system

Abstract

The system according to this embodiment aims to suggest optimal stores and recipes in order to respond to rising prices and help households save money. [Solution] The system according to the embodiment comprises an acquisition unit, a suggestion unit, a discrimination unit, an analysis unit, a store suggestion unit, a reception unit, and a recipe suggestion unit. The acquisition unit acquires price information. The suggestion unit suggests the price information acquired by the acquisition unit to the user. The discrimination unit reads the receipt and identifies the purchased items. The analysis unit analyzes the purchase pattern from the purchase history identified by the discrimination unit. The store suggestion unit suggests the optimal store based on the purchase pattern analyzed by the analysis unit. The reception unit inputs information about the daily dinner. The recipe suggestion unit suggests the optimal recipe based on the information input by the reception unit and the data obtained by the acquisition unit and the analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to find an optimal store or recipe when purchasing food products that put pressure on household budgets due to rising prices, and there is room for improvement.

[0005] The system according to the embodiment aims to propose an optimal store or recipe in order to cope with rising prices and save household budgets.

Means for Solving the Problems

[0006] The system according to this embodiment includes an acquisition unit, a suggestion unit, a discrimination unit, an analysis unit, a store suggestion unit, a reception unit, and a recipe suggestion unit. The acquisition unit acquires price information. The suggestion unit suggests the price information acquired by the acquisition unit to the user. The discrimination unit reads the receipt and identifies the purchased items. The analysis unit analyzes the purchase pattern from the purchase history identified by the discrimination unit. The store suggestion unit suggests the optimal store based on the purchase pattern analyzed by the analysis unit. The reception unit inputs information about the daily dinner. The recipe suggestion unit suggests the optimal recipe based on the information input by the reception unit and the data obtained by the acquisition unit and the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can suggest optimal stores and recipes to help households save money in response to rising prices. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] 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.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] 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.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The savings support system according to an embodiment of the present invention is a system for low- and middle-income groups whose household budgets are being strained by rising prices. This savings support system utilizes GPS to obtain the daily prices of grocery stores near the user and suggests them to the user. Next, it reads the receipt to identify purchased items and analyzes the user's purchasing patterns from the history. Based on this, it suggests the best store to shop at that day. Furthermore, by inputting information about daily dinners, it suggests the best recipe in conjunction with the acquired data. This system enables savings in household expenses, time and effort, promotion of smart consumer behavior, contribution to the local economy, and reduction of food waste. For example, the savings support system utilizes GPS to obtain the daily prices of grocery stores near the user. At this time, price information from each store is collected in real time and the user is provided with the best price information. For example, if a user wants to buy a specific ingredient at a nearby supermarket, the lowest price of the day is displayed, allowing the user to make the most economical choice. Next, the savings support system reads the receipt to identify purchased items. Information on the products purchased by the user is obtained from the receipt and saved as history. This allows for the analysis of the user's purchasing patterns. For example, the system can identify products users frequently purchase and their preference for specific brands. Furthermore, based on the acquired data, it suggests the best store for shopping that day. Considering the user's purchasing patterns and price information of nearby stores, it selects the most economical store. For example, when a user is purchasing a specific ingredient, the system suggests the cheapest store, helping them save money. Finally, the savings support system suggests the best recipe based on the acquired data, based on the user's input of daily dinner information. When a user inputs their dinner menu, the system generates the best recipe based on the cheapest ingredients available that day. This allows users to prepare economical and healthy meals. This system helps save money, time, and effort. Users can make optimal purchasing decisions intuitively without complex operations. It can also contribute to the local economy and reduce food waste. For example, by allowing users to select the cheapest ingredients, it can increase sales at local stores and reduce food waste.This allows savings support systems to help households save money, time and effort, and promote smarter consumption.

[0029] The savings support system according to the embodiment comprises an acquisition unit, a suggestion unit, a discrimination unit, an analysis unit, a store suggestion unit, a reception unit, and a recipe suggestion unit. The acquisition unit acquires price information. The acquisition unit can, for example, acquire price information from grocery stores near the user using GPS. The acquisition unit can also collect price information from each store via the internet. Furthermore, the acquisition unit can update store price information in real time. For example, the acquisition unit can identify the user's current location using GPS and acquire price information from stores in the surrounding area. It can also collect price information from each store's website or online database via the internet. By updating price information in real time, the system can always provide the latest price information. The suggestion unit suggests the price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display the price information on the user's smartphone or personal computer. Furthermore, the suggestion unit can suggest optimal price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify the user of price information. For example, the suggestion unit can send a push notification to the user's smartphone to inform them of the cheapest ingredients. Based on the user's purchase history and preferences, the system can prioritize suggesting price information for specific stores and products. A notification function can provide users with real-time price information. The discrimination unit reads receipts to identify purchased items. For example, the discrimination unit can read text information from receipts using OCR technology. It can also read barcode information from receipts using a barcode scanner. Furthermore, the discrimination unit can obtain information about purchased items by analyzing images of receipts. For example, the discrimination unit can convert text information from receipts into digital data using OCR technology. It can also read barcode information printed on receipts using a barcode scanner. By analyzing images of receipts, detailed information about purchased items can be obtained. The analysis unit analyzes purchase patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store the user's purchase history in a database to understand frequently purchased items and preferences for specific brands.The analysis department can also predict user preferences and needs based on purchasing patterns. Furthermore, the analysis department has a function to visualize purchasing patterns. For example, the analysis department stores user purchase history in a database to understand the tendency for users to frequently purchase certain products or prefer specific brands. It can also predict user preferences and needs based on purchasing patterns. By visualizing purchasing patterns as graphs and charts, it can be presented to users in an easy-to-understand manner. The store recommendation department proposes the most suitable store based on the purchasing patterns analyzed by the analysis department. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores according to the user's preferences and needs. Furthermore, the store recommendation department has a function to make suggestions based on store ratings and reviews. For example, the store recommendation department selects the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores according to the user's preferences and needs. It can suggest highly reliable stores based on store ratings and reviews. The reception department inputs daily dinner information. The reception unit allows users to input their dinner menu using a smartphone or personal computer. The reception unit can also retrieve dinner information using voice or image input. Furthermore, the reception unit has a function to suggest the most suitable input method to the user based on past input history. For example, the reception unit allows users to input their dinner menu using a smartphone or personal computer. They can also easily retrieve dinner information using voice or image input. By suggesting the most suitable input method based on past input history, the effort required for input can be reduced. The recipe suggestion unit proposes the most suitable recipe based on the information entered by the reception unit and the data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information obtained by the acquisition unit. The recipe suggestion unit can also suggest healthy recipes considering the user's preferences and nutritional balance.Furthermore, the recipe suggestion unit has a function that proposes the most suitable recipe to the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information acquired by the acquisition unit. It can also propose healthy recipes, taking into account the user's preferences and nutritional balance. By proposing the most suitable recipe to the user, taking into account cooking time and difficulty, it is possible to prepare economical and healthy meals. As a result, the savings support system according to the embodiment can save household expenses, save time and effort, and promote smart consumption behavior.

[0030] The acquisition unit acquires price information. For example, the acquisition unit can acquire price information from grocery stores near the user using GPS. The acquisition unit can also collect price information from each store via the internet. Furthermore, the acquisition unit can update store price information in real time. For example, the acquisition unit can identify the user's current location using GPS and acquire price information from stores in that area. It can also collect price information from each store's website or online database via the internet. By updating price information in real time, it can always provide the latest price information. The acquisition unit centrally manages this information and provides an interface for easy access by the user. For example, the acquisition unit has a function to visually display price information through the user's smartphone app or web portal. This allows the user to compare prices at nearby stores and make the most economical choice. In addition, the acquisition unit can adjust the frequency of price information collection to understand price fluctuations at specific times of day or on specific days of the week. For example, it can focus on collecting price information on weekends or sale days to provide users with advantageous information. Furthermore, the data acquisition unit can also provide individually customized pricing information based on the user's purchase history and preferences. This allows the data acquisition unit to provide flexible information tailored to the user's needs, maximizing the effectiveness of the savings support system.

[0031] The suggestion unit proposes price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display price information on the user's smartphone or personal computer. It can also suggest optimal price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify users of price information. For example, it can send push notifications to the user's smartphone to inform them of the cheapest ingredients. It can also prioritize suggesting price information for specific stores or products based on the user's purchase history and preferences. Using the notification function, it can provide users with price information in real time. The suggestion unit can analyze the user's purchase history and preferences to provide individually customized suggestions. For example, users who prefer a particular brand or product can receive notifications when products from that brand become cheaper. Additionally, the suggestion unit can predict products the user is most likely to purchase next based on their past purchase patterns and prioritize displaying price information for those products. Furthermore, the suggestion unit can utilize the user's location information to provide price information for the store closest to their current location. This allows users to make the most economical purchases while saving travel time and transportation costs. The suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, it can track whether users actually made purchases based on the suggested price information and adjust the suggestion algorithm based on the results. This allows the suggestion department to provide users with the most useful information and maximize the effectiveness of the savings support system.

[0032] The discrimination unit reads the receipt and identifies the purchased items. For example, the discrimination unit can read text information from the receipt using OCR technology. It can also read barcode information from the receipt using a barcode scanner. Furthermore, the discrimination unit can obtain information about purchased items by analyzing the receipt image. For example, the discrimination unit converts the text information from the receipt into digital data using OCR technology. It can also read barcode information printed on the receipt using a barcode scanner. By analyzing the receipt image, detailed information about purchased items can be obtained. The discrimination unit centrally manages this information and stores it in a database as the user's purchase history. When converting text information from the receipt into digital data using OCR technology, the discrimination unit uses advanced algorithms to prevent misrecognition. For example, it can accurately read text information by considering differences in character shape and font. Additionally, by using a barcode scanner, detailed information such as product name, price, and quantity can be quickly obtained. Furthermore, by using receipt image analysis technology, it can handle handwritten notes and receipts with special formats. The discrimination unit stores the acquired information in a database as the user's purchase history and uses it for subsequent analysis and recommendations. For example, it can identify products and specific brands that a user frequently purchases and make optimal suggestions for their next shopping trip. Based on the user's purchase history, the discrimination unit provides a foundation for making individually customized savings suggestions. This allows the discrimination unit to understand the user's purchasing behavior in detail and maximize the effectiveness of the savings support system.

[0033] The analysis unit analyzes purchasing patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store a user's purchase history in a database to understand their tendency to frequently purchase certain products or brands. Furthermore, the analysis unit can predict user preferences and needs based on these purchasing patterns. In addition, the analysis unit has a function to visualize purchasing patterns. For example, it can store a user's purchase history in a database to understand their tendency to frequently purchase certain products or brands. It can also predict user preferences and needs based on these purchasing patterns. By visualizing purchasing patterns as graphs and charts, the information can be presented to users in an easy-to-understand manner. The analysis unit uses advanced algorithms to analyze purchase history in detail and understand user consumption behavior. For example, it can use time-series data to identify purchasing patterns associated with specific seasons or events. It can also use clustering technology to identify user groups with similar purchasing patterns and provide optimal suggestions to each. Furthermore, the analysis unit can monitor changes in purchasing patterns in real time and respond quickly to changes in user needs. For example, when a new product is introduced to the market, the system can quickly grasp the purchasing trends for that product and make appropriate suggestions to users. The analytics department visualizes purchasing patterns, making it easier for users to understand their own consumption behavior. For instance, it displays monthly spending amounts and spending percentages by category in graphs and charts, allowing users to see the effects of their savings. This enables the analytics department to gain a detailed understanding of users' purchasing behavior and maximize the effectiveness of the savings support system.

