based on the inventory shortage and generates an order instruction.

[0649] Output: Order instructions to suppliers.

[0650] Step 5:

[0651] The server uses a generated AI model to perform demand forecasting.

[0652] Input: Past sales data and trend information.

[0653] Processing: The generative AI model analyzes the input data and predicts future demand.

[0654] Output: Forecasted demand data.

[0655] Step 6:

[0656] The server creates an inventory management plan based on demand forecasts.

[0657] Input: Forecasted demand data.

[0658] Processing: The server analyzes the prediction results and develops a future inventory replenishment plan.

[0659] Output: Inventory securing plan.

[0660] Step 7:

[0661] The device uses an emotion analysis engine to analyze the user's voice and facial expressions.

[0662] Input: User's voice and facial expression data.

[0663] Processing: The device uses its camera and microphone to capture data and performs analysis to determine the emotional state.

[0664] Output: User sentiment data.

[0665] Step 8:

[0666] The server optimizes the user experience based on sentiment data.

[0667] Input: User sentiment data.

[0668] Processing: The server analyzes sentiment data and generates personalized services and support messages for the user.

[0669] Output: Optimized user experience information.

[0670] (Application Example 2)

[0671] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0672] A system is needed that balances efficient inventory management with an improved consumer experience. Insufficient inventory and a lack of accurate supply and demand forecasting can lead to missed sales opportunities. Furthermore, the in-store user experience often lacks emotionally responsiveness, resulting in decreased customer satisfaction and reduced willingness to return.

[0673] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0674] In this invention, the server includes detection means for detecting weight, emotion analysis means, and forecasting means for predicting demand based on past sales information and social trend information. This enables more efficient inventory management and an improved consumer experience through the provision of services adapted to the user's emotions.

[0675] A "detection means" is a mechanism for measuring weight and making that information available within the system.

[0676] "Evaluation method" refers to the process of analyzing detected weight data to determine the inventory status.

[0677] An "ordering system" is a system that automatically places orders for necessary products when inventory levels fall below a set threshold.

[0678] An "emotion analysis tool" is a mechanism that analyzes emotions from users' voices, facial expressions, etc., and supports the provision of adaptive services.

[0679] "Predictive methods" refer to the process of forecasting future demand based on past sales data and social trend information, and formulating appropriate inventory plans.

[0680] A "planning tool" is a system that provides strategies for efficiently managing inventory based on demand identified by a forecasting tool.

[0681] "Methods of acquisition" refers to the process of collecting feedback and opinions from users.

[0682] "Analysis methods" refer to techniques used to analyze user feedback and identify areas for improvement in products and services.

[0683] "Information provision methods" refer to the process of providing information optimized according to the user's emotional state in order to improve the customer experience.

[0684] This application is implemented in a system aimed at improving inventory management and user experience in physical stores. The system includes weight sensors, an emotion analysis engine, a data analysis server, and a user terminal.

[0685] The server collects data from weight sensors installed on product shelves and uses this information to evaluate inventory levels. If inventory levels fall below a set threshold, the server activates a program that automatically issues reorders via the cloud system. Weight data analysis utilizes a common database management system and scripting language running on a cloud platform.

[0686] Furthermore, the server utilizes the smartphone's camera and microphone, as well as an AI-powered emotion analysis engine, to perform advanced analysis of the user's emotions. When the user uses their smartphone, voice and facial expression data are captured and processed by the emotion analysis model. Once the emotion data is sent to the server, generative AI technology provides information and support tailored to the user.

[0687] As a concrete example, when a user makes a product inquiry in a store, a smartphone AI chatbot provides relevant information. In this case, the chatbot analyzes the user's emotions from their voice tone and facial expressions, and if anxiety is detected, it provides more detailed explanations or similar products.

[0688] The following are examples of prompts to input into a generative AI model:

[0689] Dissatisfaction was detected from the user's facial expression. Please provide the following supplementary product information: Product name. Customer inquiry: Inquiry details. Please suggest additional information and similar products.

[0690] By combining these technologies, it becomes possible to improve the accuracy of inventory management in physical stores and to individually optimize the customer experience.

[0691] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0692] Step 1:

[0693] The terminal acquires data in real time from weight sensors placed on product shelves. The input is weight data obtained from the sensors. This data is periodically sent to a server, providing raw data to understand the current inventory status.

[0694] Step 2:

[0695] The server analyzes weight data and evaluates inventory levels. The evaluation uses an analysis algorithm running on a database system. Input is weight data sent from the terminal, and output is numerical information about inventory levels. A purchase order is generated when the inventory level falls below a set threshold.

