system

Abstract

Provide a system. 【Solution means】 Means for receiving data from a detection device that detects the inventory status of consumables, Means for determining a shortage of consumables based on the received data, Means for exploring an information processing platform using a generated AI model and selecting an optimal purchase option, Means for notifying the user of the selected purchase option, Means for receiving an order from the user via a command device, Means for transmitting the user's order to an information processing platform, Means for accumulating purchase history and analyzing consumption patterns, Means for providing savings advice based on the analysis results, Means for monitoring the usage status of consumables in real time according to the operation of industrial machinery, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including 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] For consumers, inventory management of daily consumables in the home is time-consuming, and due to the non-uniform out-of-stock timing, there is a need to hold more inventory or make frequent purchases. Also, for suppliers, there is a high risk that consumers will switch to other companies' products when purchasing at stores, and continuous promotion costs are required to acquire new customers.

Means for Solving the Problems

[0005] This invention provides a means for receiving data from sensors that detect the inventory status of consumables and determining stock shortages based on that data. Furthermore, it includes means for searching e-commerce sites using a generative AI model, selecting the most suitable purchase option, and notifying the user of the selection result. Orders from users are accepted via an order button, and means for automatically placing orders with e-commerce sites are also included. By accumulating purchase history and analyzing consumption patterns, the invention provides savings advice based on the analysis results. As a result, consumers can efficiently manage consumables, and suppliers can reduce the risk of customer switching.

[0006] A "sensor" is a device that detects physical or environmental changes and outputs them as electrical signals.

[0007] "Data" refers to a formalized code or description used to record, process, or transmit information.

[0008] "Out of stock" refers to a situation where inventory is lost or insufficient, causing inconvenience to consumers.

[0009] A "generative AI model" refers to an algorithm trained to perform a specific task using artificial intelligence technology.

[0010] An "e-commerce site" is a platform for buying and selling goods and services over the internet.

[0011] "Purchase options" refer to choices that offer consumers different conditions or price ranges when purchasing a product.

[0012] "Notification" refers to the process of transmitting information or a message to a specific recipient.

[0013] An "order button" is a button provided on the interface to indicate a user's intention to purchase a product and to initiate the order process.

[0014] "Purchase history" means the record or log of past purchases, based on which consumption patterns can be analyzed.

[0015] "Consumption pattern" refers to a series of behavioral habits such as the frequency and amount of product use by consumers.

[0016] "Analysis" is a process of examining data and information to obtain conclusions and insights.

[0017] "Saving advice" refers to proposals and recommendations for users to reduce consumption volume or purchase costs.

Brief Description of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, the numbered 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), etc.

[0022] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention provides a system to automate inventory management of consumables and streamline user purchasing. The system operates by using sensors to monitor the inventory status of consumables in the home in real time and transmitting the data to a server. The server analyzes this data to determine if items are out of stock. When a shortage is detected, the server utilizes a generative AI model to search multiple e-commerce sites on the internet and select the optimal purchase option.

[0040] The selected purchase options are notified to the user from the server. This notification is sent to the device, such as a smartphone or tablet, and the user can then decide on a purchase based on it. When the user presses the order button on the device, that information is sent to the server, which automatically places the order with the selected e-commerce site.

[0041] Furthermore, the server accumulates past purchase history and analyzes consumption patterns. Based on this analysis, the server provides users with money-saving advice that leads to optimized consumption and cost reduction. For example, if the server detects through analysis that a user's detergent consumption is higher than the average household, it may notify the user of discounts available for bulk purchases.

[0042] Thus, this system significantly streamlines users' daily consumable management, providing time savings and economic benefits. Furthermore, for suppliers, it reduces the risk of customers switching to other products, enabling stable customer retention.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives data transmitted from various sensors installed in the home. This data includes the current inventory status of consumables such as detergent and tissue paper.

[0046] Step 2:

[0047] The server analyzes the received inventory data to determine if the inventory of consumables falls below a set threshold. If it does, it is determined to be out of stock.

[0048] Step 3:

[0049] If the server determines that an item is out of stock, it uses a generative AI model to search multiple e-commerce sites and retrieve purchase options for detergent or tissue paper. During this process, it selects the optimal purchase option based on factors such as price, delivery time, and user reviews.

[0050] Step 4:

[0051] The server notifies the user of their selected purchase option. This notification is sent to the user's smartphone or tablet, allowing the user to confirm the best purchase method.

[0052] Step 5:

[0053] The user reviews the purchase options displayed on their device and presses the order button if necessary. This action sends the user's purchase intention to the server.

[0054] Step 6:

[0055] The server receives the user's order request and automatically places the order on a selected e-commerce site. This process is efficient and saves the user time and effort.

[0056] Step 7:

[0057] The server saves this order history to a database and uses it to analyze future consumption patterns. This data helps understand the user's spending tendencies and is used to make future purchase suggestions and savings advice.

[0058] (Example 1)

[0059] 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."

[0060] Manually managing consumable inventory is time-consuming and labor-intensive, and carries the risk of stockouts and overpurchases. Furthermore, analyzing consumption patterns to obtain appropriate purchasing advice is difficult. This leads to decreased efficiency in daily life and increased financial burden. Therefore, there is a need for a system that automatically manages consumable inventory and provides optimal purchasing options to streamline daily life.

[0061] 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.

[0062] In this invention, the server includes means for receiving information from a device that senses the inventory of consumables, means for determining the shortage status of consumables based on the received information, and means for searching e-commerce sites using a generating AI program to determine the optimal purchase option. This enables automatic management of consumable inventory and selection and notification of the optimal purchase option.

[0063] "Consumables" refer to items that gradually decrease in quantity through use and require replenishment.

[0064] "Inventory information" refers to information regarding the quantity and condition of consumables currently held.

[0065] "Device" refers to hardware and peripheral equipment used to perform a specific function.

[0066] "Means of receiving information" refers to methods and devices for acquiring external data or signals.

[0067] "Means for determining shortages" refers to algorithms or devices for detecting when consumables are decreasing based on specific criteria.

[0068] A "generative AI program" refers to artificial intelligence software that analyzes large amounts of data and derives the optimal solution based on the results.

[0069] A "commercial trading site" refers to a web platform that sells goods and services online.

[0070] "Optimal purchase options" refer to the results of selecting the most desirable products or transactions based on multiple criteria such as price, quality, and delivery conditions.

[0071] "Storage" refers to the act of saving data and information for a long period of time in preparation for later analysis and reference.

[0072] "Consumption trends" refer to the patterns and trends in the use of consumable goods over time.

[0073] "Savings advice" refers to suggestions or notices aimed at reducing costs and promoting efficient consumption.

[0074] In embodiments of this invention, the system operates using the following hardware and software.

[0075] First, users monitor the inventory status of consumables using sensors installed in their homes. These sensors include, for example, weight sensors and optical sensors. This allows for real-time detection of physical changes in consumables.

[0076] The sensor transmits acquired inventory information to a server via the internet. Wi-Fi or Bluetooth is used for transmission, and HTTP or MQTT is used as the data protocol.

[0077] Next, the server analyzes the received data using analysis libraries such as Pandas and NumPy in Python. The purpose of the analysis is to determine whether the inventory is appropriate or whether replenishment is necessary.

[0078] If a shortage is detected, the server uses a generative AI model to suggest the optimal purchase option. The GPT series from OpenAI (registered trademark) is used as the generative AI model. This allows the system to explore multiple e-commerce sites and make a comprehensive judgment based on price and delivery conditions.

[0079] Examples of prompt messages used in this situation include specific details such as, "Please suggest the best toilet paper purchase options for the user's specified address. Priorities are low price, fast delivery, and high customer reviews. Please also consider current stock levels and past consumption patterns."

[0080] The server notifies the user of their chosen purchase option on their device, such as a smartphone or tablet. Push notification technologies, such as Firebase Cloud Messaging, are used for this purpose.

[0081] Once a user decides to purchase something on their device, the server automatically sends the data via the e-commerce site's API, and the order is completed.

[0082] Furthermore, the server stores users' purchase history and analyzes consumption patterns using statistical tools. This makes it possible to create efficient purchasing plans for consumables and provide users with money-saving advice.

[0083] In this way, the management of consumables in the user's daily life is automated, resulting in a system that supports an efficient and economical lifestyle.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] Sensors installed in the user's home monitor consumable inventory information in real time. For example, a weight sensor measures the remaining amount of toilet paper. The input is physical weight data, and the output generates inventory level data. This data is used to detect when inventory falls below a set threshold.

[0087] Step 2:

[0088] The monitored inventory data is transmitted from the sensor to the server. Wi-Fi is used as the communication protocol, and the data is sent via HTTP requests. The input is inventory data from the sensor, and the output is an update to the database stored on the server. The server receives this data and stores it in the database.

[0089] Step 3:

[0090] The server analyzes the accumulated inventory data using the Python Pandas library. The input is the inventory database record, and the output is the result of determining whether consumables are out of stock. This analysis determines whether replenishment of consumables is necessary.

[0091] Step 4:

[0092] If a stock shortage is detected, the server uses a generative AI model to search for the best purchase option. It utilizes an AI model from the GPT series, taking the prompt "Suggest the best toilet paper purchase option to the user's specified address" as input. The output is purchase option information from online e-commerce sites.

[0093] Step 5:

[0094] The server notifies the user's device of the acquired purchase options. Using push notification technology (e.g., Firebase Cloud Messaging), the input is data of the selected purchase options, and the output is a purchase recommendation message displayed on the device.

[0095] Step 6:

[0096] The user reviews the purchase options displayed on their device and presses the "Purchase" button. The input is the user's action on the device, and the output is the order processing request data. This data is sent to the server.

[0097] Step 7:

[0098] The server receives order requests and connects to the e-commerce site via an API to execute the orders. The input is the order request data from the user, and the output is an order slip sent to the e-commerce site.

[0099] Step 8:

[0100] After an order is completed, the server stores the purchase history in a database and analyzes the consumption pattern. The input is past purchase history data, and the output is a report of consumption patterns based on statistical analysis. Based on this information, it provides a means to generate and notify the user of future savings advice.

[0101] (Application Example 1)

[0102] 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."

[0103] Traditionally, managing consumables within factories has often been done manually, which has led to a high likelihood of inventory management deficiencies and production line stoppages due to shortages. Furthermore, obtaining real-time information on large orders and selecting optimal suppliers is difficult, resulting in increased operational costs. In this context, there is a need for a means of efficiently and automatically managing industrial consumables.

[0104] 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.

[0105] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, and means for searching for an information processing platform using a generative AI model and selecting the optimal purchase option. This enables real-time consumable management within the factory and efficient procurement of consumables from the optimal supplier.

[0106] "Consumables" refer to items that are consumed through use and require regular replenishment. In a factory setting, this would include bolts, nuts, and lubricants.

[0107] A "detection device" is a device that uses various sensors to monitor the inventory status of goods in real time.

[0108] An "information processing platform" refers to the foundation for data processing and purchasing activities on the internet, such as commercial websites and e-commerce services.

[0109] A "generative AI model" refers to an artificial intelligence algorithm that generates the optimal choice based on past data and trends.

[0110] A "supplier" is a producer or distributor that supplies goods or services.

[0111] "Inventory status" is an indicator that shows the usable quantity of a particular item at a given time.

[0112] "Real-time" refers to the instantaneous processing of data and updating of information.

[0113] The "optimal purchase option" refers to the most advantageous purchase choice, taking into account multiple factors such as cost, delivery time, and supply stability.

[0114] A "consumption pattern" refers to a consistent trend in the use or purchase of a particular item over a certain period of time.

[0115] "Savings advice" refers to guidelines for efficiently managing goods and making suggestions that lead to cost reduction.

[0116] The system for implementing this invention is designed to efficiently manage the inventory of consumables used in a factory. This system consists of sensors, a server, and user terminals.

[0117] First, sensors are installed throughout the factory, and weight sensors and image recognition cameras are used as needed to detect the inventory status of consumables in real time. The inventory data obtained from the sensors is transmitted to a server via wireless communication.

[0118] The server receives this data and performs data analysis to determine stock shortages. The server uses Python to analyze inventory data and utilizes a generative AI model—specifically TENSORFLOW®—to predict future consumption patterns. Furthermore, this model is used to explore multiple information processing platforms on the internet and select the optimal purchase option.

[0119] The server sends a notification to the user's device, such as a smartphone or tablet, when an option is selected. Upon receiving the notification, the user can decide to purchase the item via their device. Once the user confirms the purchase, the information is sent back to the server, which automatically sends the order to the selected supplier.

[0120] As a concrete example, when a robot in a factory detects the remaining amount of lubricant, the server selects the optimal supplier and notifies the user of a cost-saving proposal through bulk purchasing. The user approves the proposal using a control device and completes the order in a few operations.

[0121] An example of a prompt message would be, "Please tell me how to apply AI to consumable inventory management in a factory and create optimal purchase suggestions when supplies run out."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The sensors monitor consumables within the factory in real time, acquiring inventory data such as weight and quantity. This acquired data is transmitted to a server via wireless communication. The input is the sensor's measurement data, and the output is the data transfer to the server.

[0125] Step 2:

[0126] The server analyzes the received inventory data. Using Python, it determines whether items are out of stock by comparing current inventory levels with past consumption patterns. The input is inventory data transmitted from sensors, and the output is a flag indicating whether items are out of stock.

