system

Abstract

The system according to this embodiment aims to elicit the user's vague needs and propose the most suitable product. [Solution] The system according to the embodiment comprises a reception unit, a questioning unit, a filtering unit, and a suggestion unit. The reception unit receives user input. The questioning unit asks necessary questions based on the input received by the reception unit. The filtering unit narrows down the products based on the information obtained by the questioning unit. The suggestion unit proposes the products narrowed down by the filtering unit.

Description

Technical Field

[0001] The technology disclosed herein relates to a system.

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to find an optimal product when a user has ambiguous needs.

[0005] The system according to the embodiment aims to elicit ambiguous needs of a user and propose an optimal product.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a questioning unit, a filtering unit, and a suggestion unit. The reception unit receives user input. The questioning unit asks necessary questions based on the input received by the reception unit. The filtering unit narrows down the products based on the information obtained by the questioning unit. The suggestion unit proposes the products narrowed down by the filtering unit. [Effects of the Invention]

[0007] The system according to this embodiment can elicit the user's vague needs and propose the most suitable product. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The product search system according to an embodiment of the present invention is a system that provides a new means for users to search for products on e-commerce sites by utilizing generative AI. The product search system solves the problem that conventional keyword searches have difficulty in eliciting users' vague needs and finding the optimal product. In the present invention, by narrowing down products in a dialogue format, the user's vague image becomes concrete, making it easier to find the optimal product. First, the user inputs a vague image in a dialogue format, such as "I want a product that is like XX." For example, an input such as "I want a stylish lamp that will suit my living room" is possible. This input is analyzed by the generative AI. Next, the generative AI asks necessary questions in response to the user's input. For example, the generative AI may ask questions such as "What kind of design do you prefer?" or "What is your budget?" This narrows down the products that are most suitable for the user's requirements. Furthermore, by making not only text but also voice dialogue, photos, and explanatory illustrations drawn by the user available, a more intuitive search experience is realized. For example, the user can upload a photo taken with their smartphone, and the generative AI can suggest products based on that photo. This system allows users who are not particular about brands, those with vague needs, and even those unfamiliar with internet searches to easily find the products they are looking for, reducing stress. For example, if a user enters "I want an AI," the generating AI can suggest "smart speaker." Furthermore, the generating AI learns the user's conversation history and can make suggestions that reflect the user's preferences and needs in subsequent searches. This allows users to find products more efficiently. In this way, a conversational search method utilizing generating AI can concretize users' vague needs and make it easier for them to find the most suitable products. As a result, the product search system can concretize users' vague needs and make it easier for them to find the most suitable products.

[0029] The product search system according to this embodiment comprises a reception unit, a questioning unit, a filtering unit, and a suggestion unit. The reception unit receives user input. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception unit can receive text input from the user such as "I want a stylish lamp that would suit my living room." The reception unit can also receive voice input from the user such as "I want a stylish lamp that would suit my living room." Furthermore, the reception unit can also receive uploads of photos taken by the user with a smartphone. For example, the reception unit can receive a photo of the living room taken by the user with a smartphone and suggest products based on that photo. The questioning unit uses a generation AI to ask necessary questions based on the input received by the reception unit. For example, if the user inputs "I want a stylish lamp that would suit my living room," the questioning unit might ask, "What kind of design do you prefer?" The questioning unit may also ask, "What is your budget?" Furthermore, the questioning unit may also ask, "What kind of color do you prefer?" For example, the questioning unit uses a generating AI to ask the user, "What kind of design do you prefer?" based on the user's input. The filtering unit uses the generating AI to narrow down the products based on the information obtained by the questioning unit. For example, if the user answers, "I prefer modern designs," the filtering unit will filter for lamps with modern designs. The filtering unit can also filter for lamps under 10,000 yen if the user answers, "My budget is under 10,000 yen." Furthermore, if the user answers, "I prefer white," the filtering unit can filter for white lamps. For example, the filtering unit uses a generating AI to narrow down lamps with modern designs based on the user's answers. The suggestion unit uses a generating AI to suggest products narrowed down by the filtering unit. For example, the suggestion unit might suggest to the user, "How about this modern design lamp?" The suggestion unit could also suggest, "How about this lamp under 10,000 yen?" Furthermore, the suggestion unit could also suggest, "How about this white lamp?"For example, the suggestion section uses a generation AI to suggest to the user, "How about this modernly designed lamp?" This allows the product search system, according to the embodiment, to concretize the user's vague needs and make it easier for them to find the optimal product.