[0696] Step 3:

[0697] The server incorporates historical sales data and trend information to perform demand forecasting. Using a data analysis-based algorithm, it forecasts demand for a specific period based on the input data. The output is a list of products predicted to experience increased demand. This information is used as a planning tool to create a plan for securing inventory in advance.

[0698] Step 4:

[0699] The terminal uses the user's smartphone camera and microphone to acquire the user's voice and facial expression data. The input is voice and video data. After pre-processing for emotion analysis, this data is sent to the server.

[0700] Step 5:

[0701] The server processes the received voice and facial expression data using an emotion analysis engine to determine the user's emotions. Input consists of voice and facial expression data acquired from the terminal, and output is fed back to the system as emotion data. This data is used to improve real-time services.

[0702] Step 6:

[0703] The server uses a generative AI model to provide users with optimal information based on analyzed sentiment data. Inputs are analyzed sentiment data and product information. It generates prompts, and the output is personalized information presented to the user via an AI chatbot.

[0704] Throughout the system, efficient data processing and analysis are performed to optimize inventory management and user experience.

[0705] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0706] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0707] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0708] [Fourth Embodiment]

[0709] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0710] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0711] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0712] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0713] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0714] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0715] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0716] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0717] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0718] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0719] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0720] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0721] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0722] This invention is designed to provide an efficient inventory management system for retail stores. Key elements of the inventory management system include weight sensors, a data analysis server, user terminals, and an AI chatbot.

[0723] Specifically, the terminal periodically detects the weight of products using weight sensors installed on the shelf floor. This weight data is transmitted to a server via a communication method. The server analyzes the received data and evaluates the inventory level. Based on this evaluation, if the inventory level falls below a set threshold, the system automatically generates an order. The order is then electronically transmitted to the supplier.

[0724] Furthermore, the server utilizes generational AI to analyze past sales data and information on social trends. This analysis allows it to identify products that are predicted to see increased demand in the future. Based on this, the server can formulate a pre-inventory plan and automatically link it to placing orders.

[0725] Furthermore, store employees, who are also users, can check inventory information in real time via the AI ​​chatbot. For example, if a user asks the AI ​​chatbot, "What is the inventory status of a specific model?", the server retrieves the current status from the inventory database and immediately provides information such as, "There are 7 units left." Also, when a user changes models, the user's terminal collects feedback through a questionnaire, and the server can analyze this feedback to help improve the product.

[0726] Thus, this system highly automates inventory management, has the ability to flexibly respond to market demand trends, and supports efficient operations.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] The terminal collects weight data in real time from weight sensors installed on the shelf floor. The terminal periodically updates this data and prepares it to be sent to the server.

[0730] Step 2:

[0731] The server receives weight data sent from the terminal. After receiving the data, it calculates the inventory quantity based on the weight of each product unit. This calculation is programmed to reflect the exact inventory quantity of each product.

[0732] Step 3:

[0733] The server compares the calculated inventory quantity with a pre-set threshold. If the inventory falls below the threshold, the server automatically creates an order.

[0734] Step 4:

[0735] The server sends the generated order instructions to the supplier. Digital communication methods such as email or APIs are used for transmission.

[0736] Step 5:

[0737] The server uses generative AI to analyze historical sales data and current social trend data. This analysis identifies products that are expected to see increased demand in the future.

[0738] Step 6:

[0739] The server creates an inventory pre-order plan based on demand forecast information. Based on this plan, it places additional orders to meet the predicted demand.

[0740] Step 7:

[0741] If a user wants to obtain inventory information via an AI chatbot, they will make a natural language inquiry from their device. This inquiry might take the form of, for example, "What is the inventory status of a specific model?"

[0742] Step 8:

[0743] The server receives a user inquiry, consults the current inventory database, and retrieves the appropriate information. After collecting the information, the server sends the results to the user's terminal via an AI chatbot to provide an answer.

[0744] Step 9:

[0745] The device collects survey responses from users when they switch to a new model. The collected opinions are sent from the device to a server and used to improve the product lineup and services.

[0746] Step 10:

[0747] The server analyzes the received survey results and extracts trends and areas for improvement. Based on this data, it provides reports to the product development team and marketing department to be used in product strategy.

[0748] (Example 1)

[0749] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0750] Traditional inventory management systems struggled to respond flexibly to fluctuations in product demand, leading to risks of stockouts and increased costs due to excess inventory. Furthermore, there was a lack of effective means to utilize collected customer feedback for product improvement. Additionally, real-time inventory monitoring was difficult, hindering the efficiency of store operations.