[0127] Step 3:

[0128] The server uses a generative AI model to predict future consumption patterns. This model runs on TensorFlow and calculates optimal purchase timing and quantity from diverse data. Inputs are inventory data and historical consumption history, and outputs are predicted consumption patterns and recommended purchase options.

[0129] Step 4:

[0130] The server uses a generative AI model to search for the optimal purchase options from information processing platforms on the internet. An optimization algorithm selects the best option considering factors such as price, delivery time, and supplier quality. The input is predicted consumption patterns and platform information, while the output is the purchase options suggested to the user.

[0131] Step 5:

[0132] A notification of selected purchase options is sent from the server to the user's device. The user receives the notification on their smartphone or tablet and checks the displayed options. The input is the notification content from the server, and the output is the information displayed on the user's device.

[0133] Step 6:

[0134] The user reviews the notification and decides to purchase. When the user presses the purchase button on the command device on their terminal, that information is sent back to the server. The input is the user's decision, and the output is the order confirmation data.

[0135] Step 7:

[0136] The server automatically sends orders to selected suppliers based on the order confirmation data. The input is the purchase confirmation data, and the output is the order data sent to the suppliers.

[0137] 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.

[0138] This invention provides a system for streamlining inventory management of consumables and improving user convenience. This system functions by combining sensors that monitor the inventory status of consumables in real time, a server that analyzes inventory data, a terminal that notifies the user of selected purchase options, and an emotion engine that recognizes the user's emotions.

[0139] Specifically, sensors installed in the home transmit inventory information for each consumable item to a server. The server analyzes this information, and if a shortage is detected, it uses a generative AI model to select the optimal purchase option. The selected option is sent as a notification to the user's device, and the user makes a purchase decision based on that information.

[0140] Furthermore, this system incorporates an emotion engine that analyzes the user's emotions. For example, the server uses the emotion engine to infer the user's emotional state from their facial expressions and tone of voice, and if it determines that the user is stressed, it optimizes the user experience by reducing the frequency of reminder notifications.

[0141] Furthermore, the emotion engine also evaluates the user's satisfaction with the purchase options they have selected and uses the results to improve future suggestions. For example, by combining and analyzing the user's purchase history and emotion data, the server can suggest better alternative products or discounted products to users who "purchase the same products every time," thereby increasing added value for the user.

[0142] The introduction of this system will allow users to manage consumables without unnecessary hassle and receive optimal suggestions tailored to their needs. As a result, time and cost savings will be achieved, and suppliers can expect improved customer retention.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The server receives inventory data transmitted from sensors installed in the home. This data includes information on the current remaining amount of consumables such as detergent and tissues.

[0146] Step 2:

[0147] The server analyzes the received data to determine if the consumables are below a set threshold. If a shortage is detected, the server proceeds to the next step based on this information.

[0148] Step 3:

[0149] The server uses a generated AI model to search multiple e-commerce sites and select the best purchase option for consumables that are out of stock. This comparison is based on factors such as price, delivery time, and customer reviews.

[0150] Step 4:

[0151] The emotion engine analyzes the user's emotional state. This detects emotions from the user's facial expression data and voice input, and estimates the user's stress and satisfaction levels.

[0152] Step 5:

[0153] The server customizes purchase suggestion notifications based on data from the emotion engine. For example, if the system determines that the user is stressed, purchase suggestion notifications will be sent in a calmer tone.

[0154] Step 6:

[0155] The device receives notifications from the server and presents the user with the most suitable purchase options. This includes emotionally sensitive messages and suggestions that take into account the user's recent purchase history.

[0156] Step 7:

[0157] The user reviews the presented purchase options and confirms their purchase intention by pressing the order button. This input is sent to the server via the terminal.

[0158] Step 8:

[0159] The server receives a purchase order from the user and automatically places the order with the selected e-commerce site. This process is efficient and requires no extra effort from the user.

[0160] Step 9:

[0161] The server stores past purchase history and user sentiment data in a database. This allows for further personalization of future purchase suggestions.

[0162] Through this process, not only is consumables managed, but services that also take into account the user's feelings are provided.

[0163] (Example 2)

[0164] 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 as the "terminal".

[0165] Traditional inventory management systems struggled to accurately track the stock status of consumables, leading to daily inconvenience due to unnoticed shortages. Furthermore, uniform notification methods and purchase suggestions failed to adequately address the diverse needs and emotions of users, hindering efficient purchasing. Moreover, the lack of optimization of suggestions based on emotional states prevented a sufficient improvement in user satisfaction.

[0166] 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.

[0167] In this invention, the server includes means for receiving data from sensors that detect the inventory status of consumables, means for selecting the optimal purchase option using a generative AI model, and means for optimizing notification content according to the user's emotional state. This streamlines inventory management of consumables and enables appropriate purchase suggestions that respond to the user's emotions.

[0168] "Consumable goods" are items that are used regularly in daily life or work, and whose demand is generated once they are used up.

[0169] "Inventory status" refers to information indicating how much of a particular item is currently on hand or how much has been consumed.

[0170] A "sensor" is a device that detects physical environmental information and transmits it to a system as digital data.

[0171] A "generative AI model" is an algorithm that learns patterns and relationships from large amounts of data and generates appropriate results for new data.

[0172] A "communication network" is a general term for the technical infrastructure used to transmit data to remote locations.

[0173] "Purchase options" refer to the choices available when replenishing consumables, indicating the means or sources of purchase and supply.

[0174] A "user" is an individual or organization that uses a particular product or service.

[0175] "Emotional state" refers to the state of emotions and psychological reactions experienced by individual users.

[0176] An "algorithm" is a set of computational procedures or rules established to solve a specific problem.

[0177] "Improving the proposal" means improving the options and advice offered to make them more useful, based on past data and new information.

[0178] This invention is a system designed to streamline inventory management of consumables and improve the user experience. The system consists of sensors, a server, an emotion analysis engine, and terminals.

[0179] First, sensors are installed in the home to monitor the remaining amount of each consumable in real time. Weight sensors and RFID tags may be used for this purpose. The collected data is transmitted to a server via wireless communication.

[0180] The server analyzes the received inventory data. A generative AI model is used for the analysis, which generates optimal purchase options when consumables fall below a certain level. Operating this AI model requires cloud services and high-performance server hardware, and it implements computationally intensive AI algorithms. An example of a prompt given to the AI ​​model might be, "Recommend the best time and place to purchase detergent."

[0181] Analysis results are notified to the user via a terminal. Smartphones and PCs are used as terminals, and information is provided via dedicated apps or web pages. Based on this, users decide whether to purchase consumables. The terminal has a built-in interface for displaying notifications, allowing users to respond quickly.

[0182] Furthermore, the server uses an emotion analysis engine to understand the user's emotional state. For example, it analyzes the user's tone of voice and facial expressions to infer their current emotional state. This function is implemented using speech recognition and image analysis technologies, and it is possible to adjust the frequency and content of notifications according to the user's stress level.

[0183] For example, if a user has low satisfaction with a frequently purchased consumable item, the sentiment analysis engine feeds that data back, and the AI ​​model generates more suitable suggestions. In this way, time and cost savings can be achieved, and the user experience can be significantly improved. This system is expected to streamline complex inventory management and dramatically improve user convenience.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] Sensors installed in the user's home collect inventory information on consumables in real time. The sensors measure the remaining quantity of items via weight and RFID, and transmit this data to a server. The input is the physical state of each consumable, and the output is digitized inventory data. At this stage, data collection and transmission are the main operations.

[0187] Step 2:

[0188] The server analyzes the inventory status of consumables based on inventory data received from sensors. Here, the received data is stored in a database, and calculations are performed to evaluate the degree of consumption. The input is inventory data from sensors, and the output is the analysis result indicating whether the consumables need to be replenished. Specific operations include database querying and threshold-based determination.

[0189] Step 3:

[0190] The server uses a generative AI model to select the optimal purchase option based on prompt messages. The AI ​​model performs inference using the prompt message "What should I buy next?" when consumables fall below a predetermined threshold. The input consists of inventory data analysis results and prompt messages, while the output is a purchase suggestion tailored to the user's needs. This process involves executing the AI ​​algorithm and extracting the results.

[0191] Step 4:

[0192] The selected purchase option is sent from the server to the terminal and notified to the user. The terminal is a smartphone or PC, and it accepts the user's decision on whether or not to purchase based on the notification. The input is the notification information of the purchase option, and the output is the user's purchase decision or further action. The specific operation here is the process of displaying an application notification on the terminal and the user's response.

[0193] Step 5:

[0194] The server uses an emotion analysis engine to analyze the user's emotional state. It evaluates psychological responses from audio and image data, and adjusts the frequency and content of notifications based on the acquired data. The input is data related to the user's emotions, and the output is optimized settings aimed at improving the user experience. The use of audio analysis and image recognition technologies is a concrete implementation of this process.

[0195] Step 6:

[0196] Ultimately, the server stores purchase history and sentiment analysis results for future recommendation improvements. This involves a learning and updating process using historical data. Inputs are past purchase history and sentiment data, and outputs are improved purchase options for the next recommendation. The specific operations are recording to a database and the algorithm learning process.

[0197] (Application Example 2)

[0198] 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".

[0199] Traditional inventory management systems were limited to detecting shortages of consumables and offering purchase options, lacking the ability to provide flexible suggestions that took into account the user's emotional state. This resulted in a lack of timely suggestions tailored to user needs, reducing overall convenience. Furthermore, standard advice failed to reflect individual user emotions or circumstances, making the system less user-friendly.

[0200] 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.

[0201] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, means for searching for a digital sales platform using a generative AI model and selecting the optimal purchase option, and means for enhancing the suggestions provided using sentiment analysis results. This makes it possible to provide appropriate and timely suggestions that reflect the user's emotions, greatly improving user convenience.

[0202] A "detection device" is a device used to monitor the inventory of consumables in real time and acquire that data.

[0203] "Means for determining stock shortages" refers to a function that uses data obtained from a detection device to determine whether the inventory of consumables meets the required standard.

[0204] A "generative AI model" is a system that uses artificial intelligence technology to select the optimal purchase option from a digital sales platform.

[0205] A "digital sales platform" is an e-commerce platform that provides options for purchasing goods and services over the internet.

[0206] "Methods for improving suggestions using emotion analysis results" refers to a function that analyzes the user's emotional state and adjusts the content and timing of purchase suggestions based on the results.

[0207] A "user" is an individual user who uses the system to manage their inventory of consumables and receive purchase options.

[0208] This invention is a system for streamlining the inventory management of consumables in the home. To implement it, the following elements are required:

[0209] 1. Hardware

[0210] Multiple detection devices are installed in the home to monitor the inventory status of consumables. These devices detect real-time data on consumables and send it to a server. Furthermore, users receive notifications using their smartphones.

[0211] 2. Software

[0212] The server is equipped with software that analyzes received real-time data to determine if there are any stock shortages. Next, it uses a generative AI model to search for and select the optimal purchase option from the digital sales platform. An emotion analysis engine evaluates the user's emotional state based on their facial expressions and tone of voice, and adjusts the content of suggestions and notification timing based on the results to provide the most appropriate recommendations.

[0213] 3. Data processing and calculations

[0214] A server receives inventory data sent from a detection device, and a generative AI model is used to explore digital sales platforms. Furthermore, an emotion analysis algorithm evaluates the user's emotions using data from their facial expressions and voice. Purchase options selected by the generative AI model are then notified to the user's smartphone in a customized format based on the user's emotion data.

[0215] Specific example

[0216] When a user is relaxing on the weekend, the system uses emotion analysis to detect if they are experiencing stress. As a result, notifications about low-stock consumables can include suggestions for stress-reducing products, thereby increasing user satisfaction.

[0217] Example of a prompt

[0218] "We've analyzed the data from the [sensor name] and it appears our milk inventory is running low. Please suggest a stress-relieving product as our next purchase option."

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The server receives inventory data for consumables sent from detection devices within the home. This input data includes the current quantity of each consumable. The server analyzes this data and determines that an item is out of stock if the inventory falls below a certain threshold. A simple thresholding algorithm is used for this data processing. The output is a list of consumables that have been determined to be out of stock.

[0222] Step 2:

[0223] The server, upon detecting an item as out of stock, utilizes a generative AI model to search for a digital sales platform. The input to this search is a list of out-of-stock items, and the output is the optimal purchase option for that item. The generative AI model considers user purchasing trends based on inventory data and selects the best option from a cloud-based database.

[0224] Step 3:

[0225] The server uses facial expression and voice data acquired from the user's smartphone to input into an emotion analysis engine and estimate the user's emotional state. The input data includes image data of facial expressions and audio data, and the output is information about the emotional state. The analysis process uses machine learning algorithms to determine whether the input data is negative, positive, or neutral.

[0226] Step 4:

[0227] The server processes notifications for purchase options based on the user's emotional state. This step adjusts the content and frequency of notifications based on the emotional state. For example, if a user's stress level is detected, specific actions are taken, such as adding suggestions for products that promote relaxation. The input is emotional state information, and the output is the optimized notification content.

[0228] Step 5:

[0229] The device (smartphone) displays a notification sent from the server to the user. The user can proceed with the purchase by reviewing the notification and selecting the presented purchase option. The output is the user's selected purchase option, which is then added to the next purchase history data.