[0030] The reception desk receives user input. User input includes, but is not limited to, text input, voice input, and image input. Specifically, in the case of text input, users can freely input the characteristics and uses of the desired product using a keyboard or touchscreen. For example, they can input a specific request such as, "I want a stylish lamp that would suit my living room." In the case of voice input, users can communicate their requests by voice through a microphone, and the content is converted into text using voice recognition technology. For example, they can input by voice, "I want a stylish lamp that would suit my living room." In the case of image input, users can upload photos taken with a smartphone or camera. For example, they can upload a photo of their living room, and products can be suggested based on that photo. By supporting these diverse input methods, the reception desk allows users to communicate their requests in the way that is easiest for them. The reception desk also plays a role in appropriately processing the entered data and passing it on to the next step, the questioning desk. This allows for an accurate understanding of user needs and improves the accuracy and efficiency of the entire system. Furthermore, the reception desk also has a function to preprocess the input data and remove noise and input errors. For example, in the case of voice input, it removes background noise and improves the accuracy of voice recognition. Furthermore, in the case of image input, the image resolution is adjusted and the necessary parts are cropped to ensure smoother subsequent processing. This allows the reception unit to efficiently process diverse user inputs and improve the overall system performance.

[0031] The questioning unit uses a generative AI to ask necessary questions based on the input received by the reception unit. Specifically, the generative AI uses natural language processing technology to analyze the user's input and generate appropriate questions. For example, if a user inputs "I want a stylish lamp that would suit my living room," the generative AI understands this and generates a specific question such as "What kind of design do you prefer?" It can also ask questions about important factors in product selection, such as the user's budget and color preferences. For example, it can generate questions such as "What is your budget?" or "What colors do you prefer?" This allows the questioning unit to concretize the user's vague needs and collect more detailed information. Furthermore, the questioning unit can dynamically generate subsequent questions based on the user's answers. For example, if a user answers "I prefer modern designs," the generative AI can use this information to ask additional questions such as "Specifically, what kind of modern designs do you prefer?" This allows the questioning unit to gain a deeper understanding of the user's needs and collect information to suggest the most suitable products. The questioning unit can also analyze the user's answers in real time and adjust the content and order of questions as needed. For example, if a user does not answer a question about their budget, the generating AI can prioritize other questions. This allows the questioning unit to respond flexibly to the user's needs and efficiently gather information.

[0032] The filtering unit uses a generative AI to narrow down products based on the information obtained from the questioning unit. Specifically, the generative AI analyzes the user's answers and compares them with product information in the database to select the most suitable product. For example, if the user answers, "I prefer modern designs," the generative AI searches the database for lamps with modern designs and further narrows down the selection to products that match the criteria. If the user answers, "My budget is under 10,000 yen," the generative AI can narrow down the selection to lamps under 10,000 yen. Furthermore, if the user answers, "I prefer white," the generative AI can narrow down the selection to white lamps. In this way, the filtering unit can efficiently narrow down products based on the user's specific needs. Moreover, the filtering unit can combine multiple conditions to narrow down products. For example, if the user answers, "I want a modern design, my budget is under 10,000 yen, and I prefer white," the generative AI searches the database for products that meet all of these conditions and narrows down the selection to the most suitable product. In addition, the filtering unit can provide more personalized product suggestions by considering the user's past search and purchase history. For example, the system analyzes the design and color trends of products purchased in the past and suggests new products based on that analysis. This allows the filtering function to suggest products that are best suited to the user's preferences and needs. Furthermore, the filtering function can perform filtering based on real-time updated product information, reflecting the latest inventory status and price information. This ensures that users are always provided with the latest information and can be supported in choosing the best product.

