System

Abstract

To provide a system that enables users to search for products and efficiently compare information on a plurality of products.SOLUTION: A system comprises a reception unit, a collection unit, a comparison unit, and a comparison result providing unit. The reception unit receives input from a user. The collection unit collects information on a plurality of products according to the input received by the reception unit when the input received by the reception unit pertains to a product search. The comparison unit compares the information on the plurality of products collected by the collection unit. The comparison result providing unit provides the comparison results by the comparison unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem that it is difficult for users to search for products and efficiently compare information on multiple products.

[0005] The system according to the embodiment aims to enable a user to search for a product and efficiently compare information on a plurality of products. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a collection unit, a comparison unit, and a comparison result providing unit. The reception unit receives input from a user. When the input received by the reception unit is a product search, the collection unit collects information on multiple products corresponding to the input received by the reception unit. The comparison unit compares the information on the multiple products collected by the collection unit. The comparison result providing unit provides the comparison result by the comparison unit. Effect of the Invention

[0007] The system according to the embodiment allows a user to search for products and efficiently compare information on multiple products. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a 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. The database 24 and the communication I / F 26 are also 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The online store purchase support AI assistant according to the embodiment of the present invention is a system that helps users search for products and compare prices and features. The system includes a reception unit that receives input from a user, and when a product search is performed, a collection unit collects information on multiple products, and a comparison unit compares the information. The comparison result is provided to the user by a comparison result providing unit. In addition, the system has a customer support function that quickly responds to questions from users. When the reception unit receives a question, the response unit answers the question. In particular, for questions about delivery status and stock status, the response unit provides this information. In addition, the system has an order tracking function, and when a user inputs an input to check the progress of an order, the progress information providing unit provides information indicating the progress in real time. The progress information providing unit can also provide information via smart home appliances, for example, by using the display of a smart refrigerator to display the delivery status of ingredients, or by linking with smart lighting to provide notifications in different colors or blinking patterns. In addition, the system has a personalized suggestion function that recommends related products based on the user's past purchase history. The suggestion unit can suggest products based on the user's product purchase history and reviews of influencers the user follows. It can also suggest bundled products that are great value when purchased together. Finally, there is a feedback function, which collects user feedback and improves the comparison section based on the collected feedback. This allows the online store's purchasing support AI assistant to not only help users search for products and compare prices and features, but also provide multiple functions such as customer support, order tracking, personalized suggestions, and feedback collection.

[0029] The online store purchase support AI assistant according to the embodiment includes a reception unit, a collection unit, a comparison unit, and a comparison result providing unit. The reception unit receives input from a user. The input from the user includes, but is not limited to, for example, text input, voice input, image input, and the like. The reception unit receives the input when, for example, a user searches for a product. The collection unit collects information on a plurality of products according to the input received by the reception unit. The collected product information includes, but is not limited to, for example, price information, product features, reviews, and the like. The collection unit collects product information from a plurality of online stores, for example, using a web scraping technique. The collection unit can also obtain product information using an API. Furthermore, the collection unit can also perform a database search to collect product information. The comparison unit compares the information on a plurality of products collected by the collection unit. Comparison criteria include, but are not limited to, for example, price comparison, performance comparison, and user evaluation comparison. The comparison unit compares products based on, for example, price information. The comparison unit can also compare products based on performance information. Furthermore, the comparison unit can compare products based on user evaluations. The comparison result providing unit provides the comparison results by the comparison unit. The display method of the comparison results includes, but is not limited to, for example, a ranking format, a graph display, a text display, and the like. The comparison result providing unit displays products, for example, in a ranking format. The comparison result providing unit can also display products in a graph display. The comparison result providing unit can also display products in a text display. This allows the purchase support AI assistant of the online store according to the embodiment to help users search for products and compare prices and features. Some or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can compare products using an AI model that inputs product information collected by the collection unit and outputs a comparison result.

[0030] The reception unit receives input from a user. Examples of input from a user include, but are not limited to, text input, voice input, and image input. Specifically, in the case of text input, the user inputs a product name and a category using a keyboard or a touch screen. In the case of voice input, the user inputs a product name and a desired feature by voice through a microphone, and the voice input is converted into text using voice recognition technology. In the case of image input, the user takes a photo of the product using a camera, and the product is identified using image recognition technology. The reception unit processes these inputs in real time and generates a search query according to the user's request. Furthermore, the reception unit can refer to the user's past search history and purchase history, and perform input completion and suggestions taking into account the user's preferences and tendencies. For example, if the user has searched for many products of a specific brand in the past, products of that brand are preferentially displayed. In addition, the reception unit can provide immediate feedback to the user's input and prompt the user to confirm or correct the input content. This allows the reception unit to respond to various input methods of the user and quickly and accurately receive the user's request.

[0031] The collection unit collects information on a plurality of products according to the input received by the reception unit. The collected product information includes, for example, price information, product features, reviews, etc., but is not limited to such examples. Specifically, the collection unit collects product information from a plurality of online stores using web scraping technology. Web scraping technology is a technology that analyzes the HTML structure of a web page and extracts necessary data. For example, price information, product features, and user reviews are automatically obtained from the product page of a specific online store. The collection unit can also acquire product information using an API. An API is an interface for exchanging data between different systems, and the latest product information can be efficiently acquired using the API provided by the online store. Furthermore, the collection unit can also perform a database search to collect product information. The database stores product information and user reviews collected in the past, and searches these data to acquire the required information. The collection unit can combine these methods to collect comprehensive product information from various information sources and provide optimal product information according to the user's request.

[0032] The comparison unit compares information on a plurality of products collected by the collection unit. Comparison criteria include, but are not limited to, price comparison, performance comparison, and user evaluation comparison. Specifically, the comparison unit compares products based on price information. For example, the comparison unit identifies the cheapest product or the product with the highest cost performance among products in the same category. The comparison unit can also compare products based on performance information. For example, in the case of smartphones, the comparison unit compares technical features such as processor performance, battery life, and camera pixel count to identify the product that best suits the user's requirements. Furthermore, the comparison unit can compare products based on user evaluation. For example, the comparison unit analyzes user reviews and evaluation scores in an online store to identify products with high overall ratings or products with high ratings for specific features. The comparison unit can combine these comparison criteria to propose the optimal product in response to the user's diverse requirements. Furthermore, the comparison unit can analyze the product information collected using AI and comprehensively evaluate multiple criteria. For example, the comparison unit uses an AI model to comprehensively evaluate price, performance, and user evaluation to identify the product that is most suitable for the user. This allows the comparison unit to quickly and accurately compare products and provide the user with the best option.

[0033] The comparison result providing unit provides the comparison result by the comparison unit. The display method of the comparison result includes, but is not limited to, for example, a ranking format, a graph display, a text display, and the like. Specifically, the comparison result providing unit displays the products in a ranking format. For example, a ranking such as the lowest price, the highest performance, or the highest user rating is displayed, so that the user can easily understand the comparison result. The comparison result providing unit can also display the products in a graph display. For example, a scatter diagram showing the relationship between price and performance, or a bar graph showing the distribution of user ratings, is used to visually provide the comparison result. Furthermore, the comparison result providing unit can also display the products in a text display. For example, the features and evaluation points of each product are explained in detail in text, making it easier for the user to understand the features of the product. The comparison result providing unit can combine these display methods to provide the comparison result in a format that is most easily understandable for the user. Furthermore, the comparison result providing unit can collect user feedback and improve the display method or add a new display format. For example, if a user prefers a specific display format, a setting is provided to preferentially display that format. In addition, the comparison result providing unit can provide the latest comparison results based on data updated in real time, thereby enabling the comparison result providing unit to provide the user with quick and accurate comparison results and support product selection.

[0034] The reception unit includes a response unit that responds to the question when the reception unit receives the question. The response unit responds to the question from the user. The format of the question includes, for example, a text-format question, a voice-format question, a question about a specific category, and the like, but is not limited to such examples. For example, when the user inputs a question in text format, the response unit responds to the question in text format. In addition, when the user inputs a question in voice format, the response unit can also respond to the question in voice format. Furthermore, the response unit can provide corresponding information in response to a question about a specific category. For example, the response unit provides information such as a delivery status and a scheduled delivery date in response to a question about a delivery status. In addition, the response unit can provide information such as the number of items in stock and a scheduled arrival date in response to a question about an inventory status. This makes it possible to quickly respond to the user's question. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can respond to the question using an AI model that receives the user's question as an input and outputs a response.

[0035] The response unit responds with the delivery status or the stock status as an answer to the question. The response unit provides information such as the delivery status and the scheduled delivery date in response to a question regarding the delivery status. The information on the delivery status includes, for example, the delivery status, the scheduled delivery date, and the information of the delivery company, but is not limited to such examples. For example, when a user wants to check the delivery status, the response unit provides the current delivery status in response to the question. The response unit can also provide the scheduled delivery date. Furthermore, the response unit can also provide the information of the delivery company. The response unit provides information such as the number of items in stock and the scheduled arrival date in response to a question regarding the stock status. The information on the stock status includes, for example, the number of items in stock, the scheduled arrival date, and the location of the stock, but is not limited to such examples. For example, when a user wants to check the stock status, the response unit provides the current number of items in stock in response to the question. The response unit can also provide the scheduled arrival date. Furthermore, the response unit can also provide the location of the stock. This allows a quick response to a question regarding the delivery status or the stock status. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can respond to a user's question using an AI model that takes a user's question as input and outputs information on delivery status and inventory status.

[0036] The reception unit includes a progress information providing unit that provides progress information when a confirmation of the progress of the order is received. When a user makes an input to confirm the progress of the order, the progress information providing unit provides information indicating the progress. The information on the progress of the order includes, for example, order reception, preparing for shipment, in delivery, and delivery completed, but is not limited to such examples. For example, when a user wants to confirm the progress of the order, the progress information providing unit provides the current progress in response to the input. In addition, the progress information providing unit can also provide a status of being prepared for shipment. Furthermore, the progress information providing unit can also provide a status of being delivered. The progress information providing unit can also provide a status of delivery completion. This allows the user to check the progress of the order in real time. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can provide progress information using an AI model that receives the user's order information as an input and outputs the progress.

[0037] The progress information providing unit provides information indicating the progress of the order via the user's smart home appliance. The progress information providing unit provides information indicating the progress via the user's smart home appliance. Smart home appliances include, for example, a smart refrigerator, smart lighting, smart curtains, etc., but are not limited to such examples. The progress information providing unit, for example, uses the display of the smart refrigerator to display the delivery status of the ordered ingredients. In addition, the progress information providing unit can also notify with different colors or blinking patterns according to the progress of the order in conjunction with the smart lighting. Furthermore, the progress information providing unit can also open and close the curtain according to the progress of the order using the smart curtain. In this way, the progress information can be provided using the smart home appliance. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can provide the progress information using an AI model that inputs data of the smart home appliance and outputs the progress.

[0038] The progress information providing unit uses the display of the smart refrigerator to instantly display the delivery status of the ordered ingredients. The progress information providing unit uses the display of the smart refrigerator to display the delivery status of the ordered ingredients. The display of the smart refrigerator includes, for example, the display position, the display content, the operation method, etc., but is not limited to such examples. The progress information providing unit displays, for example, the current delivery status on the display of the smart refrigerator. In addition, the progress information providing unit can also display the scheduled delivery date. Furthermore, the progress information providing unit can also display information of the delivery company. In this way, the delivery status of the ingredients can be displayed using the display of the smart refrigerator. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can display the delivery status using an AI model that inputs data from the smart refrigerator and outputs the delivery status.

[0039] The progress information providing unit works in conjunction with the smart lighting to notify in different colors or blinking patterns depending on the progress of the order. The progress information providing unit works in conjunction with the smart lighting to notify in different colors or blinking patterns depending on the progress of the order. Smart lighting includes, for example, color changes, blinking patterns, and notification timing, but is not limited to such examples. For example, the progress information providing unit turns on the smart lighting in blue when the order is being prepared for shipment. In addition, the progress information providing unit can also turn on the smart lighting in green when the order is being delivered. Furthermore, the progress information providing unit can also turn on the smart lighting in red when the order has been delivered. This makes it possible to notify the progress using the smart lighting. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can notify the progress using an AI model that inputs data from the smart lighting and outputs the progress.