[0034] The Store Recommendation Department proposes the most suitable stores based on purchasing patterns analyzed by the Analysis Department. For example, the Store Recommendation Department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize recommending specific stores based on the user's preferences and needs. Furthermore, the Store Recommendation Department has a function to make recommendations based on store ratings and reviews. For example, the Store Recommendation Department selects the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize recommending specific stores based on the user's preferences and needs. It can recommend highly reliable stores based on store ratings and reviews. The Store Recommendation Department analyzes the user's purchase history and preferences in detail to provide individually customized store recommendations. For example, for users who prefer a particular brand or product, it can prioritize recommending stores that carry that brand's products. The Store Recommendation Department can also utilize the user's location information to suggest the store closest to their current location. This allows users to make the most economical purchases while saving travel time and transportation costs. Furthermore, the Store Recommendation Department can recommend highly reliable stores based on store ratings and reviews. For example, the system can prioritize suggesting stores that have received high ratings from other users or stores that offer specific products at low prices. The store suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For instance, it can track whether users actually shopped at the suggested stores and adjust the suggestion algorithm based on the results. This allows the store suggestion department to provide users with the most useful information and maximize the effectiveness of the savings support system.

[0035] The reception system handles the input of daily dinner information. For example, users can input dinner menus using their smartphones or personal computers. The system can also retrieve dinner information using voice input or image input. Furthermore, the system has a function to suggest the most suitable input method based on past input history. For example, users can input dinner menus using their smartphones or personal computers. Dinner information can also be easily retrieved using voice input or image input. By suggesting the most suitable input method based on past input history, the system reduces the effort required for input. The reception system provides an intuitive interface to allow users to easily input daily dinner information. For example, when a user inputs a menu, it can display a history of previously entered menus and present them as options. Additionally, the voice input function allows users to input menus simply by speaking. Furthermore, the image input function allows users to take photos of their dishes, and the system can automatically recognize the menu from the image. By combining these functions, the reception system enables users to input dinner information in the easiest and quickest way possible. Based on the user's input history, the reception system can suggest the most suitable input method for the next time the information is entered. For example, users who have frequently used voice input in the past can receive notifications recommending that they use voice input again next time. This allows the reception desk to reduce the effort required for users to input data and encourage the use of the savings support system.

[0036] The recipe suggestion unit proposes the most suitable recipe based on information entered by the reception unit and data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and price information obtained by the acquisition unit. The recipe suggestion unit can also propose healthy recipes considering the user's preferences and nutritional balance. Furthermore, the recipe suggestion unit has a function to propose the most suitable recipe for the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates a recipe using the cheapest ingredients based on the dinner menu entered by the user and price information obtained by the acquisition unit. It can also propose healthy recipes considering the user's preferences and nutritional balance. By proposing the most suitable recipe for the user, taking into account cooking time and difficulty, economical and healthy meals can be prepared. The recipe suggestion unit can analyze the user's past recipe selection history and provide individually customized recipe suggestions. For example, it can suggest new recipes using specific ingredients or dishes for users who prefer them. The recipe suggestion unit can also propose recipes that include necessary nutrients, taking into account the user's nutritional balance. This makes it easy for users to prepare healthy meals. Furthermore, the recipe suggestion department can propose recipes tailored to the user's lifestyle, taking into account cooking time and difficulty. For example, it can suggest quick and easy recipes for busy weekday evenings, and more elaborate recipes that require more time on weekends. The recipe suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For instance, it can adjust future suggestions to be more appropriate based on user evaluations of recipes they have actually made. This allows the recipe suggestion department to provide users with the most useful information and maximize the effectiveness of the money-saving support system.

[0037] The acquisition unit can collect price information from each store in real time. For example, the acquisition unit can collect price information from each store in real time and provide it to the user. For example, the acquisition unit can collect price information from each store in real time via the internet. Furthermore, the acquisition unit can use GPS to determine the user's current location and collect price information from nearby stores in real time. In addition, the acquisition unit can update store price information in real time. For example, the acquisition unit collects price information in real time from each store's website or online database via the internet. It can also use GPS to determine the user's current location and collect price information from nearby stores in real time. By updating price information in real time, it can always provide the latest price information. This means that by collecting price information in real time, it can provide the latest price information.

[0038] The discrimination unit can acquire information about purchased items from receipts and save it as a history. For example, the discrimination unit can acquire information about purchased items from receipts and save it as a history. For example, the discrimination unit can read the text information on the receipt using OCR technology and acquire information about purchased items. The discrimination unit can also read the barcode information on the receipt using a barcode scanner and acquire information about purchased items. Furthermore, the discrimination unit can analyze the image of the receipt to acquire information about purchased items and save it as a history. For example, the discrimination unit can convert the text information on the receipt into digital data using OCR technology and acquire information about purchased items. It can also read the barcode information printed on the receipt using a barcode scanner and acquire information about purchased items. By analyzing the image of the receipt, detailed information about purchased items can be acquired and saved as a history. This makes it possible to analyze purchasing patterns by saving information about purchased items as a history.

[0039] The analytics department can analyze users' purchasing patterns and understand their tendencies to prefer frequently purchased items and specific brands. For example, the analytics department can store users' purchase history in a database to understand their tendencies to prefer frequently purchased items and specific brands. Furthermore, the analytics department can predict users' preferences and needs based on their purchasing patterns. In addition, the analytics department has a function to visualize purchasing patterns. For example, the analytics department can store users' purchase history in a database to understand their tendencies to prefer frequently purchased items and specific brands. It can also predict users' preferences and needs based on their purchasing patterns. By visualizing purchasing patterns as graphs and charts, the information can be presented to users in an easy-to-understand manner. This allows for the understanding of users' preferences and tendencies through the analysis of purchasing patterns.

[0040] The store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. For example, the store recommendation department can select the most economical store based on the user's purchasing patterns and price information of nearby stores. Furthermore, the store recommendation department can prioritize suggesting specific stores based on the user's preferences and needs. In addition, the store recommendation department has a function to make suggestions based on store ratings and reviews. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores based on the user's preferences and needs. It can suggest highly reliable stores based on store ratings and reviews. This allows for savings on household expenses by selecting the most economical store.

[0041] The recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's daily dinner menu. For example, the recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's daily dinner menu. For example, the recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's dinner menu entered by the user and price information obtained by the data acquisition unit. Furthermore, the recipe suggestion unit can suggest healthy recipes considering the user's preferences and nutritional balance. In addition, the recipe suggestion unit has a function to suggest the optimal recipe for the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates the optimal recipe using the cheapest ingredients based on the user's dinner menu entered by the user and price information obtained by the data acquisition unit. It can also suggest healthy recipes considering the user's preferences and nutritional balance. By suggesting the optimal recipe for the user, taking into account cooking time and difficulty, it is possible to prepare economical and healthy meals. This means that by suggesting recipes using the cheapest ingredients, economical and healthy meals can be prepared.

[0042] The data acquisition unit can compare price information for each store with historical data and analyze price fluctuation patterns to acquire data. For example, the data acquisition unit can compare price information for each store with historical data and analyze price fluctuation patterns to acquire data. For example, the data acquisition unit can analyze seasonal price fluctuation patterns based on price data from the past year. The data acquisition unit can also analyze price fluctuation patterns for specific days of the week or time of day based on price data from the past few months. Furthermore, the data acquisition unit can analyze price fluctuation patterns during specific events or sales periods based on historical price data. For example, the data acquisition unit can analyze seasonal price fluctuation patterns based on price data from the past year. It can also analyze price fluctuation patterns for specific days of the week or time of day based on price data from the past few months. It can analyze price fluctuation patterns during specific events or sales periods based on historical price data. By analyzing price fluctuation patterns, more accurate price information can be provided.

[0043] The acquisition unit can acquire price information while considering price fluctuations on specific days of the week and time slots. For example, if prices tend to be lower on weekday mornings, the acquisition unit can acquire price information during that time. Also, if prices tend to be higher on weekend evenings, the acquisition unit can avoid acquiring price information during that time. Furthermore, if sales are held on specific days of the week, the acquisition unit can acquire price information on those days. For example, if prices tend to be lower on weekday mornings, the acquisition unit can acquire price information during that time. If prices tend to be higher on weekend evenings, the acquisition unit can avoid acquiring price information during that time. If sales are held on specific days of the week, the acquisition unit can acquire price information on those days. This allows for the provision of more economical price information by considering price fluctuations on specific days of the week and time slots.

[0044] The data acquisition unit can prioritize the acquisition of highly relevant price information by considering the user's purchase history when acquiring price information. For example, the data acquisition unit can prioritize the acquisition of highly relevant price information by considering the user's purchase history when acquiring price information. For example, the data acquisition unit can prioritize the acquisition of price information for products that the user frequently purchases. Furthermore, if the user prefers a particular brand, the data acquisition unit can prioritize the acquisition of price information for products of that brand. In addition, the data acquisition unit can prioritize the acquisition of highly relevant price information based on the price information of products that the user has purchased in the past. For example, the data acquisition unit can prioritize the acquisition of price information for products that the user frequently purchases. If the user prefers a particular brand, the data acquisition unit can prioritize the acquisition of price information for products of that brand. Based on the price information of products that the user has purchased in the past, the data acquisition unit can prioritize the acquisition of highly relevant price information. This allows the system to provide highly relevant price information by considering the user's purchase history.

[0045] The acquisition unit can acquire price information from the most suitable store by considering the user's geographical location when acquiring price information. For example, the acquisition unit can prioritize acquiring price information from the store closest to the user's current location. It can also prioritize acquiring price information from stores along the user's commuting route. Furthermore, it can prioritize acquiring price information from stores near the user's home. For example, the acquisition unit prioritizes acquiring price information from the store closest to the user's current location. It can also prioritize acquiring price information from stores along the user's commuting route. It can prioritize acquiring price information from stores near the user's home. By considering the user's geographical location, it can provide price information from the most suitable store.

[0046] The proposal department can adjust the level of detail in a proposal based on the importance of the product. For example, the proposal department can provide detailed proposals for important products. For less important products, the proposal department can provide concise proposals. Furthermore, the proposal department can provide detailed proposals for products that users frequently purchase. For example, the proposal department can provide detailed proposals for important products. For less important products, it can provide concise proposals. For products that users frequently purchase, it can provide detailed proposals. By adjusting the level of detail in proposals based on the importance of the product, more appropriate proposals become possible.

[0047] The proposal function can apply different proposal algorithms depending on the product category when making a proposal. For example, the proposal function can apply different proposal algorithms depending on the product category when making a proposal. For example, for products in the food category, the proposal function can make proposals that include nutritional information. For products in the daily necessities category, the proposal function can also make proposals that include usage instructions. Furthermore, for products in the home appliance category, the proposal function can make proposals that include technical specifications. By applying different proposal algorithms depending on the product category, more appropriate proposals become possible.

[0048] The proposal department can prioritize proposals based on the product submission timing. For example, the proposal department can prioritize proposals for products with approaching deadlines. Furthermore, for seasonal products, the proposal department can make proposals tailored to the season. Additionally, for new products, the proposal department can submit proposals immediately after launch. This allows for more appropriate proposals by prioritizing proposals based on product submission timing.

[0049] The suggestion function can adjust the order of suggestions based on the relevance of the products when making suggestions. For example, the suggestion function can prioritize suggesting products that the user frequently purchases. It can also suggest highly relevant products in sequence. Furthermore, the suggestion function can suggest highly relevant products based on the user's purchase history. For example, the suggestion function can prioritize suggesting products that the user frequently purchases. It can also suggest highly relevant products in sequence. It can suggest highly relevant products based on the user's purchase history. By adjusting the order of suggestions based on the relevance of the products, more appropriate suggestions become possible.

[0050] The discrimination unit can apply different discrimination algorithms to each category of purchased items when reading a receipt. For example, the discrimination unit can apply a discrimination algorithm that includes nutritional information to purchased items in the food category. It can also apply a discrimination algorithm that includes usage instructions to purchased items in the daily necessities category. Furthermore, it can apply a discrimination algorithm that includes technical specifications to purchased items in the home appliance category. By applying different discrimination algorithms to each category of purchased items, discrimination accuracy is improved.

[0051] The discrimination unit can automatically calculate and save the quantity and price of purchased items when reading a receipt. For example, the discrimination unit can automatically calculate and save the quantity and price of purchased items when reading a receipt. The discrimination unit can also automatically calculate and save the price of purchased items when reading a receipt. Furthermore, the discrimination unit can automatically calculate and save the total amount of purchased items when reading a receipt. This makes it easier to manage purchase history by automatically calculating and saving the quantity and price of purchased items.