[0230] Step 6:

[0231] Users provide feedback based on their purchase history data to improve future recommendations. This input represents user satisfaction data with their choices, and the server analyzes this feedback and incorporates it into the algorithm of the generating AI model to improve the accuracy of future recommendations. The output is information about algorithm updates aimed at improving future recommendations.

[0232] 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.

[0233] Data generation model 58 is a type of 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 those described above. 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 shown 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.

[0234] 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.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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".

[0248] This invention provides a system to automate inventory management of consumables and streamline user purchasing. The system operates by using sensors to monitor the inventory status of consumables in the home in real time and transmitting the data to a server. The server analyzes this data to determine if items are out of stock. When a shortage is detected, the server utilizes a generative AI model to search multiple e-commerce sites on the internet and select the optimal purchase option.

[0249] The selected purchase options are notified to the user from the server. This notification is sent to the device, such as a smartphone or tablet, and the user can then decide on a purchase based on it. When the user presses the order button on the device, that information is sent to the server, which automatically places the order with the selected e-commerce site.

[0250] Furthermore, the server accumulates past purchase history and analyzes consumption patterns. Based on this analysis, the server provides users with money-saving advice that leads to optimized consumption and cost reduction. For example, if the server detects through analysis that a user's detergent consumption is higher than the average household, it may notify the user of discounts available for bulk purchases.

[0251] Thus, this system significantly streamlines users' daily consumable management, providing time savings and economic benefits. Furthermore, for suppliers, it reduces the risk of customers switching to other products, enabling stable customer retention.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server receives data transmitted from various sensors installed in the home. This data includes the current inventory status of consumables such as detergent and tissue paper.

[0255] Step 2:

[0256] The server analyzes the received inventory data to determine if the inventory of consumables falls below a set threshold. If it does, it is determined to be out of stock.

[0257] Step 3:

[0258] If the server determines that an item is out of stock, it uses a generative AI model to search multiple e-commerce sites and retrieve purchase options for detergent or tissue paper. During this process, it selects the optimal purchase option based on factors such as price, delivery time, and user reviews.

[0259] Step 4:

[0260] The server notifies the user of their selected purchase option. This notification is sent to the user's smartphone or tablet, allowing the user to confirm the best purchase method.

[0261] Step 5:

[0262] The user reviews the purchase options displayed on their device and presses the order button if necessary. This action sends the user's purchase intention to the server.

[0263] Step 6:

[0264] The server receives the user's order request and automatically places the order on a selected e-commerce site. This process is efficient and saves the user time and effort.

[0265] Step 7:

[0266] The server saves this order history to a database and uses it to analyze future consumption patterns. This data helps understand the user's spending tendencies and is used to make future purchase suggestions and savings advice.

[0267] (Example 1)

[0268] 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 glasses 214 will be referred to as the "terminal."

[0269] Manually managing consumable inventory is time-consuming and labor-intensive, and carries the risk of stockouts and overpurchases. Furthermore, analyzing consumption patterns to obtain appropriate purchasing advice is difficult. This leads to decreased efficiency in daily life and increased financial burden. Therefore, there is a need for a system that automatically manages consumable inventory and provides optimal purchasing options to streamline daily life.

[0270] 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.

[0271] In this invention, the server includes means for receiving information from a device that senses the inventory of consumables, means for determining the shortage status of consumables based on the received information, and means for searching e-commerce sites using a generating AI program to determine the optimal purchase option. This enables automatic management of consumable inventory and selection and notification of the optimal purchase option.

[0272] "Consumables" refer to items that gradually decrease in quantity through use and require replenishment.

[0273] "Inventory information" refers to information regarding the quantity and condition of consumables currently held.

[0274] "Device" refers to hardware and peripheral equipment used to perform a specific function.

[0275] "Means of receiving information" refers to methods and devices for acquiring external data or signals.

[0276] "Means for determining shortages" refers to algorithms or devices for detecting when consumables are decreasing based on specific criteria.

[0277] A "generative AI program" refers to artificial intelligence software that analyzes large amounts of data and derives the optimal solution based on the results.

[0278] The "commercial trading site" refers to a web platform that conducts online sales of goods and services.

[0279] The "optimal purchase option" refers to the result of selecting the most desirable goods or transactions based on multiple criteria such as price, quality, and delivery conditions.

[0280] "Accumulation" refers to the act of storing data and information for a long time in preparation for later analysis and reference.

[0281] "Consumption trend" refers to the usage patterns and trends of consumables over time.

[0282] "Saving advice" refers to proposals and notifications for reducing costs and promoting efficient consumption.

[0283] In the form for implementing this invention, the system operates using the following hardware and software.

[0284] First, the user monitors the inventory status of consumables using sensors installed in the home. This sensor is composed of, for example, a weight sensor or an optical sensor. Thereby, the physical changes of the consumables can be sensed in real time.

[0285] The sensor transmits the acquired inventory information to the server via the Internet. Wi-Fi or Bluetooth is used for transmission, and HTTP or MQTT is used as the data protocol.

[0286] Next, the server analyzes the received data using analysis libraries such as Python's Pandas and NumPy. The purpose of the analysis is to determine whether the inventory is appropriate or whether replenishment is necessary.

[0287] If a shortage is detected, the server uses a generative AI model to suggest the best purchase option. The OpenAI GPT series is used as the generative AI model. This allows the system to explore multiple e-commerce sites and make a comprehensive judgment based on price and delivery conditions.

[0288] Examples of prompt messages used in this situation include specific details such as, "Please suggest the best toilet paper purchase options for the user's specified address. Priorities are low price, fast delivery, and high customer reviews. Please also consider current stock levels and past consumption patterns."

[0289] The server notifies the user of their chosen purchase option on their device, such as a smartphone or tablet. Push notification technologies, such as Firebase Cloud Messaging, are used for this purpose.

[0290] Once a user decides to purchase something on their device, the server automatically sends the data via the e-commerce site's API, and the order is completed.

[0291] Furthermore, the server stores users' purchase history and analyzes consumption patterns using statistical tools. This makes it possible to create efficient purchasing plans for consumables and provide users with money-saving advice.

[0292] In this way, the management of consumables in the user's daily life is automated, resulting in a system that supports an efficient and economical lifestyle.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] Sensors installed in the user's home monitor consumable inventory information in real time. For example, a weight sensor measures the remaining amount of toilet paper. The input is physical weight data, and the output generates inventory level data. This data is used to detect when inventory falls below a set threshold.

[0296] Step 2:

[0297] The monitored inventory data is transmitted from the sensor to the server. Wi-Fi is used as the communication protocol, and the data is sent via HTTP requests. The input is inventory data from the sensor, and the output is an update to the database stored on the server. The server receives this data and stores it in the database.

[0298] Step 3:

[0299] The server analyzes the accumulated inventory data using the Python Pandas library. The input is the inventory database record, and the output is the result of determining whether consumables are out of stock. This analysis determines whether replenishment of consumables is necessary.

[0300] Step 4:

[0301] If a stock shortage is detected, the server uses a generative AI model to search for the best purchase option. It utilizes an AI model from the GPT series, taking the prompt "Suggest the best toilet paper purchase option to the user's specified address" as input. The output is purchase option information from online e-commerce sites.

[0302] Step 5:

[0303] The server notifies the user's terminal of the acquired purchase options. Using push notification technology (e.g., Firebase Cloud Messaging), the input is the data of the selected purchase options, and the output is the purchase recommendation message displayed on the terminal.

[0304] Step 6:

[0305] The user checks the purchase options notified on the terminal and presses the "Purchase" button. The input is the user's action on the terminal, and the output is the order processing request data. This data is sent to the server.

[0306] Step 7:

[0307] The server receives the order request, connects to the trading site via the API, and executes the order. The input is the order request data from the user, and the output is the order slip to the trading site.

[0308] Step 8:

[0309] After the order is completed, the server accumulates the purchase history in the database and analyzes the consumption pattern. The input is the past purchase history data, and the output is a report on the consumption pattern based on statistical analysis. Based on this information, means are provided to generate future savings advice and notify the user.

[0310] (Application Example 1)

[0311] Next, Application 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".

[0312] Traditionally, managing consumables within factories has often been done manually, which has led to a high likelihood of inventory management deficiencies and production line stoppages due to shortages. Furthermore, obtaining real-time information on large orders and selecting optimal suppliers is difficult, resulting in increased operational costs. In this context, there is a need for a means of efficiently and automatically managing industrial consumables.

[0313] 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.

[0314] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, and means for searching for an information processing platform using a generative AI model and selecting the optimal purchase option. This enables real-time consumable management within the factory and efficient procurement of consumables from the optimal supplier.

[0315] "Consumables" refer to items that are consumed through use and require regular replenishment. In a factory setting, this would include bolts, nuts, and lubricants.

[0316] A "detection device" is a device that uses various sensors to monitor the inventory status of goods in real time.

[0317] An "information processing platform" refers to the foundation for data processing and purchasing activities on the internet, such as commercial websites and e-commerce services.

[0318] A "generative AI model" refers to an artificial intelligence algorithm that generates the optimal choice based on past data and trends.

[0319] A "supplier" is a producer or distributor that supplies goods or services.

[0320] "Inventory status" is an indicator that shows the usable quantity of a particular item at a given time.

[0321] "Real-time" refers to the instantaneous processing of data and updating of information.

[0322] The "optimal purchase option" refers to the most advantageous purchase choice, taking into account multiple factors such as cost, delivery time, and supply stability.

[0323] A "consumption pattern" refers to a consistent trend in the use or purchase of a particular item over a certain period of time.

[0324] "Savings advice" refers to guidelines for efficiently managing goods and making suggestions that lead to cost reduction.

[0325] The system for implementing this invention is designed to efficiently manage the inventory of consumables used in a factory. This system consists of sensors, a server, and user terminals.

[0326] First, sensors are installed throughout the factory, and weight sensors and image recognition cameras are used as needed to detect the inventory status of consumables in real time. The inventory data obtained from the sensors is transmitted to a server via wireless communication.

[0327] The server receives this data and performs data analysis to determine stock shortages. The server uses Python to analyze inventory data and leverages a generative AI model—specifically TensorFlow—to predict future consumption patterns. Furthermore, this model is used to explore multiple information processing platforms on the internet and select the optimal purchase option.

[0328] The server sends a notification to the user's device, such as a smartphone or tablet, when an option is selected. Upon receiving the notification, the user can decide to purchase the item via their device. Once the user confirms the purchase, the information is sent back to the server, which automatically sends the order to the selected supplier.

[0329] As a concrete example, when a robot in a factory detects the remaining amount of lubricant, the server selects the optimal supplier and notifies the user of a cost-saving proposal through bulk purchasing. The user approves the proposal using a control device and completes the order in a few operations.

[0330] An example of a prompt message would be, "Please tell me how to apply AI to consumable inventory management in a factory and create optimal purchase suggestions when supplies run out."

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The sensors monitor consumables within the factory in real time, acquiring inventory data such as weight and quantity. This acquired data is transmitted to a server via wireless communication. The input is the sensor's measurement data, and the output is the data transfer to the server.

[0334] Step 2:

[0335] The server analyzes the received inventory data. Using Python, it determines whether items are out of stock by comparing current inventory levels with past consumption patterns. The input is inventory data transmitted from sensors, and the output is a flag indicating whether items are out of stock.

[0336] Step 3:

[0337] The server uses a generative AI model to predict future consumption patterns. This model runs on TensorFlow and calculates optimal purchase timing and quantity from diverse data. Inputs are inventory data and historical consumption history, and outputs are predicted consumption patterns and recommended purchase options.

[0338] Step 4:

[0339] The server uses a generative AI model to search for the optimal purchase options from information processing platforms on the internet. An optimization algorithm selects the best option considering factors such as price, delivery time, and supplier quality. The input is predicted consumption patterns and platform information, while the output is the purchase options suggested to the user.

[0340] Step 5:

[0341] A notification of selected purchase options is sent from the server to the user's device. The user receives the notification on their smartphone or tablet and checks the displayed options. The input is the notification content from the server, and the output is the information displayed on the user's device.

[0342] Step 6:

[0343] The user reviews the notification and decides to purchase. When the user presses the purchase button on the command device on their terminal, that information is sent back to the server. The input is the user's decision, and the output is the order confirmation data.

[0344] Step 7:

[0345] The server automatically sends orders to selected suppliers based on the order confirmation data. The input is the purchase confirmation data, and the output is the order data sent to the suppliers.

[0346] 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.

[0347] This invention provides a system for streamlining inventory management of consumables and improving user convenience. This system functions by combining sensors that monitor the inventory status of consumables in real time, a server that analyzes inventory data, a terminal that notifies the user of selected purchase options, and an emotion engine that recognizes the user's emotions.

[0348] Specifically, sensors installed in the home transmit inventory information for each consumable item to a server. The server analyzes this information, and if a shortage is detected, it uses a generative AI model to select the optimal purchase option. The selected option is sent as a notification to the user's device, and the user makes a purchase decision based on that information.

[0349] Furthermore, this system incorporates an emotion engine that analyzes the user's emotions. For example, the server uses the emotion engine to infer the user's emotional state from their facial expressions and tone of voice, and if it determines that the user is stressed, it optimizes the user experience by reducing the frequency of reminder notifications.