[0040] The progress information providing unit uses the smart curtain to open and close the curtain according to the progress of the order. The smart curtain includes, for example, a speed of opening and closing, a timing of opening and closing, and a method of remote operation, but is not limited to such examples. For example, the progress information providing unit opens the smart curtain halfway when the order is being prepared for shipment. In addition, the progress information providing unit can also fully open the smart curtain when the order is being delivered. Furthermore, the progress information providing unit can also close the smart curtain when the order has been delivered. In this way, the smart curtain can be used to open and close the curtain according to the progress. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can open and close the curtain using an AI model that inputs data of the smart curtain and outputs the progress.

[0041] The progress information providing unit adjusts the reclining or massage function of the bed according to the progress of the order through the smart bed. The smart bed includes, for example, the reclining angle, the strength of the massage function, the operation method, and the like, but is not limited to such examples. For example, the progress information providing unit adjusts the reclining angle of the smart bed when the order is being prepared for shipment. In addition, the progress information providing unit can also enhance the massage function of the smart bed when the order is being delivered. Furthermore, the progress information providing unit can also return the reclining angle of the smart bed to its original state when the order is delivered. This allows the smart bed to be used to adjust the bed according to the progress. Part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can adjust the bed using an AI model that inputs data of the smart bed and outputs the progress.

[0042] The suggestion unit suggests products to the user based on the user's product purchase history. The product purchase history includes, for example, purchase date and time, the type of product purchased, and purchase frequency, but is not limited to such examples. The suggestion unit suggests related products based on, for example, the history of products purchased by the user in the past. The suggestion unit can also suggest products to be purchased periodically based on the user's purchase frequency. Furthermore, the suggestion unit can also analyze the user's purchase history and suggest products that match the user's preferences. This makes it possible to suggest related products based on the user's past purchase history. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest products using an AI model that inputs the user's purchase history data and outputs product suggestions.

[0043] The suggestion unit suggests products based on the user's product purchase history and reviews of influencers followed by the user. The reviews of influencers include, for example, the reliability of the reviews, the contents of the reviews, and the source of the reviews, but are not limited to such examples. The suggestion unit suggests related products based on, for example, reviews of influencers followed by the user. The suggestion unit can also evaluate the reliability of the reviews of influencers and suggest products based on the reviews with high reliability. Furthermore, the suggestion unit can analyze the contents of the reviews of influencers and suggest products that match the preferences of the user. This makes it possible to suggest products taking into account the reviews of influencers. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest products using an AI model that inputs the reviews of influencers and outputs product suggestions.

[0044] The suggestion unit suggests a set product that is advantageous when purchased at the same time based on the user's purchase history. The set product includes, for example, the type of set product, the price of the set product, and a suggestion criterion for the set product, but is not limited to such examples. For example, the suggestion unit suggests a set product related to a product previously purchased by the user. The suggestion unit can also suggest a set product that is advantageous to the user based on the price of the set product. Furthermore, the suggestion unit can set a suggestion criterion for the set product and suggest a set product that matches the user's preferences. In this way, the suggestion unit can encourage the user to make a purchase that is advantageous by suggesting the set product. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest a set product using an AI model that inputs the user's purchase history data and outputs a set product suggestion.

[0045] The feedback unit collects user feedback and improves the comparison unit based on the collected feedback. The user feedback includes, for example, the form of feedback, the content of feedback, and the timing of collecting feedback, but is not limited to such examples. For example, when the user provides feedback in text format, the feedback unit collects the feedback. In addition, when the user provides feedback in voice format, the feedback unit can also collect the feedback. Furthermore, the feedback unit can collect feedback at a specific timing. For example, the feedback unit collects feedback immediately after the user purchases a product. In addition, the feedback unit can collect feedback after the user uses the product. This makes it possible to improve the comparison unit based on the user feedback. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can improve the comparison unit using an AI model that inputs user feedback data and outputs improvements to the comparison unit.

[0046] The reception unit analyzes the user's past input history and selects the optimal reception method. The past input history includes, for example, input date and time, input contents, input frequency, etc., but is not limited to such examples. The reception unit, for example, preferentially suggests an input method (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past input history. Furthermore, the reception unit can also provide a shortcut to reduce the effort of inputting by referring to the contents that the user has input in the past. In this way, the optimal reception method can be provided by analyzing the user's past input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can select a reception method using an AI model that inputs the user's input history data and outputs the optimal reception method.

[0047] The reception unit performs filtering based on the user's current field of interest when receiving the input. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The reception unit preferentially receives related input, for example, based on a product category recently searched by the user. The reception unit can also filter the input based on a specific brand or product in which the user is interested. Furthermore, the reception unit can also preferentially receive related input based on the user's past purchase history. As a result, by filtering the input based on the user's current field of interest, highly relevant information can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can filter the input using an AI model that receives the user's field of interest data as input and outputs the filtering result.

[0048] The reception unit preferentially receives highly relevant inputs in consideration of the geographical location information of the user when receiving the input. The geographical location information includes, but is not limited to, for example, GPS data, IP address, and location information services. For example, when the user is in a specific area, the reception unit preferentially receives inputs of products and services related to the area. In addition, when the user is traveling, the reception unit can also preferentially receive information related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive inputs related to daily life. In this way, highly relevant information can be preferentially received by considering the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can preferentially receive inputs using an AI model that receives the geographical location information of the user as input and outputs highly relevant inputs.

[0049] The reception unit analyzes the user's social media activity at the time of receiving the input, and receives the relevant input. The social media activity includes, but is not limited to, for example, the content of the post, the number of followers, the number of likes, and the like. The reception unit preferentially receives the input, for example, based on the products and services in which the user shows interest on social media. The reception unit can also receive the relevant input based on the content of the post of an influencer the user follows. Furthermore, the reception unit can also filter the input based on the information shared by the user on social media. In this way, the user's social media activity can be analyzed to preferentially receive the relevant input. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can receive the input using an AI model that receives the user's social media data as input and outputs the related input.

[0050] The collection unit selects an appropriate information source based on the user's past search history when collecting information. The past search history includes, for example, search keywords, search date and time, and click history of search results, but is not limited to such examples. For example, the collection unit preferentially collects information sources that the user has frequently used in the past. The collection unit can also select a highly reliable information source from the user's past search history. Furthermore, the collection unit can also select a related information source based on the content that the user has searched in the past. This makes it possible to select an optimal information source by referring to the user's past search history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can select an information source using an AI model that inputs the user's search history data and outputs an appropriate information source.

[0051] The collection unit adjusts the information to be collected based on the user's current field of interest when collecting information. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The collection unit collects related information, for example, based on a product category in which the user has recently shown interest. In addition, if the user shows interest in a particular brand or product, the collection unit can also preferentially collect information about the brand or product. Furthermore, the collection unit can customize and collect related information based on the user's past purchase history. This makes it possible to collect highly relevant information by customizing information based on the user's current field of interest. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can adjust the information using an AI model that inputs the user's field of interest data and outputs the information to be collected.

[0052] Examples of the information service include, but are not limited to, a service for providing information related to a specific area. For example, when the user is in a specific area, the collection unit preferentially collects information related to the area. In addition, when the user is traveling, the collection unit can also preferentially collect information related to the travel destination. Furthermore, when the user is at home, the collection unit can also preferentially collect information related to daily life. In this way, by taking into account the geographical location information of the user, highly relevant information can be preferentially collected. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can preferentially collect information using an AI model that inputs the geographical location information of the user and outputs highly relevant information.

[0053] The collection unit analyzes the user's social media activity at the time of collecting information, and collects related information. The social media activity includes, for example, the content of posts, the number of followers, the number of likes, and the like, but is not limited to such examples. The collection unit preferentially collects information, for example, based on products and services in which the user shows interest on social media. The collection unit can also collect related information based on the content of posts of influencers followed by the user. Furthermore, the collection unit can also filter information based on information shared by the user on social media. In this way, by analyzing the user's social media activity, related information can be preferentially collected. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the user's social media data and outputs related information.

[0054] The comparison unit improves the accuracy of the comparison based on the interrelationship of the products during the comparison. The interrelationship of the products includes, for example, compatibility, complementarity, and competitiveness, but is not limited to such examples. The comparison unit performs the comparison, for example, taking into consideration the compatibility of the products. The comparison unit can also perform the comparison while taking into consideration the complementarity of the products. Furthermore, the comparison unit can also perform the comparison while taking into consideration the competitive relationship of the products. As a result, the accuracy of the comparison can be improved by taking into consideration the interrelationship of the products. A part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can improve the accuracy of the comparison by using an AI model that inputs interrelationship data of the products and outputs a comparison result.

[0055] The comparison unit performs the comparison based on the attribute information of the products at the time of comparison. The attribute information of the products includes, for example, product specifications, functions, designs, etc., but is not limited to such examples. The comparison unit performs the comparison based on, for example, the prices of the products. The comparison unit can also perform the comparison based on the functions of the products. Furthermore, the comparison unit can also perform the comparison based on the evaluations of the products. This allows a more detailed comparison to be performed by taking the attribute information of the products into consideration. A part or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit can perform the comparison using an AI model that inputs the attribute information of the products and outputs the comparison results.

[0056] The comparison unit performs the comparison based on the geographical distribution of the product at the time of comparison. The geographical distribution of the product includes, for example, a sales area, an area where the product is in stock, and an area where the product can be delivered, but is not limited to such examples. The comparison unit performs the comparison, for example, by taking into consideration the sales area of ​​the product. The comparison unit can also perform the comparison by taking into consideration the area where the product can be delivered. Furthermore, the comparison unit can also perform the comparison by taking into consideration the evaluation of the product by region. In this way, the comparison can be performed by region by taking into consideration the geographical distribution of the product. A part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can perform the comparison using an AI model that inputs the geographical distribution data of the product and outputs the comparison result.

[0057] The comparison unit improves the accuracy of the comparison based on the related literature of the product during the comparison. The related literature of the product includes, but is not limited to, academic papers, technical reports, patent documents, and the like. The comparison unit, for example, performs the comparison by referring to technical literature of the product. The comparison unit can also perform the comparison by referring to review articles of the product. Furthermore, the comparison unit can also perform the comparison by referring to patent information of the product. In this way, the accuracy of the comparison can be improved by referring to the related literature of the product. Part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can improve the accuracy of the comparison by using an AI model that inputs the related literature data of the product and outputs the comparison result.

[0058] When providing the comparison result, the comparison result providing unit selects an appropriate display method based on the user's past selection history. The past selection history includes, for example, the selected product, the date and time of selection, the frequency of selection, and the like, but is not limited to such examples. For example, the comparison result providing unit preferentially provides the display method selected by the user in the past. The comparison result providing unit can also predict and provide the optimal display method from the user's past selection history. Furthermore, the comparison result providing unit can also customize the display method based on the display style that the user preferred in the past. In this way, the optimal display method can be provided by referring to the user's past selection history. A part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can select the display method using an AI model that inputs the user's selection history data and outputs the display method.

[0059] The comparison result providing unit adjusts the display contents based on the user's current field of interest when providing the comparison results. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The comparison result providing unit preferentially displays related comparison results, for example, based on a product category in which the user has recently shown interest. In addition, if the user has shown interest in a specific brand or product, the comparison result providing unit can also preferentially display comparison results related to the brand or product. Furthermore, the comparison result providing unit can customize and display related comparison results based on the user's past purchase history. This makes it possible to provide highly relevant information by customizing the display contents based on the user's current field of interest. Part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can adjust the display contents using an AI model that receives the user's field of interest data as input and outputs the display contents.

[0060] The comparison result providing unit selects an appropriate display method based on the geographical location information of the user when providing the comparison result. The geographical location information includes, but is not limited to, for example, GPS data, IP address, location information service, etc. For example, when the user is in a specific area, the comparison result providing unit preferentially displays the comparison results of products related to the area. In addition, when the user is traveling, the comparison result providing unit can also preferentially display the comparison results of products related to the travel destination. Furthermore, when the user is at home, the comparison result providing unit can also preferentially display the comparison results of products related to daily life. In this way, the optimal display method can be provided by taking the geographical location information of the user into consideration. Part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can select the display method using an AI model that inputs the geographical location information of the user and outputs the display method.