[0033] The suggestion department uses generative AI to propose products narrowed down by the filtering department. Specifically, the generative AI selects the most suitable products based on the user's needs and preferences and generates suggestions. For example, it might suggest to the user, "How about this modern-designed lamp?" Depending on the user's budget and color preferences, it can also suggest, "How about this lamp under 10,000 yen?" or "How about this white lamp?" This allows the suggestion department to propose the most suitable products based on the user's specific needs. Furthermore, the suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, if a user provides feedback that they "don't like" a suggested product, the generative AI adjusts the next suggestion based on that information. The suggestion department can also provide more personalized suggestions by considering the user's past purchase and search history. For example, it can analyze the design and color trends of products purchased in the past and propose new products based on that. This allows the suggestion department to propose products that are best suited to the user's preferences and needs. In addition, the suggestion department can provide suggestions that reflect the latest inventory status and price information based on product information that is updated in real time. This allows us to always provide users with the latest information and support them in choosing the optimal product. Furthermore, the recommendation department has a function to clearly explain product features and benefits to increase user purchasing intent. For example, by providing information such as, "This lamp is energy-efficient and has a long lifespan," it makes it easier for users to choose a product. In this way, the recommendation department can suggest the most suitable product to users and increase their purchasing intent.

[0034] The voice reception unit can accept voice input. For example, the voice reception unit can accept voice input from a user using a microphone. The voice reception unit can also accept voice input using the voice recognition function of a smartphone. For example, the voice reception unit can accept a user inputting "I want a stylish lamp that would suit my living room" using the voice recognition function of their smartphone. This improves user convenience by supporting voice input. Some or all of the above processing in the voice reception unit may be performed using AI, for example, or without AI. For example, the voice reception unit can input the user's voice data into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0035] The image reception unit can accept photographs and illustrations. For example, the image reception unit can accept user uploads of JPEG images. It can also accept user uploads of PNG images. Furthermore, the image reception unit can accept user uploads of hand-drawn illustrations. For example, the image reception unit can accept a user uploading a photo of their living room taken with their smartphone, and then suggest products based on that photo. This allows for a more intuitive search experience by supporting image input. Some or all of the processing described above in the image reception unit may be performed using AI, for example, or not. For example, the image reception unit can input the user-uploaded image data into a generating AI, and have the generating AI generate product suggestions from the image data.

[0036] The learning unit can learn from the conversation history. For example, the learning unit can save the user's past conversation history as a text log. The learning unit can also save the user's past conversation history as an audio recording. Furthermore, based on the user's past conversation history, the learning unit can make suggestions that reflect the user's preferences and needs in subsequent searches. For example, the learning unit's generative AI learns the user's conversation history and makes suggestions that reflect the user's preferences and needs in subsequent searches. In this way, learning from the conversation history makes it possible to make suggestions that reflect the user's preferences and needs in subsequent searches. Some or all of the above processing in the learning unit is performed using the generative AI. For example, the learning unit can input the user's conversation history into the generative AI and have the generative AI perform the learning of the conversation history.

[0037] The questioning unit can ask necessary questions based on user input using generative AI. For example, if the user inputs "I want a stylish lamp that would suit my living room," the questioning unit will ask, "What kind of design do you prefer?" The questioning unit can also ask, "What is your budget?" Furthermore, the questioning unit can ask, "What kind of color do you prefer?" For example, the generative AI in the questioning unit asks, "What kind of design do you prefer?" based on the user's input. This makes it possible to ask questions that clarify the user's vague needs by using generative AI. Some or all of the above processing in the questioning unit is performed using generative AI. For example, the questioning unit can input user input data into the generative AI and have the generative AI generate the necessary questions.

[0038] The filtering unit can use generative AI to narrow down the products that best suit the user's requirements. For example, if the user answers, "I prefer modern designs," the filtering unit will filter for lamps with modern designs. Similarly, if the user answers, "My budget is under 10,000 yen," the filtering unit can filter for lamps under 10,000 yen. Furthermore, if the user answers, "I prefer white," the filtering unit can filter for white lamps. For example, the filtering unit uses generative AI to filter for lamps with modern designs based on the user's answers. This allows for efficient filtering of products that best suit the user's requirements by using generative AI. Some or all of the above processing in the filtering unit is performed using generative AI. For example, the filtering unit can input user response data into the generative AI and have the generative AI perform the product filtering process.