[0350] Furthermore, the emotion engine also evaluates the user's satisfaction with the purchase options they have selected and uses the results to improve future suggestions. For example, by combining and analyzing the user's purchase history and emotion data, the server can suggest better alternative products or discounted products to users who "purchase the same products every time," thereby increasing added value for the user.

[0351] The introduction of this system will allow users to manage consumables without unnecessary hassle and receive optimal suggestions tailored to their needs. As a result, time and cost savings will be achieved, and suppliers can expect improved customer retention.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server receives inventory data transmitted from sensors installed in the home. This data includes information on the current remaining amount of consumables such as detergent and tissues.

[0355] Step 2:

[0356] The server analyzes the received data to determine if the consumables are below a set threshold. If a shortage is detected, the server proceeds to the next step based on this information.

[0357] Step 3:

[0358] The server uses a generated AI model to search multiple e-commerce sites and select the best purchase option for consumables that are out of stock. This comparison is based on factors such as price, delivery time, and customer reviews.

[0359] Step 4:

[0360] The emotion engine analyzes the user's emotional state. This detects emotions from the user's facial expression data and voice input, and estimates the user's stress and satisfaction levels.

[0361] Step 5:

[0362] The server customizes purchase suggestion notifications based on data from the emotion engine. For example, if the system determines that the user is stressed, purchase suggestion notifications will be sent in a calmer tone.

[0363] Step 6:

[0364] The device receives notifications from the server and presents the user with the most suitable purchase options. This includes emotionally sensitive messages and suggestions that take into account the user's recent purchase history.

[0365] Step 7:

[0366] The user reviews the presented purchase options and confirms their purchase intention by pressing the order button. This input is sent to the server via the terminal.

[0367] Step 8:

[0368] The server receives a purchase order from the user and automatically places the order with the selected e-commerce site. This process is efficient and requires no extra effort from the user.

[0369] Step 9:

[0370] The server stores past purchase history and user sentiment data in a database. This allows for further personalization of future purchase suggestions.

[0371] Through this process, not only is consumables managed, but services that also take into account the user's feelings are provided.

[0372] (Example 2)

[0373] 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".

[0374] Traditional inventory management systems struggled to accurately track the stock status of consumables, leading to daily inconvenience due to unnoticed shortages. Furthermore, uniform notification methods and purchase suggestions failed to adequately address the diverse needs and emotions of users, hindering efficient purchasing. Moreover, the lack of optimization of suggestions based on emotional states prevented a sufficient improvement in user satisfaction.

[0375] 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.

[0376] In this invention, the server includes means for receiving data from sensors that detect the inventory status of consumables, means for selecting the optimal purchase option using a generative AI model, and means for optimizing notification content according to the user's emotional state. This streamlines inventory management of consumables and enables appropriate purchase suggestions that respond to the user's emotions.

[0377] "Consumable goods" are items that are used regularly in daily life or work, and whose demand is generated once they are used up.

[0378] "Inventory status" refers to information indicating how much of a particular item is currently on hand or how much has been consumed.

[0379] A "sensor" is a device that detects physical environmental information and transmits it to a system as digital data.

[0380] A "generative AI model" is an algorithm that learns patterns and relationships from large amounts of data and generates appropriate results for new data.

[0381] A "communication network" is a general term for the technical infrastructure used to transmit data to remote locations.

[0382] "Purchase options" refer to the choices available when replenishing consumables, indicating the means or sources of purchase and supply.

[0383] A "user" is an individual or organization that uses a particular product or service.

[0384] "Emotional state" refers to the state of emotions and psychological reactions experienced by individual users.

[0385] An "algorithm" is a set of computational procedures or rules established to solve a specific problem.

[0386] "Improving the proposal" means improving the options and advice offered to make them more useful, based on past data and new information.

[0387] This invention is a system designed to streamline inventory management of consumables and improve the user experience. The system consists of sensors, a server, an emotion analysis engine, and terminals.

[0388] First, sensors are installed in the home to monitor the remaining amount of each consumable in real time. Weight sensors and RFID tags may be used for this purpose. The collected data is transmitted to a server via wireless communication.

[0389] The server analyzes the received inventory data. A generative AI model is used for the analysis, which generates optimal purchase options when consumables fall below a certain level. Operating this AI model requires cloud services and high-performance server hardware, and it implements computationally intensive AI algorithms. An example of a prompt given to the AI ​​model might be, "Recommend the best time and place to purchase detergent."

[0390] Analysis results are notified to the user via a terminal. Smartphones and PCs are used as terminals, and information is provided via dedicated apps or web pages. Based on this, users decide whether to purchase consumables. The terminal has a built-in interface for displaying notifications, allowing users to respond quickly.

[0391] Furthermore, the server uses an emotion analysis engine to understand the user's emotional state. For example, it analyzes the user's tone of voice and facial expressions to infer their current emotional state. This function is implemented using speech recognition and image analysis technologies, and it is possible to adjust the frequency and content of notifications according to the user's stress level.

[0392] For example, if a user has low satisfaction with a frequently purchased consumable item, the sentiment analysis engine feeds that data back, and the AI ​​model generates more suitable suggestions. In this way, time and cost savings can be achieved, and the user experience can be significantly improved. This system is expected to streamline complex inventory management and dramatically improve user convenience.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] Sensors installed in the user's home collect inventory information on consumables in real time. The sensors measure the remaining quantity of items via weight and RFID, and transmit this data to a server. The input is the physical state of each consumable, and the output is digitized inventory data. At this stage, data collection and transmission are the main operations.

[0396] Step 2:

[0397] The server analyzes the inventory status of consumables based on inventory data received from sensors. Here, the received data is stored in a database, and calculations are performed to evaluate the degree of consumption. The input is inventory data from sensors, and the output is the analysis result indicating whether the consumables need to be replenished. Specific operations include database querying and threshold-based determination.

[0398] Step 3:

[0399] The server uses a generative AI model to select the optimal purchase option based on prompt messages. The AI ​​model performs inference using the prompt message "What should I buy next?" when consumables fall below a predetermined threshold. The input consists of inventory data analysis results and prompt messages, while the output is a purchase suggestion tailored to the user's needs. This process involves executing the AI ​​algorithm and extracting the results.

[0400] Step 4:

[0401] The selected purchase option is sent from the server to the terminal and notified to the user. The terminal is a smartphone or PC, and it accepts the user's decision on whether or not to purchase based on the notification. The input is the notification information of the purchase option, and the output is the user's purchase decision or further action. The specific operation here is the process of displaying an application notification on the terminal and the user's response.

[0402] Step 5:

[0403] The server uses an emotion analysis engine to analyze the user's emotional state. It evaluates psychological responses from audio and image data, and adjusts the frequency and content of notifications based on the acquired data. The input is data related to the user's emotions, and the output is optimized settings aimed at improving the user experience. The use of audio analysis and image recognition technologies is a concrete implementation of this process.

[0404] Step 6:

[0405] Ultimately, the server stores purchase history and sentiment analysis results for future recommendation improvements. This involves a learning and updating process using historical data. Inputs are past purchase history and sentiment data, and outputs are improved purchase options for the next recommendation. The specific operations are recording to a database and the algorithm learning process.

[0406] (Application Example 2)

[0407] 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."

[0408] Traditional inventory management systems were limited to detecting shortages of consumables and offering purchase options, lacking the ability to provide flexible suggestions that took into account the user's emotional state. This resulted in a lack of timely suggestions tailored to user needs, reducing overall convenience. Furthermore, standard advice failed to reflect individual user emotions or circumstances, making the system less user-friendly.

[0409] 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.

[0410] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, means for searching for a digital sales platform using a generative AI model and selecting the optimal purchase option, and means for enhancing the suggestions provided using sentiment analysis results. This makes it possible to provide appropriate and timely suggestions that reflect the user's emotions, greatly improving user convenience.

[0411] A "detection device" is a device used to monitor the inventory of consumables in real time and acquire that data.

[0412] "Means for determining stock shortages" refers to a function that uses data obtained from a detection device to determine whether the inventory of consumables meets the required standard.

[0413] A "generative AI model" is a system that uses artificial intelligence technology to select the optimal purchase option from a digital sales platform.

[0414] A "digital sales platform" is an e-commerce platform that provides options for purchasing goods and services over the internet.

[0415] "Methods for improving suggestions using emotion analysis results" refers to a function that analyzes the user's emotional state and adjusts the content and timing of purchase suggestions based on the results.

[0416] A "user" is an individual user who uses the system to manage their inventory of consumables and receive purchase options.

[0417] This invention is a system for streamlining the inventory management of consumables in the home. To implement it, the following elements are required:

[0418] 1. Hardware

[0419] Multiple detection devices are installed in the home to monitor the inventory status of consumables. These devices detect real-time data on consumables and send it to a server. Furthermore, users receive notifications using their smartphones.

[0420] 2. Software

[0421] The server is equipped with software that analyzes received real-time data to determine if there are any stock shortages. Next, it uses a generative AI model to search for and select the optimal purchase option from the digital sales platform. An emotion analysis engine evaluates the user's emotional state based on their facial expressions and tone of voice, and adjusts the content of suggestions and notification timing based on the results to provide the most appropriate recommendations.

[0422] 3. Data processing and calculations

[0423] A server receives inventory data sent from a detection device, and a generative AI model is used to explore digital sales platforms. Furthermore, an emotion analysis algorithm evaluates the user's emotions using data from their facial expressions and voice. Purchase options selected by the generative AI model are then notified to the user's smartphone in a customized format based on the user's emotion data.

[0424] Specific example

[0425] When a user is relaxing on the weekend, the system uses emotion analysis to detect if they are experiencing stress. As a result, notifications about low-stock consumables can include suggestions for stress-reducing products, thereby increasing user satisfaction.

[0426] Example of a prompt

[0427] "We've analyzed the data from the [sensor name] and it appears our milk inventory is running low. Please suggest a stress-relieving product as our next purchase option."

[0428] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0429] Step 1:

[0430] The server receives inventory data for consumables sent from detection devices within the home. This input data includes the current quantity of each consumable. The server analyzes this data and determines that an item is out of stock if the inventory falls below a certain threshold. A simple thresholding algorithm is used for this data processing. The output is a list of consumables that have been determined to be out of stock.

[0431] Step 2:

[0432] The server, upon detecting an item as out of stock, utilizes a generative AI model to search for a digital sales platform. The input to this search is a list of out-of-stock items, and the output is the optimal purchase option for that item. The generative AI model considers user purchasing trends based on inventory data and selects the best option from a cloud-based database.

[0433] Step 3:

[0434] The server uses facial expression and voice data acquired from the user's smartphone to input into an emotion analysis engine and estimate the user's emotional state. The input data includes image data of facial expressions and audio data, and the output is information about the emotional state. The analysis process uses machine learning algorithms to determine whether the input data is negative, positive, or neutral.

[0435] Step 4:

[0436] The server processes notifications for purchase options based on the user's emotional state. This step adjusts the content and frequency of notifications based on the emotional state. For example, if a user's stress level is detected, specific actions are taken, such as adding suggestions for products that promote relaxation. The input is emotional state information, and the output is the optimized notification content.

[0437] Step 5:

[0438] The device (smartphone) displays a notification sent from the server to the user. The user can proceed with the purchase by reviewing the notification and selecting the presented purchase option. The output is the user's selected purchase option, which is then added to the next purchase history data.

[0439] Step 6:

[0440] Users provide feedback based on their purchase history data to improve future recommendations. This input represents user satisfaction data with their choices, and the server analyzes this feedback and incorporates it into the algorithm of the generating AI model to improve the accuracy of future recommendations. The output is information about algorithm updates aimed at improving future recommendations.

[0441] 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.

[0442] 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 those described above. 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 shown 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.

[0443] 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.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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).

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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".

[0457] This invention provides a system to automate inventory management of consumables and streamline user purchasing. The system operates by using sensors to monitor the inventory status of consumables in the home in real time and transmitting the data to a server. The server analyzes this data to determine if items are out of stock. When a shortage is detected, the server utilizes a generative AI model to search multiple e-commerce sites on the internet and select the optimal purchase option.

[0458] The selected purchase options are notified to the user from the server. This notification is sent to the device, such as a smartphone or tablet, and the user can then decide on a purchase based on it. When the user presses the order button on the device, that information is sent to the server, which automatically places the order with the selected e-commerce site.

[0459] Furthermore, the server accumulates past purchase history and analyzes consumption patterns. Based on this analysis, the server provides users with money-saving advice that leads to optimized consumption and cost reduction. For example, if the server detects through analysis that a user's detergent consumption is higher than the average household, it may notify the user of discounts available for bulk purchases.

[0460] Thus, this system significantly streamlines users' daily consumable management, providing time savings and economic benefits. Furthermore, for suppliers, it reduces the risk of customers switching to other products, enabling stable customer retention.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The server receives data transmitted from various sensors installed in the home. This data includes the current inventory status of consumables such as detergent and tissue paper.

[0464] Step 2:

[0465] The server analyzes the received inventory data to determine if the inventory of consumables falls below a set threshold. If it does, it is determined to be out of stock.

[0466] Step 3:

[0467] If the server determines that an item is out of stock, it uses a generative AI model to search multiple e-commerce sites and retrieve purchase options for detergent or tissue paper. During this process, it selects the optimal purchase option based on factors such as price, delivery time, and user reviews.