[0052] The discrimination unit can improve its discrimination accuracy by considering the brand information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy by considering the brand information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the brand information of the purchased items when reading the receipt. Furthermore, the discrimination unit can improve the discrimination accuracy of products of a specific brand when reading the receipt. In addition, the discrimination unit can obtain detailed information about the purchased items based on the brand information when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the brand information of the purchased items when reading the receipt. It can also improve the discrimination accuracy of products of a specific brand when reading the receipt. It can obtain detailed information about the purchased items based on the brand information when reading the receipt. As a result, discrimination accuracy is improved by considering the brand information of the purchased items.

[0053] The discrimination unit can improve its discrimination accuracy by utilizing the barcode information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy by utilizing the barcode information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the barcode information of the purchased items when reading the receipt. Furthermore, the discrimination unit can obtain detailed information about the purchased items based on the barcode information when reading the receipt. In addition, the discrimination unit can obtain price information about the purchased items based on the barcode information when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the barcode information of the purchased items when reading the receipt. It can also obtain detailed information about the purchased items based on the barcode information when reading the receipt. It can obtain price information about the purchased items based on the barcode information when reading the receipt. As a result, discrimination accuracy is improved by utilizing the barcode information of the purchased items.

[0054] The analysis unit can optimize its analysis algorithm by referring to past purchase history when analyzing purchasing patterns. For example, the analysis unit can optimize its analysis algorithm by referring to past purchase history. For example, the analysis unit can optimize its analysis algorithm based on purchase history over the past year. Furthermore, the analysis unit can optimize its analysis algorithm based on purchase history over the past few months. In addition, the analysis unit can analyze purchasing patterns for specific products based on past purchase history. For example, the analysis unit can optimize its analysis algorithm based on purchase history over the past year. It can also optimize its analysis algorithm based on purchase history over the past few months. By referring to past purchase history, the analysis algorithm can be optimized, improving the accuracy of the analysis.

[0055] The analysis department can apply different analytical methods to each category of purchased goods when analyzing purchasing patterns. For example, the analysis department can apply analytical methods that include nutritional information to purchasing patterns in the food category. Furthermore, the analysis department can apply analytical methods that include frequency of use to purchasing patterns in the daily necessities category. In addition, the analysis department can apply analytical methods that include technical specifications to purchasing patterns in the home appliance category. This improves analytical accuracy by applying different analytical methods to each category of purchased goods.

[0056] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location when analyzing purchasing patterns. For example, the analysis unit can improve the accuracy of its analysis by considering the user's geographical location when analyzing purchasing patterns. For example, the analysis unit can analyze region-specific purchasing patterns based on the user's current location. It can also analyze purchasing patterns based on store information along the user's commuting route. Furthermore, the analysis unit can analyze purchasing patterns based on store information around the user's home. This improves the accuracy of the analysis by considering the user's geographical location.

[0057] The analytics department can improve the accuracy of its analysis of purchasing patterns by referring to users' social media activity. For example, the analytics department can improve the accuracy of its analysis by referring to users' social media activity when analyzing purchasing patterns. For example, the analytics department can analyze purchasing patterns based on the content of users' social media posts. Furthermore, the analytics department can analyze purchasing patterns based on users' "likes" and comments on social media. In addition, the analytics department can analyze purchasing patterns based on the brands and stores that users follow on social media. For example, the analytics department can analyze purchasing patterns based on the content of users' social media posts. It can also analyze purchasing patterns based on users' "likes" and comments on social media. It can analyze purchasing patterns based on the brands and stores that users follow on social media. This improves the accuracy of the analysis by referring to users' social media activity.

[0058] The store suggestion department can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting stores. For example, the store suggestion department can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting stores. For example, the store suggestion department can prioritize suggesting stores that users prefer based on past suggestion history. The store suggestion department can also exclude stores that users avoid from suggestions based on past suggestion history. Furthermore, the store suggestion department can suggest stores that match the user's purchasing patterns based on past suggestion history. For example, the store suggestion department can prioritize suggesting stores that users prefer based on past suggestion history. It can also exclude stores that users avoid from suggestions based on past suggestion history. It can suggest stores that match the user's purchasing patterns based on past suggestion history. As a result, by referring to past suggestion history, the optimal suggestion algorithm can be applied, improving the accuracy of suggestions.

[0059] The store recommendation department can adjust the level of detail in its recommendations based on the user's purchasing patterns. For example, the store recommendation department can provide detailed recommendations for stores that carry products the user frequently purchases. Furthermore, if the user prefers a particular brand, the store recommendation department can provide detailed recommendations for stores that carry that brand. In addition, the store recommendation department can provide detailed recommendations for highly relevant stores based on the user's purchasing patterns. For example, the store recommendation department can provide detailed recommendations for stores that carry products the user frequently purchases. If the user prefers a particular brand, it can also provide detailed recommendations for stores that carry that brand. It can provide detailed recommendations for highly relevant stores based on the user's purchasing patterns. This allows for more appropriate recommendations by adjusting the level of detail based on the user's purchasing patterns.

[0060] The store recommendation department can suggest the most suitable store by considering the user's geographical location. For example, the store recommendation department can prioritize suggesting the store closest to the user's current location. It can also prioritize suggesting stores along the user's commute route. Furthermore, it can prioritize suggesting stores near the user's home. For example, the store recommendation department prioritizes suggesting the store closest to the user's current location. It can also prioritize suggesting stores along the user's commute route. It can also prioritize suggesting stores near the user's home. By considering the user's geographical location, the department can suggest the most suitable store.

[0061] The store recommendation department can suggest the most suitable stores by referring to the user's social media activity when making store recommendations. For example, the store recommendation department can suggest stores based on the user's social media posts. Furthermore, the store recommendation department can suggest stores based on the user's "likes" and comments on social media. In addition, the store recommendation department can suggest stores based on the brands and stores the user follows on social media. For example, the store recommendation department can suggest stores based on the user's social media posts. It can also suggest stores based on the user's "likes" and comments on social media. It can also suggest stores based on the brands and stores the user follows on social media. This allows the department to suggest the most suitable stores by referring to the user's social media activity.

[0062] The reception system can suggest the optimal input method when a user enters dinner information by referring to their past input history. For example, the reception system can automatically display as suggestions dinner menus that the user has frequently entered in the past. The reception system can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). Furthermore, the reception system can predict and suggest menus that the user will use at a specific time of day based on their past input history. For example, the reception system can automatically display as suggestions dinner menus that the user has frequently entered in the past. It can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). It can predict and suggest menus that the user will use at a specific time of day based on their past input history. This improves input efficiency by suggesting the optimal input method by referring to past input history.

[0063] The reception desk can customize input fields based on the user's dietary preferences when entering dinner information. For example, the reception desk can customize input fields based on the user's dietary preferences when entering dinner information. For example, the reception desk can prioritize displaying ingredients that the user likes as input fields. It can also exclude ingredients that the user avoids from the input fields. Furthermore, the reception desk can suggest customized input fields based on the user's dietary preferences. For example, the reception desk can prioritize displaying ingredients that the user likes as input fields. It can also exclude ingredients that the user avoids from the input fields. It can suggest customized input fields based on the user's dietary preferences. This allows for more appropriate information to be entered by customizing input fields based on the user's dietary preferences.

[0064] The reception desk can suggest the optimal input method when a user enters dinner information, taking into account the user's geographical location. For example, the reception desk can suggest the optimal input method when a user enters dinner information, taking into account the user's geographical location. For example, the reception desk can suggest region-specific menus as input fields based on the user's current location. Furthermore, the reception desk can suggest menus as input fields based on store information along the user's commute route. In addition, the reception desk can suggest menus as input fields based on store information around the user's home. This allows the system to suggest the optimal input method by considering the user's geographical location.

[0065] The reception desk can suggest the most suitable input method when a user enters dinner information by referring to their social media activity. For example, when a user enters dinner information, the reception desk can suggest the most suitable input method by referring to their social media activity. For example, the reception desk can suggest preferred menu items as input fields based on the user's social media posts. Furthermore, the reception desk can suggest preferred menu items as input fields based on the user's social media "likes" and comments. In addition, the reception desk can suggest preferred menu items as input fields based on the brands and stores the user follows on social media. For example, the reception desk can suggest preferred menu items as input fields based on the user's social media posts. It can also suggest preferred menu items as input fields based on the user's social media "likes" and comments. It can also suggest preferred menu items as input fields based on the brands and stores the user follows on social media. This allows the reception desk to suggest the most suitable input method by referring to the user's social media activity.

[0066] The recipe suggestion unit can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting recipes. For example, the recipe suggestion unit can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting recipes. For example, the recipe suggestion unit can prioritize suggesting recipes that the user likes based on past suggestion history. The recipe suggestion unit can also exclude recipes that the user avoids from suggestions based on past suggestion history. Furthermore, the recipe suggestion unit can suggest recipes that match the user's dietary preferences based on past suggestion history. For example, the recipe suggestion unit prioritizes suggesting recipes that the user likes based on past suggestion history. It can also exclude recipes that the user avoids from suggestions based on past suggestion history. It can suggest recipes that match the user's dietary preferences based on past suggestion history. As a result, by referring to past suggestion history, the optimal suggestion algorithm is applied, improving the accuracy of suggestions.

[0067] The recipe suggestion function can adjust the level of detail in its suggestions based on the user's dietary preferences. For example, the recipe suggestion function can suggest detailed recipes using ingredients the user likes. It can also suggest detailed recipes that do not use ingredients the user avoids. Furthermore, the recipe suggestion function can suggest highly relevant recipes in detail based on the user's dietary preferences. For example, the recipe suggestion function can suggest detailed recipes using ingredients the user likes. It can also suggest detailed recipes that do not use ingredients the user avoids. It can suggest highly relevant recipes in detail based on the user's dietary preferences. By adjusting the level of detail in suggestions based on the user's dietary preferences, more appropriate suggestions become possible.

[0068] The recipe suggestion function can propose the most suitable recipe by considering the user's geographical location. For example, it can suggest recipes using local ingredients based on the user's current location. It can also suggest recipes using readily available ingredients based on store information along the user's commute route. Furthermore, it can suggest recipes using readily available ingredients based on store information near the user's home. This allows the system to propose the most suitable recipe by considering the user's geographical location.

[0069] The recipe suggestion department can suggest the most suitable recipe by referring to the user's social media activity. For example, the recipe suggestion department can suggest a recipe based on the user's social media posts. It can also suggest a recipe based on the user's "likes" and comments on social media. Furthermore, the recipe suggestion department can suggest a recipe based on the brands and food information the user follows on social media. This allows the system to suggest the most suitable recipe by referring to the user's social media activity.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The acquisition unit can predict price fluctuations for specific products based on the user's purchase history and suggest the optimal purchase timing. For example, by analyzing past data, it can predict when the price of a particular product will drop and encourage purchases at that time. It can also provide users with information if there is a tendency for prices to drop on specific days of the week or time of day. Furthermore, it can predict price fluctuations during specific events or sales periods and suggest the optimal purchase timing to the user. This allows users to make more economical purchasing decisions.

[0072] The analytics department can improve the accuracy of its analysis of user purchasing patterns by referencing users' social media activity. For example, it can analyze purchasing patterns based on the content of users' social media posts. It can also analyze purchasing patterns based on users' "likes" and comments on social media. Furthermore, it can analyze purchasing patterns based on the brands and store information that users follow on social media. In this way, referencing users' social media activity improves the accuracy of the analysis.

[0073] The acquisition unit can prioritize acquiring price information for specific areas, taking into account the user's geographical location. For example, it can prioritize acquiring price information for the store closest to the user's current location. It can also prioritize acquiring price information for stores along the user's commute route. Furthermore, it can prioritize acquiring price information for stores near the user's home. This allows the system to provide optimal price information by considering the user's geographical location.