[0039] The suggestion department can propose products that have been narrowed down using generative AI. For example, the suggestion department might suggest to the user, "How about this modernly designed lamp?" It could also suggest, "How about this lamp under 10,000 yen?" Furthermore, it could suggest, "How about this white lamp?" For example, the generative AI in the suggestion department might suggest to the user, "How about this modernly designed lamp?" In this way, by using generative AI, it is possible to propose the most suitable product to the user. Some or all of the above processing in the suggestion department is performed using generative AI. For example, the suggestion department can input narrowed-down product data into the generative AI and have the generative AI execute the product proposal process.

[0040] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception desk can suggest relevant input methods by referring to content the user has entered in the past. For example, the reception desk prioritizes suggesting input methods that the user has frequently used in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI select the optimal reception method.

[0041] The reception unit can filter input based on the user's current areas of interest. For example, the reception unit can prioritize input based on product categories the user has recently searched for. The reception unit can also filter input based on topics the user has shown interest in. Furthermore, the reception unit can analyze the user's social media activity and prioritize input related to their areas of interest. For example, the reception unit can prioritize input based on product categories the user has recently searched for. This allows the reception unit to prioritize input that is highly relevant by filtering based on the user's current areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's areas of interest data into a generating AI and have the generating AI perform the filtering process.

[0042] The reception unit can prioritize accepting highly relevant inputs by considering the user's geographical location information. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to products and services in that region. Furthermore, if the user is traveling, the reception unit can prioritize accepting inputs related to their travel destination. Additionally, if the user is at home, the reception unit can prioritize accepting inputs related to information about their home area. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to products and services in that region. This allows for the prioritization of highly relevant inputs by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant inputs.

[0043] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can prioritize accepting inputs related to products or services that the user has recently mentioned on social media. The reception unit can also accept relevant inputs based on the user's interests on social media. Furthermore, the reception unit can prioritize accepting inputs related to brands or topics that the user follows on social media. For example, the reception unit can prioritize accepting inputs related to products or services that the user has recently mentioned on social media. This allows the reception unit to prioritize accepting relevant inputs by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI select relevant inputs.

[0044] The questioning unit can adjust the level of detail of a question based on the user's importance. For example, if the user is looking for an important product, the questioning unit will ask detailed questions. Conversely, if the user is looking for a general product, the questioning unit can ask concise questions. Furthermore, if the user is particular about a specific brand, the questioning unit can ask detailed questions related to that brand. For example, if the questioning unit is looking for an important product, it will ask detailed questions. By adjusting the level of detail of questions based on the user's importance, more appropriate questions can be asked. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the questions.

[0045] The questioning unit can apply different questioning algorithms depending on the user's category when a question is asked. For example, if the user is looking for home appliances, the questioning unit will apply a questioning algorithm specifically for home appliances. Similarly, if the user is looking for fashion items, the questioning unit can apply a questioning algorithm specifically for fashion. Furthermore, if the user is looking for food, the questioning unit can apply a questioning algorithm specifically for food. For example, if the user is looking for home appliances, the questioning unit will apply a questioning algorithm specifically for home appliances. This allows for more appropriate questions to be asked by applying different questioning algorithms depending on the user's category. Some or all of the above processing in the questioning unit may be performed using AI, or not. For example, the questioning unit can input user category data into a generating AI and have the generating AI perform the application of the questioning algorithm.

[0046] The questioning unit can determine the priority of questions based on the timing of user input. For example, the questioning unit can prioritize relevant questions based on the user's most recent input. It can also determine the priority of questions based on the user's input during a specific time period. Furthermore, the questioning unit can prioritize relevant questions by referring to the user's past input. For example, the questioning unit can prioritize relevant questions based on the user's most recent input. This allows for more appropriate questions to be asked by determining the priority of questions based on the timing of user input. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input user input timing data into a generating AI and have the generating AI perform the determination of question priorities.

[0047] The questioning unit can adjust the order of questions based on the user's relevance. For example, if the user has shown interest in a particular product category, the questioning unit will prioritize questions related to that category. Similarly, if the user is interested in a particular brand, the questioning unit can prioritize questions related to that brand. Furthermore, if the user is looking for products in a specific price range, the questioning unit can prioritize questions related to that price range. By adjusting the order of questions based on user relevance, more appropriate questions can be asked. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input user relevance data into a generating AI and have the generating AI adjust the order of questions.