[0061] The comparison result providing unit adjusts the display contents by analyzing the social media activity of the user when providing the comparison results. The social media activity includes, for example, the posting contents, the number of followers, the number of likes, and the like, but is not limited to such examples. The comparison result providing unit preferentially displays the comparison results, for example, based on products and services in which the user shows interest on social media. The comparison result providing unit can also display related comparison results based on the posting contents of influencers followed by the user. Furthermore, the comparison result providing unit can also filter the comparison results based on information shared by the user on social media. In this way, by analyzing the social media activity of the user, related information can be preferentially displayed. A part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can adjust the display contents using an AI model that inputs the social media data of the user and outputs the display contents.

[0062] The response unit adjusts the level of detail of the response based on the importance of the question when responding. The importance of the question includes, but is not limited to, the urgency of the question, the impact of the question, and the frequency of the question. For example, the response unit provides a detailed response to an important question. The response unit can also provide a simple response to a general question. Furthermore, the response unit can also provide a quick response to an urgent question. This allows a more appropriate response to be made by adjusting the level of detail of the response based on the importance of the question. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI or may be performed without using AI. For example, the response unit can adjust the level of detail of the response using an AI model that inputs the importance data of the question and outputs the level of detail of the response.

[0063] The response unit applies different response algorithms depending on the category of the question when responding. The response unit applies different response algorithms depending on the category of the question when responding. The question categories include, for example, technical questions, questions about products, questions about support, and the like, but are not limited to such examples. For example, the response unit responds to a question about a delivery status based on delivery information. In addition, the response unit can also respond to a question about an inventory status based on inventory information. Furthermore, the response unit can also respond to a question about a product's features based on product information. In this way, by applying different response algorithms depending on the category of the question, a more appropriate response can be made. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can apply a response algorithm using an AI model that inputs question category data and outputs a response algorithm.

[0064] The response unit determines the priority of the response based on the time of question submission when responding. The time of question submission includes, but is not limited to, the submission date and time, the frequency of submission, and the timing of submission. For example, the response unit prioritizes the response to a question submitted recently. The response unit can also respond to an urgent question with the highest priority. Furthermore, the response unit can respond to a question submitted in the past later. In this way, by determining the priority of the response based on the time of question submission, the response can be made in a more appropriate order. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can determine the priority of the response using an AI model that inputs question submission time data and outputs the priority of the response.

[0065] The response unit adjusts the order of responses based on the relevance of the questions when responding. The relevance of the questions includes, but is not limited to, the content of the questions, the category of the questions, and the frequency of the questions. For example, the response unit prioritizes responses to questions with high relevance. The response unit can also respond to questions with general content later. Furthermore, the response unit can also respond to questions with high urgency as a top priority. By adjusting the order of responses based on the relevance of the questions, responses can be made in a more appropriate order. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can adjust the order of responses using an AI model that inputs question relevance data and outputs the order of responses.

[0066] The progress information providing unit predicts the current progress based on the past progress data when providing the progress information. The past progress data includes, for example, a progress history, a change in progress, and a frequency of progress, but is not limited to such examples. The progress information providing unit predicts the current progress status based on, for example, the past progress data. The progress information providing unit can also notify a predicted delay from the past progress data. Furthermore, the progress information providing unit can also analyze the past progress data and provide an optimal progress prediction. This makes it possible to predict the current progress by referring to the past progress data. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can predict the progress using an AI model that inputs past progress data and outputs the current progress.

[0067] The progress information providing unit applies a different progress display method for each order category when providing progress information. The order categories include, for example, food, home appliances, clothing, etc., but are not limited to such examples. For example, the progress information providing unit displays the delivery status in detail for a food order. Furthermore, for an order of a home appliance, the progress information providing unit can also display the expected arrival date of the product. Furthermore, for an order of clothing, the progress information providing unit can also display the date on which the product can be tried on. In this way, by applying a different progress display method for each order category, more appropriate progress information can be provided. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can apply the progress display method using an AI model that inputs order category data and outputs a progress display method.

[0068] The progress information providing unit analyzes the change in progress based on the time of submission of the order when providing the progress information. The time of submission of the order includes, for example, the submission date and time, the frequency of submission, and the timing of submission, but is not limited to such examples. For example, the progress information providing unit preferentially displays the progress of the order submitted recently. The progress information providing unit can also display the progress of the order submitted in the past later. Furthermore, the progress information providing unit can display the progress of the urgent order with the highest priority. In this way, the change in progress can be analyzed based on the time of submission of the order, thereby providing more appropriate progress information. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can analyze the change in progress using an AI model that inputs the submission time data of the order and outputs the change in progress.

[0069] The progress information providing unit analyzes the progress based on the relevant market data of the order when providing the progress information. The relevant market data includes, for example, market demand, supply status, trends, etc., but is not limited to such examples. The progress information providing unit predicts a change in the progress based on, for example, market demand. The progress information providing unit can also predict a change in the progress based on the supply status of the market. Furthermore, the progress information providing unit can also predict a change in the progress based on a market trend. Thereby, the change in the progress can be predicted by referring to the relevant market data of the order. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can analyze the progress using an AI model that inputs the relevant market data and outputs the change in the progress.

[0070] The suggestion unit adjusts the level of detail of the proposal based on the importance of the product at the time of proposal. The importance of the product includes, for example, the urgency of the product, the impact of the product, the frequency of the product, and the like, but is not limited to such examples. For example, the suggestion unit provides a detailed proposal for an important product. The suggestion unit can also provide a simple proposal for a general product. Furthermore, the suggestion unit can also provide a proposal for a product with high urgency so that the product can be quickly confirmed. As a result, a more appropriate proposal can be made by adjusting the level of detail of the proposal based on the importance of the product. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can adjust the level of detail of the proposal using an AI model that inputs the importance data of the product and outputs the level of detail of the proposal.

[0071] The suggestion unit applies different suggestion algorithms depending on the category of the product when making a suggestion. The categories of the product include, but are not limited to, for example, home appliances, clothing, and food. For example, the suggestion unit provides a suggestion that emphasizes technical features for home appliances. For clothing, the suggestion unit can also provide a suggestion that emphasizes design and materials. For food, the suggestion unit can also provide a suggestion that emphasizes nutritional value and taste. This allows more appropriate suggestions to be made by applying different suggestion algorithms depending on the category of the product. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can apply the suggestion algorithm using an AI model that inputs product category data and outputs a suggestion algorithm.

[0072] The suggestion unit determines the priority of the suggestions based on the submission time of the products at the time of suggestion. The submission time of the products includes, for example, the submission date and time, the frequency of submission, and the timing of submission, but is not limited to such examples. For example, the suggestion unit provides a suggestion of a recently added product with priority. The suggestion unit can also provide a suggestion of a product with high urgency with the highest priority. Furthermore, the suggestion unit can provide a suggestion of a product added in the past at a later date. In this way, by determining the priority of the suggestions based on the submission time of the products, the suggestions can be made in a more appropriate order. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can determine the priority of the suggestions using an AI model that inputs the submission time data of the products and outputs the priority of the suggestions.

[0073] The suggestion unit adjusts the order of suggestions based on the relevance of the products when making suggestions. The relevance of the products includes, for example, the user's interest level, product evaluation, and ascending order of price, but is not limited to such examples. For example, the suggestion unit provides a suggestion of a product that the user is highly interested in preferentially. The suggestion unit can also provide a suggestion of a product that the user is less interested in later. Furthermore, the suggestion unit can also provide a suggestion of a product that is highly related preferentially based on the user's past purchase history. As a result, by adjusting the order of suggestions based on the relevance of the products, suggestions can be made in a more appropriate order. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can adjust the order of suggestions using an AI model that inputs product relevance data and outputs the order of suggestions.

[0074] The feedback unit selects an appropriate collection method based on past feedback data when collecting feedback. The past feedback data includes, for example, the form of feedback, the content of feedback, and the timing of collecting feedback, but is not limited to such examples. For example, the feedback unit preferentially provides the form of feedback provided by the user in the past. The feedback unit can also predict and provide the optimal collection method from the user's past feedback data. Furthermore, the feedback unit can customize the collection method based on the feedback form that the user preferred in the past. In this way, the optimal collection method can be provided by referring to the past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can select the collection method using an AI model that inputs past feedback data and outputs the collection method.

[0075] The feedback unit adjusts the feedback to be collected based on the user's current field of interest when collecting feedback. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The feedback unit preferentially collects relevant feedback, for example, based on a product category in which the user has recently shown interest. In addition, if the user has shown interest in a particular brand or product, the feedback unit can also preferentially collect feedback on the brand or product. Furthermore, the feedback unit can customize and collect relevant feedback based on the user's past purchase history. This makes it possible to collect highly relevant feedback by customizing the feedback based on the user's current field of interest. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can adjust the feedback using an AI model that inputs the user's field of interest data and outputs the feedback to be collected.

[0076] The feedback unit, when collecting feedback, preferentially collects feedback with high relevance based on the geographical location information of the user. The geographical location information includes, but is not limited to, for example, GPS data, IP address, location information service, etc. For example, when the user is in a specific area, the feedback unit preferentially collects feedback related to the area. In addition, when the user is traveling, the feedback unit can also preferentially collect feedback related to the travel destination. Furthermore, when the user is at home, the feedback unit can also preferentially collect feedback related to daily life. In this way, by taking the geographical location information of the user into consideration, it is possible to preferentially collect feedback with high relevance. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can collect feedback using an AI model that inputs the geographical location information of the user and outputs feedback with high relevance.

[0077] The feedback unit analyzes the user's social media activity at the time of collecting feedback and collects relevant feedback. The social media activity includes, but is not limited to, for example, the content of posts, the number of followers, the number of likes, and the like. The feedback unit preferentially collects feedback, for example, based on products and services in which the user shows interest on social media. The feedback unit can also collect relevant feedback based on the content of posts of influencers followed by the user. Furthermore, the feedback unit can also filter feedback based on information shared by the user on social media. This allows the user's social media activity to be analyzed to preferentially collect relevant feedback. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can collect feedback using an AI model that inputs the user's social media data and outputs relevant feedback.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The collection unit can also collect product information for each region, taking into account the geographic location information of the user. For example, when the user is in a particular region, the collection unit can preferentially collect information on products and services that are popular in that region. In addition, when the user is traveling, the collection unit can also collect product information related to the travel destination. Furthermore, when the user is at home, the collection unit can also collect product information related to daily life. In this way, more relevant product information can be provided by taking into account the geographic location information of the user.

[0080] The response unit can also analyze the user's past question history and select the optimal response method. For example, the response method (text, voice, etc.) that the user has used frequently in the past is provided preferentially. The response unit can also predict and suggest the response method to be used during a specific time period from the user's past question history. Furthermore, the response unit can provide shortcuts to reduce the effort of responding by referring to the content of questions asked by the user in the past. In this way, the optimal response method can be provided by analyzing the user's past question history.

[0081] The progress information providing unit can also analyze the user's past progress check history and select the optimal progress information providing method. For example, the progress check method (smart refrigerator, smart lighting, etc.) that the user has used frequently in the past is provided preferentially. The progress information providing unit can also predict and suggest the progress check method to be used in a specific time period from the user's past progress check history. Furthermore, the progress information providing unit can provide shortcuts to reduce the effort of providing progress information by referring to the content that the user has checked in the past. In this way, the optimal progress information providing method can be provided by analyzing the user's past progress check history.

[0082] The suggestion unit can also analyze the user's past proposal history and select the optimal proposal method. For example, the suggestion unit can preferentially provide a proposal method (text, image, etc.) that the user has frequently accepted in the past. The suggestion unit can also predict and suggest a proposal method to be used in a specific time period from the user's past proposal history. Furthermore, the suggestion unit can provide a shortcut to reduce the effort of making suggestions by referring to the content that the user has accepted in the past. In this way, the optimal proposal method can be provided by analyzing the user's past proposal history.

[0083] The feedback unit can also analyze the user's past feedback history and select the optimal feedback collection method. For example, the feedback unit can provide feedback methods (text, voice, etc.) that the user has used frequently in the past with priority. The feedback unit can also predict and suggest the feedback method to be used in a specific time period from the user's past feedback history. Furthermore, the feedback unit can provide shortcuts to reduce the effort of providing feedback by referring to the content provided by the user in the past. In this way, the optimal feedback collection method can be provided by analyzing the user's past feedback history.