[0468] Step 4:

[0469] The server notifies the user of their selected purchase option. This notification is sent to the user's smartphone or tablet, allowing the user to confirm the best purchase method.

[0470] Step 5:

[0471] The user reviews the purchase options displayed on their device and presses the order button if necessary. This action sends the user's purchase intention to the server.

[0472] Step 6:

[0473] The server receives the user's order request and automatically places the order on a selected e-commerce site. This process is efficient and saves the user time and effort.

[0474] Step 7:

[0475] The server saves this order history to a database and uses it to analyze future consumption patterns. This data helps understand the user's spending tendencies and is used to make future purchase suggestions and savings advice.

[0476] (Example 1)

[0477] 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."

[0478] Manually managing consumable inventory is time-consuming and labor-intensive, and carries the risk of stockouts and overpurchases. Furthermore, analyzing consumption patterns to obtain appropriate purchasing advice is difficult. This leads to decreased efficiency in daily life and increased financial burden. Therefore, there is a need for a system that automatically manages consumable inventory and provides optimal purchasing options to streamline daily life.

[0479] 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.

[0480] In this invention, the server includes means for receiving information from a device that senses the inventory of consumables, means for determining the shortage status of consumables based on the received information, and means for searching e-commerce sites using a generating AI program to determine the optimal purchase option. This enables automatic management of consumable inventory and selection and notification of the optimal purchase option.

[0481] "Consumables" refer to items that gradually decrease in quantity through use and require replenishment.

[0482] "Inventory information" refers to information regarding the quantity and condition of consumables currently held.

[0483] "Device" refers to hardware and peripheral equipment used to perform a specific function.

[0484] "Means of receiving information" refers to methods and devices for acquiring external data or signals.

[0485] "Means for determining shortages" refers to algorithms or devices for detecting when consumables are decreasing based on specific criteria.

[0486] A "generative AI program" refers to artificial intelligence software that analyzes large amounts of data and derives the optimal solution based on the results.

[0487] A "commercial trading site" refers to a web platform that sells goods and services online.

[0488] "Optimal purchase options" refer to the results of selecting the most desirable products or transactions based on multiple criteria such as price, quality, and delivery conditions.

[0489] "Storage" refers to the act of saving data and information for a long period of time in preparation for later analysis and reference.

[0490] "Consumption trends" refer to the patterns and trends in the use of consumable goods over time.

[0491] "Savings advice" refers to suggestions or notices aimed at reducing costs and promoting efficient consumption.

[0492] In embodiments of this invention, the system operates using the following hardware and software.

[0493] First, users monitor the inventory status of consumables using sensors installed in their homes. These sensors include, for example, weight sensors and optical sensors. This allows for real-time detection of physical changes in consumables.

[0494] The sensor transmits acquired inventory information to a server via the internet. Wi-Fi or Bluetooth is used for transmission, and HTTP or MQTT is used as the data protocol.

[0495] Next, the server analyzes the received data using analysis libraries such as Pandas and NumPy in Python. The purpose of the analysis is to determine whether the inventory is appropriate or whether replenishment is necessary.

[0496] If a shortage is detected, the server uses a generative AI model to suggest the best purchase option. The OpenAI GPT series is used as the generative AI model. This allows the system to explore multiple e-commerce sites and make a comprehensive judgment based on price and delivery conditions.

[0497] Examples of prompt messages used in this situation include specific details such as, "Please suggest the best toilet paper purchase options for the user's specified address. Priorities are low price, fast delivery, and high customer reviews. Please also consider current stock levels and past consumption patterns."

[0498] The server notifies the user of their chosen purchase option on their device, such as a smartphone or tablet. Push notification technologies, such as Firebase Cloud Messaging, are used for this purpose.

[0499] Once a user decides to purchase something on their device, the server automatically sends the data via the e-commerce site's API, and the order is completed.

[0500] Furthermore, the server stores users' purchase history and analyzes consumption patterns using statistical tools. This makes it possible to create efficient purchasing plans for consumables and provide users with money-saving advice.

[0501] In this way, the management of consumables in the user's daily life is automated, resulting in a system that supports an efficient and economical lifestyle.

[0502] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0503] Step 1:

[0504] Sensors installed in the user's home monitor consumable inventory information in real time. For example, a weight sensor measures the remaining amount of toilet paper. The input is physical weight data, and the output generates inventory level data. This data is used to detect when inventory falls below a set threshold.

[0505] Step 2:

[0506] The monitored inventory data is transmitted from the sensor to the server. Wi-Fi is used as the communication protocol, and the data is sent via HTTP requests. The input is inventory data from the sensor, and the output is an update to the database stored on the server. The server receives this data and stores it in the database.

[0507] Step 3:

[0508] The server analyzes the accumulated inventory data using the Python Pandas library. The input is the inventory database record, and the output is the result of determining whether consumables are out of stock. This analysis determines whether replenishment of consumables is necessary.

[0509] Step 4:

[0510] If a stock shortage is detected, the server uses a generative AI model to search for the best purchase option. It utilizes an AI model from the GPT series, taking the prompt "Suggest the best toilet paper purchase option to the user's specified address" as input. The output is purchase option information from online e-commerce sites.

[0511] Step 5:

[0512] The server notifies the user's device of the acquired purchase options. Using push notification technology (e.g., Firebase Cloud Messaging), the input is data of the selected purchase options, and the output is a purchase recommendation message displayed on the device.

[0513] Step 6:

[0514] The user reviews the purchase options displayed on their device and presses the "Purchase" button. The input is the user's action on the device, and the output is the order processing request data. This data is sent to the server.

[0515] Step 7:

[0516] The server receives order requests and connects to the e-commerce site via an API to execute the orders. The input is the order request data from the user, and the output is an order slip sent to the e-commerce site.

[0517] Step 8:

[0518] After an order is completed, the server stores the purchase history in a database and analyzes the consumption pattern. The input is past purchase history data, and the output is a report of consumption patterns based on statistical analysis. Based on this information, it provides a means to generate and notify the user of future savings advice.

[0519] (Application Example 1)

[0520] 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."

[0521] Traditionally, managing consumables within factories has often been done manually, which has led to a high likelihood of inventory management deficiencies and production line stoppages due to shortages. Furthermore, obtaining real-time information on large orders and selecting optimal suppliers is difficult, resulting in increased operational costs. In this context, there is a need for a means of efficiently and automatically managing industrial consumables.

[0522] 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.

[0523] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, and means for searching for an information processing platform using a generative AI model and selecting the optimal purchase option. This enables real-time consumable management within the factory and efficient procurement of consumables from the optimal supplier.

[0524] "Consumables" refer to items that are consumed through use and require regular replenishment. In a factory setting, this would include bolts, nuts, and lubricants.

[0525] A "detection device" is a device that uses various sensors to monitor the inventory status of goods in real time.

[0526] An "information processing platform" refers to the foundation for data processing and purchasing activities on the internet, such as commercial websites and e-commerce services.

[0527] A "generative AI model" refers to an artificial intelligence algorithm that generates the optimal choice based on past data and trends.

[0528] A "supplier" is a producer or distributor that supplies goods or services.

[0529] "Inventory status" is an indicator that shows the usable quantity of a particular item at a given time.

[0530] "Real-time" refers to the instantaneous processing of data and updating of information.

[0531] The "optimal purchase option" refers to the most advantageous purchase choice, taking into account multiple factors such as cost, delivery time, and supply stability.

[0532] A "consumption pattern" refers to a consistent trend in the use or purchase of a particular item over a certain period of time.

[0533] "Savings advice" refers to guidelines for efficiently managing goods and making suggestions that lead to cost reduction.

[0534] The system for implementing this invention is designed to efficiently manage the inventory of consumables used in a factory. This system consists of sensors, a server, and user terminals.

[0535] First, sensors are installed throughout the factory, and weight sensors and image recognition cameras are used as needed to detect the inventory status of consumables in real time. The inventory data obtained from the sensors is transmitted to a server via wireless communication.

[0536] The server receives this data and performs data analysis to determine stock shortages. The server uses Python to analyze inventory data and leverages a generative AI model—specifically TensorFlow—to predict future consumption patterns. Furthermore, this model is used to explore multiple information processing platforms on the internet and select the optimal purchase option.

[0537] The server sends a notification to the user's device, such as a smartphone or tablet, when an option is selected. Upon receiving the notification, the user can decide to purchase the item via their device. Once the user confirms the purchase, the information is sent back to the server, which automatically sends the order to the selected supplier.

[0538] As a concrete example, when a robot in a factory detects the remaining amount of lubricant, the server selects the optimal supplier and notifies the user of a cost-saving proposal through bulk purchasing. The user approves the proposal using a control device and completes the order in a few operations.

[0539] An example of a prompt message would be, "Please tell me how to apply AI to consumable inventory management in a factory and create optimal purchase suggestions when supplies run out."

[0540] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0541] Step 1:

[0542] The sensors monitor consumables within the factory in real time, acquiring inventory data such as weight and quantity. This acquired data is transmitted to a server via wireless communication. The input is the sensor's measurement data, and the output is the data transfer to the server.

[0543] Step 2:

[0544] The server analyzes the received inventory data. Using Python, it determines whether items are out of stock by comparing current inventory levels with past consumption patterns. The input is inventory data transmitted from sensors, and the output is a flag indicating whether items are out of stock.

[0545] Step 3:

[0546] The server uses a generative AI model to predict future consumption patterns. This model runs on TensorFlow and calculates optimal purchase timing and quantity from diverse data. Inputs are inventory data and historical consumption history, and outputs are predicted consumption patterns and recommended purchase options.

[0547] Step 4:

[0548] The server uses a generative AI model to search for the optimal purchase options from information processing platforms on the internet. An optimization algorithm selects the best option considering factors such as price, delivery time, and supplier quality. The input is predicted consumption patterns and platform information, while the output is the purchase options suggested to the user.

[0549] Step 5:

[0550] A notification of selected purchase options is sent from the server to the user's device. The user receives the notification on their smartphone or tablet and checks the displayed options. The input is the notification content from the server, and the output is the information displayed on the user's device.

[0551] Step 6:

[0552] The user reviews the notification and decides to purchase. When the user presses the purchase button on the command device on their terminal, that information is sent back to the server. The input is the user's decision, and the output is the order confirmation data.

[0553] Step 7:

[0554] The server automatically sends orders to selected suppliers based on the order confirmation data. The input is the purchase confirmation data, and the output is the order data sent to the suppliers.

[0555] 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.

[0556] This invention provides a system for streamlining inventory management of consumables and improving user convenience. This system functions by combining sensors that monitor the inventory status of consumables in real time, a server that analyzes inventory data, a terminal that notifies the user of selected purchase options, and an emotion engine that recognizes the user's emotions.

[0557] Specifically, sensors installed in the home transmit inventory information for each consumable item to a server. The server analyzes this information, and if a shortage is detected, it uses a generative AI model to select the optimal purchase option. The selected option is sent as a notification to the user's device, and the user makes a purchase decision based on that information.

[0558] Furthermore, this system incorporates an emotion engine that analyzes the user's emotions. For example, the server uses the emotion engine to infer the user's emotional state from their facial expressions and tone of voice, and if it determines that the user is stressed, it optimizes the user experience by reducing the frequency of reminder notifications.

[0559] Furthermore, the emotion engine also evaluates the user's satisfaction with the purchase options they have selected and uses the results to improve future suggestions. For example, by combining and analyzing the user's purchase history and emotion data, the server can suggest better alternative products or discounted products to users who "purchase the same products every time," thereby increasing added value for the user.

[0560] The introduction of this system will allow users to manage consumables without unnecessary hassle and receive optimal suggestions tailored to their needs. As a result, time and cost savings will be achieved, and suppliers can expect improved customer retention.

[0561] The following describes the processing flow.

[0562] Step 1:

[0563] The server receives inventory data transmitted from sensors installed in the home. This data includes information on the current remaining amount of consumables such as detergent and tissues.

[0564] Step 2:

[0565] The server analyzes the received data to determine if the consumables are below a set threshold. If a shortage is detected, the server proceeds to the next step based on this information.

[0566] Step 3:

[0567] The server uses a generated AI model to search multiple e-commerce sites and select the best purchase option for consumables that are out of stock. This comparison is based on factors such as price, delivery time, and customer reviews.

[0568] Step 4:

[0569] The emotion engine analyzes the user's emotional state. This detects emotions from the user's facial expression data and voice input, and estimates the user's stress and satisfaction levels.

[0570] Step 5:

[0571] The server customizes purchase suggestion notifications based on data from the emotion engine. For example, if the system determines that the user is stressed, purchase suggestion notifications will be sent in a calmer tone.

[0572] Step 6:

[0573] The device receives notifications from the server and presents the user with the most suitable purchase options. This includes emotionally sensitive messages and suggestions that take into account the user's recent purchase history.

[0574] Step 7:

[0575] The user reviews the presented purchase options and confirms their purchase intention by pressing the order button. This input is sent to the server via the terminal.

[0576] Step 8:

[0577] The server receives a purchase order from the user and automatically places the order with the selected e-commerce site. This process is efficient and requires no extra effort from the user.

[0578] Step 9:

[0579] The server stores past purchase history and user sentiment data in a database. This allows for further personalization of future purchase suggestions.