[0074] The recipe suggestion system can propose recipes using ingredients from a specific region, taking into account the user's geographical location. For example, it can suggest recipes using regionally specific ingredients based on the user's current location. It can also suggest recipes using easily available ingredients based on store information along the user's commute route. Furthermore, it can suggest recipes using easily available ingredients based on store information around the user's home. In this way, the system can suggest the most suitable recipes by considering the user's geographical location.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The acquisition unit acquires price information. The acquisition unit can, for example, use GPS to acquire price information from grocery stores near the user. The acquisition unit can also collect price information from individual stores via the internet. Furthermore, the acquisition unit can update store price information in real time. Step 2: The suggestion unit proposes the price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display the price information on the user's smartphone or personal computer. The suggestion unit can also propose the most suitable price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify the user of the price information. Step 3: The discrimination unit reads the receipt and identifies the purchased items. The discrimination unit can, for example, read the text information on the receipt using OCR technology. It can also read the barcode information on the receipt using a barcode scanner. Furthermore, the discrimination unit can analyze the image of the receipt to obtain information about the purchased items. Step 4: The analysis unit analyzes purchasing patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store the user's purchase history in a database and understand the tendency to frequently purchase certain products or prefer specific brands. The analysis unit can also predict the user's preferences and needs based on the purchasing patterns. Furthermore, the analysis unit has a function to visualize the purchasing patterns. Step 5: The store recommendation department proposes the most suitable stores based on the purchasing patterns analyzed by the analysis department. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. The store recommendation department can also prioritize suggesting specific stores according to the user's preferences and needs. Furthermore, the store recommendation department has a function to make suggestions based on store ratings and reviews. Step 6: The reception desk inputs daily dinner information. The reception desk can, for example, allow users to input dinner menus using their smartphones or personal computers. It can also acquire dinner information using voice input or image input. Furthermore, the reception desk has a function that suggests the most suitable input method to the user based on past input history. Step 7: The recipe suggestion unit proposes the optimal recipe based on the information entered by the reception unit and the data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information obtained by the acquisition unit. The recipe suggestion unit can also propose healthy recipes considering the user's preferences and nutritional balance. Furthermore, the recipe suggestion unit has a function to propose the most suitable recipe for the user, taking into account cooking time and difficulty level.

[0077] (Example of form 2) The savings support system according to an embodiment of the present invention is a system for low- and middle-income groups whose household budgets are being strained by rising prices. This savings support system utilizes GPS to obtain the daily prices of grocery stores near the user and suggests them to the user. Next, it reads the receipt to identify purchased items and analyzes the user's purchasing patterns from the history. Based on this, it suggests the best store to shop at that day. Furthermore, by inputting information about daily dinners, it suggests the best recipe in conjunction with the acquired data. This system enables savings in household expenses, time and effort, promotion of smart consumer behavior, contribution to the local economy, and reduction of food waste. For example, the savings support system utilizes GPS to obtain the daily prices of grocery stores near the user. At this time, price information from each store is collected in real time and the user is provided with the best price information. For example, if a user wants to buy a specific ingredient at a nearby supermarket, the lowest price of the day is displayed, allowing the user to make the most economical choice. Next, the savings support system reads the receipt to identify purchased items. Information on the products purchased by the user is obtained from the receipt and saved as history. This allows for the analysis of the user's purchasing patterns. For example, the system can identify products users frequently purchase and their preference for specific brands. Furthermore, based on the acquired data, it suggests the best store for shopping that day. Considering the user's purchasing patterns and price information of nearby stores, it selects the most economical store. For example, when a user is purchasing a specific ingredient, the system suggests the cheapest store, helping them save money. Finally, the savings support system suggests the best recipe based on the acquired data, based on the user's input of daily dinner information. When a user inputs their dinner menu, the system generates the best recipe based on the cheapest ingredients available that day. This allows users to prepare economical and healthy meals. This system helps save money, time, and effort. Users can make optimal purchasing decisions intuitively without complex operations. It can also contribute to the local economy and reduce food waste. For example, by allowing users to select the cheapest ingredients, it can increase sales at local stores and reduce food waste.This allows savings support systems to help households save money, time and effort, and promote smarter consumption.

[0078] The savings support system according to the embodiment comprises an acquisition unit, a suggestion unit, a discrimination unit, an analysis unit, a store suggestion unit, a reception unit, and a recipe suggestion unit. The acquisition unit acquires price information. The acquisition unit can, for example, acquire price information from grocery stores near the user using GPS. The acquisition unit can also collect price information from each store via the internet. Furthermore, the acquisition unit can update store price information in real time. For example, the acquisition unit can identify the user's current location using GPS and acquire price information from stores in the surrounding area. It can also collect price information from each store's website or online database via the internet. By updating price information in real time, the system can always provide the latest price information. The suggestion unit suggests the price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display the price information on the user's smartphone or personal computer. Furthermore, the suggestion unit can suggest optimal price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify the user of price information. For example, the suggestion unit can send a push notification to the user's smartphone to inform them of the cheapest ingredients. Based on the user's purchase history and preferences, the system can prioritize suggesting price information for specific stores and products. A notification function can provide users with real-time price information. The discrimination unit reads receipts to identify purchased items. For example, the discrimination unit can read text information from receipts using OCR technology. It can also read barcode information from receipts using a barcode scanner. Furthermore, the discrimination unit can obtain information about purchased items by analyzing images of receipts. For example, the discrimination unit can convert text information from receipts into digital data using OCR technology. It can also read barcode information printed on receipts using a barcode scanner. By analyzing images of receipts, detailed information about purchased items can be obtained. The analysis unit analyzes purchase patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store the user's purchase history in a database to understand frequently purchased items and preferences for specific brands.The analysis department can also predict user preferences and needs based on purchasing patterns. Furthermore, the analysis department has a function to visualize purchasing patterns. For example, the analysis department stores user purchase history in a database to understand the tendency for users to frequently purchase certain products or prefer specific brands. It can also predict user preferences and needs based on purchasing patterns. By visualizing purchasing patterns as graphs and charts, it can be presented to users in an easy-to-understand manner. The store recommendation department proposes the most suitable store based on the purchasing patterns analyzed by the analysis department. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores according to the user's preferences and needs. Furthermore, the store recommendation department has a function to make suggestions based on store ratings and reviews. For example, the store recommendation department selects the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores according to the user's preferences and needs. It can suggest highly reliable stores based on store ratings and reviews. The reception department inputs daily dinner information. The reception unit allows users to input their dinner menu using a smartphone or personal computer. The reception unit can also retrieve dinner information using voice or image input. Furthermore, the reception unit has a function to suggest the most suitable input method to the user based on past input history. For example, the reception unit allows users to input their dinner menu using a smartphone or personal computer. They can also easily retrieve dinner information using voice or image input. By suggesting the most suitable input method based on past input history, the effort required for input can be reduced. The recipe suggestion unit proposes the most suitable recipe based on the information entered by the reception unit and the data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information obtained by the acquisition unit. The recipe suggestion unit can also suggest healthy recipes considering the user's preferences and nutritional balance.Furthermore, the recipe suggestion unit has a function that proposes the most suitable recipe to the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information acquired by the acquisition unit. It can also propose healthy recipes, taking into account the user's preferences and nutritional balance. By proposing the most suitable recipe to the user, taking into account cooking time and difficulty, it is possible to prepare economical and healthy meals. As a result, the savings support system according to the embodiment can save household expenses, save time and effort, and promote smart consumption behavior.

[0079] The acquisition unit acquires price information. For example, the acquisition unit can acquire price information from grocery stores near the user using GPS. The acquisition unit can also collect price information from each store via the internet. Furthermore, the acquisition unit can update store price information in real time. For example, the acquisition unit can identify the user's current location using GPS and acquire price information from stores in that area. It can also collect price information from each store's website or online database via the internet. By updating price information in real time, it can always provide the latest price information. The acquisition unit centrally manages this information and provides an interface for easy access by the user. For example, the acquisition unit has a function to visually display price information through the user's smartphone app or web portal. This allows the user to compare prices at nearby stores and make the most economical choice. In addition, the acquisition unit can adjust the frequency of price information collection to understand price fluctuations at specific times of day or on specific days of the week. For example, it can focus on collecting price information on weekends or sale days to provide users with advantageous information. Furthermore, the data acquisition unit can also provide individually customized pricing information based on the user's purchase history and preferences. This allows the data acquisition unit to provide flexible information tailored to the user's needs, maximizing the effectiveness of the savings support system.

[0080] The suggestion unit proposes price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display price information on the user's smartphone or personal computer. It can also suggest optimal price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify users of price information. For example, it can send push notifications to the user's smartphone to inform them of the cheapest ingredients. It can also prioritize suggesting price information for specific stores or products based on the user's purchase history and preferences. Using the notification function, it can provide users with price information in real time. The suggestion unit can analyze the user's purchase history and preferences to provide individually customized suggestions. For example, users who prefer a particular brand or product can receive notifications when products from that brand become cheaper. Additionally, the suggestion unit can predict products the user is most likely to purchase next based on their past purchase patterns and prioritize displaying price information for those products. Furthermore, the suggestion unit can utilize the user's location information to provide price information for the store closest to their current location. This allows users to make the most economical purchases while saving travel time and transportation costs. The suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, it can track whether users actually made purchases based on the suggested price information and adjust the suggestion algorithm based on the results. This allows the suggestion department to provide users with the most useful information and maximize the effectiveness of the savings support system.

[0081] The discrimination unit reads the receipt and identifies the purchased items. For example, the discrimination unit can read text information from the receipt using OCR technology. It can also read barcode information from the receipt using a barcode scanner. Furthermore, the discrimination unit can obtain information about purchased items by analyzing the receipt image. For example, the discrimination unit converts the text information from the receipt into digital data using OCR technology. It can also read barcode information printed on the receipt using a barcode scanner. By analyzing the receipt image, detailed information about purchased items can be obtained. The discrimination unit centrally manages this information and stores it in a database as the user's purchase history. When converting text information from the receipt into digital data using OCR technology, the discrimination unit uses advanced algorithms to prevent misrecognition. For example, it can accurately read text information by considering differences in character shape and font. Additionally, by using a barcode scanner, detailed information such as product name, price, and quantity can be quickly obtained. Furthermore, by using receipt image analysis technology, it can handle handwritten notes and receipts with special formats. The discrimination unit stores the acquired information in a database as the user's purchase history and uses it for subsequent analysis and recommendations. For example, it can identify products and specific brands that a user frequently purchases and make optimal suggestions for their next shopping trip. Based on the user's purchase history, the discrimination unit provides a foundation for making individually customized savings suggestions. This allows the discrimination unit to understand the user's purchasing behavior in detail and maximize the effectiveness of the savings support system.

[0082] The analysis unit analyzes purchasing patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store a user's purchase history in a database to understand their tendency to frequently purchase certain products or brands. Furthermore, the analysis unit can predict user preferences and needs based on these purchasing patterns. In addition, the analysis unit has a function to visualize purchasing patterns. For example, it can store a user's purchase history in a database to understand their tendency to frequently purchase certain products or brands. It can also predict user preferences and needs based on these purchasing patterns. By visualizing purchasing patterns as graphs and charts, the information can be presented to users in an easy-to-understand manner. The analysis unit uses advanced algorithms to analyze purchase history in detail and understand user consumption behavior. For example, it can use time-series data to identify purchasing patterns associated with specific seasons or events. It can also use clustering technology to identify user groups with similar purchasing patterns and provide optimal suggestions to each. Furthermore, the analysis unit can monitor changes in purchasing patterns in real time and respond quickly to changes in user needs. For example, when a new product is introduced to the market, the system can quickly grasp the purchasing trends for that product and make appropriate suggestions to users. The analytics department visualizes purchasing patterns, making it easier for users to understand their own consumption behavior. For instance, it displays monthly spending amounts and spending percentages by category in graphs and charts, allowing users to see the effects of their savings. This enables the analytics department to gain a detailed understanding of users' purchasing behavior and maximize the effectiveness of the savings support system.