[0084] The feedback unit may also collect feedback for each region by taking into account the geographic location information of the user. For example, when the user is in a particular region, feedback on products and services in that region may be preferentially collected. In addition, when the user is traveling, the feedback unit may collect feedback related to the travel destination. Furthermore, when the user is at home, the feedback unit may collect feedback related to daily life. In this way, more relevant feedback can be provided by taking into account the geographic location information of the user.

[0085] The process flow of the first embodiment will be briefly described below.

[0086] Step 1: The reception unit receives input from a user. The input from a user includes text input, voice input, image input, etc. For example, when a user searches for a product, the input is received. Step 2: The collection unit collects information on multiple products according to the input received by the reception unit. The collected product information includes price information, product features, reviews, etc. The collection unit collects product information from multiple online stores using web scraping technology and APIs. The collection unit can also collect product information by performing database searches. Step 3: The comparison unit compares the information of the multiple products collected by the collection unit. Comparison criteria include price comparison, performance comparison, user evaluation comparison, etc. For example, products are compared based on price information. Products can also be compared based on performance information and user evaluation. Step 4: The comparison result providing unit provides the comparison result by the comparison unit. The comparison result display method includes a ranking format, a graph display, a text display, and the like. For example, the products are displayed in a ranking format. The products can also be displayed in a graph display or a text display.

[0087] (Example 2) The online store purchase support AI assistant according to the embodiment of the present invention is a system that helps users search for products and compare prices and features. The system includes a reception unit that receives input from a user, and when a product search is performed, a collection unit collects information on multiple products, and a comparison unit compares the information. The comparison result is provided to the user by a comparison result providing unit. In addition, the system has a customer support function that quickly responds to questions from users. When the reception unit receives a question, the response unit answers the question. In particular, for questions about delivery status and stock status, the response unit provides this information. In addition, the system has an order tracking function, and when a user inputs an input to check the progress of an order, the progress information providing unit provides information indicating the progress in real time. The progress information providing unit can also provide information via smart home appliances, for example, by using the display of a smart refrigerator to display the delivery status of ingredients, or by linking with smart lighting to provide notifications in different colors or blinking patterns. In addition, the system has a personalized suggestion function that recommends related products based on the user's past purchase history. The suggestion unit can suggest products based on the user's product purchase history and reviews of influencers the user follows. It can also suggest bundled products that are great value when purchased together. Finally, there is a feedback function, which collects user feedback and improves the comparison section based on the collected feedback. This allows the online store's purchasing support AI assistant to not only help users search for products and compare prices and features, but also provide multiple functions such as customer support, order tracking, personalized suggestions, and feedback collection.

[0088] The online store purchase support AI assistant according to the embodiment includes a reception unit, a collection unit, a comparison unit, and a comparison result providing unit. The reception unit receives input from a user. The input from the user includes, but is not limited to, for example, text input, voice input, image input, and the like. The reception unit receives the input when, for example, a user searches for a product. The collection unit collects information on a plurality of products according to the input received by the reception unit. The collected product information includes, but is not limited to, for example, price information, product features, reviews, and the like. The collection unit collects product information from a plurality of online stores, for example, using a web scraping technique. The collection unit can also obtain product information using an API. Furthermore, the collection unit can also perform a database search to collect product information. The comparison unit compares the information on a plurality of products collected by the collection unit. Comparison criteria include, but are not limited to, for example, price comparison, performance comparison, and user evaluation comparison. The comparison unit compares products based on, for example, price information. The comparison unit can also compare products based on performance information. Furthermore, the comparison unit can compare products based on user evaluations. The comparison result providing unit provides the comparison results by the comparison unit. The display method of the comparison results includes, but is not limited to, for example, a ranking format, a graph display, a text display, and the like. The comparison result providing unit displays products, for example, in a ranking format. The comparison result providing unit can also display products in a graph display. The comparison result providing unit can also display products in a text display. This allows the purchase support AI assistant of the online store according to the embodiment to help users search for products and compare prices and features. Some or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can compare products using an AI model that inputs product information collected by the collection unit and outputs a comparison result.

[0089] The reception unit receives input from a user. Examples of input from a user include, but are not limited to, text input, voice input, and image input. Specifically, in the case of text input, the user inputs a product name and a category using a keyboard or a touch screen. In the case of voice input, the user inputs a product name and a desired feature by voice through a microphone, and the voice input is converted into text using voice recognition technology. In the case of image input, the user takes a photo of the product using a camera, and the product is identified using image recognition technology. The reception unit processes these inputs in real time and generates a search query according to the user's request. Furthermore, the reception unit can refer to the user's past search history and purchase history, and perform input completion and suggestions taking into account the user's preferences and tendencies. For example, if the user has searched for many products of a specific brand in the past, products of that brand are preferentially displayed. In addition, the reception unit can provide immediate feedback to the user's input and prompt the user to confirm or correct the input content. This allows the reception unit to respond to various input methods of the user and quickly and accurately receive the user's request.

[0090] The collection unit collects information on a plurality of products according to the input received by the reception unit. The collected product information includes, for example, price information, product features, reviews, etc., but is not limited to such examples. Specifically, the collection unit collects product information from a plurality of online stores using web scraping technology. Web scraping technology is a technology that analyzes the HTML structure of a web page and extracts necessary data. For example, price information, product features, and user reviews are automatically obtained from the product page of a specific online store. The collection unit can also obtain product information using an API. An API is an interface for exchanging data between different systems, and the latest product information can be efficiently obtained by using the API provided by the online store. Furthermore, the collection unit can also perform a database search to collect product information. The database stores product information and user reviews collected in the past, and the necessary information is obtained by searching this data. The collection unit can combine these methods to collect comprehensive product information from various information sources and provide optimal product information according to the user's request.

[0091] The comparison unit compares information on a plurality of products collected by the collection unit. Comparison criteria include, but are not limited to, price comparison, performance comparison, and user evaluation comparison. Specifically, the comparison unit compares products based on price information. For example, the comparison unit identifies the cheapest product or the product with the highest cost performance among products in the same category. The comparison unit can also compare products based on performance information. For example, in the case of smartphones, the comparison unit compares technical features such as processor performance, battery life, and camera pixel count to identify the product that best suits the user's requirements. Furthermore, the comparison unit can compare products based on user evaluation. For example, the comparison unit analyzes user reviews and evaluation scores in an online store to identify products with high overall ratings or products with high ratings for specific features. The comparison unit can combine these comparison criteria to propose the optimal product in response to the user's diverse requirements. Furthermore, the comparison unit can analyze the product information collected using AI and comprehensively evaluate multiple criteria. For example, the comparison unit uses an AI model to comprehensively evaluate price, performance, and user evaluation to identify the product that is most suitable for the user. This allows the comparison unit to quickly and accurately compare products and provide the user with the best option.

[0092] The comparison result providing unit provides the comparison result by the comparison unit. The display method of the comparison result includes, but is not limited to, for example, a ranking format, a graph display, a text display, and the like. Specifically, the comparison result providing unit displays the products in a ranking format. For example, a ranking such as the lowest price, the highest performance, or the highest user rating is displayed, so that the user can easily understand the comparison result. The comparison result providing unit can also display the products in a graph display. For example, a scatter diagram showing the relationship between price and performance, or a bar graph showing the distribution of user ratings, is used to visually provide the comparison result. Furthermore, the comparison result providing unit can also display the products in a text display. For example, the features and evaluation points of each product are explained in detail in text, making it easier for the user to understand the features of the product. The comparison result providing unit can combine these display methods to provide the comparison result in a format that is most easily understandable for the user. Furthermore, the comparison result providing unit can collect user feedback and improve the display method or add a new display format. For example, if a user prefers a specific display format, a setting is provided to preferentially display that format. In addition, the comparison result providing unit can provide the latest comparison results based on data updated in real time, thereby enabling the comparison result providing unit to provide the user with quick and accurate comparison results and support product selection.

[0093] The reception unit includes a response unit that responds to the question when the reception unit receives the question. The response unit responds to the question from the user. The format of the question includes, for example, a text-format question, a voice-format question, a question about a specific category, and the like, but is not limited to such examples. For example, when the user inputs a question in text format, the response unit responds to the question in text format. In addition, when the user inputs a question in voice format, the response unit can also respond to the question in voice format. Furthermore, the response unit can provide corresponding information in response to a question about a specific category. For example, the response unit provides information such as a delivery status and a scheduled delivery date in response to a question about a delivery status. In addition, the response unit can provide information such as the number of items in stock and a scheduled arrival date in response to a question about an inventory status. This makes it possible to quickly respond to the user's question. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can respond to the question using an AI model that receives the user's question as an input and outputs a response.

[0094] The response unit responds with the delivery status or the stock status as an answer to the question. The response unit provides information such as the delivery status and the scheduled delivery date in response to a question regarding the delivery status. The information on the delivery status includes, for example, the delivery status, the scheduled delivery date, and the information of the delivery company, but is not limited to such examples. For example, when a user wants to check the delivery status, the response unit provides the current delivery status in response to the question. The response unit can also provide the scheduled delivery date. Furthermore, the response unit can also provide the information of the delivery company. The response unit provides information such as the number of items in stock and the scheduled arrival date in response to a question regarding the stock status. The information on the stock status includes, for example, the number of items in stock, the scheduled arrival date, and the location of the stock, but is not limited to such examples. For example, when a user wants to check the stock status, the response unit provides the current number of items in stock in response to the question. The response unit can also provide the scheduled arrival date. Furthermore, the response unit can also provide the location of the stock. This allows a quick response to a question regarding the delivery status or the stock status. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can respond to a user's question using an AI model that takes a user's question as input and outputs information on delivery status and inventory status.

[0095] The reception unit includes a progress information providing unit that provides progress information when a confirmation of the progress of the order is received. When a user makes an input to confirm the progress of the order, the progress information providing unit provides information indicating the progress. The information on the progress of the order includes, for example, order reception, preparing for shipment, in delivery, and delivery completed, but is not limited to such examples. For example, when a user wants to confirm the progress of the order, the progress information providing unit provides the current progress in response to the input. In addition, the progress information providing unit can also provide a status of being prepared for shipment. Furthermore, the progress information providing unit can also provide a status of being delivered. The progress information providing unit can also provide a status of delivery completion. This allows the user to check the progress of the order in real time. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can provide progress information using an AI model that receives the user's order information as an input and outputs the progress.

[0096] The progress information providing unit provides information indicating the progress of the order via the user's smart home appliance. The progress information providing unit provides information indicating the progress via the user's smart home appliance. Smart home appliances include, for example, a smart refrigerator, smart lighting, smart curtains, etc., but are not limited to such examples. The progress information providing unit, for example, uses the display of the smart refrigerator to display the delivery status of the ordered ingredients. In addition, the progress information providing unit can also notify with different colors or blinking patterns according to the progress of the order in conjunction with the smart lighting. Furthermore, the progress information providing unit can also open and close the curtain according to the progress of the order using the smart curtain. In this way, the progress information can be provided using the smart home appliance. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can provide the progress information using an AI model that inputs data of the smart home appliance and outputs the progress.

[0097] The progress information providing unit uses the display of the smart refrigerator to instantly display the delivery status of the ordered ingredients. The progress information providing unit uses the display of the smart refrigerator to display the delivery status of the ordered ingredients. The display of the smart refrigerator includes, for example, the display position, the display content, the operation method, etc., but is not limited to such examples. The progress information providing unit displays, for example, the current delivery status on the display of the smart refrigerator. In addition, the progress information providing unit can also display the scheduled delivery date. Furthermore, the progress information providing unit can also display information of the delivery company. In this way, the delivery status of the ingredients can be displayed using the display of the smart refrigerator. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can display the delivery status using an AI model that inputs data from the smart refrigerator and outputs the delivery status.