[0048] The filtering unit can improve the accuracy of filtering by considering user relationships during the filtering process. For example, the filtering unit can filter by considering the relevance of products the user has previously purchased. It can also analyze the user's social media activity and filter related products. Furthermore, the filtering unit can filter related products by referring to the purchase history of the user's friends and family. For example, the filtering unit can filter by considering the relevance of products the user has previously purchased. This improves the accuracy of filtering by considering user relationships. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input user relationship data into a generating AI and have the generating AI perform the filtering accuracy improvement.

[0049] The filtering unit can filter products by considering user attribute information. For example, the filtering unit can filter related products based on the user's age and gender. It can also filter related products based on the user's place of residence. Furthermore, it can filter related products based on the user's occupation and hobbies. For example, the filtering unit can filter related products based on the user's age and gender. This allows for the filtering of more appropriate products by considering user attribute information. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input user attribute information data into a generating AI and have the generating AI perform the filtering process.

[0050] The filtering unit can filter results while considering the user's geographical distribution. For example, if a user is in a specific region, the filtering unit will prioritize filtering for products related to that region. Furthermore, if a user is traveling, the filtering unit can prioritize filtering for products related to their travel destination. Additionally, if a user is at home, the filtering unit can prioritize filtering for products related to their home area. This allows for the filtering of more appropriate products by considering the user's geographical distribution. Some or all of the above processing in the filtering unit may be performed using AI, or without AI. For example, the filtering unit can input the user's geographical distribution data into a generating AI and have the generating AI perform the filtering process.

[0051] The filtering unit can improve the accuracy of its filtering by referring to the user's relevant literature during the filtering process. For example, the filtering unit can filter related products based on relevant literature the user has read in the past. Furthermore, the filtering unit can improve the accuracy of its filtering by referring to literature related to the user's interests. In addition, the filtering unit can filter related products based on literature the user has shared on social media. For example, the filtering unit can filter related products based on relevant literature the user has read in the past. This allows for improved filtering accuracy by referring to the user's relevant literature. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input the user's relevant literature data into a generating AI and have the generating AI perform the filtering accuracy improvement.

[0052] The suggestion unit can adjust the level of detail in its suggestions based on the importance of the products. For example, if the user is looking for an important product, the suggestion unit will provide a detailed suggestion. It can also provide a concise suggestion if the user is looking for a general product. Furthermore, if the user is particular about a specific brand, the suggestion unit can provide detailed suggestions related to that brand. For example, if the suggestion unit is looking for an important product, it will provide a detailed suggestion. By adjusting the level of detail in suggestions based on the importance of the products, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input user importance data into a generating AI and have the generating AI adjust the level of detail in the suggestions.

[0053] The suggestion unit can apply different suggestion algorithms depending on the product category when making suggestions. For example, if the user is looking for home appliances, the suggestion unit will apply a suggestion algorithm specialized for home appliances. Similarly, if the user is looking for fashion items, the suggestion unit can apply a suggestion algorithm specialized for fashion. Furthermore, if the user is looking for food, the suggestion unit can apply a suggestion algorithm specialized for food. For example, if the user is looking for home appliances, the suggestion unit will apply a suggestion algorithm specialized for home appliances. By applying different suggestion algorithms depending on the product category, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, or not. For example, the suggestion unit can input the user's category data into a generating AI and have the generating AI execute the application of the suggestion algorithm.

[0054] The proposal department can prioritize proposals based on the timing of product submission. For example, the proposal department can prioritize relevant proposals based on products the user has recently searched for. It can also prioritize proposals based on products the user has searched for during a specific time period. Furthermore, the proposal department can prioritize relevant proposals by referring to products the user has searched for in the past. For example, the proposal department can prioritize relevant proposals based on products the user has recently searched for. This allows for more appropriate proposals to be made by prioritizing proposals based on the timing of product submission. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input user submission timing data into a generating AI and have the generating AI determine the priority of proposals.

[0055] The suggestion unit can adjust the order of suggestions based on the relevance of the products. For example, if a user has shown interest in a particular product category, the suggestion unit will prioritize suggestions related to that category. Similarly, if a user is interested in a particular brand, the suggestion unit can prioritize suggestions related to that brand. Furthermore, if a user is looking for products in a specific price range, the suggestion unit can prioritize suggestions related to that price range. For example, if a user has shown interest in a particular product category, the suggestion unit will prioritize suggestions related to that category. By adjusting the order of suggestions based on the relevance of the products, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, or not. For example, the suggestion unit can input user relevance data into a generating AI and have the generating AI adjust the order of suggestions.