[0580] Through this process, not only is consumables managed, but services that also take into account the user's feelings are provided.

[0581] (Example 2)

[0582] 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."

[0583] Traditional inventory management systems struggled to accurately track the stock status of consumables, leading to daily inconvenience due to unnoticed shortages. Furthermore, uniform notification methods and purchase suggestions failed to adequately address the diverse needs and emotions of users, hindering efficient purchasing. Moreover, the lack of optimization of suggestions based on emotional states prevented a sufficient improvement in user satisfaction.

[0584] 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.

[0585] In this invention, the server includes means for receiving data from sensors that detect the inventory status of consumables, means for selecting the optimal purchase option using a generative AI model, and means for optimizing notification content according to the user's emotional state. This streamlines inventory management of consumables and enables appropriate purchase suggestions that respond to the user's emotions.

[0586] "Consumable goods" are items that are used regularly in daily life or work, and whose demand is generated once they are used up.

[0587] "Inventory status" refers to information indicating how much of a particular item is currently on hand or how much has been consumed.

[0588] A "sensor" is a device that detects physical environmental information and transmits it to a system as digital data.

[0589] A "generative AI model" is an algorithm that learns patterns and relationships from large amounts of data and generates appropriate results for new data.

[0590] A "communication network" is a general term for the technical infrastructure used to transmit data to remote locations.

[0591] "Purchase options" refer to the choices available when replenishing consumables, indicating the means or sources of purchase and supply.

[0592] A "user" is an individual or organization that uses a particular product or service.

[0593] "Emotional state" refers to the state of emotions and psychological reactions experienced by individual users.

[0594] An "algorithm" is a set of computational procedures or rules established to solve a specific problem.

[0595] "Improving the proposal" means improving the options and advice offered to make them more useful, based on past data and new information.

[0596] This invention is a system designed to streamline inventory management of consumables and improve the user experience. The system consists of sensors, a server, an emotion analysis engine, and terminals.

[0597] First, sensors are installed in the home to monitor the remaining amount of each consumable in real time. Weight sensors and RFID tags may be used for this purpose. The collected data is transmitted to a server via wireless communication.

[0598] The server analyzes the received inventory data. A generative AI model is used for the analysis, which generates optimal purchase options when consumables fall below a certain level. Operating this AI model requires cloud services and high-performance server hardware, and it implements computationally intensive AI algorithms. An example of a prompt given to the AI ​​model might be, "Recommend the best time and place to purchase detergent."

[0599] Analysis results are notified to the user via a terminal. Smartphones and PCs are used as terminals, and information is provided via dedicated apps or web pages. Based on this, users decide whether to purchase consumables. The terminal has a built-in interface for displaying notifications, allowing users to respond quickly.

[0600] Furthermore, the server uses an emotion analysis engine to understand the user's emotional state. For example, it analyzes the user's tone of voice and facial expressions to infer their current emotional state. This function is implemented using speech recognition and image analysis technologies, and it is possible to adjust the frequency and content of notifications according to the user's stress level.

[0601] For example, if a user has low satisfaction with a frequently purchased consumable item, the sentiment analysis engine feeds that data back, and the AI ​​model generates more suitable suggestions. In this way, time and cost savings can be achieved, and the user experience can be significantly improved. This system is expected to streamline complex inventory management and dramatically improve user convenience.

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] Sensors installed in the user's home collect inventory information on consumables in real time. The sensors measure the remaining quantity of items via weight and RFID, and transmit this data to a server. The input is the physical state of each consumable, and the output is digitized inventory data. At this stage, data collection and transmission are the main operations.

[0605] Step 2:

[0606] The server analyzes the inventory status of consumables based on inventory data received from sensors. Here, the received data is stored in a database, and calculations are performed to evaluate the degree of consumption. The input is inventory data from sensors, and the output is the analysis result indicating whether the consumables need to be replenished. Specific operations include database querying and threshold-based determination.

[0607] Step 3:

[0608] The server uses a generative AI model to select the optimal purchase option based on prompt messages. The AI ​​model performs inference using the prompt message "What should I buy next?" when consumables fall below a predetermined threshold. The input consists of inventory data analysis results and prompt messages, while the output is a purchase suggestion tailored to the user's needs. This process involves executing the AI ​​algorithm and extracting the results.

[0609] Step 4:

[0610] The selected purchase option is sent from the server to the terminal and notified to the user. The terminal is a smartphone or PC, and it accepts the user's decision on whether or not to purchase based on the notification. The input is the notification information of the purchase option, and the output is the user's purchase decision or further action. The specific operation here is the process of displaying an application notification on the terminal and the user's response.

[0611] Step 5:

[0612] The server uses an emotion analysis engine to analyze the user's emotional state. It evaluates psychological responses from audio and image data, and adjusts the frequency and content of notifications based on the acquired data. The input is data related to the user's emotions, and the output is optimized settings aimed at improving the user experience. The use of audio analysis and image recognition technologies is a concrete implementation of this process.

[0613] Step 6:

[0614] Ultimately, the server stores purchase history and sentiment analysis results for future recommendation improvements. This involves a learning and updating process using historical data. Inputs are past purchase history and sentiment data, and outputs are improved purchase options for the next recommendation. The specific operations are recording to a database and the algorithm learning process.

[0615] (Application Example 2)

[0616] 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."

[0617] Traditional inventory management systems were limited to detecting shortages of consumables and offering purchase options, lacking the ability to provide flexible suggestions that took into account the user's emotional state. This resulted in a lack of timely suggestions tailored to user needs, reducing overall convenience. Furthermore, standard advice failed to reflect individual user emotions or circumstances, making the system less user-friendly.

[0618] 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.

[0619] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, means for searching for a digital sales platform using a generative AI model and selecting the optimal purchase option, and means for enhancing the suggestions provided using sentiment analysis results. This makes it possible to provide appropriate and timely suggestions that reflect the user's emotions, greatly improving user convenience.

[0620] A "detection device" is a device used to monitor the inventory of consumables in real time and acquire that data.

[0621] "Means for determining stock shortages" refers to a function that uses data obtained from a detection device to determine whether the inventory of consumables meets the required standard.

[0622] A "generative AI model" is a system that uses artificial intelligence technology to select the optimal purchase option from a digital sales platform.

[0623] A "digital sales platform" is an e-commerce platform that provides options for purchasing goods and services over the internet.

[0624] "Methods for improving suggestions using emotion analysis results" refers to a function that analyzes the user's emotional state and adjusts the content and timing of purchase suggestions based on the results.

[0625] A "user" is an individual user who uses the system to manage their inventory of consumables and receive purchase options.

[0626] This invention is a system for streamlining the inventory management of consumables in the home. To implement it, the following elements are required:

[0627] 1. Hardware

[0628] Multiple detection devices are installed in the home to monitor the inventory status of consumables. These devices detect real-time data on consumables and send it to a server. Furthermore, users receive notifications using their smartphones.

[0629] 2. Software

[0630] The server is equipped with software that analyzes received real-time data to determine if there are any stock shortages. Next, it uses a generative AI model to search for and select the optimal purchase option from the digital sales platform. An emotion analysis engine evaluates the user's emotional state based on their facial expressions and tone of voice, and adjusts the content of suggestions and notification timing based on the results to provide the most appropriate recommendations.

[0631] 3. Data processing and calculations

[0632] A server receives inventory data sent from a detection device, and a generative AI model is used to explore digital sales platforms. Furthermore, an emotion analysis algorithm evaluates the user's emotions using data from their facial expressions and voice. Purchase options selected by the generative AI model are then notified to the user's smartphone in a customized format based on the user's emotion data.

[0633] Specific example

[0634] When a user is relaxing on the weekend, the system uses emotion analysis to detect if they are experiencing stress. As a result, notifications about low-stock consumables can include suggestions for stress-reducing products, thereby increasing user satisfaction.

[0635] Example of a prompt

[0636] "We've analyzed the data from the [sensor name] and it appears our milk inventory is running low. Please suggest a stress-relieving product as our next purchase option."

[0637] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0638] Step 1:

[0639] The server receives inventory data for consumables sent from detection devices within the home. This input data includes the current quantity of each consumable. The server analyzes this data and determines that an item is out of stock if the inventory falls below a certain threshold. A simple thresholding algorithm is used for this data processing. The output is a list of consumables that have been determined to be out of stock.

[0640] Step 2:

[0641] The server, upon detecting an item as out of stock, utilizes a generative AI model to search for a digital sales platform. The input to this search is a list of out-of-stock items, and the output is the optimal purchase option for that item. The generative AI model considers user purchasing trends based on inventory data and selects the best option from a cloud-based database.

[0642] Step 3:

[0643] The server uses facial expression and voice data acquired from the user's smartphone to input into an emotion analysis engine and estimate the user's emotional state. The input data includes image data of facial expressions and audio data, and the output is information about the emotional state. The analysis process uses machine learning algorithms to determine whether the input data is negative, positive, or neutral.

[0644] Step 4:

[0645] The server processes notifications for purchase options based on the user's emotional state. This step adjusts the content and frequency of notifications based on the emotional state. For example, if a user's stress level is detected, specific actions are taken, such as adding suggestions for products that promote relaxation. The input is emotional state information, and the output is the optimized notification content.

[0646] Step 5:

[0647] The device (smartphone) displays a notification sent from the server to the user. The user can proceed with the purchase by reviewing the notification and selecting the presented purchase option. The output is the user's selected purchase option, which is then added to the next purchase history data.

[0648] Step 6:

[0649] Users provide feedback based on their purchase history data to improve future recommendations. This input represents user satisfaction data with their choices, and the server analyzes this feedback and incorporates it into the algorithm of the generating AI model to improve the accuracy of future recommendations. The output is information about algorithm updates aimed at improving future recommendations.

[0650] 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.

[0651] 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 those described above. 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 shown 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.

[0652] 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.

[0653] [Fourth Embodiment]

[0654] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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".

[0667] This invention provides a system to automate inventory management of consumables and streamline user purchasing. The system operates by using sensors to monitor the inventory status of consumables in the home in real time and transmitting the data to a server. The server analyzes this data to determine if items are out of stock. When a shortage is detected, the server utilizes a generative AI model to search multiple e-commerce sites on the internet and select the optimal purchase option.

[0668] The selected purchase options are notified to the user from the server. This notification is sent to the device, such as a smartphone or tablet, and the user can then decide on a purchase based on it. When the user presses the order button on the device, that information is sent to the server, which automatically places the order with the selected e-commerce site.

[0669] Furthermore, the server accumulates past purchase history and analyzes consumption patterns. Based on this analysis, the server provides users with money-saving advice that leads to optimized consumption and cost reduction. For example, if the server detects through analysis that a user's detergent consumption is higher than the average household, it may notify the user of discounts available for bulk purchases.

[0670] Thus, this system significantly streamlines users' daily consumable management, providing time savings and economic benefits. Furthermore, for suppliers, it reduces the risk of customers switching to other products, enabling stable customer retention.

[0671] The following describes the processing flow.

[0672] Step 1:

[0673] The server receives data transmitted from various sensors installed in the home. This data includes the current inventory status of consumables such as detergent and tissue paper.

[0674] Step 2:

[0675] The server analyzes the received inventory data to determine if the inventory of consumables falls below a set threshold. If it does, it is determined to be out of stock.

[0676] Step 3:

[0677] If the server determines that an item is out of stock, it uses a generative AI model to search multiple e-commerce sites and retrieve purchase options for detergent or tissue paper. During this process, it selects the optimal purchase option based on factors such as price, delivery time, and user reviews.

[0678] Step 4:

[0679] The server notifies the user of their selected purchase option. This notification is sent to the user's smartphone or tablet, allowing the user to confirm the best purchase method.

[0680] Step 5:

[0681] The user reviews the purchase options displayed on their device and presses the order button if necessary. This action sends the user's purchase intention to the server.

[0682] Step 6:

[0683] The server receives the user's order request and automatically places the order on a selected e-commerce site. This process is efficient and saves the user time and effort.

[0684] Step 7:

[0685] The server saves this order history to a database and uses it to analyze future consumption patterns. This data helps understand the user's spending tendencies and is used to make future purchase suggestions and savings advice.

[0686] (Example 1)

[0687] 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".

[0688] Manually managing consumable inventory is time-consuming and labor-intensive, and carries the risk of stockouts and overpurchases. Furthermore, analyzing consumption patterns to obtain appropriate purchasing advice is difficult. This leads to decreased efficiency in daily life and increased financial burden. Therefore, there is a need for a system that automatically manages consumable inventory and provides optimal purchasing options to streamline daily life.

[0689] 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.

[0690] In this invention, the server includes means for receiving information from a device that senses the inventory of consumables, means for determining the shortage status of consumables based on the received information, and means for searching e-commerce sites using a generating AI program to determine the optimal purchase option. This enables automatic management of consumable inventory and selection and notification of the optimal purchase option.

[0691] "Consumables" refer to items that gradually decrease in quantity through use and require replenishment.

[0692] "Inventory information" refers to information regarding the quantity and condition of consumables currently held.

[0693] "Device" refers to hardware and peripheral equipment used to perform a specific function.

[0694] "Means of receiving information" refers to methods and devices for acquiring external data or signals.

[0695] "Means for determining shortages" refers to algorithms or devices for detecting when consumables are decreasing based on specific criteria.