[0098] The progress information providing unit works in conjunction with the smart lighting to notify in different colors or blinking patterns depending on the progress of the order. The progress information providing unit works in conjunction with the smart lighting to notify in different colors or blinking patterns depending on the progress of the order. Smart lighting includes, for example, color changes, blinking patterns, and notification timing, but is not limited to such examples. For example, the progress information providing unit turns on the smart lighting in blue when the order is being prepared for shipment. In addition, the progress information providing unit can also turn on the smart lighting in green when the order is being delivered. Furthermore, the progress information providing unit can also turn on the smart lighting in red when the order has been delivered. This makes it possible to notify the progress using the smart lighting. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can notify the progress using an AI model that inputs data from the smart lighting and outputs the progress.

[0099] The progress information providing unit uses the smart curtain to open and close the curtain according to the progress of the order. The smart curtain includes, for example, a speed of opening and closing, a timing of opening and closing, and a method of remote operation, but is not limited to such examples. For example, the progress information providing unit opens the smart curtain halfway when the order is being prepared for shipment. In addition, the progress information providing unit can also fully open the smart curtain when the order is being delivered. Furthermore, the progress information providing unit can also close the smart curtain when the order has been delivered. In this way, the smart curtain can be used to open and close the curtain according to the progress. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can open and close the curtain using an AI model that inputs data of the smart curtain and outputs the progress.

[0100] The progress information providing unit adjusts the reclining or massage function of the bed according to the progress of the order through the smart bed. The smart bed includes, for example, the reclining angle, the strength of the massage function, the operation method, and the like, but is not limited to such examples. For example, the progress information providing unit adjusts the reclining angle of the smart bed when the order is being prepared for shipment. In addition, the progress information providing unit can also enhance the massage function of the smart bed when the order is being delivered. Furthermore, the progress information providing unit can also return the reclining angle of the smart bed to its original state when the order is delivered. This allows the smart bed to be used to adjust the bed according to the progress. Part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can adjust the bed using an AI model that inputs data of the smart bed and outputs the progress.

[0101] The suggestion unit suggests products to the user based on the user's product purchase history. The product purchase history includes, for example, purchase date and time, the type of product purchased, and purchase frequency, but is not limited to such examples. The suggestion unit suggests related products based on, for example, the history of products purchased by the user in the past. The suggestion unit can also suggest products to be purchased periodically based on the user's purchase frequency. Furthermore, the suggestion unit can also analyze the user's purchase history and suggest products that match the user's preferences. This makes it possible to suggest related products based on the user's past purchase history. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest products using an AI model that inputs the user's purchase history data and outputs product suggestions.

[0102] The suggestion unit suggests products based on the user's product purchase history and reviews of influencers followed by the user. The reviews of influencers include, for example, the reliability of the reviews, the contents of the reviews, and the source of the reviews, but are not limited to such examples. The suggestion unit suggests related products based on, for example, reviews of influencers followed by the user. The suggestion unit can also evaluate the reliability of the reviews of influencers and suggest products based on the reviews with high reliability. Furthermore, the suggestion unit can analyze the contents of the reviews of influencers and suggest products that match the preferences of the user. This makes it possible to suggest products taking into account the reviews of influencers. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest products using an AI model that inputs the reviews of influencers and outputs product suggestions.

[0103] The suggestion unit suggests a set product that is advantageous when purchased at the same time based on the user's purchase history. The set product includes, for example, the type of set product, the price of the set product, and a suggestion criterion for the set product, but is not limited to such examples. For example, the suggestion unit suggests a set product related to a product previously purchased by the user. The suggestion unit can also suggest a set product that is advantageous to the user based on the price of the set product. Furthermore, the suggestion unit can set a suggestion criterion for the set product and suggest a set product that matches the user's preferences. In this way, the suggestion unit can encourage the user to make a purchase that is advantageous by suggesting the set product. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can suggest a set product using an AI model that inputs the user's purchase history data and outputs a set product suggestion.

[0104] The feedback unit collects user feedback and improves the comparison unit based on the collected feedback. The user feedback includes, for example, the form of feedback, the content of feedback, and the timing of collecting feedback, but is not limited to such examples. For example, when the user provides feedback in text format, the feedback unit collects the feedback. In addition, when the user provides feedback in voice format, the feedback unit can also collect the feedback. Furthermore, the feedback unit can collect feedback at a specific timing. For example, the feedback unit collects feedback immediately after the user purchases a product. In addition, the feedback unit can collect feedback after the user uses the product. This makes it possible to improve the comparison unit based on the user feedback. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can improve the comparison unit using an AI model that inputs user feedback data and outputs improvements to the comparison unit.

[0105] The reception unit estimates the user's emotion and adjusts the timing of input reception based on the estimated emotion. The user's emotion includes, but is not limited to, stress, relaxation, and hurry. For example, when the user is feeling stressed, the reception unit delays the timing of input reception to allow the user to relax. Also, when the user is in a hurry, the reception unit can advance the timing of input reception to quickly respond. Furthermore, when the user is relaxed, the reception unit can also accept input at a normal timing. In this way, by adjusting the timing of input reception according to the user's emotion, it is possible to accept input at a more appropriate timing. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can adjust the timing of input reception using an AI model that receives the user's emotion data as an input and outputs the timing of input reception.

[0106] The reception unit analyzes the user's past input history and selects the optimal reception method. The past input history includes, for example, input date and time, input contents, input frequency, etc., but is not limited to such examples. The reception unit, for example, preferentially suggests an input method (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used in a specific time period from the user's past input history. Furthermore, the reception unit can also provide a shortcut to reduce the effort of inputting by referring to the contents that the user has input in the past. In this way, the optimal reception method can be provided by analyzing the user's past input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can select a reception method using an AI model that inputs the user's input history data and outputs the optimal reception method.

[0107] The reception unit performs filtering based on the user's current field of interest when receiving the input. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The reception unit preferentially receives related input, for example, based on a product category recently searched by the user. The reception unit can also filter the input based on a specific brand or product in which the user is interested. Furthermore, the reception unit can also preferentially receive related input based on the user's past purchase history. As a result, by filtering the input based on the user's current field of interest, highly relevant information can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can filter the input using an AI model that receives the user's field of interest data as input and outputs the filtering result.

[0108] The reception unit estimates the user's emotion and determines the priority of the input to be received based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is feeling stressed, the reception unit receives important input with priority. Also, when the user is relaxed, the reception unit can receive input with normal priority. Furthermore, when the user is in a hurry, the reception unit can receive urgent input with top priority. In this way, by determining the priority of the input according to the user's emotion, the input can be received in a more appropriate order. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can determine the priority of the input using an AI model that receives the user's emotion data as an input and outputs the priority of the input.

[0109] The reception unit preferentially receives highly relevant inputs in consideration of the geographical location information of the user when receiving the input. The geographical location information includes, but is not limited to, for example, GPS data, IP address, and location information services. For example, when the user is in a specific area, the reception unit preferentially receives inputs of products and services related to the area. In addition, when the user is traveling, the reception unit can also preferentially receive information related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive inputs related to daily life. In this way, highly relevant information can be preferentially received by considering the geographical location information of the user. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can preferentially receive inputs using an AI model that receives the geographical location information of the user as input and outputs highly relevant inputs.

[0110] The reception unit analyzes the user's social media activity at the time of receiving the input, and receives the relevant input. The social media activity includes, but is not limited to, for example, the content of the post, the number of followers, the number of likes, and the like. The reception unit preferentially receives the input, for example, based on the products and services in which the user shows interest on social media. The reception unit can also receive the relevant input based on the content of the post of an influencer the user follows. Furthermore, the reception unit can also filter the input based on the information shared by the user on social media. In this way, the user's social media activity can be analyzed to preferentially receive the relevant input. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can receive the input using an AI model that receives the user's social media data as input and outputs the related input.

[0111] The collection unit estimates the user's emotion and adjusts the method of information collection based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is feeling stressed, the collection unit preferentially collects simple and easy-to-understand information. Furthermore, when the user is relaxed, the collection unit can also collect detailed information. Furthermore, when the user is in a hurry, the collection unit can also preferentially collect information that can be collected quickly. In this way, more appropriate information can be collected by adjusting the method of information collection according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can adjust the method of information collection using an AI model that inputs the user's emotion data and outputs the method of information collection.

[0112] The collection unit selects an appropriate information source based on the user's past search history when collecting information. The past search history includes, for example, search keywords, search date and time, and click history of search results, but is not limited to such examples. For example, the collection unit preferentially collects information sources that the user has frequently used in the past. The collection unit can also select a highly reliable information source from the user's past search history. Furthermore, the collection unit can also select a related information source based on the content that the user has searched in the past. This makes it possible to select an optimal information source by referring to the user's past search history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can select an information source using an AI model that inputs the user's search history data and outputs an appropriate information source.

[0113] The collection unit adjusts the information to be collected based on the user's current field of interest when collecting information. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The collection unit collects related information, for example, based on a product category in which the user has recently shown interest. In addition, if the user shows interest in a particular brand or product, the collection unit can also preferentially collect information about the brand or product. Furthermore, the collection unit can customize and collect related information based on the user's past purchase history. This makes it possible to collect highly relevant information by customizing information based on the user's current field of interest. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can adjust the information using an AI model that inputs the user's field of interest data and outputs the information to be collected.

[0114] The collection unit estimates the user's emotion and determines the priority of information to be collected based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is feeling stressed, the collection unit collects important information with priority. In addition, when the user is relaxed, the collection unit can also collect information with normal priority. Furthermore, when the user is in a hurry, the collection unit can also collect urgent information with top priority. In this way, important information can be collected with priority by determining the priority of information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can determine the priority of information using an AI model that inputs the user's emotion data and outputs the priority of information.

[0115] When collecting information, the collection unit preferentially collects highly relevant information in consideration of the geographical location information of the user. The geographical location information includes, but is not limited to, for example, GPS data, IP address, location information service, etc. For example, when the user is in a specific area, the collection unit preferentially collects information related to the area. In addition, when the user is traveling, the collection unit can also preferentially collect information related to the travel destination. Furthermore, when the user is at home, the collection unit can also preferentially collect information related to daily life. In this way, by considering the geographical location information of the user, highly relevant information can be preferentially collected. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can preferentially collect information using an AI model that inputs the geographical location information of the user and outputs highly relevant information.

[0116] The collection unit analyzes the user's social media activity at the time of collecting information, and collects related information. The social media activity includes, for example, the content of posts, the number of followers, the number of likes, and the like, but is not limited to such examples. The collection unit preferentially collects information, for example, based on products and services in which the user shows interest on social media. The collection unit can also collect related information based on the content of posts of influencers followed by the user. Furthermore, the collection unit can also filter information based on information shared by the user on social media. In this way, by analyzing the user's social media activity, related information can be preferentially collected. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the user's social media data and outputs related information.

[0117] The comparison unit estimates the user's emotion and adjusts the comparison criteria based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is stressed, the comparison unit uses a simple comparison criterion. Also, when the user is relaxed, the comparison unit can use a detailed comparison criterion. Furthermore, when the user is in a hurry, the comparison unit can use a criterion that allows quick comparison. This allows for more appropriate comparison by adjusting the comparison criterion according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the comparison unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comparison unit can adjust the comparison criterion using an AI model that inputs the user's emotion data and outputs the comparison criterion.

[0118] The comparison unit improves the accuracy of the comparison based on the interrelationship of the products during the comparison. The interrelationship of the products includes, for example, compatibility, complementarity, and competitiveness, but is not limited to such examples. The comparison unit performs the comparison, for example, taking into consideration the compatibility of the products. The comparison unit can also perform the comparison while taking into consideration the complementarity of the products. Furthermore, the comparison unit can also perform the comparison while taking into consideration the competitive relationship of the products. As a result, the accuracy of the comparison can be improved by taking into consideration the interrelationship of the products. A part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can improve the accuracy of the comparison by using an AI model that inputs interrelationship data of the products and outputs a comparison result.

[0119] The comparison unit performs the comparison based on the attribute information of the products at the time of comparison. The attribute information of the products includes, for example, product specifications, functions, designs, etc., but is not limited to such examples. The comparison unit performs the comparison based on, for example, the prices of the products. The comparison unit can also perform the comparison based on the functions of the products. Furthermore, the comparison unit can also perform the comparison based on the evaluations of the products. This allows a more detailed comparison to be performed by taking the attribute information of the products into consideration. A part or all of the above-mentioned processing in the comparison unit may be performed using, for example, AI, or may be performed without using AI. For example, the comparison unit can perform the comparison using an AI model that inputs the attribute information of the products and outputs the comparison results.