[0751] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0752] In this invention, the server includes measuring means for detecting product weight, analysis means for evaluating inventory based on the measured data, and learning means for analyzing past transaction history and market trends. This enables appropriate inventory management based on demand forecasts and reduces the risk of stockouts through automated ordering. Furthermore, by analyzing collected feedback and reflecting it in product improvements, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0753] "Measuring means" refers to devices or methods for accurately detecting the weight of a product.

[0754] "Analysis means" refers to a system for processing measured data and evaluating inventory status.

[0755] "Control means" refers to a mechanism that automatically replenishes products when inventory falls below a set threshold.

[0756] "Learning tools" refer to algorithms and programs used to analyze past trading history and market trends.

[0757] "Identification means" refers to a method for identifying products whose demand will increase based on the results of learning means.

[0758] "Planning measures" refer to strategies and methods for securing advance inventory for identified goods.

[0759] "Opinion gathering means" refers to technology for obtaining user opinions based on generated prompts.

[0760] "Analysis tools" refer to a system that processes collected user feedback to identify areas for improvement in a product or service.

[0761] "Information provision means" refers to a method of obtaining inventory information in real time using communication technology and providing information necessary for store operations.

[0762] "Communication methods" refer to technologies used to transmit necessary instructions to store operators and systems based on acquired inventory information.

[0763] This system is designed to provide advanced inventory management, primarily for use in retail stores. The equipment necessary for implementing this invention includes a terminal equipped with a weight-measuring sensor, a server for data analysis and management, and a terminal to support information exchange with users.

[0764] The terminal uses weight sensors installed on the shelves to detect the weight of products in real time. This data is transmitted to a server using wireless communication technology. Wi-Fi modules and Bluetooth are commonly used for this purpose.

[0765] The server utilizes a database management system and data analysis software to calculate the inventory quantity of products using the received weight data. Big data analysis tools such as Hadoop and Spark are expected to be used. When the calculated inventory quantity falls below a pre-set threshold, the server automatically places a replenishment order with the supplier using EDI (Electronic Data Interchange System).

[0766] Furthermore, the server utilizes generative AI models to analyze historical sales data and current social trend data. This analysis is crucial for predicting demand and securing inventory in advance. Specifically, a deep learning model using the TensorFlow library in Python is employed.

[0767] Store employees, acting as users, can check inventory information via an AI chatbot using a dedicated terminal or PC. For example, if they enter a question such as "What is the stock of the NX100 model?" as a text prompt into the chatbot, the server will retrieve the information from the database and return an answer immediately.

[0768] As a concrete example of its use, the server can proactively identify products whose demand is expected to increase during the Christmas season and facilitate additional replenishment. This enables proper inventory management and prevents lost sales opportunities due to stockouts. Furthermore, users can review survey results based on collected customer feedback and see how that feedback can be used in future product development.

[0769] Thus, the system of the present invention utilizes the latest technology to improve the efficiency and accuracy of inventory management and enable rapid response to fluctuations in market demand.

[0770] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0771] Step 1:

[0772] The terminal detects the weight of the products using weight sensors installed on the shelves. It receives the current weight data of the products as input, and the sensors convert it into a digital value. The converted weight data is then transmitted to the server via a wireless communication module. This process captures the latest status of the products on the shelves in data format.

[0773] Step 2:

[0774] The server calculates the inventory quantity based on the received weight data. The input is weight data sent from the terminal, and the output generates calculated inventory quantity data. The database management system calculates the total inventory quantity using the unit weight of the products. This data is stored in the inventory database, contributing to accurate inventory management.

[0775] Step 3:

[0776] The server uses analytical tools to analyze past sales data and market trends to predict demand fluctuations. Inputs are historical transaction history and external data, and output is a predicted list of products with potentially increasing demand. The analysis is performed using a generative AI model, such as the TensorFlow library, and the results are used to inform future sales strategies.

[0777] Step 4:

[0778] The server uses forecast information to develop a plan for securing advance stock of specific products. The input is the demand forecast list obtained in step 3, and the output is a specific ordering plan. The automated ordering system is activated and requests the supplier to replenish the necessary products via the EDI system. This action is taken as a preventative measure to prevent stockouts.

[0779] Step 5:

[0780] A user (store employee) inquires about inventory status via a terminal using an AI chatbot. The input is a prompt such as "How much stock do you have of the NX100 model?", and the output is inventory information. The server refers to a database and provides the user with specific inventory figures in real time via the chatbot.