[0056] The voice reception unit can select the optimal reception method by referring to the user's past voice input history when voice input is received. For example, the voice reception unit may prioritize suggesting voice input methods that the user has frequently used in the past. The voice reception unit can also predict and suggest voice input methods to be used during specific time periods based on the user's past voice input history. Furthermore, the voice reception unit can suggest relevant voice input methods by referring to content that the user has previously entered. For example, the voice reception unit may prioritize suggesting voice input methods that the user has frequently used in the past. This allows the optimal voice input method to be selected by referring to the user's past voice input history. Some or all of the above processing in the voice reception unit may be performed using AI, for example, or without AI. For example, the voice reception unit can input the user's past voice input history data into a generating AI and have the generating AI select the optimal reception method.

[0057] The voice reception unit can select the optimal reception method when a voice input is received, taking into account the user's device information. For example, if the user is using a smartphone, the voice reception unit can suggest a voice input method optimized for smartphones. Furthermore, if the user is using a tablet, the voice reception unit can suggest a voice input method optimized for tablets. In addition, if the user is using a smartwatch, the voice reception unit can suggest a voice input method optimized for smartwatches. For example, if the user is using a smartphone, the voice reception unit can suggest a voice input method optimized for smartphones. This allows the optimal voice input method to be selected by considering the user's device information. Some or all of the above processing in the voice reception unit may be performed using AI, or without AI. For example, the voice reception unit can input user device information data into a generating AI and have the generating AI select the optimal reception method.

[0058] The image reception unit can select the optimal reception method by referring to the user's past image input history when an image is input. For example, the image reception unit may prioritize suggesting image input methods that the user has frequently used in the past. The image reception unit can also predict and suggest image input methods to be used during specific time periods based on the user's past image input history. Furthermore, the image reception unit can suggest relevant image input methods by referring to content that the user has previously entered. For example, the image reception unit may prioritize suggesting image input methods that the user has frequently used in the past. This allows the optimal image input method to be selected by referring to the user's past image input history. Some or all of the above processing in the image reception unit may be performed using AI, for example, or without AI. For example, the image reception unit can input the user's past image input history data into a generating AI and have the generating AI select the optimal reception method.

[0059] The image reception unit can select the optimal reception method when an image is input, taking into account the user's device information. For example, if the user is using a smartphone, the image reception unit can suggest an image input method optimized for smartphones. Furthermore, if the user is using a tablet, the image reception unit can suggest an image input method optimized for tablets. In addition, if the user is using a desktop, the image reception unit can suggest an image input method optimized for desktops. For example, if the user is using a smartphone, the image reception unit can suggest an image input method optimized for smartphones. This allows the optimal image input method to be selected by considering the user's device information. Some or all of the above processing in the image reception unit may be performed using AI, or without AI. For example, the image reception unit can input user device information data into a generating AI and have the generating AI select the optimal reception method.

[0060] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also extract specific patterns from past learning data and optimize the learning algorithm. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. For example, the learning unit can select the optimal learning algorithm based on past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0061] The learning unit can weight the training data based on the timing of user input during training. For example, the learning unit can weight the training data based on data recently entered by the user. It can also weight the training data based on data entered by the user during a specific time period. Furthermore, the learning unit can weight the training data by referring to data entered by the user in the past. For example, the learning unit can weight the training data based on data recently entered by the user. This allows for more appropriate training by weighting the training data based on the timing of user input. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user input timing data into a generating AI and have the generating AI perform the training data weighting.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The product search system can also include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit collects and analyzes data on products and services that the user has purchased in the past. For example, it can understand the user's purchasing trends based on information such as the category, price range, and brand of products the user has purchased in the past. This allows the system to suggest products similar to or related to products the user has purchased in the past. For example, if the user has purchased home appliances in the past, the system can suggest new products in the same category or related accessories. Also, if the user prefers a particular brand, the system can suggest new products from that brand or other products from the same brand. Furthermore, the purchase history analysis unit can analyze the user's purchase frequency and timing and suggest products at the appropriate time. For example, if a user regularly purchases a product, the system can predict when that product will need to be repurchased and suggest it as a reminder. This makes it possible to provide more personalized product suggestions by utilizing the user's purchase history.