[0083] The Store Recommendation Department proposes the most suitable stores based on purchasing patterns analyzed by the Analysis Department. For example, the Store Recommendation Department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize recommending specific stores based on the user's preferences and needs. Furthermore, the Store Recommendation Department has a function to make recommendations based on store ratings and reviews. For example, the Store Recommendation Department selects the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize recommending specific stores based on the user's preferences and needs. It can recommend highly reliable stores based on store ratings and reviews. The Store Recommendation Department analyzes the user's purchase history and preferences in detail to provide individually customized store recommendations. For example, for users who prefer a particular brand or product, it can prioritize recommending stores that carry that brand's products. The Store Recommendation Department can also utilize the user's location information to suggest the store closest to their current location. This allows users to make the most economical purchases while saving travel time and transportation costs. Furthermore, the Store Recommendation Department can recommend highly reliable stores based on store ratings and reviews. For example, the system can prioritize suggesting stores that have received high ratings from other users or stores that offer specific products at low prices. The store suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For instance, it can track whether users actually shopped at the suggested stores and adjust the suggestion algorithm based on the results. This allows the store suggestion department to provide users with the most useful information and maximize the effectiveness of the savings support system.

[0084] The reception system handles the input of daily dinner information. For example, users can input dinner menus using their smartphones or personal computers. The system can also retrieve dinner information using voice input or image input. Furthermore, the system has a function to suggest the most suitable input method based on past input history. For example, users can input dinner menus using their smartphones or personal computers. Dinner information can also be easily retrieved using voice input or image input. By suggesting the most suitable input method based on past input history, the system reduces the effort required for input. The reception system provides an intuitive interface to allow users to easily input daily dinner information. For example, when a user inputs a menu, it can display a history of previously entered menus and present them as options. Additionally, the voice input function allows users to input menus simply by speaking. Furthermore, the image input function allows users to take photos of their dishes, and the system can automatically recognize the menu from the image. By combining these functions, the reception system enables users to input dinner information in the easiest and quickest way possible. Based on the user's input history, the reception system can suggest the most suitable input method for the next time the information is entered. For example, users who have frequently used voice input in the past can receive notifications recommending that they use voice input again next time. This allows the reception desk to reduce the effort required for users to input data and encourage the use of the savings support system.

[0085] The recipe suggestion unit proposes the most suitable recipe based on information entered by the reception unit and data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and price information obtained by the acquisition unit. The recipe suggestion unit can also propose healthy recipes considering the user's preferences and nutritional balance. Furthermore, the recipe suggestion unit has a function to propose the most suitable recipe for the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates a recipe using the cheapest ingredients based on the dinner menu entered by the user and price information obtained by the acquisition unit. It can also propose healthy recipes considering the user's preferences and nutritional balance. By proposing the most suitable recipe for the user, taking into account cooking time and difficulty, economical and healthy meals can be prepared. The recipe suggestion unit can analyze the user's past recipe selection history and provide individually customized recipe suggestions. For example, it can suggest new recipes using specific ingredients or dishes for users who prefer them. The recipe suggestion unit can also propose recipes that include necessary nutrients, taking into account the user's nutritional balance. This makes it easy for users to prepare healthy meals. Furthermore, the recipe suggestion department can propose recipes tailored to the user's lifestyle, taking into account cooking time and difficulty. For example, it can suggest quick and easy recipes for busy weekday evenings, and more elaborate recipes that require more time on weekends. The recipe suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For instance, it can adjust future suggestions to be more appropriate based on user evaluations of recipes they have actually made. This allows the recipe suggestion department to provide users with the most useful information and maximize the effectiveness of the money-saving support system.

[0086] The acquisition unit can collect price information from each store in real time. For example, the acquisition unit can collect price information from each store in real time and provide it to the user. For example, the acquisition unit can collect price information from each store in real time via the internet. Furthermore, the acquisition unit can use GPS to determine the user's current location and collect price information from nearby stores in real time. In addition, the acquisition unit can update store price information in real time. For example, the acquisition unit collects price information in real time from each store's website or online database via the internet. It can also use GPS to determine the user's current location and collect price information from nearby stores in real time. By updating price information in real time, it can always provide the latest price information. This means that by collecting price information in real time, it can provide the latest price information.

[0087] The discrimination unit can acquire information about purchased items from receipts and save it as a history. For example, the discrimination unit can acquire information about purchased items from receipts and save it as a history. For example, the discrimination unit can read the text information on the receipt using OCR technology and acquire information about purchased items. The discrimination unit can also read the barcode information on the receipt using a barcode scanner and acquire information about purchased items. Furthermore, the discrimination unit can analyze the image of the receipt to acquire information about purchased items and save it as a history. For example, the discrimination unit can convert the text information on the receipt into digital data using OCR technology and acquire information about purchased items. It can also read the barcode information printed on the receipt using a barcode scanner and acquire information about purchased items. By analyzing the image of the receipt, detailed information about purchased items can be acquired and saved as a history. This makes it possible to analyze purchasing patterns by saving information about purchased items as a history.

[0088] The analytics department can analyze users' purchasing patterns and understand their tendencies to prefer frequently purchased items and specific brands. For example, the analytics department can store users' purchase history in a database to understand their tendencies to prefer frequently purchased items and specific brands. Furthermore, the analytics department can predict users' preferences and needs based on their purchasing patterns. In addition, the analytics department has a function to visualize purchasing patterns. For example, the analytics department can store users' purchase history in a database to understand their tendencies to prefer frequently purchased items and specific brands. It can also predict users' preferences and needs based on their purchasing patterns. By visualizing purchasing patterns as graphs and charts, the information can be presented to users in an easy-to-understand manner. This allows for the understanding of users' preferences and tendencies through the analysis of purchasing patterns.

[0089] The store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. For example, the store recommendation department can select the most economical store based on the user's purchasing patterns and price information of nearby stores. Furthermore, the store recommendation department can prioritize suggesting specific stores based on the user's preferences and needs. In addition, the store recommendation department has a function to make suggestions based on store ratings and reviews. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. It can also prioritize suggesting specific stores based on the user's preferences and needs. It can suggest highly reliable stores based on store ratings and reviews. This allows for savings on household expenses by selecting the most economical store.

[0090] The recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's daily dinner menu. For example, the recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's daily dinner menu. For example, the recipe suggestion unit can generate the optimal recipe using the cheapest ingredients based on the user's dinner menu entered by the user and price information obtained by the data acquisition unit. Furthermore, the recipe suggestion unit can suggest healthy recipes considering the user's preferences and nutritional balance. In addition, the recipe suggestion unit has a function to suggest the optimal recipe for the user, taking into account cooking time and difficulty. For example, the recipe suggestion unit generates the optimal recipe using the cheapest ingredients based on the user's dinner menu entered by the user and price information obtained by the data acquisition unit. It can also suggest healthy recipes considering the user's preferences and nutritional balance. By suggesting the optimal recipe for the user, taking into account cooking time and difficulty, it is possible to prepare economical and healthy meals. This means that by suggesting recipes using the cheapest ingredients, economical and healthy meals can be prepared.

[0091] The acquisition unit can estimate the user's emotions and adjust the timing of price information acquisition based on the estimated emotions. For example, if the user is stressed, the acquisition unit can reduce the frequency of price information acquisition and reduce notifications. If the user is relaxed, the acquisition unit can increase the frequency of price information acquisition and provide more detailed information. Furthermore, if the user is in a hurry, the acquisition unit can quickly acquire and notify only the most important price information. For example, if the user is stressed, the acquisition unit reduces the frequency of price information acquisition and reduces notifications. If the user is relaxed, it can increase the frequency of price information acquisition and provide more detailed information. If the user is in a hurry, it can quickly acquire and notify only the most important price information. This allows for more appropriate information to be provided by adjusting the timing of price information acquisition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The data acquisition unit can compare price information for each store with historical data and analyze price fluctuation patterns to acquire data. For example, the data acquisition unit can compare price information for each store with historical data and analyze price fluctuation patterns to acquire data. For example, the data acquisition unit can analyze seasonal price fluctuation patterns based on price data from the past year. The data acquisition unit can also analyze price fluctuation patterns for specific days of the week or time of day based on price data from the past few months. Furthermore, the data acquisition unit can analyze price fluctuation patterns during specific events or sales periods based on historical price data. For example, the data acquisition unit can analyze seasonal price fluctuation patterns based on price data from the past year. It can also analyze price fluctuation patterns for specific days of the week or time of day based on price data from the past few months. It can analyze price fluctuation patterns during specific events or sales periods based on historical price data. By analyzing price fluctuation patterns, more accurate price information can be provided.

[0093] The acquisition unit can acquire price information while considering price fluctuations on specific days of the week and time slots. For example, if prices tend to be lower on weekday mornings, the acquisition unit can acquire price information during that time. Also, if prices tend to be higher on weekend evenings, the acquisition unit can avoid acquiring price information during that time. Furthermore, if sales are held on specific days of the week, the acquisition unit can acquire price information on those days. For example, if prices tend to be lower on weekday mornings, the acquisition unit can acquire price information during that time. If prices tend to be higher on weekend evenings, the acquisition unit can avoid acquiring price information during that time. If sales are held on specific days of the week, the acquisition unit can acquire price information on those days. This allows for the provision of more economical price information by considering price fluctuations on specific days of the week and time slots.

[0094] The acquisition unit can estimate the user's emotions and determine the priority of price information to acquire based on the estimated emotions. For example, if the user is stressed, the acquisition unit can prioritize acquiring price information for the cheapest product. If the user is relaxed, the acquisition unit can also prioritize acquiring price information for high-quality products. Furthermore, if the user is in a hurry, the acquisition unit can prioritize acquiring price information for the nearest store. For example, if the user is stressed, the acquisition unit prioritizes acquiring price information for the cheapest product. If the user is relaxed, it can also prioritize acquiring price information for high-quality products. If the user is in a hurry, it can prioritize acquiring price information for the nearest store. This makes it possible to provide more appropriate information by prioritizing price information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The data acquisition unit can prioritize the acquisition of highly relevant price information by considering the user's purchase history when acquiring price information. For example, the data acquisition unit can prioritize the acquisition of highly relevant price information by considering the user's purchase history when acquiring price information. For example, the data acquisition unit can prioritize the acquisition of price information for products that the user frequently purchases. Furthermore, if the user prefers a particular brand, the data acquisition unit can prioritize the acquisition of price information for products of that brand. In addition, the data acquisition unit can prioritize the acquisition of highly relevant price information based on the price information of products that the user has purchased in the past. For example, the data acquisition unit can prioritize the acquisition of price information for products that the user frequently purchases. If the user prefers a particular brand, the data acquisition unit can prioritize the acquisition of price information for products of that brand. Based on the price information of products that the user has purchased in the past, the data acquisition unit can prioritize the acquisition of highly relevant price information. This allows the system to provide highly relevant price information by considering the user's purchase history.

[0096] The acquisition unit can acquire price information from the most suitable store by considering the user's geographical location when acquiring price information. For example, the acquisition unit can prioritize acquiring price information from the store closest to the user's current location. It can also prioritize acquiring price information from stores along the user's commuting route. Furthermore, it can prioritize acquiring price information from stores near the user's home. For example, the acquisition unit prioritizes acquiring price information from the store closest to the user's current location. It can also prioritize acquiring price information from stores along the user's commuting route. It can prioritize acquiring price information from stores near the user's home. By considering the user's geographical location, it can provide price information from the most suitable store.

[0097] The suggestion function can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is stressed, the suggestion function can provide simple and easy-to-understand suggestions. If the user is relaxed, the suggestion function can provide suggestions that include more detailed information. Furthermore, if the user is in a hurry, the suggestion function can provide concise and to-the-point suggestions. For example, if the user is stressed, the suggestion function can provide simple and easy-to-understand suggestions. If the user is relaxed, it can provide suggestions that include more detailed information. If the user is in a hurry, it can provide concise and to-the-point suggestions. By adjusting the way suggestions are presented according to the user's emotions, more appropriate suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The proposal department can adjust the level of detail in a proposal based on the importance of the product. For example, the proposal department can provide detailed proposals for important products. For less important products, the proposal department can provide concise proposals. Furthermore, the proposal department can provide detailed proposals for products that users frequently purchase. For example, the proposal department can provide detailed proposals for important products. For less important products, it can provide concise proposals. For products that users frequently purchase, it can provide detailed proposals. By adjusting the level of detail in proposals based on the importance of the product, more appropriate proposals become possible.