[0781] Step 6:

[0782] Users send opinions and feedback collected from customers to a server, which analyzes the data to improve products. Inputs are customer survey data and feedback, and output is suggested improvements. The analysis is performed using natural language processing technology and provided to the product team. This enables product development that meets customer needs.

[0783] (Application Example 1)

[0784] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0785] Traditional inventory management systems struggled to track product inventory levels in real time and create flexible inventory plans based on demand fluctuations. In particular, when demand for a product surged due to social trends or other factors, it was difficult to replenish inventory at the appropriate time, leading to missed sales opportunities. Furthermore, the inability for users to quickly access inventory information created a need for increased efficiency in store operations.

[0786] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0787] In this invention, the server includes detection means for detecting weight, analysis means for analyzing social trends to identify products expected to see increased demand, and dialogue means for users to check inventory information in real time and make inquiries. This enables accurate understanding of product inventory status and rapid, flexible inventory management in response to fluctuations in demand.

[0788] "Detection means" refers to equipment or a mechanism for continuously measuring the weight of goods and understanding their inventory status.

[0789] "Evaluation means" refers to a system or algorithm for analyzing and determining the current inventory status based on weight data obtained from detection means.

[0790] An "ordering mechanism" is a function or process that automatically places an additional order when inventory falls below a predetermined threshold.

[0791] "Analysis means" refers to a function or system that analyzes social trends and past data to identify products that are predicted to see increased demand in the future.

[0792] "Planning means" refers to a function or system for formulating strategies to secure inventory in advance of products for which demand is expected to increase, as identified by analytical means.

[0793] A "dialogue mechanism" is a user interface that allows users to easily check inventory information in real time and make inquiries to the automated system as needed.

[0794] This invention's system combines multiple technological elements to streamline inventory management. First, a terminal periodically measures the weight of each product through weight sensors installed on the shelves. The measured weight data is transmitted to a server via a communication means. The server uses this data to evaluate the inventory status and identify which products are below a certain level.

[0795] Regarding the ordering process, the server automatically generates order instructions for products whose inventory levels fall below a certain threshold and sends them to suppliers. This enables timely inventory replenishment. In addition, the server analyzes social trends and past sales data to identify products for which demand is expected to increase in the future. AI-powered analysis is used, and based on this, a planning system develops a pre-emptive inventory securing plan.

[0796] Furthermore, users can obtain real-time inventory information through an AI chatbot. By entering prompts such as "Tell me the inventory status of a specific model" into the chatbot, the server will quickly provide the information. In addition, when users provide feedback, the system acquires and analyzes that feedback to help improve the product lineup and services.

[0797] As a concrete example, this can function as a smart assistant for inventory management used in physical stores, allowing store employees to easily check the status of products using their smartphones and manage inventory in anticipation of future demand. Furthermore, by using generative AI models, it becomes possible to perform data analysis that reflects social trends.

[0798] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0799] Step 1:

[0800] The terminal periodically acquires product weight data from weight sensors installed on the shelves. The input is an analog signal from the weight sensor, which is converted into digital data and sent to the server as a data packet along with product identification information.

[0801] Step 2:

[0802] The server receives weight data transmitted from the terminal. The input is a data packet, which is then compared with product information stored in the database to calculate the inventory quantity. For data processing, the server compares the standard weight of each product with the data from the sensor to evaluate the current inventory quantity.

[0803] Step 3:

[0804] The server automatically generates an order instruction when the calculated inventory level falls below a threshold. The output of the ordering process is order information sent to the supplier. This information includes product identification, required quantity, delivery date, etc., and is sent via email or electronic data interchange (EDI).

[0805] Step 4:

[0806] The server uses a generative AI model to analyze historical sales data and social trend information to identify products that will see increased demand in the future. Its inputs are sales history and trend data, which it analyzes to output predictive data. Data calculations include time series analysis and machine learning algorithms.

[0807] Step 5:

[0808] The server creates an inventory pre-ordering plan based on identified demand forecasts. The input is forecast data, and the output plan takes into account the store's current inventory status and supply-demand balance. Specifically, it determines the timing of inventory adjustments and new orders.

[0809] Step 6:

[0810] Users can inquire about inventory information in real time via an AI chatbot. The prompts sent by users are such as "Tell me the inventory status of a specific model," and the server responds by outputting the current inventory number as a text message.