[0120] The comparison unit estimates the user's emotion and adjusts the display order of the comparison results based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is feeling stressed, the comparison unit preferentially displays important comparison results. Also, when the user is relaxed, the comparison unit can display the comparison results in a normal order. Furthermore, when the user is in a hurry, the comparison unit can display the comparison results so that the comparison results can be quickly confirmed. In this way, by adjusting the display order of the comparison results according to the user's emotion, the results can be displayed in a more appropriate order. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the comparison unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comparison unit can adjust the display order of the comparison results using an AI model that inputs the user's emotion data and outputs the display order.

[0121] The comparison unit performs the comparison based on the geographical distribution of the product at the time of comparison. The geographical distribution of the product includes, for example, a sales area, an area where the product is in stock, and an area where the product can be delivered, but is not limited to such examples. The comparison unit performs the comparison, for example, by taking into consideration the sales area of ​​the product. The comparison unit can also perform the comparison by taking into consideration the area where the product can be delivered. Furthermore, the comparison unit can also perform the comparison by taking into consideration the evaluation of the product by region. In this way, the comparison can be performed by region by taking into consideration the geographical distribution of the product. A part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can perform the comparison using an AI model that inputs the geographical distribution data of the product and outputs the comparison result.

[0122] The comparison unit improves the accuracy of the comparison based on the related literature of the product during the comparison. The related literature of the product includes, but is not limited to, academic papers, technical reports, patent documents, and the like. The comparison unit, for example, performs the comparison by referring to technical literature of the product. The comparison unit can also perform the comparison by referring to review articles of the product. Furthermore, the comparison unit can also perform the comparison by referring to patent information of the product. In this way, the accuracy of the comparison can be improved by referring to the related literature of the product. Part or all of the above-mentioned processing in the comparison unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison unit can improve the accuracy of the comparison by using an AI model that inputs the related literature data of the product and outputs the comparison result.

[0123] The comparison result providing unit estimates the user's emotion and adjusts the display method of the comparison result based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is stressed, the comparison result providing unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the comparison result providing unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the comparison result providing unit can also provide a display method that focuses on the main points. This allows for more appropriate display by adjusting the display method of the comparison result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the comparison result providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comparison result providing unit can adjust the display method of the comparison result using an AI model that inputs the user's emotion data and outputs a display method.

[0124] When providing the comparison result, the comparison result providing unit selects an appropriate display method based on the user's past selection history. The past selection history includes, for example, the selected product, the date and time of selection, the frequency of selection, and the like, but is not limited to such examples. For example, the comparison result providing unit preferentially provides the display method selected by the user in the past. The comparison result providing unit can also predict and provide the optimal display method from the user's past selection history. Furthermore, the comparison result providing unit can also customize the display method based on the display style that the user preferred in the past. In this way, the optimal display method can be provided by referring to the user's past selection history. A part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can select the display method using an AI model that inputs the user's selection history data and outputs the display method.

[0125] The comparison result providing unit adjusts the display contents based on the user's current field of interest when providing the comparison results. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The comparison result providing unit preferentially displays related comparison results, for example, based on a product category in which the user has recently shown interest. In addition, if the user has shown interest in a specific brand or product, the comparison result providing unit can also preferentially display comparison results related to the brand or product. Furthermore, the comparison result providing unit can customize and display related comparison results based on the user's past purchase history. This makes it possible to provide highly relevant information by customizing the display contents based on the user's current field of interest. Part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can adjust the display contents using an AI model that receives the user's field of interest data as input and outputs the display contents.

[0126] The comparison result providing unit estimates the user's emotion and determines the priority order of the comparison results based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is feeling stressed, the comparison result providing unit preferentially displays important comparison results. Also, when the user is relaxed, the comparison result providing unit can also display the comparison results in a normal order. Furthermore, when the user is in a hurry, the comparison result providing unit can also display the comparison results so that the user can quickly check them. In this way, important information can be preferentially displayed by determining the priority order of the comparison results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the comparison result providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comparison result providing unit can determine the priority order of the comparison results using an AI model that receives the user's emotion data as input and outputs the priority order.

[0127] The comparison result providing unit selects an appropriate display method based on the geographical location information of the user when providing the comparison result. The geographical location information includes, but is not limited to, for example, GPS data, IP address, location information service, etc. For example, when the user is in a specific area, the comparison result providing unit preferentially displays the comparison results of products related to the area. In addition, when the user is traveling, the comparison result providing unit can also preferentially display the comparison results of products related to the travel destination. Furthermore, when the user is at home, the comparison result providing unit can also preferentially display the comparison results of products related to daily life. In this way, the optimal display method can be provided by taking the geographical location information of the user into consideration. Part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can select the display method using an AI model that inputs the geographical location information of the user and outputs the display method.

[0128] The comparison result providing unit adjusts the display contents by analyzing the social media activity of the user when providing the comparison results. The social media activity includes, for example, the posting contents, the number of followers, the number of likes, and the like, but is not limited to such examples. The comparison result providing unit preferentially displays the comparison results, for example, based on products and services in which the user shows interest on social media. The comparison result providing unit can also display related comparison results based on the posting contents of influencers followed by the user. Furthermore, the comparison result providing unit can also filter the comparison results based on information shared by the user on social media. In this way, by analyzing the social media activity of the user, related information can be preferentially displayed. A part or all of the above-mentioned processing in the comparison result providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the comparison result providing unit can adjust the display contents using an AI model that inputs the social media data of the user and outputs the display contents.

[0129] The response unit estimates the user's emotion and adjusts the way of expressing the response based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is stressed, the response unit provides a simple and easy-to-understand response. Furthermore, when the user is relaxed, the response unit can also provide a response including detailed information. Furthermore, when the user is in a hurry, the response unit can also provide a response so that the user can quickly confirm. This allows a more appropriate response to be made by adjusting the way of expressing the response according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the response unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the response unit can adjust the way of expressing the response using an AI model that inputs the user's emotion data and outputs the way of expressing the response.

[0130] The response unit adjusts the level of detail of the response based on the importance of the question when responding. The importance of the question includes, but is not limited to, the urgency of the question, the impact of the question, and the frequency of the question. For example, the response unit provides a detailed response to an important question. The response unit can also provide a simple response to a general question. Furthermore, the response unit can also provide a quick response to an urgent question. This allows a more appropriate response to be made by adjusting the level of detail of the response based on the importance of the question. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI or may be performed without using AI. For example, the response unit can adjust the level of detail of the response using an AI model that inputs the importance data of the question and outputs the level of detail of the response.

[0131] The response unit applies different response algorithms depending on the category of the question when responding. The response unit applies different response algorithms depending on the category of the question when responding. The question categories include, for example, technical questions, questions about products, questions about support, and the like, but are not limited to such examples. For example, the response unit responds to a question about a delivery status based on delivery information. In addition, the response unit can also respond to a question about an inventory status based on inventory information. Furthermore, the response unit can also respond to a question about a product's features based on product information. In this way, by applying different response algorithms depending on the category of the question, a more appropriate response can be made. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can apply a response algorithm using an AI model that inputs question category data and outputs a response algorithm.

[0132] The response unit estimates the user's emotion and adjusts the length of the response based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is stressed, the response unit provides a short and to-the-point response. Also, when the user is relaxed, the response unit can provide a response including a detailed explanation. Furthermore, when the user is in a hurry, the response unit can provide a short response so that the user can quickly confirm. This allows a more appropriate response to be made by adjusting the length of the response according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the response unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response unit can adjust the length of the response using an AI model that inputs the user's emotion data and outputs the length of the response.

[0133] The response unit determines the priority of the response based on the time of question submission when responding. The time of question submission includes, but is not limited to, the submission date and time, the frequency of submission, and the timing of submission. For example, the response unit prioritizes the response to a question submitted recently. The response unit can also respond to an urgent question with the highest priority. Furthermore, the response unit can respond to a question submitted in the past later. In this way, by determining the priority of the response based on the time of question submission, the response can be made in a more appropriate order. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can determine the priority of the response using an AI model that inputs question submission time data and outputs the priority of the response.

[0134] The response unit adjusts the order of responses based on the relevance of the questions when responding. The relevance of the questions includes, but is not limited to, the content of the questions, the category of the questions, and the frequency of the questions. For example, the response unit prioritizes responses to questions with high relevance. The response unit can also respond to questions with general content later. Furthermore, the response unit can also respond to questions with high urgency as a top priority. By adjusting the order of responses based on the relevance of the questions, responses can be made in a more appropriate order. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can adjust the order of responses using an AI model that inputs question relevance data and outputs the order of responses.

[0135] The progress information providing unit estimates the user's emotion and adjusts the display method of the progress information based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is feeling stressed, the progress information providing unit provides a display method that is simple and highly visible. Furthermore, when the user is relaxed, the progress information providing unit can also provide a display method that includes detailed information. Furthermore, when the user is in a hurry, the progress information providing unit can also provide a display method that focuses on the main points. This allows the display method of the progress information to be adjusted according to the user's emotion, thereby enabling more appropriate display. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the progress information providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the progress information providing unit can adjust the display method of the progress information using an AI model that inputs the user's emotion data and outputs a display method.

[0136] The progress information providing unit predicts the current progress based on the past progress data when providing the progress information. The past progress data includes, for example, a progress history, a change in progress, and a frequency of progress, but is not limited to such examples. The progress information providing unit predicts the current progress status based on, for example, the past progress data. The progress information providing unit can also notify a predicted delay from the past progress data. Furthermore, the progress information providing unit can also analyze the past progress data and provide an optimal progress prediction. This makes it possible to predict the current progress by referring to the past progress data. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can predict the progress using an AI model that inputs past progress data and outputs the current progress.

[0137] The progress information providing unit applies a different progress display method for each order category when providing progress information. The order categories include, for example, food, home appliances, clothing, etc., but are not limited to such examples. For example, the progress information providing unit displays the delivery status in detail for a food order. Furthermore, for an order of a home appliance, the progress information providing unit can also display the expected arrival date of the product. Furthermore, for an order of clothing, the progress information providing unit can also display the date on which the product can be tried on. In this way, by applying a different progress display method for each order category, more appropriate progress information can be provided. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can apply the progress display method using an AI model that inputs order category data and outputs a progress display method.

[0138] The progress information providing unit estimates the user's emotion and adjusts the importance of the progress information based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is feeling stressed, the progress information providing unit preferentially displays important progress information. Furthermore, when the user is relaxed, the progress information providing unit can also display the progress information in a normal order. Furthermore, when the user is in a hurry, the progress information providing unit can also display the progress information so that the user can quickly check it. In this way, important information can be preferentially displayed by adjusting the importance of the progress information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the progress information providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the progress information providing unit can adjust the importance of the progress information using an AI model that inputs the user's emotion data and outputs the importance of the progress information.

[0139] The progress information providing unit analyzes the change in progress based on the time of submission of the order when providing the progress information. The time of submission of the order includes, for example, the submission date and time, the frequency of submission, and the timing of submission, but is not limited to such examples. For example, the progress information providing unit preferentially displays the progress of the order submitted recently. The progress information providing unit can also display the progress of the order submitted in the past later. Furthermore, the progress information providing unit can display the progress of the urgent order with the highest priority. In this way, the change in progress can be analyzed based on the time of submission of the order, thereby providing more appropriate progress information. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can analyze the change in progress using an AI model that inputs the submission time data of the order and outputs the change in progress.

[0140] The progress information providing unit analyzes the progress based on the relevant market data of the order when providing the progress information. The relevant market data includes, for example, market demand, supply status, trends, etc., but is not limited to such examples. The progress information providing unit predicts a change in the progress based on, for example, market demand. The progress information providing unit can also predict a change in the progress based on the supply status of the market. Furthermore, the progress information providing unit can also predict a change in the progress based on a market trend. Thereby, the change in the progress can be predicted by referring to the relevant market data of the order. A part or all of the above-mentioned processing in the progress information providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the progress information providing unit can analyze the progress using an AI model that inputs the relevant market data and outputs the change in the progress.