[0099] The proposal function can apply different proposal algorithms depending on the product category when making a proposal. For example, the proposal function can apply different proposal algorithms depending on the product category when making a proposal. For example, for products in the food category, the proposal function can make proposals that include nutritional information. For products in the daily necessities category, the proposal function can also make proposals that include usage instructions. Furthermore, for products in the home appliance category, the proposal function can make proposals that include technical specifications. By applying different proposal algorithms depending on the product category, more appropriate proposals become possible.

[0100] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the user is stressed, the suggestion unit can provide a short, to-the-point suggestion. If the user is relaxed, the suggestion unit can provide a longer suggestion with more detailed information. Furthermore, if the user is in a hurry, the suggestion unit can provide a quick and concise suggestion. For example, if the user is stressed, the suggestion unit will provide a short, to-the-point suggestion. If the user is relaxed, it can provide a longer suggestion with more detailed information. If the user is in a hurry, it can provide a quick and concise suggestion. This allows for more appropriate suggestions by adjusting the length of the suggestion according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The proposal department can prioritize proposals based on the product submission timing. For example, the proposal department can prioritize proposals for products with approaching deadlines. Furthermore, for seasonal products, the proposal department can make proposals tailored to the season. Additionally, for new products, the proposal department can submit proposals immediately after launch. This allows for more appropriate proposals by prioritizing proposals based on product submission timing.

[0102] The suggestion function can adjust the order of suggestions based on the relevance of the products when making suggestions. For example, the suggestion function can prioritize suggesting products that the user frequently purchases. It can also suggest highly relevant products in sequence. Furthermore, the suggestion function can suggest highly relevant products based on the user's purchase history. For example, the suggestion function can prioritize suggesting products that the user frequently purchases. It can also suggest highly relevant products in sequence. It can suggest highly relevant products based on the user's purchase history. By adjusting the order of suggestions based on the relevance of the products, more appropriate suggestions become possible.

[0103] The discrimination unit can estimate the user's emotions and adjust the receipt reading accuracy based on the estimated emotions. For example, the discrimination unit can estimate the user's emotions and adjust the receipt reading accuracy based on the estimated emotions. For example, if the user is stressed, the discrimination unit can increase the reading accuracy to reduce errors. Also, if the user is relaxed, the discrimination unit can process with normal reading accuracy. Furthermore, if the user is in a hurry, the discrimination unit can adjust the accuracy to read quickly. For example, if the user is stressed, the discrimination unit can increase the reading accuracy to reduce errors. If the user is relaxed, it can process with normal reading accuracy. If the user is in a hurry, the accuracy can be adjusted to read quickly. This allows for obtaining more accurate information by adjusting the receipt reading accuracy according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The discrimination unit can apply different discrimination algorithms to each category of purchased items when reading a receipt. For example, the discrimination unit can apply a discrimination algorithm that includes nutritional information to purchased items in the food category. It can also apply a discrimination algorithm that includes usage instructions to purchased items in the daily necessities category. Furthermore, it can apply a discrimination algorithm that includes technical specifications to purchased items in the home appliance category. By applying different discrimination algorithms to each category of purchased items, discrimination accuracy is improved.

[0105] The discrimination unit can automatically calculate and save the quantity and price of purchased items when reading a receipt. For example, the discrimination unit can automatically calculate and save the quantity and price of purchased items when reading a receipt. The discrimination unit can also automatically calculate and save the price of purchased items when reading a receipt. Furthermore, the discrimination unit can automatically calculate and save the total amount of purchased items when reading a receipt. This makes it easier to manage purchase history by automatically calculating and saving the quantity and price of purchased items.

[0106] The discrimination unit can estimate the user's emotions and adjust the order in which receipts are read based on the estimated emotions. For example, if the user is stressed, the discrimination unit can prioritize reading important items. If the user is relaxed, the discrimination unit can read in the normal order. Furthermore, if the user is in a hurry, the discrimination unit can adjust the order to read quickly. For example, if the user is stressed, the discrimination unit prioritizes reading important items. If the user is relaxed, it can also read in the normal order. If the user is in a hurry, it can adjust the order to read quickly. This allows for more efficient information acquisition by adjusting the order in which receipts are read according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The discrimination unit can improve its discrimination accuracy by considering the brand information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy by considering the brand information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the brand information of the purchased items when reading the receipt. Furthermore, the discrimination unit can improve the discrimination accuracy of products of a specific brand when reading the receipt. In addition, the discrimination unit can obtain detailed information about the purchased items based on the brand information when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the brand information of the purchased items when reading the receipt. It can also improve the discrimination accuracy of products of a specific brand when reading the receipt. It can obtain detailed information about the purchased items based on the brand information when reading the receipt. As a result, discrimination accuracy is improved by considering the brand information of the purchased items.

[0108] The discrimination unit can improve its discrimination accuracy by utilizing the barcode information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy by utilizing the barcode information of the purchased items when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the barcode information of the purchased items when reading the receipt. Furthermore, the discrimination unit can obtain detailed information about the purchased items based on the barcode information when reading the receipt. In addition, the discrimination unit can obtain price information about the purchased items based on the barcode information when reading the receipt. For example, the discrimination unit can improve its discrimination accuracy based on the barcode information of the purchased items when reading the receipt. It can also obtain detailed information about the purchased items based on the barcode information when reading the receipt. It can obtain price information about the purchased items based on the barcode information when reading the receipt. As a result, discrimination accuracy is improved by utilizing the barcode information of the purchased items.

[0109] The analysis unit can estimate the user's emotions and adjust the analysis method of purchasing patterns based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the analysis method of purchasing patterns based on the estimated user emotions. For example, if the user is stressed, the analysis unit can apply a concise analysis method. If the user is relaxed, the analysis unit can also apply a detailed analysis method. Furthermore, if the user is in a hurry, the analysis unit can adjust the method to perform the analysis quickly. For example, if the user is stressed, the analysis unit applies a concise analysis method. If the user is relaxed, a detailed analysis method can also be applied. If the user is in a hurry, the method can be adjusted to perform the analysis quickly. This allows for more appropriate analysis by adjusting the analysis method of purchasing patterns according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The analysis unit can optimize its analysis algorithm by referring to past purchase history when analyzing purchasing patterns. For example, the analysis unit can optimize its analysis algorithm by referring to past purchase history. For example, the analysis unit can optimize its analysis algorithm based on purchase history over the past year. Furthermore, the analysis unit can optimize its analysis algorithm based on purchase history over the past few months. In addition, the analysis unit can analyze purchasing patterns for specific products based on past purchase history. For example, the analysis unit can optimize its analysis algorithm based on purchase history over the past year. It can also optimize its analysis algorithm based on purchase history over the past few months. By referring to past purchase history, the analysis algorithm can be optimized, improving the accuracy of the analysis.

[0111] The analysis department can apply different analytical methods to each category of purchased goods when analyzing purchasing patterns. For example, the analysis department can apply analytical methods that include nutritional information to purchasing patterns in the food category. Furthermore, the analysis department can apply analytical methods that include frequency of use to purchasing patterns in the daily necessities category. In addition, the analysis department can apply analytical methods that include technical specifications to purchasing patterns in the home appliance category. This improves analytical accuracy by applying different analytical methods to each category of purchased goods.

[0112] The analysis unit can estimate the user's emotions and adjust the order in which it displays the analysis results of purchasing patterns based on the estimated emotions. For example, if the user is feeling stressed, the analysis unit can prioritize displaying important analysis results. If the user is relaxed, the analysis unit can also display detailed analysis results in a sequential manner. Furthermore, if the user is in a hurry, the analysis unit can quickly display concise analysis results. For example, if the user is feeling stressed, the analysis unit prioritizes displaying important analysis results. If the user is relaxed, it can also display detailed analysis results in a sequential manner. If the user is in a hurry, it can quickly display concise analysis results. This allows for the provision of more appropriate information by adjusting the display order of analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0113] The analysis unit can improve the accuracy of its analysis by considering the user's geographical location when analyzing purchasing patterns. For example, the analysis unit can improve the accuracy of its analysis by considering the user's geographical location when analyzing purchasing patterns. For example, the analysis unit can analyze region-specific purchasing patterns based on the user's current location. It can also analyze purchasing patterns based on store information along the user's commuting route. Furthermore, the analysis unit can analyze purchasing patterns based on store information around the user's home. This improves the accuracy of the analysis by considering the user's geographical location.

[0114] The analytics department can improve the accuracy of its analysis of purchasing patterns by referring to users' social media activity. For example, the analytics department can improve the accuracy of its analysis by referring to users' social media activity when analyzing purchasing patterns. For example, the analytics department can analyze purchasing patterns based on the content of users' social media posts. Furthermore, the analytics department can analyze purchasing patterns based on users' "likes" and comments on social media. In addition, the analytics department can analyze purchasing patterns based on the brands and stores that users follow on social media. For example, the analytics department can analyze purchasing patterns based on the content of users' social media posts. It can also analyze purchasing patterns based on users' "likes" and comments on social media. It can analyze purchasing patterns based on the brands and stores that users follow on social media. This improves the accuracy of the analysis by referring to users' social media activity.

[0115] The store recommendation department can estimate the user's emotions and adjust its store recommendation method based on the estimated emotions. For example, if the user is stressed, the store recommendation department can provide simple and easy-to-understand store recommendations. If the user is relaxed, the store recommendation department can provide store recommendations that include detailed information. Furthermore, if the user is in a hurry, the store recommendation department can provide concise and to-the-point store recommendations. For example, if the user is stressed, the store recommendation department will provide simple and easy-to-understand store recommendations. If the user is relaxed, it can provide store recommendations that include detailed information. If the user is in a hurry, it can provide concise and to-the-point store recommendations. By adjusting the store recommendation method according to the user's emotions, more appropriate recommendations become possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0116] The store suggestion department can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting stores. For example, the store suggestion department can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting stores. For example, the store suggestion department can prioritize suggesting stores that users prefer based on past suggestion history. The store suggestion department can also exclude stores that users avoid from suggestions based on past suggestion history. Furthermore, the store suggestion department can suggest stores that match the user's purchasing patterns based on past suggestion history. For example, the store suggestion department can prioritize suggesting stores that users prefer based on past suggestion history. It can also exclude stores that users avoid from suggestions based on past suggestion history. It can suggest stores that match the user's purchasing patterns based on past suggestion history. As a result, by referring to past suggestion history, the optimal suggestion algorithm can be applied, improving the accuracy of suggestions.

[0117] The store recommendation department can adjust the level of detail in its recommendations based on the user's purchasing patterns. For example, the store recommendation department can provide detailed recommendations for stores that carry products the user frequently purchases. Furthermore, if the user prefers a particular brand, the store recommendation department can provide detailed recommendations for stores that carry that brand. In addition, the store recommendation department can provide detailed recommendations for highly relevant stores based on the user's purchasing patterns. For example, the store recommendation department can provide detailed recommendations for stores that carry products the user frequently purchases. If the user prefers a particular brand, it can also provide detailed recommendations for stores that carry that brand. It can provide detailed recommendations for highly relevant stores based on the user's purchasing patterns. This allows for more appropriate recommendations by adjusting the level of detail based on the user's purchasing patterns.

[0118] The store recommendation system can estimate the user's emotions and prioritize store recommendations based on those emotions. For example, if the user is stressed, the system can prioritize recommending the cheapest store. If the user is relaxed, the system can prioritize recommending a high-quality store. Furthermore, if the user is in a hurry, the system can prioritize recommending the nearest store. This allows for more appropriate recommendations by prioritizing store recommendations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The store recommendation department can suggest the most suitable store by considering the user's geographical location. For example, the store recommendation department can prioritize suggesting the store closest to the user's current location. It can also prioritize suggesting stores along the user's commute route. Furthermore, it can prioritize suggesting stores near the user's home. For example, the store recommendation department prioritizes suggesting the store closest to the user's current location. It can also prioritize suggesting stores along the user's commute route. It can also prioritize suggesting stores near the user's home. By considering the user's geographical location, the department can suggest the most suitable store.