[0811] Step 7:

[0812] User feedback is sent to the server via the terminal. The server receives the input feedback and analyzes it using text analysis techniques. The resulting analysis results are used as feedback to improve the product lineup and services.

[0813] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0814] This invention is a system designed to streamline inventory management in stores and improve the user experience. The system includes weight sensors, a data analysis server, a user terminal, an AI chatbot, and an emotion engine.

[0815] Specifically, the terminal continuously detects the weight of products using weight sensors installed on the shelf floor. The collected weight data is sent to a server, which then evaluates the inventory status based on it. If the evaluation indicates that inventory falls below a set threshold, the server automatically generates an order and sends it electronically to the supplier. This entire process prevents inventory shortages and enables appropriate product replenishment.

[0816] Furthermore, the server uses generative AI technology to analyze past sales data and trend information to predict which products will see increased demand in the future. Based on these predictions, a plan is created to secure inventory in advance, thereby ensuring that sales opportunities are not missed.

[0817] A unique feature of this invention is the incorporation of an emotion engine into the system. The terminal analyzes the user's voice and facial expressions using the emotion engine and sends the data to the server. Based on the obtained emotion data, the server adaptively adjusts the user experience to improve satisfaction. For example, if the user shows a dissatisfied expression, the system detects this and immediately provides a special support message.

[0818] For example, when a user asks an AI chatbot a question about a product, the emotion engine analyzes the user's tone of voice and facial expressions. If the server detects that the user is confused, it provides more detailed explanations or extra support.

[0819] This system not only improves inventory management but also significantly enhances the quality of in-store interactions, increasing customer satisfaction and the likelihood of repeat visits.

[0820] The following describes the processing flow.

[0821] Step 1:

[0822] The device acquires weight data in real time from weight sensors installed on the shelf floor. The data is set to be updated at regular time intervals.

[0823] Step 2:

[0824] The device transmits the acquired weight data to the server using a communication method. The transmitted data is encrypted and transferred securely.

[0825] Step 3:

[0826] The server analyzes the weight data it receives and calculates the inventory quantity. The calculation results are designed to accurately reflect the current inventory status.

[0827] Step 4:

[0828] The server compares the inventory level to a set threshold. If the inventory falls below the threshold, the server automatically generates an order.

[0829] Step 5:

[0830] The server electronically sends order instructions to suppliers. This transmission is done via email or API.

[0831] Step 6:

[0832] The server uses generated AI to analyze historical sales data and trend information. This analysis identifies products that are likely to see increased demand in the future.

[0833] Step 7:

[0834] The server develops a plan to systematically secure inventory based on predicted demand. Additional orders are placed based on this plan.

[0835] Step 8:

[0836] The device acquires emotional data from the user's voice and facial expressions. The acquired data is then analyzed by an emotion engine.

[0837] Step 9:

[0838] The server receives emotion data and adjusts the user experience accordingly. For example, if a negative emotion is detected, it provides a special support message.

[0839] Step 10:

[0840] When a user inquires about information via an AI chatbot, communication takes place in natural language. While the emotion engine analyzes the user's emotions, the server generates and provides an appropriate response to the user.

[0841] (Example 2)

[0842] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0843] The challenges lie in improving the efficiency of inventory management and enhancing the consumer experience. Traditional systems failed to adequately track inventory levels and forecast future demand, resulting in lost opportunities due to excess or insufficient stock. Furthermore, providing services that reflected user emotions and opinions was difficult, hindering improvements in consumer satisfaction.

[0844] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0845] In this invention, the server includes a sensor means for detecting weight, an evaluation means for evaluating the inventory status based on the detected weight information, an ordering means for automatically placing an order when the inventory falls below a set threshold, an analysis means using a generative AI model for analyzing past sales information and trend information, an emotion analysis means for analyzing the emotional state of the user, and an improvement means for adjusting the user experience based on the analysis results. This enables improved accuracy in inventory management, appropriate product supply, and optimization of the consumer experience.

[0846] "Sensing means" is a general term for devices and technologies used to detect the weight of a product.

[0847] "Evaluation methods" refer to the process of analyzing inventory status based on detected weight information and implementing appropriate management.

[0848] An "ordering method" refers to a method or system for automatically generating an order instruction and notifying the supplier when inventory falls below a set threshold.

[0849] A "generative AI model" is an artificial intelligence technology that uses past sales and trend information to analyze and predict future demand.

[0850] "Analysis methods" refer to techniques and technologies that utilize generative AI models to perform data analysis and obtain useful information.