[0696] A "generative AI program" refers to artificial intelligence software that analyzes large amounts of data and derives the optimal solution based on the results.

[0697] A "commercial trading site" refers to a web platform that sells goods and services online.

[0698] "Optimal purchase options" refer to the results of selecting the most desirable products or transactions based on multiple criteria such as price, quality, and delivery conditions.

[0699] "Storage" refers to the act of saving data and information for a long period of time in preparation for later analysis and reference.

[0700] "Consumption trends" refer to the patterns and trends in the use of consumable goods over time.

[0701] "Savings advice" refers to suggestions or notices aimed at reducing costs and promoting efficient consumption.

[0702] In embodiments of this invention, the system operates using the following hardware and software.

[0703] First, users monitor the inventory status of consumables using sensors installed in their homes. These sensors include, for example, weight sensors and optical sensors. This allows for real-time detection of physical changes in consumables.

[0704] The sensor transmits acquired inventory information to a server via the internet. Wi-Fi or Bluetooth is used for transmission, and HTTP or MQTT is used as the data protocol.

[0705] Next, the server analyzes the received data using analysis libraries such as Pandas and NumPy in Python. The purpose of the analysis is to determine whether the inventory is appropriate or whether replenishment is necessary.

[0706] If a shortage is detected, the server uses a generative AI model to suggest the best purchase option. The OpenAI GPT series is used as the generative AI model. This allows the system to explore multiple e-commerce sites and make a comprehensive judgment based on price and delivery conditions.

[0707] Examples of prompt messages used in this situation include specific details such as, "Please suggest the best toilet paper purchase options for the user's specified address. Priorities are low price, fast delivery, and high customer reviews. Please also consider current stock levels and past consumption patterns."

[0708] The server notifies the user of their chosen purchase option on their device, such as a smartphone or tablet. Push notification technologies, such as Firebase Cloud Messaging, are used for this purpose.

[0709] Once a user decides to purchase something on their device, the server automatically sends the data via the e-commerce site's API, and the order is completed.

[0710] Furthermore, the server stores users' purchase history and analyzes consumption patterns using statistical tools. This makes it possible to create efficient purchasing plans for consumables and provide users with money-saving advice.

[0711] In this way, the management of consumables in the user's daily life is automated, resulting in a system that supports an efficient and economical lifestyle.

[0712] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0713] Step 1:

[0714] Sensors installed in the user's home monitor consumable inventory information in real time. For example, a weight sensor measures the remaining amount of toilet paper. The input is physical weight data, and the output generates inventory level data. This data is used to detect when inventory falls below a set threshold.

[0715] Step 2:

[0716] The monitored inventory data is transmitted from the sensor to the server. Wi-Fi is used as the communication protocol, and the data is sent via HTTP requests. The input is inventory data from the sensor, and the output is an update to the database stored on the server. The server receives this data and stores it in the database.

[0717] Step 3:

[0718] The server analyzes the accumulated inventory data using the Python Pandas library. The input is the inventory database record, and the output is the result of determining whether consumables are out of stock. This analysis determines whether replenishment of consumables is necessary.

[0719] Step 4:

[0720] If a stock shortage is detected, the server uses a generative AI model to search for the best purchase option. It utilizes an AI model from the GPT series, taking the prompt "Suggest the best toilet paper purchase option to the user's specified address" as input. The output is purchase option information from online e-commerce sites.

[0721] Step 5:

[0722] The server notifies the user's device of the acquired purchase options. Using push notification technology (e.g., Firebase Cloud Messaging), the input is data of the selected purchase options, and the output is a purchase recommendation message displayed on the device.

[0723] Step 6:

[0724] The user reviews the purchase options displayed on their device and presses the "Purchase" button. The input is the user's action on the device, and the output is the order processing request data. This data is sent to the server.

[0725] Step 7:

[0726] The server receives order requests and connects to the e-commerce site via an API to execute the orders. The input is the order request data from the user, and the output is an order slip sent to the e-commerce site.

[0727] Step 8:

[0728] After an order is completed, the server stores the purchase history in a database and analyzes the consumption pattern. The input is past purchase history data, and the output is a report of consumption patterns based on statistical analysis. Based on this information, it provides a means to generate and notify the user of future savings advice.

[0729] (Application Example 1)

[0730] 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".

[0731] Traditionally, managing consumables within factories has often been done manually, which has led to a high likelihood of inventory management deficiencies and production line stoppages due to shortages. Furthermore, obtaining real-time information on large orders and selecting optimal suppliers is difficult, resulting in increased operational costs. In this context, there is a need for a means of efficiently and automatically managing industrial consumables.

[0732] 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.

[0733] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, and means for searching for an information processing platform using a generative AI model and selecting the optimal purchase option. This enables real-time consumable management within the factory and efficient procurement of consumables from the optimal supplier.

[0734] "Consumables" refer to items that are consumed through use and require regular replenishment. In a factory setting, this would include bolts, nuts, and lubricants.

[0735] A "detection device" is a device that uses various sensors to monitor the inventory status of goods in real time.

[0736] An "information processing platform" refers to the foundation for data processing and purchasing activities on the internet, such as commercial websites and e-commerce services.

[0737] A "generative AI model" refers to an artificial intelligence algorithm that generates the optimal choice based on past data and trends.

[0738] A "supplier" is a producer or distributor that supplies goods or services.

[0739] "Inventory status" is an indicator that shows the usable quantity of a particular item at a given time.

[0740] "Real-time" refers to the instantaneous processing of data and updating of information.

[0741] The "optimal purchase option" refers to the most advantageous purchase choice, taking into account multiple factors such as cost, delivery time, and supply stability.

[0742] A "consumption pattern" refers to a consistent trend in the use or purchase of a particular item over a certain period of time.

[0743] "Savings advice" refers to guidelines for efficiently managing goods and making suggestions that lead to cost reduction.

[0744] The system for implementing this invention is designed to efficiently manage the inventory of consumables used in a factory. This system consists of sensors, a server, and user terminals.

[0745] First, sensors are installed throughout the factory, and weight sensors and image recognition cameras are used as needed to detect the inventory status of consumables in real time. The inventory data obtained from the sensors is transmitted to a server via wireless communication.

[0746] The server receives this data and performs data analysis to determine stock shortages. The server uses Python to analyze inventory data and leverages a generative AI model—specifically TensorFlow—to predict future consumption patterns. Furthermore, this model is used to explore multiple information processing platforms on the internet and select the optimal purchase option.

[0747] The server sends a notification to the user's device, such as a smartphone or tablet, when an option is selected. Upon receiving the notification, the user can decide to purchase the item via their device. Once the user confirms the purchase, the information is sent back to the server, which automatically sends the order to the selected supplier.

[0748] As a concrete example, when a robot in a factory detects the remaining amount of lubricant, the server selects the optimal supplier and notifies the user of a cost-saving proposal through bulk purchasing. The user approves the proposal using a control device and completes the order in a few operations.

[0749] An example of a prompt message would be, "Please tell me how to apply AI to consumable inventory management in a factory and create optimal purchase suggestions when supplies run out."

[0750] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0751] Step 1:

[0752] The sensors monitor consumables within the factory in real time, acquiring inventory data such as weight and quantity. This acquired data is transmitted to a server via wireless communication. The input is the sensor's measurement data, and the output is the data transfer to the server.

[0753] Step 2:

[0754] The server analyzes the received inventory data. Using Python, it determines whether items are out of stock by comparing current inventory levels with past consumption patterns. The input is inventory data transmitted from sensors, and the output is a flag indicating whether items are out of stock.

[0755] Step 3:

[0756] The server uses a generative AI model to predict future consumption patterns. This model runs on TensorFlow and calculates optimal purchase timing and quantity from diverse data. Inputs are inventory data and historical consumption history, and outputs are predicted consumption patterns and recommended purchase options.

[0757] Step 4:

[0758] The server uses a generative AI model to search for the optimal purchase options from information processing platforms on the internet. An optimization algorithm selects the best option considering factors such as price, delivery time, and supplier quality. The input is predicted consumption patterns and platform information, while the output is the purchase options suggested to the user.

[0759] Step 5:

[0760] A notification of selected purchase options is sent from the server to the user's device. The user receives the notification on their smartphone or tablet and checks the displayed options. The input is the notification content from the server, and the output is the information displayed on the user's device.

[0761] Step 6:

[0762] The user reviews the notification and decides to purchase. When the user presses the purchase button on the command device on their terminal, that information is sent back to the server. The input is the user's decision, and the output is the order confirmation data.

[0763] Step 7:

[0764] The server automatically sends orders to selected suppliers based on the order confirmation data. The input is the purchase confirmation data, and the output is the order data sent to the suppliers.

[0765] 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.

[0766] This invention provides a system for streamlining inventory management of consumables and improving user convenience. This system functions by combining sensors that monitor the inventory status of consumables in real time, a server that analyzes inventory data, a terminal that notifies the user of selected purchase options, and an emotion engine that recognizes the user's emotions.

[0767] Specifically, sensors installed in the home transmit inventory information for each consumable item to a server. The server analyzes this information, and if a shortage is detected, it uses a generative AI model to select the optimal purchase option. The selected option is sent as a notification to the user's device, and the user makes a purchase decision based on that information.

[0768] Furthermore, this system incorporates an emotion engine that analyzes the user's emotions. For example, the server uses the emotion engine to infer the user's emotional state from their facial expressions and tone of voice, and if it determines that the user is stressed, it optimizes the user experience by reducing the frequency of reminder notifications.

[0769] Furthermore, the emotion engine also evaluates the user's satisfaction with the purchase options they have selected and uses the results to improve future suggestions. For example, by combining and analyzing the user's purchase history and emotion data, the server can suggest better alternative products or discounted products to users who "purchase the same products every time," thereby increasing added value for the user.

[0770] The introduction of this system will allow users to manage consumables without unnecessary hassle and receive optimal suggestions tailored to their needs. As a result, time and cost savings will be achieved, and suppliers can expect improved customer retention.

[0771] The following describes the processing flow.

[0772] Step 1:

[0773] The server receives inventory data transmitted from sensors installed in the home. This data includes information on the current remaining amount of consumables such as detergent and tissues.

[0774] Step 2:

[0775] The server analyzes the received data to determine if the consumables are below a set threshold. If a shortage is detected, the server proceeds to the next step based on this information.

[0776] Step 3:

[0777] The server uses a generated AI model to search multiple e-commerce sites and select the best purchase option for consumables that are out of stock. This comparison is based on factors such as price, delivery time, and customer reviews.

[0778] Step 4:

[0779] The emotion engine analyzes the user's emotional state. This detects emotions from the user's facial expression data and voice input, and estimates the user's stress and satisfaction levels.

[0780] Step 5:

[0781] The server customizes purchase suggestion notifications based on data from the emotion engine. For example, if the system determines that the user is stressed, purchase suggestion notifications will be sent in a calmer tone.

[0782] Step 6:

[0783] The device receives notifications from the server and presents the user with the most suitable purchase options. This includes emotionally sensitive messages and suggestions that take into account the user's recent purchase history.

[0784] Step 7:

[0785] The user reviews the presented purchase options and confirms their purchase intention by pressing the order button. This input is sent to the server via the terminal.

[0786] Step 8:

[0787] The server receives a purchase order from the user and automatically places the order with the selected e-commerce site. This process is efficient and requires no extra effort from the user.

[0788] Step 9:

[0789] The server stores past purchase history and user sentiment data in a database. This allows for further personalization of future purchase suggestions.

[0790] Through this process, not only is consumables managed, but services that also take into account the user's feelings are provided.

[0791] (Example 2)

[0792] 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".

[0793] Traditional inventory management systems struggled to accurately track the stock status of consumables, leading to daily inconvenience due to unnoticed shortages. Furthermore, uniform notification methods and purchase suggestions failed to adequately address the diverse needs and emotions of users, hindering efficient purchasing. Moreover, the lack of optimization of suggestions based on emotional states prevented a sufficient improvement in user satisfaction.

[0794] 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.

[0795] In this invention, the server includes means for receiving data from sensors that detect the inventory status of consumables, means for selecting the optimal purchase option using a generative AI model, and means for optimizing notification content according to the user's emotional state. This streamlines inventory management of consumables and enables appropriate purchase suggestions that respond to the user's emotions.

[0796] "Consumable goods" are items that are used regularly in daily life or work, and whose demand is generated once they are used up.

[0797] "Inventory status" refers to information indicating how much of a particular item is currently on hand or how much has been consumed.

[0798] A "sensor" is a device that detects physical environmental information and transmits it to a system as digital data.

[0799] A "generative AI model" is an algorithm that learns patterns and relationships from large amounts of data and generates appropriate results for new data.

[0800] A "communication network" is a general term for the technical infrastructure used to transmit data to remote locations.

[0801] "Purchase options" refer to the choices available when replenishing consumables, indicating the means or sources of purchase and supply.

[0802] A "user" is an individual or organization that uses a particular product or service.

[0803] "Emotional state" refers to the state of emotions and psychological reactions experienced by individual users.

[0804] An "algorithm" is a set of computational procedures or rules established to solve a specific problem.

[0805] "Improving the proposal" means improving the options and advice offered to make them more useful, based on past data and new information.

[0806] This invention is a system designed to streamline inventory management of consumables and improve the user experience. The system consists of sensors, a server, an emotion analysis engine, and terminals.