[0120] The store recommendation department can suggest the most suitable stores by referring to the user's social media activity when making store recommendations. For example, the store recommendation department can suggest stores based on the user's social media posts. Furthermore, the store recommendation department can suggest stores based on the user's "likes" and comments on social media. In addition, the store recommendation department can suggest stores based on the brands and stores the user follows on social media. For example, the store recommendation department can suggest stores based on the user's social media posts. It can also suggest stores based on the user's "likes" and comments on social media. It can also suggest stores based on the brands and stores the user follows on social media. This allows the department to suggest the most suitable stores by referring to the user's social media activity.

[0121] The reception desk can estimate the user's emotions and adjust the input method for dinner information based on the estimated emotions. For example, if the user is stressed, the reception desk can provide a simple interface and minimize the input steps. If the user is relaxed, the reception desk can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception desk can prioritize voice input to allow for quick input of dinner information. For example, if the user is stressed, the reception desk can provide a simple interface and minimize the input steps. If the user is relaxed, it can also provide detailed input options and suggest customizable input methods. If the user is in a hurry, it can prioritize voice input to allow for quick input of dinner information. This allows for more appropriate information input by adjusting the input method for dinner information according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0122] The reception system can suggest the optimal input method when a user enters dinner information by referring to their past input history. For example, the reception system can automatically display as suggestions dinner menus that the user has frequently entered in the past. The reception system can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). Furthermore, the reception system can predict and suggest menus that the user will use at a specific time of day based on their past input history. For example, the reception system can automatically display as suggestions dinner menus that the user has frequently entered in the past. It can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). It can predict and suggest menus that the user will use at a specific time of day based on their past input history. This improves input efficiency by suggesting the optimal input method by referring to past input history.

[0123] The reception desk can customize input fields based on the user's dietary preferences when entering dinner information. For example, the reception desk can customize input fields based on the user's dietary preferences when entering dinner information. For example, the reception desk can prioritize displaying ingredients that the user likes as input fields. It can also exclude ingredients that the user avoids from the input fields. Furthermore, the reception desk can suggest customized input fields based on the user's dietary preferences. For example, the reception desk can prioritize displaying ingredients that the user likes as input fields. It can also exclude ingredients that the user avoids from the input fields. It can suggest customized input fields based on the user's dietary preferences. This allows for more appropriate information to be entered by customizing input fields based on the user's dietary preferences.

[0124] The reception desk can estimate the user's emotions and adjust the input order of dinner information based on the estimated emotions. For example, if the user is feeling stressed, the reception desk can prioritize inputting important items. If the user is relaxed, the reception desk can also input in the normal order. Furthermore, if the user is in a hurry, the reception desk can adjust the order to allow for quick input. For example, if the user is feeling stressed, the reception desk prioritizes inputting important items. If the user is relaxed, the reception desk can also input in the normal order. If the user is in a hurry, the order can be adjusted to allow for quick input. This allows for more efficient information input by adjusting the input order of dinner information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0125] The reception desk can suggest the optimal input method when a user enters dinner information, taking into account the user's geographical location. For example, the reception desk can suggest the optimal input method when a user enters dinner information, taking into account the user's geographical location. For example, the reception desk can suggest region-specific menus as input fields based on the user's current location. Furthermore, the reception desk can suggest menus as input fields based on store information along the user's commute route. In addition, the reception desk can suggest menus as input fields based on store information around the user's home. This allows the system to suggest the optimal input method by considering the user's geographical location.

[0126] The reception desk can suggest the most suitable input method when a user enters dinner information by referring to their social media activity. For example, when a user enters dinner information, the reception desk can suggest the most suitable input method by referring to their social media activity. For example, the reception desk can suggest preferred menu items as input fields based on the user's social media posts. Furthermore, the reception desk can suggest preferred menu items as input fields based on the user's social media "likes" and comments. In addition, the reception desk can suggest preferred menu items as input fields based on the brands and stores the user follows on social media. For example, the reception desk can suggest preferred menu items as input fields based on the user's social media posts. It can also suggest preferred menu items as input fields based on the user's social media "likes" and comments. It can also suggest preferred menu items as input fields based on the brands and stores the user follows on social media. This allows the reception desk to suggest the most suitable input method by referring to the user's social media activity.

[0127] The recipe suggestion unit can estimate the user's emotions and adjust its recipe suggestion method based on those emotions. For example, if the user is stressed, the recipe suggestion unit can suggest a simple and easy-to-understand recipe. If the user is relaxed, the recipe suggestion unit can suggest a recipe with more detailed information. Furthermore, if the user is in a hurry, the recipe suggestion unit can suggest a short, to-the-point recipe. For example, if the user is stressed, the recipe suggestion unit can suggest a simple and easy-to-understand recipe. If the user is relaxed, it can suggest a recipe with more detailed information. If the user is in a hurry, it can suggest a short, to-the-point recipe. By adjusting the recipe suggestion method according to the user's emotions, more appropriate suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0128] The recipe suggestion unit can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting recipes. For example, the recipe suggestion unit can apply the optimal suggestion algorithm by referring to past suggestion history when suggesting recipes. For example, the recipe suggestion unit can prioritize suggesting recipes that the user likes based on past suggestion history. The recipe suggestion unit can also exclude recipes that the user avoids from suggestions based on past suggestion history. Furthermore, the recipe suggestion unit can suggest recipes that match the user's dietary preferences based on past suggestion history. For example, the recipe suggestion unit prioritizes suggesting recipes that the user likes based on past suggestion history. It can also exclude recipes that the user avoids from suggestions based on past suggestion history. It can suggest recipes that match the user's dietary preferences based on past suggestion history. As a result, by referring to past suggestion history, the optimal suggestion algorithm is applied, improving the accuracy of suggestions.

[0129] The recipe suggestion function can adjust the level of detail in its suggestions based on the user's dietary preferences. For example, the recipe suggestion function can suggest detailed recipes using ingredients the user likes. It can also suggest detailed recipes that do not use ingredients the user avoids. Furthermore, the recipe suggestion function can suggest highly relevant recipes in detail based on the user's dietary preferences. For example, the recipe suggestion function can suggest detailed recipes using ingredients the user likes. It can also suggest detailed recipes that do not use ingredients the user avoids. It can suggest highly relevant recipes in detail based on the user's dietary preferences. By adjusting the level of detail in suggestions based on the user's dietary preferences, more appropriate suggestions become possible.

[0130] The recipe suggestion unit can estimate the user's emotions and determine the priority of recipe suggestions based on those emotions. For example, if the user is feeling stressed, the recipe suggestion unit can prioritize suggesting easy and quick recipes. If the user is relaxed, the recipe suggestion unit can prioritize suggesting recipes that can be made over a longer period of time. Furthermore, if the user is in a hurry, the recipe suggestion unit can prioritize suggesting recipes that can be made quickly. This allows for more appropriate suggestions by prioritizing recipe suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0131] The recipe suggestion function can propose the most suitable recipe by considering the user's geographical location. For example, it can suggest recipes using local ingredients based on the user's current location. It can also suggest recipes using readily available ingredients based on store information along the user's commute route. Furthermore, it can suggest recipes using readily available ingredients based on store information near the user's home. This allows the system to propose the most suitable recipe by considering the user's geographical location.

[0132] The recipe suggestion department can suggest the most suitable recipe by referring to the user's social media activity. For example, the recipe suggestion department can suggest a recipe based on the user's social media posts. It can also suggest a recipe based on the user's "likes" and comments on social media. Furthermore, the recipe suggestion department can suggest a recipe based on the brands and food information the user follows on social media. This allows the system to suggest the most suitable recipe by referring to the user's social media activity.

[0133] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0134] The savings support system can estimate the user's emotions and adjust the timing of suggestions based on those emotions. For example, if the user is stressed, the suggestion system will be less prominent, while if the user is relaxed, it can provide more detailed suggestions. Furthermore, if the user is in a hurry, only the most important suggestions can be delivered quickly. This allows for suggestions to be made at the appropriate time, tailored to the user's emotions.

[0135] The acquisition unit can predict price fluctuations for specific products based on the user's purchase history and suggest the optimal purchase timing. For example, by analyzing past data, it can predict when the price of a particular product will drop and encourage purchases at that time. It can also provide users with information if there is a tendency for prices to drop on specific days of the week or time of day. Furthermore, it can predict price fluctuations during specific events or sales periods and suggest the optimal purchase timing to the user. This allows users to make more economical purchasing decisions.

[0136] The discrimination unit can estimate the user's emotions and adjust the receipt reading accuracy based on the estimated emotions. For example, if the user is stressed, the reading accuracy can be increased to reduce errors. If the user is relaxed, the system can process the receipt with normal reading accuracy. Furthermore, if the user is in a hurry, the accuracy can be adjusted to allow for faster reading. By adjusting the receipt reading accuracy according to the user's emotions, more accurate information can be obtained.

[0137] The analytics department can improve the accuracy of its analysis of user purchasing patterns by referencing users' social media activity. For example, it can analyze purchasing patterns based on the content of users' social media posts. It can also analyze purchasing patterns based on users' "likes" and comments on social media. Furthermore, it can analyze purchasing patterns based on the brands and store information that users follow on social media. In this way, referencing users' social media activity improves the accuracy of the analysis.

[0138] The store recommendation department can estimate the user's emotions and adjust the store recommendation method based on those estimates. For example, if the user is stressed, it can provide a simple and easy-to-understand store recommendation. If the user is relaxed, it can provide a store recommendation that includes detailed information. Furthermore, if the user is in a hurry, it can provide a concise store recommendation that gets straight to the point. By adjusting the store recommendation method according to the user's emotions, it becomes possible to provide more appropriate recommendations.

[0139] The recipe suggestion function can estimate the user's emotions and adjust the recipe suggestion method based on those estimates. For example, if the user is stressed, it can suggest a simple and easy-to-understand recipe. If the user is relaxed, it can suggest a recipe with more detailed information. Furthermore, if the user is in a hurry, it can suggest a short, to-the-point recipe. By adjusting the recipe suggestion method according to the user's emotions, more appropriate suggestions can be made.

[0140] The acquisition unit can prioritize acquiring price information for specific areas, taking into account the user's geographical location. For example, it can prioritize acquiring price information for the store closest to the user's current location. It can also prioritize acquiring price information for stores along the user's commute route. Furthermore, it can prioritize acquiring price information for stores near the user's home. This allows the system to provide optimal price information by considering the user's geographical location.

[0141] The suggestion function can estimate the user's emotions and adjust the way suggestions are presented based on those estimates. For example, if the user is stressed, it can provide simple and easy-to-understand suggestions. If the user is relaxed, it can provide suggestions that include detailed information. Furthermore, if the user is in a hurry, it can provide concise suggestions that get straight to the point. By adjusting the way suggestions are presented according to the user's emotions, more appropriate suggestions can be made.

[0142] The reception desk can estimate the user's emotions and adjust the way dinner information is entered based on those emotions. For example, if the user is stressed, it can provide a simple interface and minimize the input steps. If the user is relaxed, it can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick entry of dinner information. By adjusting the dinner information entry method according to the user's emotions, more appropriate information can be entered.

[0143] The recipe suggestion system can propose recipes using ingredients from a specific region, taking into account the user's geographical location. For example, it can suggest recipes using regionally specific ingredients based on the user's current location. It can also suggest recipes using easily available ingredients based on store information along the user's commute route. Furthermore, it can suggest recipes using easily available ingredients based on store information around the user's home. In this way, the system can suggest the most suitable recipes by considering the user's geographical location.

[0144] The following briefly describes the processing flow for example form 2.