[0851] "Emotional analysis methods" refer to technologies and systems that read and analyze a user's emotional state from their voice and facial expressions.

[0852] "Improvement measures" refer to strategies and measures to optimize the user experience and improve the service based on the analyzed data.

[0853] This invention is a system that improves the efficiency of inventory management in stores and optimizes the user experience. The specific system configuration includes sensors for detecting weight, a server for collecting and analyzing data, and a terminal for user use. Furthermore, it is equipped with a generative AI model and an emotion analysis engine, which are used in conjunction with each other.

[0854] The terminal continuously detects the weight of the product via weight sensors installed on the shelf floor. This weight data is first collected by the terminal and then transmitted in real time to a server via the internet.

[0855] The server evaluates the inventory status based on the received data. This evaluation includes an algorithm that determines if inventory is insufficient when it falls below a set threshold, and automatically places an order. The server also utilizes a generative AI model to analyze past sales data and social trend information. This analysis predicts future demand, and a plan is created to secure inventory in advance based on the results.

[0856] Furthermore, this system is equipped with an emotion analysis engine. The terminal detects the user's voice and facial expressions and sends this as emotion data to the server. The server then analyzes this data and provides adaptive user services tailored to the user's emotions. For example, if the system detects that the user is feeling dissatisfied, it immediately generates and presents a special support message.

[0857] As a concrete example, consider a scenario where a user asks an AI chatbot a question about a product. In this case, the user can input a prompt into the generative AI model such as, "Predict which products are likely to see increased demand in the next month. Specify the necessary historical dataset and explain your reasoning."

[0858] By adopting this system, the accuracy of inventory management will improve, and high-quality customer service will be provided along with the appropriate supply of goods, thereby improving both the operational efficiency of stores and customer satisfaction.

[0859] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0860] Step 1:

[0861] The device uses a weight sensor to detect the weight of the product.

[0862] Input: The physical weight of the product on the shelf.

[0863] Processing: A weight sensor measures the weight of the product and records the value as digital data.

[0864] Output: Detected weight data.

[0865] Step 2:

[0866] The device sends the collected weight data to the server.

[0867] Input: Detected weight data.

[0868] Processing: The terminal uses network protocols to packetize the data and send it to the server over the internet.

[0869] Output: Weight data sent to the server.

[0870] Step 3:

[0871] The server evaluates the inventory status based on the weight data it receives.

[0872] Input: Weight data sent to the server.

[0873] Processing: The server queries the database, calculates the current inventory level, and compares it to the set baseline value.

[0874] Output: Current inventory status report.

[0875] Step 4:

[0876] The server generates an order instruction when inventory falls below a certain threshold.

[0877] Input: Inventory status report.

[0878] Processing: The automated ordering algorithm determines the required order quantity based on the inventory shortage and generates an order instruction.

[0879] Output: Order instructions to suppliers.

[0880] Step 5:

[0881] The server uses a generated AI model to perform demand forecasting.

[0882] Input: Past sales data and trend information.

[0883] Processing: The generative AI model analyzes the input data and predicts future demand.

[0884] Output: Forecasted demand data.

[0885] Step 6:

[0886] The server creates an inventory management plan based on demand forecasts.

[0887] Input: Forecasted demand data.

[0888] Processing: The server analyzes the prediction results and develops a future inventory replenishment plan.

[0889] Output: Inventory securing plan.

[0890] Step 7:

[0891] The device uses an emotion analysis engine to analyze the user's voice and facial expressions.

[0892] Input: User's voice and facial expression data.

[0893] Processing: The device uses its camera and microphone to capture data and performs analysis to determine the emotional state.

[0894] Output: User sentiment data.

[0895] Step 8:

[0896] The server optimizes the user experience based on sentiment data.

[0897] Input: User sentiment data.

[0898] Processing: The server analyzes sentiment data and generates personalized services and support messages for the user.

[0899] Output: Optimized user experience information.

[0900] (Application Example 2)

[0901] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0902] A system is needed that balances efficient inventory management with an improved consumer experience. Insufficient inventory and a lack of accurate supply and demand forecasting can lead to missed sales opportunities. Furthermore, the in-store user experience often lacks emotionally responsiveness, resulting in decreased customer satisfaction and reduced willingness to return.

[0903] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0904] In this invention, the server includes detection means for detecting weight, emotion analysis means, and forecasting means for predicting demand based on past sales information and social trend information. This enables more efficient inventory management and an improved consumer experience through the provision of services adapted to the user's emotions.