[0807] First, sensors are installed in the home to monitor the remaining amount of each consumable in real time. Weight sensors and RFID tags may be used for this purpose. The collected data is transmitted to a server via wireless communication.

[0808] The server analyzes the received inventory data. A generative AI model is used for the analysis, which generates optimal purchase options when consumables fall below a certain level. Operating this AI model requires cloud services and high-performance server hardware, and it implements computationally intensive AI algorithms. An example of a prompt given to the AI ​​model might be, "Recommend the best time and place to purchase detergent."

[0809] Analysis results are notified to the user via a terminal. Smartphones and PCs are used as terminals, and information is provided via dedicated apps or web pages. Based on this, users decide whether to purchase consumables. The terminal has a built-in interface for displaying notifications, allowing users to respond quickly.

[0810] Furthermore, the server uses an emotion analysis engine to understand the user's emotional state. For example, it analyzes the user's tone of voice and facial expressions to infer their current emotional state. This function is implemented using speech recognition and image analysis technologies, and it is possible to adjust the frequency and content of notifications according to the user's stress level.

[0811] For example, if a user has low satisfaction with a frequently purchased consumable item, the sentiment analysis engine feeds that data back, and the AI ​​model generates more suitable suggestions. In this way, time and cost savings can be achieved, and the user experience can be significantly improved. This system is expected to streamline complex inventory management and dramatically improve user convenience.

[0812] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0813] Step 1:

[0814] Sensors installed in the user's home collect inventory information on consumables in real time. The sensors measure the remaining quantity of items via weight and RFID, and transmit this data to a server. The input is the physical state of each consumable, and the output is digitized inventory data. At this stage, data collection and transmission are the main operations.

[0815] Step 2:

[0816] The server analyzes the inventory status of consumables based on inventory data received from sensors. Here, the received data is stored in a database, and calculations are performed to evaluate the degree of consumption. The input is inventory data from sensors, and the output is the analysis result indicating whether the consumables need to be replenished. Specific operations include database querying and threshold-based determination.

[0817] Step 3:

[0818] The server uses a generative AI model to select the optimal purchase option based on prompt messages. The AI ​​model performs inference using the prompt message "What should I buy next?" when consumables fall below a predetermined threshold. The input consists of inventory data analysis results and prompt messages, while the output is a purchase suggestion tailored to the user's needs. This process involves executing the AI ​​algorithm and extracting the results.

[0819] Step 4:

[0820] The selected purchase option is sent from the server to the terminal and notified to the user. The terminal is a smartphone or PC, and it accepts the user's decision on whether or not to purchase based on the notification. The input is the notification information of the purchase option, and the output is the user's purchase decision or further action. The specific operation here is the process of displaying an application notification on the terminal and the user's response.

[0821] Step 5:

[0822] The server uses an emotion analysis engine to analyze the user's emotional state. It evaluates psychological responses from audio and image data, and adjusts the frequency and content of notifications based on the acquired data. The input is data related to the user's emotions, and the output is optimized settings aimed at improving the user experience. The use of audio analysis and image recognition technologies is a concrete implementation of this process.

[0823] Step 6:

[0824] Ultimately, the server stores purchase history and sentiment analysis results for future recommendation improvements. This involves a learning and updating process using historical data. Inputs are past purchase history and sentiment data, and outputs are improved purchase options for the next recommendation. The specific operations are recording to a database and the algorithm learning process.

[0825] (Application Example 2)

[0826] 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".

[0827] Traditional inventory management systems were limited to detecting shortages of consumables and offering purchase options, lacking the ability to provide flexible suggestions that took into account the user's emotional state. This resulted in a lack of timely suggestions tailored to user needs, reducing overall convenience. Furthermore, standard advice failed to reflect individual user emotions or circumstances, making the system less user-friendly.

[0828] 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.

[0829] In this invention, the server includes means for receiving data from a detection device that detects the inventory status of consumables, means for determining consumable shortages based on the received data, means for searching for a digital sales platform using a generative AI model and selecting the optimal purchase option, and means for enhancing the suggestions provided using sentiment analysis results. This makes it possible to provide appropriate and timely suggestions that reflect the user's emotions, greatly improving user convenience.

[0830] A "detection device" is a device used to monitor the inventory of consumables in real time and acquire that data.

[0831] "Means for determining stock shortages" refers to a function that uses data obtained from a detection device to determine whether the inventory of consumables meets the required standard.

[0832] A "generative AI model" is a system that uses artificial intelligence technology to select the optimal purchase option from a digital sales platform.

[0833] A "digital sales platform" is an e-commerce platform that provides options for purchasing goods and services over the internet.

[0834] "Methods for improving suggestions using emotion analysis results" refers to a function that analyzes the user's emotional state and adjusts the content and timing of purchase suggestions based on the results.

[0835] A "user" is an individual user who uses the system to manage their inventory of consumables and receive purchase options.

[0836] This invention is a system for streamlining the inventory management of consumables in the home. To implement it, the following elements are required:

[0837] 1. Hardware

[0838] Multiple detection devices are installed in the home to monitor the inventory status of consumables. These devices detect real-time data on consumables and send it to a server. Furthermore, users receive notifications using their smartphones.

[0839] 2. Software

[0840] The server is equipped with software that analyzes received real-time data to determine if there are any stock shortages. Next, it uses a generative AI model to search for and select the optimal purchase option from the digital sales platform. An emotion analysis engine evaluates the user's emotional state based on their facial expressions and tone of voice, and adjusts the content of suggestions and notification timing based on the results to provide the most appropriate recommendations.

[0841] 3. Data processing and calculations

[0842] A server receives inventory data sent from a detection device, and a generative AI model is used to explore digital sales platforms. Furthermore, an emotion analysis algorithm evaluates the user's emotions using data from their facial expressions and voice. Purchase options selected by the generative AI model are then notified to the user's smartphone in a customized format based on the user's emotion data.

[0843] Specific example

[0844] When a user is relaxing on the weekend, the system uses emotion analysis to detect if they are experiencing stress. As a result, notifications about low-stock consumables can include suggestions for stress-reducing products, thereby increasing user satisfaction.

[0845] Example of a prompt

[0846] "We've analyzed the data from the [sensor name] and it appears our milk inventory is running low. Please suggest a stress-relieving product as our next purchase option."

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The server receives inventory data for consumables sent from detection devices within the home. This input data includes the current quantity of each consumable. The server analyzes this data and determines that an item is out of stock if the inventory falls below a certain threshold. A simple thresholding algorithm is used for this data processing. The output is a list of consumables that have been determined to be out of stock.

[0850] Step 2:

[0851] The server, upon detecting an item as out of stock, utilizes a generative AI model to search for a digital sales platform. The input to this search is a list of out-of-stock items, and the output is the optimal purchase option for that item. The generative AI model considers user purchasing trends based on inventory data and selects the best option from a cloud-based database.

[0852] Step 3:

[0853] The server uses facial expression and voice data acquired from the user's smartphone to input into an emotion analysis engine and estimate the user's emotional state. The input data includes image data of facial expressions and audio data, and the output is information about the emotional state. The analysis process uses machine learning algorithms to determine whether the input data is negative, positive, or neutral.

[0854] Step 4:

[0855] The server processes notifications for purchase options based on the user's emotional state. This step adjusts the content and frequency of notifications based on the emotional state. For example, if a user's stress level is detected, specific actions are taken, such as adding suggestions for products that promote relaxation. The input is emotional state information, and the output is the optimized notification content.

[0856] Step 5:

[0857] The device (smartphone) displays a notification sent from the server to the user. The user can proceed with the purchase by reviewing the notification and selecting the presented purchase option. The output is the user's selected purchase option, which is then added to the next purchase history data.

[0858] Step 6:

[0859] Users provide feedback based on their purchase history data to improve future recommendations. This input represents user satisfaction data with their choices, and the server analyzes this feedback and incorporates it into the algorithm of the generating AI model to improve the accuracy of future recommendations. The output is information about algorithm updates aimed at improving future recommendations.

[0860] 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.

[0861] 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 those described above. 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 shown 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] The following is further disclosed regarding the embodiments described above.

[0882] (Claim 1)

[0883] A means for receiving data from a sensor that detects the inventory status of consumables,

[0884] A means of determining a shortage of consumables based on the received data,

[0885] A method for exploring e-commerce sites using a generative AI model and selecting the optimal purchase option,

[0886] A means of notifying the user of the selected purchase options,

[0887] A means of receiving orders from users via an order button,

[0888] A means of sending user orders to an e-commerce site,

[0889] A means of accumulating purchase history and analyzing consumption patterns,

[0890] A means of providing savings advice based on the analysis results,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, which includes a procedure for detecting stock shortages based on a threshold and notifying the user only if such a shortage occurs.

[0894] (Claim 3)

[0895] The system according to claim 1, comprising an algorithm that compares the purchase history of consumables with data from other users and generates savings advice.

[0896] "Example 1"

[0897] (Claim 1)

[0898] Means for receiving information from a device that senses inventory information of consumables,

[0899] A means for determining the shortage status of consumables based on the received information,

[0900] A method for searching e-commerce sites using a generation AI program and determining the optimal purchase option,

[0901] A means of informing the user of the decided purchase option,

[0902] A means of receiving orders from users via a purchase button,

[0903] A means of sending user orders to the e-commerce site,

[0904] A means of accumulating purchase history and analyzing consumption trends,

[0905] A means of providing savings advice based on the analysis results,

[0906] A means of sending notifications to users via the device,

[0907] A means of selecting the optimal purchase option considering delivery conditions and costs,

[0908] A means of evaluating consumption patterns based on past purchase history and generating suggestions for optimizing consumption,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, comprising a procedure for detecting shortages based on a threshold and providing notifications as appropriate.

[0912] (Claim 3)

[0913] The system according to claim 1, which includes a calculation process that compares the purchase history of consumables with information of other users and generates savings advice.

[0914] "Application Example 1"

[0915] (Claim 1)

[0916] A means for receiving data from a detection device that detects the inventory status of consumables,

[0917] A means of determining a shortage of consumables based on the received data,

[0918] A means of exploring information processing platforms using generative AI models and selecting the optimal purchase option,

[0919] A means of notifying the user of the selected purchase options,

[0920] A means of receiving orders from users via a command device,

[0921] A means of transmitting user orders to an information processing platform,

[0922] A means of accumulating purchase history and analyzing consumption patterns,

[0923] A means of providing savings advice based on the analysis results,

[0924] A means for monitoring the usage status of consumables in real time according to the operation of industrial machinery,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, which includes a procedure for detecting stock shortages based on a threshold and notifying the user only if such a shortage occurs.

[0928] (Claim 3)

[0929] The system according to claim 1, comprising an algorithm that compares the purchase history of consumables with data from other users and generates savings advice.

[0930] "Example 2 of combining an emotion engine"

[0931] (Claim 1)

[0932] A means for receiving data from a sensor that detects the inventory status of consumables,

[0933] A means of determining a shortage of consumables based on the received data,

[0934] A method for selecting the optimal purchase option via a communication network using a generative AI model,

[0935] A means of notifying the user of the selected purchase options,

[0936] A method that utilizes algorithms to analyze the emotional state of users,

[0937] A means to optimize notification content according to the user's emotional state,

[0938] A method for improving suggestions by combining purchase history and sentiment analysis results,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, which includes means for detecting stock shortages based on a threshold and notifying the user only if such a situation occurs.

[0942] (Claim 3)

[0943] The system according to claim 1, comprising an algorithm that compares the purchase history of consumables with data from other users and generates savings advice.

[0944] "Application example 2 when combining with an emotional engine"

[0945] (Claim 1)

[0946] A device that receives data from a detection device that detects the inventory status of consumables,

[0947] A device that determines the shortage of consumables based on received data,

[0948] A device that uses a generative AI model to explore digital sales platforms and select the optimal purchase option,

[0949] A device that informs the user of the selected purchase option,

[0950] A device that receives orders from users through an order operation,

[0951] A device that transmits user orders to a digital sales platform,

[0952] A device that records purchase history and analyzes consumption trends,

[0953] A device that provides savings suggestions based on analysis results,

[0954] A device that analyzes the user's emotional state and adjusts the frequency and content of notifications based on that state,

[0955] A device that enhances the suggestions provided using the results of emotion analysis,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, which includes a process for determining whether an item is out of stock based on a standard value and notifying the user only if it is found to be out of stock.

[0959] (Claim 3)

[0960] The system according to claim 1, comprising a program that compares the purchase history of consumables with data from other users and generates savings suggestions. [Explanation of symbols]

[0961] 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 means for receiving data from a detection device that detects the inventory status of consumables, A means of determining a shortage of consumables based on the received data, A means of exploring information processing platforms using generative AI models and selecting the optimal purchase option, A means of notifying the user of the selected purchase options, A means of receiving orders from users via a command device, A means of transmitting user orders to an information processing platform, A means of accumulating purchase history and analyzing consumption patterns, A means of providing savings advice based on the analysis results, A means for monitoring the usage status of consumables in real time according to the operation of industrial machinery, A system that includes this.

2. The system according to claim 1, which includes a procedure for detecting stock shortages based on a threshold and notifying the user only if such a shortage occurs.

3. The system according to claim 1, which includes an algorithm that compares the purchase history of consumables with data from other users and generates savings advice.

Images