[0141] The suggestion unit estimates the user's emotion and adjusts the expression method of the proposal based on the estimated emotion. The user's emotion includes, for example, stress, relaxation, and hurry, but is not limited to such examples. For example, when the user is stressed, the suggestion unit provides a simple and easy-to-understand proposal. Furthermore, when the user is relaxed, the suggestion unit can also provide a proposal including detailed information. Furthermore, when the user is in a hurry, the suggestion unit can also provide a proposal so that the user can quickly confirm. In this way, by adjusting the expression method of the proposal according to the user's emotion, a more appropriate proposal can be made. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can adjust the expression method of the proposal using an AI model that inputs the user's emotion data and outputs the expression method of the proposal.

[0142] The suggestion unit adjusts the level of detail of the proposal based on the importance of the product at the time of proposal. The importance of the product includes, for example, the urgency of the product, the impact of the product, the frequency of the product, and the like, but is not limited to such examples. For example, the suggestion unit provides a detailed proposal for an important product. The suggestion unit can also provide a simple proposal for a general product. Furthermore, the suggestion unit can also provide a proposal for a product with high urgency so that the product can be quickly confirmed. As a result, a more appropriate proposal can be made by adjusting the level of detail of the proposal based on the importance of the product. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can adjust the level of detail of the proposal using an AI model that inputs the importance data of the product and outputs the level of detail of the proposal.

[0143] The suggestion unit applies different suggestion algorithms depending on the category of the product when making a suggestion. The categories of the product include, but are not limited to, for example, home appliances, clothing, and food. For example, the suggestion unit provides a suggestion that emphasizes technical features for home appliances. For clothing, the suggestion unit can also provide a suggestion that emphasizes design and materials. For food, the suggestion unit can also provide a suggestion that emphasizes nutritional value and taste. This allows more appropriate suggestions to be made by applying different suggestion algorithms depending on the category of the product. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can apply the suggestion algorithm using an AI model that inputs product category data and outputs a suggestion algorithm.

[0144] The suggestion unit estimates the user's emotion and adjusts the length of the proposal based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is stressed, the suggestion unit provides a short and to-the-point proposal. Furthermore, when the user is relaxed, the suggestion unit can also provide a proposal including a detailed explanation. Furthermore, when the user is in a hurry, the suggestion unit can also provide a short proposal so that the user can quickly confirm. In this way, by adjusting the length of the proposal according to the user's emotion, a more appropriate proposal can be made. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can adjust the length of the proposal using an AI model that inputs the user's emotion data and outputs the length of the proposal.

[0145] The suggestion unit determines the priority of the suggestions based on the submission time of the products at the time of suggestion. The submission time of the products includes, for example, the submission date and time, the frequency of submission, and the timing of submission, but is not limited to such examples. For example, the suggestion unit provides a suggestion of a recently added product with priority. The suggestion unit can also provide a suggestion of a product with high urgency with the highest priority. Furthermore, the suggestion unit can provide a suggestion of a product added in the past at a later date. In this way, by determining the priority of the suggestions based on the submission time of the products, the suggestions can be made in a more appropriate order. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can determine the priority of the suggestions using an AI model that inputs the submission time data of the products and outputs the priority of the suggestions.

[0146] The suggestion unit adjusts the order of suggestions based on the relevance of the products when making suggestions. The relevance of the products includes, for example, the user's interest level, product evaluation, and ascending order of price, but is not limited to such examples. For example, the suggestion unit provides a suggestion of a product that the user is highly interested in preferentially. The suggestion unit can also provide a suggestion of a product that the user is less interested in later. Furthermore, the suggestion unit can also provide a suggestion of a product that is highly related preferentially based on the user's past purchase history. As a result, by adjusting the order of suggestions based on the relevance of the products, suggestions can be made in a more appropriate order. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can adjust the order of suggestions using an AI model that inputs product relevance data and outputs the order of suggestions.

[0147] The feedback unit estimates the user's emotion and adjusts the feedback collection method based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is stressed, the feedback unit provides a simple and easy-to-understand feedback form. Furthermore, when the user is relaxed, the feedback unit can also provide a form that requests detailed feedback. Furthermore, when the user is in a hurry, the feedback unit can also provide a form that allows feedback to be collected quickly. This allows more appropriate feedback to be collected by adjusting the feedback collection method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can adjust the feedback collection method using an AI model that inputs the user's emotion data and outputs the feedback collection method.

[0148] The feedback unit selects an appropriate collection method based on past feedback data when collecting feedback. The past feedback data includes, for example, the form of feedback, the content of feedback, and the timing of collecting feedback, but is not limited to such examples. For example, the feedback unit preferentially provides the form of feedback provided by the user in the past. The feedback unit can also predict and provide the optimal collection method from the user's past feedback data. Furthermore, the feedback unit can customize the collection method based on the feedback form that the user preferred in the past. In this way, the optimal collection method can be provided by referring to the past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can select the collection method using an AI model that inputs past feedback data and outputs the collection method.

[0149] The feedback unit adjusts the feedback to be collected based on the user's current field of interest when collecting feedback. The current field of interest includes, but is not limited to, recent search history, browsing history, purchase history, and the like. The feedback unit preferentially collects relevant feedback, for example, based on a product category in which the user has recently shown interest. In addition, if the user has shown interest in a particular brand or product, the feedback unit can also preferentially collect feedback on the brand or product. Furthermore, the feedback unit can customize and collect relevant feedback based on the user's past purchase history. This makes it possible to collect highly relevant feedback by customizing the feedback based on the user's current field of interest. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can adjust the feedback using an AI model that inputs the user's field of interest data and outputs the feedback to be collected.

[0150] The feedback unit estimates the user's emotion and determines the priority of the feedback based on the estimated emotion. The user's emotion includes, but is not limited to, for example, stress, relaxation, and hurry. For example, when the user is feeling stressed, the feedback unit preferentially collects important feedback. Also, when the user is relaxed, the feedback unit can also collect feedback in a normal order. Furthermore, when the user is in a hurry, the feedback unit can also collect feedback so that it can be quickly confirmed. In this way, by determining the priority of the feedback according to the user's emotion, it is possible to preferentially collect important feedback. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can determine the priority of the feedback using an AI model that inputs the user's emotion data and outputs the priority of the feedback.

[0151] The feedback unit, when collecting feedback, preferentially collects feedback with high relevance based on the geographical location information of the user. The geographical location information includes, but is not limited to, for example, GPS data, IP address, location information service, etc. For example, when the user is in a specific area, the feedback unit preferentially collects feedback related to the area. In addition, when the user is traveling, the feedback unit can also preferentially collect feedback related to the travel destination. Furthermore, when the user is at home, the feedback unit can also preferentially collect feedback related to daily life. In this way, by taking the geographical location information of the user into consideration, it is possible to preferentially collect feedback with high relevance. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can collect feedback using an AI model that inputs the geographical location information of the user and outputs feedback with high relevance.

[0152] The feedback unit analyzes the user's social media activity at the time of collecting feedback and collects relevant feedback. The social media activity includes, but is not limited to, for example, the content of posts, the number of followers, the number of likes, and the like. The feedback unit preferentially collects feedback, for example, based on products and services in which the user shows interest on social media. The feedback unit can also collect relevant feedback based on the content of posts of influencers followed by the user. Furthermore, the feedback unit can also filter feedback based on information shared by the user on social media. This allows the user's social media activity to be analyzed to preferentially collect relevant feedback. Some or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can collect feedback using an AI model that inputs the user's social media data and outputs relevant feedback.

[0153] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0154] The collection unit can also collect product information for each region, taking into account the geographic location information of the user. For example, when the user is in a particular region, the collection unit can preferentially collect information on products and services that are popular in that region. In addition, when the user is traveling, the collection unit can also collect product information related to the travel destination. Furthermore, when the user is at home, the collection unit can also collect product information related to daily life. In this way, more relevant product information can be provided by taking into account the geographic location information of the user.

[0155] The response unit can also estimate the user's emotions and adjust the tone and expression of the response based on the estimated emotions. For example, if the user is stressed, the response unit can provide a simple and easy-to-understand response. If the user is relaxed, the response unit can provide a response containing detailed information. Furthermore, if the user is in a hurry, the response unit can provide a short response for quick confirmation. This allows a more appropriate response to be provided by adjusting the tone and expression of the response according to the user's emotions.

[0156] The response unit can also analyze the user's past question history and select the optimal response method. For example, the response method (text, voice, etc.) that the user has used frequently in the past is provided preferentially. The response unit can also predict and suggest the response method to be used during a specific time period from the user's past question history. Furthermore, the response unit can provide shortcuts to reduce the effort of responding by referring to the content of questions asked by the user in the past. In this way, the optimal response method can be provided by analyzing the user's past question history.

[0157] The progress information providing unit can also estimate the user's emotions and adjust the display method of the progress information based on the estimated emotions. For example, if the user is feeling stressed, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, a more appropriate display can be provided by adjusting the display method of the progress information according to the user's emotions.

[0158] The progress information providing unit can also analyze the user's past progress check history and select the optimal progress information providing method. For example, the progress check method (smart refrigerator, smart lighting, etc.) that the user has used frequently in the past is provided preferentially. The progress information providing unit can also predict and suggest the progress check method to be used in a specific time period from the user's past progress check history. Furthermore, the progress information providing unit can provide shortcuts to reduce the effort of providing progress information by referring to the content that the user has checked in the past. In this way, the optimal progress information providing method can be provided by analyzing the user's past progress check history.

[0159] The suggestion unit can also estimate the user's emotion and adjust the way the suggestion is expressed based on the estimated emotion. For example, if the user is stressed, a simple and easy-to-understand suggestion can be provided. If the user is relaxed, a suggestion including detailed information can be provided. Furthermore, if the user is in a hurry, a suggestion can be provided so that the user can quickly confirm it. In this way, by adjusting the way the suggestion is expressed according to the user's emotion, more appropriate suggestions can be made.

[0160] The suggestion unit can also analyze the user's past proposal history and select the optimal proposal method. For example, the suggestion unit can preferentially provide a proposal method (text, image, etc.) that the user has frequently accepted in the past. The suggestion unit can also predict and suggest a proposal method to be used in a specific time period from the user's past proposal history. Furthermore, the suggestion unit can provide a shortcut to reduce the effort of making suggestions by referring to the content that the user has accepted in the past. In this way, the optimal proposal method can be provided by analyzing the user's past proposal history.

[0161] The feedback unit can also estimate the user's emotions and adjust the feedback collection method based on the estimated emotions. For example, if the user is stressed, a simple and easy-to-understand feedback form can be provided. If the user is relaxed, a form requesting detailed feedback can be provided. Furthermore, if the user is in a hurry, a form that allows quick feedback collection can be provided. In this way, more appropriate feedback can be collected by adjusting the feedback collection method according to the user's emotions.

[0162] The feedback unit can also analyze the user's past feedback history and select the optimal feedback collection method. For example, the feedback unit can provide feedback methods (text, voice, etc.) that the user has used frequently in the past with priority. The feedback unit can also predict and suggest the feedback method to be used in a specific time period from the user's past feedback history. Furthermore, the feedback unit can provide shortcuts to reduce the effort of providing feedback by referring to the content provided by the user in the past. In this way, the optimal feedback collection method can be provided by analyzing the user's past feedback history.

[0163] The feedback unit may also collect feedback for each region by taking into account the geographic location information of the user. For example, when the user is in a particular region, feedback on products and services in that region may be preferentially collected. In addition, when the user is traveling, the feedback unit may collect feedback related to the travel destination. Furthermore, when the user is at home, the feedback unit may collect feedback related to daily life. In this way, more relevant feedback can be provided by taking into account the geographic location information of the user.

[0164] The process flow of the second embodiment will be briefly described below.

[0165] Step 1: The reception unit receives input from a user. The input from a user includes text input, voice input, image input, etc. For example, when a user searches for a product, the input is received. Step 2: The collection unit collects information on multiple products according to the input received by the reception unit. The collected product information includes price information, product features, reviews, etc. The collection unit collects product information from multiple online stores using web scraping technology and APIs. The collection unit can also collect product information by performing database searches. Step 3: The comparison unit compares the information of the multiple products collected by the collection unit. Comparison criteria include price comparison, performance comparison, user evaluation comparison, etc. For example, products are compared based on price information. Products can also be compared based on performance information and user evaluation. Step 4: The comparison result providing unit provides the comparison result by the comparison unit. The comparison result display method includes a ranking format, a graph display, a text display, and the like. For example, the products are displayed in a ranking format. The products can also be displayed in a graph display or a text display.