[0905] A "detection means" is a mechanism for measuring weight and making that information available within the system.

[0906] "Evaluation method" refers to the process of analyzing detected weight data to determine the inventory status.

[0907] An "ordering system" is a system that automatically places orders for necessary products when inventory levels fall below a set threshold.

[0908] An "emotion analysis tool" is a mechanism that analyzes emotions from users' voices, facial expressions, etc., and supports the provision of adaptive services.

[0909] "Predictive methods" refer to the process of forecasting future demand based on past sales data and social trend information, and formulating appropriate inventory plans.

[0910] A "planning tool" is a system that provides strategies for efficiently managing inventory based on demand identified by a forecasting tool.

[0911] "Methods of acquisition" refers to the process of collecting feedback and opinions from users.

[0912] "Analysis methods" refer to techniques used to analyze user feedback and identify areas for improvement in products and services.

[0913] "Information provision methods" refer to the process of providing information optimized according to the user's emotional state in order to improve the customer experience.

[0914] This application is implemented in a system aimed at improving inventory management and user experience in physical stores. The system includes weight sensors, an emotion analysis engine, a data analysis server, and a user terminal.

[0915] The server collects data from weight sensors installed on product shelves and uses this information to evaluate inventory levels. If inventory levels fall below a set threshold, the server activates a program that automatically issues reorders via the cloud system. Weight data analysis utilizes a common database management system and scripting language running on a cloud platform.

[0916] Furthermore, the server utilizes the smartphone's camera and microphone, as well as an AI-powered emotion analysis engine, to perform advanced analysis of the user's emotions. When the user uses their smartphone, voice and facial expression data are captured and processed by the emotion analysis model. Once the emotion data is sent to the server, generative AI technology provides information and support tailored to the user.

[0917] As a concrete example, when a user makes a product inquiry in a store, a smartphone AI chatbot provides relevant information. In this case, the chatbot analyzes the user's emotions from their voice tone and facial expressions, and if anxiety is detected, it provides more detailed explanations or similar products.

[0918] The following are examples of prompts to input into a generative AI model:

[0919] Dissatisfaction was detected from the user's facial expression. Please provide the following supplementary product information: Product name. Customer inquiry: Inquiry details. Please suggest additional information and similar products.

[0920] By combining these technologies, it becomes possible to improve the accuracy of inventory management in physical stores and to individually optimize the customer experience.

[0921] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0922] Step 1:

[0923] The terminal acquires data in real time from weight sensors placed on product shelves. The input is weight data obtained from the sensors. This data is periodically sent to a server, providing raw data to understand the current inventory status.

[0924] Step 2:

[0925] The server analyzes weight data and evaluates inventory levels. The evaluation uses an analysis algorithm running on a database system. Input is weight data sent from the terminal, and output is numerical information about inventory levels. A purchase order is generated when the inventory level falls below a set threshold.

[0926] Step 3:

[0927] The server incorporates historical sales data and trend information to perform demand forecasting. Using a data analysis-based algorithm, it forecasts demand for a specific period based on the input data. The output is a list of products predicted to experience increased demand. This information is used as a planning tool to create a plan for securing inventory in advance.

[0928] Step 4:

[0929] The terminal uses the user's smartphone camera and microphone to acquire the user's voice and facial expression data. The input is voice and video data. After pre-processing for emotion analysis, this data is sent to the server.

[0930] Step 5:

[0931] The server processes the received voice and facial expression data using an emotion analysis engine to determine the user's emotions. Input consists of voice and facial expression data acquired from the terminal, and output is fed back to the system as emotion data. This data is used to improve real-time services.

[0932] Step 6:

[0933] The server uses a generative AI model to provide users with optimal information based on analyzed sentiment data. Inputs are analyzed sentiment data and product information. It generates prompts, and the output is personalized information presented to the user via an AI chatbot.

[0934] Throughout the system, efficient data processing and analysis are performed to optimize inventory management and user experience.

[0935] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0936] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0937] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0938] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0939] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0940] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0941] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0942] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0943] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0944] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0945] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0946] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0947] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0948] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0949] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0950] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0951] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0952] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0953] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0954] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0955] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0956] The following is further disclosed regarding the embodiments described above.

[0957] (Claim 1)

[0958] A detection means for detecting weight,

[0959] An evaluation means for evaluating inventory status based on detected weight data,

[0960] An ordering method that automatically places an order when inventory falls below a set threshold,

[0961] A system that includes this.