[0145] Step 1: The acquisition unit acquires price information. The acquisition unit can, for example, use GPS to acquire price information from grocery stores near the user. The acquisition unit can also collect price information from individual stores via the internet. Furthermore, the acquisition unit can update store price information in real time. Step 2: The suggestion unit proposes the price information acquired by the acquisition unit to the user. The suggestion unit can, for example, display the price information on the user's smartphone or personal computer. The suggestion unit can also propose the most suitable price information based on the user's purchase history and preferences. Furthermore, the suggestion unit has a function to notify the user of the price information. Step 3: The discrimination unit reads the receipt and identifies the purchased items. The discrimination unit can, for example, read the text information on the receipt using OCR technology. It can also read the barcode information on the receipt using a barcode scanner. Furthermore, the discrimination unit can analyze the image of the receipt to obtain information about the purchased items. Step 4: The analysis unit analyzes purchasing patterns from the purchase history identified by the discrimination unit. For example, the analysis unit can store the user's purchase history in a database and understand the tendency to frequently purchase certain products or prefer specific brands. The analysis unit can also predict the user's preferences and needs based on the purchasing patterns. Furthermore, the analysis unit has a function to visualize the purchasing patterns. Step 5: The store recommendation department proposes the most suitable stores based on the purchasing patterns analyzed by the analysis department. For example, the store recommendation department can select the most economical store by considering the user's purchasing patterns and price information of nearby stores. The store recommendation department can also prioritize suggesting specific stores according to the user's preferences and needs. Furthermore, the store recommendation department has a function to make suggestions based on store ratings and reviews. Step 6: The reception desk inputs daily dinner information. The reception desk can, for example, allow users to input dinner menus using their smartphones or personal computers. It can also acquire dinner information using voice input or image input. Furthermore, the reception desk has a function that suggests the most suitable input method to the user based on past input history. Step 7: The recipe suggestion unit proposes the optimal recipe based on the information entered by the reception unit and the data obtained by the acquisition and analysis units. For example, the recipe suggestion unit can generate a recipe using the cheapest ingredients based on the dinner menu entered by the user and the price information obtained by the acquisition unit. The recipe suggestion unit can also propose healthy recipes considering the user's preferences and nutritional balance. Furthermore, the recipe suggestion unit has a function to propose the most suitable recipe for the user, taking into account cooking time and difficulty level.

[0146] 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.

[0147] Data generation model 58 is a form 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0148] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the acquisition unit, proposal unit, discrimination unit, analysis unit, store proposal unit, reception unit, and recipe proposal unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit can acquire price information of grocery stores near the user using the GPS function of the smart device 14. The proposal unit can display price information using the display 40A of the smart device 14. The discrimination unit can read receipts using the camera 42 of the smart device 14 and identify purchased items. The analysis unit can analyze purchasing patterns using the identification processing unit 290 of the data processing unit 12. The store proposal unit can propose the optimal store using the identification processing unit 290 of the data processing unit 12. The reception unit can input dinner information using the touch panel 38A of the smart device 14. The recipe proposal unit can propose the optimal recipe using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0150] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0151] 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.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0153] 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.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0155] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] 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.

[0157] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] 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.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the acquisition unit, proposal unit, discrimination unit, analysis unit, store proposal unit, reception unit, and recipe proposal unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit can acquire price information of grocery stores near the user using the GPS function of the smart glasses 214. The proposal unit can display price information using the display of the smart glasses 214. The discrimination unit can read receipts using the camera 42 of the smart glasses 214 and identify purchased items. The analysis unit can analyze purchasing patterns using the identification processing unit 290 of the data processing unit 12. The store proposal unit can propose the optimal store using the identification processing unit 290 of the data processing unit 12. The reception unit can input dinner information using the voice input function of the smart glasses 214. The recipe proposal unit can propose the optimal recipe using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0166] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0167] 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.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0169] 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.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0171] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] 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.

[0173] 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.

[0174] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] 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.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the acquisition unit, proposal unit, discrimination unit, analysis unit, store proposal unit, reception unit, and recipe proposal unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit can acquire price information of grocery stores near the user using the GPS function of the headset terminal 314. The proposal unit can display price information using the display 343 of the headset terminal 314. The discrimination unit can read receipts using the camera 42 of the headset terminal 314 and identify purchased items. The analysis unit can analyze purchasing patterns using the identification processing unit 290 of the data processing unit 12. The store proposal unit can propose the optimal store using the identification processing unit 290 of the data processing unit 12. The reception unit can input dinner information using the voice input function of the headset terminal 314. The recipe proposal unit can propose the optimal recipe using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0182] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0183] 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.

[0184] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0185] 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.

[0186] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0187] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0188] 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.

[0189] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0190] 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.

[0191] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0192] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0193] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0194] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0195] 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.

[0196] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0197] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0198] Each of the multiple elements described above, including the acquisition unit, proposal unit, discrimination unit, analysis unit, store proposal unit, reception unit, and recipe proposal unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit can acquire price information of grocery stores near the user using the GPS function of the robot 414. The proposal unit can display price information using the display of the robot 414. The discrimination unit can read receipts using the camera 42 of the robot 414 and identify purchased items. The analysis unit can analyze purchasing patterns using the identification processing unit 290 of the data processing unit 12. The store proposal unit can propose the optimal store using the identification processing unit 290 of the data processing unit 12. The reception unit can input information about dinner using the voice input function of the robot 414. The recipe proposal unit can propose the optimal recipe using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0199] 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.

[0200] Figure 9 shows the 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.

[0201] 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.

[0202] 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.

[0203] 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, and motorcycles, 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 based, for example, 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.

[0204] 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."

[0205] 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.

[0206] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0215] 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 other things 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.

[0216] 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.

[0217] (Note 1) A unit for acquiring price information, A proposal unit that proposes price information acquired by the acquisition unit to the user, A discrimination unit that reads the receipt and identifies the purchased items, An analysis unit analyzes purchasing patterns from the purchase history of items identified by the aforementioned discrimination unit, A store proposal unit proposes the optimal store based on the purchasing patterns analyzed by the aforementioned analysis unit, The reception desk where information about daily dinners is entered, The system includes a recipe suggestion unit that proposes an optimal recipe based on the information input by the reception unit and the data obtained by the acquisition unit and the analysis unit. A system characterized by the following features. (Note 2) The acquisition unit is, Collect price information from each store in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned discrimination unit is Retrieve purchase information from the receipt and save it as a history. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit is Analyze user purchasing patterns to understand their tendency to frequently buy certain products and prefer specific brands. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned store proposal department, The system selects the most economical store by considering the user's purchasing patterns and price information from nearby stores. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned recipe proposal department, Based on your daily dinner menu, we generate the best recipes using the cheapest ingredients. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system estimates user sentiment and adjusts the timing of price information acquisition based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, We analyze price fluctuation patterns by comparing price information from each store with historical data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring price information, consider price fluctuations during specific days of the week and time periods. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, It estimates the user's sentiment and determines the priority of price information to retrieve based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When retrieving price information, the system prioritizes retrieving highly relevant price information by considering the user's purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When retrieving price information, the system takes the user's geographical location into consideration to retrieve price information from the most suitable store. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, When submitting proposals, prioritize them based on when the products are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned discrimination unit is The system estimates the user's emotions and adjusts the accuracy of receipt reading based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned discrimination unit is When scanning receipts, different discrimination algorithms are applied to each category of purchased items. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned discrimination unit is When scanning a receipt, the system automatically calculates and saves the quantity and price of purchased items. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned discrimination unit is It estimates the user's emotions and adjusts the order in which receipts are read based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned discrimination unit is When scanning receipts, the accuracy of identification is improved by taking into account the brand information of the purchased items. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned discrimination unit is When scanning receipts, the barcode information of purchased items is used to improve the accuracy of the recognition process. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is We estimate user emotions and adjust the analysis method of purchasing patterns based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit is When analyzing purchasing patterns, we optimize the analysis algorithm by referring to past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit is When analyzing purchasing patterns, different analytical methods are applied to each category of purchased items. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned analysis unit is It estimates the user's emotions and adjusts the order in which it displays the analysis results of purchasing patterns based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned analysis unit is When analyzing purchasing patterns, consider the user's geographical location to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned analysis unit is When analyzing purchasing patterns, we improve the accuracy of the analysis by referencing users' social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned store proposal department, The system estimates the user's emotions and adjusts the store recommendation method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned store proposal department, When proposing stores, the optimal proposal algorithm is applied by referring to past proposal history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned store proposal department, When suggesting stores, adjust the level of detail in the suggestions based on the user's purchasing patterns. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned store proposal department, The system estimates the user's emotions and prioritizes store recommendations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned store proposal department, When suggesting stores, we take the user's geographical location into consideration to propose the most suitable store. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned store proposal department, When suggesting stores, we refer to the user's social media activity to suggest the most suitable store. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned reception unit is The system estimates the user's emotions and adjusts the input method for dinner information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned reception unit is When you enter information about your dinner, the system will refer to your past input history to suggest the most suitable input method. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned reception unit is When entering dinner information, the input fields are customized based on the user's meal preferences. The system described in Appendix 1, characterized by the features described herein. (Note 40) The reception unit estimates the user's emotion and adjusts the input order of dinner information based on the estimated user emotion The system according to appended note 1, characterized in that (Appended note 41) The reception unit proposes an optimal input method in consideration of the user's geographical location information when inputting dinner information The system according to appended note 1, characterized in that (Appended note 42) The reception unit proposes an optimal input method by referring to the user's social media activities when inputting dinner information The system according to appended note 1, characterized in that (Appended note 43) The recipe proposal unit estimates the user's emotion and adjusts the recipe proposal method based on the estimated user emotion The system according to appended note 1, characterized in that (Appended note 44) The recipe proposal unit applies an optimal proposal algorithm by referring to the past proposal history when proposing a recipe The system according to appended note 1, characterized in that (Appended note 45) The recipe proposal unit adjusts the proposal detail level based on the user's dietary preferences when proposing a recipe The system according to appended note 1, characterized in that (Appended note 46) The recipe proposal unit estimates the user's emotion and determines the priority order of recipe proposals based on the estimated user emotion The system according to appended note 1, characterized in that (Appended note 47) The recipe proposal unit proposes an optimal recipe by considering the user's geographical location information when proposing a recipe The system according to appended note 1, characterized in that (Appended note 48) The recipe proposal unit proposes an optimal recipe at the time of recipe proposal by referring to the user's social media activities []END]] The system according to appended note 1, characterized by the above []END]]

Explanation of signs

[0218] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset type terminal 414 Robot

Claims

1. A unit for acquiring price information, A proposal unit that proposes price information acquired by the acquisition unit to the user, A discrimination unit that reads the receipt and identifies the purchased items, An analysis unit analyzes purchasing patterns from the purchase history of items identified by the aforementioned discrimination unit, A store proposal unit proposes the optimal store based on the purchasing patterns analyzed by the aforementioned analysis unit, The reception desk where information about daily dinners is entered, The system includes a recipe suggestion unit that proposes an optimal recipe based on the information input by the reception unit and the data obtained by the acquisition unit and the analysis unit. A system characterized by the following features.

2. The acquisition unit is, Collect price information from each store in real time. The system according to feature 1.

3. The aforementioned discrimination unit is Retrieve purchase information from the receipt and save it as a history. The system according to feature 1.

4. The aforementioned analysis unit is Analyze user purchasing patterns to understand their tendency to frequently buy certain products and prefer specific brands. The system according to feature 1.

5. The aforementioned store proposal department, The system selects the most economical store by considering the user's purchasing patterns and price information from nearby stores. The system according to feature 1.

6. The aforementioned recipe proposal department, Based on your daily dinner menu, we generate the best recipes using the cheapest ingredients. The system according to feature 1.

7. The acquisition unit is, The system estimates user sentiment and adjusts the timing of price information acquisition based on the estimated user sentiment. The system according to feature 1.

8. The acquisition unit is, We analyze price fluctuation patterns by comparing price information from each store with historical data. The system according to feature 1.

Images