[0166] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the 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 voice data.

[0167] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0168] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0169] For example, the reception unit is realized by the reception device 38 of the smart device 14, and receives text input or voice input from the user. The collection unit is realized by the specific processing unit 290 of the data processing device 12, and collects product information using web scraping technology or API. The comparison unit is realized by the specific processing unit 290 of the data processing device 12, and compares prices and performance based on the collected product information. The comparison result providing unit is realized by the output device 40 of the smart device 14, and provides the comparison result to the user in a ranking format or graph display. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0170] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0171] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0172] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0173] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0177] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0182] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0184] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0185] For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives voice input from the user. The collection unit is realized by the specific processing unit 290 of the data processing device 12 and collects product information using web scraping technology or API. The comparison unit is realized by the specific processing unit 290 of the data processing device 12 and compares prices and performance based on the collected product information. The comparison result provision unit is realized by the speaker 240 of the smart glasses 214 and provides the comparison result to the user by voice. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0186] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0187] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0188] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0189] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0190] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0191] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0192] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0193] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0194] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0196] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0198] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0199] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0200] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0201] For example, the reception unit is realized by the microphone 238 of the headset terminal 314 and receives voice input from the user. The collection unit is realized by the specific processing unit 290 of the data processing device 12 and collects product information using web scraping technology or API. The comparison unit is realized by the specific processing unit 290 of the data processing device 12 and compares prices and performance based on the collected product information. The comparison result provision unit is realized by the display 343 of the headset terminal 314 and provides the comparison results to the user in a ranking format or graph display. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0202] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0203] 7, a 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.

[0204] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0205] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0206] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0207] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0208] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0209] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0210] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0211] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0212] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0213] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0214] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0215] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0216] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0217] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0218] For example, the reception unit is realized by the microphone 238 of the robot 414 and receives voice input from the user. The collection unit is realized by the specific processing unit 290 of the data processing device 12 and collects product information using web scraping technology or API. The comparison unit is realized by the specific processing unit 290 of the data processing device 12 and compares prices and performance based on the collected product information. The comparison result provision unit is realized by the speaker 240 of the robot 414 and provides the comparison result to the user by voice. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0219] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0220] FIG. 9 is a diagram showing an emotion map 400 on 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 emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0221] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0222] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0223] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0224] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0225] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0226] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0227] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0228] In addition, 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 upon request from the data processing device 12.

[0229] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0230] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0231] The hardware resource that executes the specific process may be one of these various processors, or may be 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). Also, the hardware resource that executes the specific process may be a single processor.

[0232] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0233] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0234] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0235] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0236] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0237] (Appendix 1) A reception unit that receives an input from a user; a collection unit that, when the input received by the reception unit is a product search, collects information on a plurality of products corresponding to the input received by the reception unit; a comparison unit that compares information on a plurality of products collected by the collection unit; A comparison result providing unit that provides a comparison result by the comparison unit. A system characterized by: (Appendix 2) and a response unit that responds to a question when the input received by the reception unit is a question. 2. The system of claim 1, (Appendix 3) The response unit: The response is made by providing the delivery status or stock status as an answer to the question. 3. The system of claim 2, (Appendix 4) and a progress information providing unit that provides information indicating the progress of an order when the input received by the receiving unit is a confirmation of the progress of the order. 2. The system of claim 1, (Appendix 5) The progress information providing unit is Providing information indicating the progress of the order via the user's smart home appliance 5. The system of claim 4. (Appendix 6) The progress information providing unit is The display of the user's smart refrigerator is used to instantly display the delivery status of the ordered ingredients. 6. The system of claim 5, (Appendix 7) The progress information providing unit is It works with the user's smart lighting to notify them of the order's progress with different colors or blinking patterns. 6. The system of claim 5, (Appendix 8) The progress information providing unit is Using the user's smart curtain, the curtain is opened or closed depending on the progress of the order. 6. The system of claim 5, (Appendix 9) The progress information providing unit is Adjust the bed's reclining or massage function according to the progress of the order via the user's smart bed. 6. The system of claim 5, (Appendix 10) A suggestion unit that suggests products to the user based on the user's product purchase history. 2. The system of claim 1, (Appendix 11) The suggestion unit, Suggesting products based on the user's product purchase history and reviews of influencers the user follows 11. The system of claim 10, (Appendix 12) The suggestion unit, Based on the user's purchasing history, a set of products that can be purchased at the same time is suggested as a good deal. 11. The system of claim 10, (Appendix 13) A feedback unit that collects feedback from the user and improves the comparison unit based on the collected feedback. 2. The system of claim 1, (Appendix 14) The reception unit is Estimate the user's emotions and adjust the timing of input acceptance based on the estimated user emotions. 2. The system of claim 1, (Appendix 15) The reception unit is Analyze the user's past input history and select the appropriate reception method 2. The system of claim 1, (Appendix 16) The reception unit is As input is accepted, filter it based on the user's current interests 2. The system of claim 1, (Appendix 17) The reception unit is Estimate the user's emotions and prioritize inputs based on the estimated user emotions. 2. The system of claim 1, (Appendix 18) The reception unit is When accepting input, prioritize input that is more relevant based on the user's geographic location information 2. The system of claim 1, (Appendix 19) The reception unit is When receiving input, analyze the user's social media activity and receive relevant input 2. The system of claim 1, (Appendix 20) The collecting unit includes: Inferring user emotions and adjusting information gathering methods based on the estimated user emotions 2. The system of claim 1, (Appendix 21) The collecting unit includes: When collecting information, select the appropriate source based on the user's past search history 2. The system of claim 1, (Appendix 22) The collecting unit includes: At the time of collection, tailor the information we collect based on your current interests 2. The system of claim 1, (Appendix 23) The collecting unit includes: Estimate user emotions and prioritize information to be collected based on the estimated user emotions. 2. The system of claim 1, (Appendix 24) The collecting unit includes: When collecting information, prioritize collection of information that is more relevant based on the user's geographic location information 2. The system of claim 1, (Appendix 25) The collecting unit includes: When collecting information, we analyze your social media activity and collect relevant information. 2. The system of claim 1, (Appendix 26) The comparison unit is Inferring a user's emotions and adjusting the comparison criteria based on the estimated user's emotions 2. The system of claim 1, (Appendix 27) The comparison unit is When comparing, improve the accuracy of the comparison based on the correlation of products 2. The system of claim 1, (Appendix 28) The comparison unit is When comparing, make comparisons based on product attribute information 2. The system of claim 1, (Appendix 29) The comparison unit is Inferring user emotion and adjusting the display order of comparison results based on the estimated user emotion 2. The system of claim 1, (Appendix 30) The comparison unit is When comparing, make comparisons based on the geographical distribution of products 2. The system of claim 1, (Appendix 31) The comparison unit is When comparing, improve the accuracy of the comparison based on the relevant literature of the product 2. The system of claim 1, (Appendix 32) The comparison result providing unit, Inferring user emotion and adjusting the way comparison results are displayed based on the estimated user emotion 2. The system of claim 1, (Appendix 33) The comparison result providing unit, When providing comparison results, select the appropriate display method based on the user's past selection history. 2. The system of claim 1, (Appendix 34) The comparison result providing unit, When providing comparison results, tailor what is displayed based on the user's current interests 2. The system of claim 1, (Appendix 35) The comparison result providing unit, A user's emotion is estimated, and a priority order of comparison results is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 36) The comparison result providing unit, When providing comparison results, select the appropriate display method based on the user's geographic location information 2. The system of claim 1, (Appendix 37) The comparison result providing unit, When providing comparison results, analyze users' social media activity to adjust the content displayed 2. The system of claim 1, (Appendix 38) The response unit: Inferring a user's emotions and adjusting the way responses are expressed based on the inferred user emotions 3. The system of claim 2, (Appendix 39) The response unit: When responding, adjust the detail of your response based on the importance of the question 3. The system of claim 2, (Appendix 40) The response unit: When answering, apply different answering algorithms depending on the question category 3. The system of claim 2, (Appendix 41) The response unit: Inferring a user's emotion and adjusting the length of a response based on the estimated user's emotion 3. The system of claim 2, (Appendix 42) The response unit: When responding, prioritize responses based on when the question was submitted 3. The system of claim 2, (Appendix 43) The response unit: As you respond, adjust the order of responses based on the relevance of the question 3. The system of claim 2, (Appendix 44) The progress information providing unit is Inferring a user's emotion and adjusting the display method of progress information based on the estimated user's emotion 5. The system of claim 4. (Appendix 45) The progress information providing unit is When providing progress information, predict current progress based on past progress data 5. The system of claim 4. (Appendix 46) The progress information providing unit is When providing progress information, apply different progress display methods to different order categories 5. The system of claim 4. (Appendix 47) The progress information providing unit is To estimate a user's emotion and adjust the importance of progress information based on the estimated user's emotion. 5. The system of claim 4. (Appendix 48) The progress information providing unit is When providing progress information, analyze progress changes based on when orders were submitted 5. The system of claim 4. (Appendix 49) The progress information providing unit is When progress information is provided, we analyze the progress based on the order's relevant market data 5. The system of claim 4. (Appendix 50) The suggestion unit, Infer user emotions and adjust the presentation of suggestions based on the inferred user emotions 11. The system of claim 10, (Appendix 51) The suggestion unit, When making a proposal, adjust the detail of the proposal based on the importance of the product 11. The system of claim 10, (Appendix 52) The suggestion unit, When making suggestions, apply different suggestion algorithms depending on the product category 11. The system of claim 10, (Appendix 53) The suggestion unit, Infer user sentiment and adjust the length of suggestions based on the estimated user sentiment 11. The system of claim 10, (Appendix 54) The suggestion unit, At the time of proposal, prioritize proposals based on when the product was submitted 11. The system of claim 10, (Appendix 55) The suggestion unit, When making suggestions, adjust the order of suggestions based on product relevance 11. The system of claim 10, (Appendix 56) The feedback unit is Infer user sentiment and adjust feedback collection methods based on the inferred user sentiment 14. The system of claim 13. (Appendix 57) The feedback unit is When collecting feedback, choose the appropriate collection method based on past feedback data 14. The system of claim 13. (Appendix 58) The feedback unit is When collecting feedback, tailor the feedback you collect based on the user's current areas of interest 14. The system of claim 13. (Appendix 59) The feedback unit is Estimate user emotions and prioritize feedback based on the estimated user emotions 14. The system of claim 13. (Appendix 60) The feedback unit is When collecting feedback, prioritize relevant feedback based on the user's geographic location 14. The system of claim 13. (Appendix 61) The feedback unit is When collecting feedback, analyze users' social media activity and collect relevant feedback 14. The system of claim 13. [Explanation of symbols]

[0238] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives an input from a user; a collection unit that, when the input received by the reception unit is a product search, collects information on a plurality of products corresponding to the input received by the reception unit; a comparison unit that compares information on a plurality of products collected by the collection unit; a comparison result providing unit that provides a comparison result by the comparison unit; A system characterized by:

2. and a response unit that responds to a question when the input received by the reception unit is a question.

2. The system of claim 1 .

3. The response unit: The response is made by providing the delivery status or stock status as an answer to the question.

3. The system of claim 2.

4. and a progress information providing unit that provides information indicating the progress of an order when the input received by the receiving unit is a confirmation of the progress of the order.

2. The system of claim 1 .

5. The progress information providing unit is Providing information indicating the progress of the order via the user's smart home appliance 5. The system of claim 4.

6. The progress information providing unit is The display of the user's smart refrigerator is used to instantly display the delivery status of the ordered ingredients.

6. The system of claim 5.

7. The progress information providing unit is It works with the user's smart lighting to notify them of the order's progress with different colors or blinking patterns.

6. The system of claim 5.

8. The progress information providing unit is Using the user's smart curtain, the curtain is opened or closed depending on the progress of the order.

6. The system of claim 5.

9. The progress information providing unit is Adjust the bed's reclining or massage function according to the progress of the order via the user's smart bed.

6. The system of claim 5.

Images