[0962] (Claim 2)

[0963] A predictive means that analyzes past sales information and social trend information to identify products for which demand is expected to increase,

[0964] A planning means that provides a plan for securing inventory of the products identified by this prediction means in advance,

[0965] The system according to claim 1, including the following:

[0966] (Claim 3)

[0967] Means for obtaining user opinions,

[0968] Analytical tools for analyzing acquired user feedback to improve product lineups and services,

[0969] The system according to claim 1, including the following:

[0970] "Example 1"

[0971] (Claim 1)

[0972] A measuring means for detecting the weight of a product,

[0973] An analytical means for evaluating inventory based on measured data,

[0974] A control means that automatically replenishes inventory when it falls below a set threshold,

[0975] A learning tool for analyzing past transaction history and market trends,

[0976] An identification method for identifying products whose demand will increase based on the results of a learning method,

[0977] A planning means for securing advance inventory for identified goods,

[0978] A system that includes this.

[0979] (Claim 2)

[0980] A means of collecting opinions from users based on the generated prompt,

[0981] An analytical tool that analyzes collected opinions to provide suggestions for improving a product or service,

[0982] The system according to claim 1, including the following:

[0983] (Claim 3)

[0984] A means of providing information that acquires inventory information in real time using communication technology,

[0985] A communication means that outputs necessary instructions based on acquired inventory information,

[0986] The system according to claim 1, including the following:

[0987] "Application Example 1"

[0988] (Claim 1)

[0989] A detection means for detecting weight,

[0990] An evaluation means for evaluating inventory status based on detected weight data,

[0991] An ordering method that automatically places an order when inventory falls below a set threshold,

[0992] Analytical means for identifying products whose demand is expected to increase by analyzing social trends,

[0993] A planning means that provides a plan for securing inventory of specified products in advance,

[0994] A means of communication for users to check inventory information in real time and make inquiries,

[0995] A system that includes this.

[0996] (Claim 2)

[0997] The system according to claim 1, comprising analytical means for analyzing past sales information and social trend information.

[0998] (Claim 3)

[0999] The system according to claim 1, comprising means for obtaining user opinions and analyzing the obtained opinions.

[1000] "Example 2 of combining an emotion engine"

[1001] (Claim 1)

[1002] A sensor means for detecting weight,

[1003] An evaluation means for evaluating inventory status based on detected weight information,

[1004] An ordering method that automatically places an order when inventory falls below a set threshold,

[1005] An analysis method using a generative AI model that analyzes past sales information and trend information,

[1006] An emotion analysis tool for analyzing the emotional state of users,

[1007] Improvement methods to adjust the user experience based on the analysis results,

[1008] A system that includes this.

[1009] (Claim 2)

[1010] A planning means that provides a plan for securing inventory in advance based on the product demand predicted by the analysis means,

[1011] The system according to claim 1, including the following:

[1012] (Claim 3)

[1013] We obtain user feedback through various means and use analytical methods to improve our products or services.

[1014] The system according to claim 1, including the following:

[1015] "Application example 2 when combining with an emotional engine"

[1016] (Claim 1)

[1017] A detection means for detecting weight,

[1018] An evaluation means for evaluating inventory status based on detected weight data,

[1019] An ordering method that automatically places an order when inventory falls below a set threshold,

[1020] An emotion analysis tool for analyzing user emotions and providing services adaptively,

[1021] A system that includes this.

[1022] (Claim 2)

[1023] A predictive means that analyzes past sales information and social trend information to identify products for which demand is expected to increase,

[1024] A planning means that provides a plan for securing inventory of the products identified by this prediction means in advance,

[1025] A means of adjusting the user experience based on emotion analysis,

[1026] The system according to claim 1, including the following:

[1027] (Claim 3)

[1028] Means for obtaining user opinions,

[1029] Analytical tools for analyzing acquired user feedback to improve product lineups and services,

[1030] Information provision methods for providing information tailored to the emotional state of users,

[1031] The system according to claim 1, including the following: [Explanation of Symbols]

[1032] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A detection means for detecting weight, An evaluation means for evaluating inventory status based on detected weight data, An ordering method that automatically places an order when inventory falls below a set threshold, Analytical means for identifying products whose demand is expected to increase by analyzing social trends, A planning means that provides a plan for securing inventory of specified products in advance, A means of communication for users to check inventory information in real time and make inquiries, A system that includes this.

2. The system according to claim 1, comprising analytical means for analyzing past sales information and social trend information.

3. The system according to claim 1, comprising means for obtaining user opinions and analyzing the obtained opinions.

Images