[0064] The product search system can also include a social media analysis unit that analyzes users' social media activity. This unit analyzes information users share on social media, accounts they follow, and posts they like. For example, if a user mentions a specific brand or product on social media, the system can collect information related to that brand or product and incorporate it into its recommendations. This enables product suggestions based on user interests. For instance, if a user shows interest in fashion items on social media, the system can suggest the latest fashion items and products that are in line with current trends. It can also suggest products recommended by influencers the user follows. Furthermore, the social media analysis unit can analyze the user's social media activity patterns and suggest products at the optimal time. For example, if a user tends to use social media at night, the system can tailor product suggestions to that time. This allows for more effective product suggestions by leveraging users' social media activity.

[0065] The product search system can also include a health monitoring unit that monitors the user's health status. This unit collects and analyzes health data such as the user's heart rate, blood pressure, and sleep patterns. For example, if the user is using a smartwatch, health data can be obtained from that device. This allows the system to make product recommendations based on the user's health status. For instance, if the user is stressed, the system can suggest products with relaxing effects or products that help relieve stress. Similarly, if the user is not getting enough exercise, fitness-related products can be suggested. Furthermore, based on the user's sleep patterns, the system can suggest products that support comfortable sleep. For example, if the user is sleep-deprived, sleep aids or products with relaxing effects can be suggested. This enables product recommendations that take the user's health status into consideration.

[0066] The product search system may also include a lifestyle analysis unit that analyzes the user's lifestyle. The lifestyle analysis unit collects and analyzes data such as the user's lifestyle habits, hobbies, and interests. For example, if the user is interested in fitness, it can suggest fitness-related products. If the user enjoys cooking, it can also suggest kitchenware and recipe books. Furthermore, if the user likes to travel, it can suggest travel-related products and services. For example, if the user is interested in fitness, it can suggest fitness-related products. This enables product suggestions based on the user's lifestyle. Some or all of the above processing in the lifestyle analysis unit may be performed using AI, for example, or without AI. For example, the lifestyle analysis unit can input the user's lifestyle data into a generating AI and have the generating AI perform the lifestyle analysis.

[0067] The product search system may further include a geographic information suggestion unit that makes product suggestions while considering the user's geographic location. The geographic information suggestion unit suggests relevant products and services based on the user's current location and past travel history. For example, if the user is in a specific region, it can suggest products and services related to that region. Also, if the user is traveling, it can suggest products and services related to their travel destination. Furthermore, if the user is at home, it can suggest products and services related to information around their home. For example, if the user is in a specific region, it can suggest products and services related to that region. This makes it possible to make product suggestions that take the user's geographic location into account. Some or all of the above processing in the geographic information suggestion unit may be performed using AI, for example, or without AI. For example, the geographic information suggestion unit can input the user's geographic location data into a generating AI and have the generating AI execute suggestions for relevant products and services.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The reception desk accepts user input. User input includes text input, voice input, and image input. For example, the desk accepts users to type "I want a stylish lamp that would suit my living room" in text, to voice the same message, or to upload a photo of their living room taken with their smartphone. Step 2: The questioning unit uses a generation AI to ask necessary questions based on the input received by the reception unit. For example, if a user inputs "I want a stylish lamp that would suit my living room," the unit will ask questions such as "What kind of design do you prefer?", "What is your budget?", and "What color do you prefer?". Step 3: The filtering section uses a generation AI to narrow down the products based on the information obtained from the question section. For example, if the user answers "I prefer modern designs," the filter will narrow down to lamps with modern designs; if they answer "My budget is under 10,000 yen," the filter will narrow down to lamps under 10,000 yen; and if they answer "I prefer white," the filter will narrow down to white lamps. Step 4: The suggestion department uses generation AI to propose products that have been narrowed down by the filtering department. For example, it might suggest to the user, "How about this modern design lamp?", "How about this lamp under 10,000 yen?", or "How about this white lamp?".

[0070] (Example of form 2) The product search system according to an embodiment of the present invention is a system that provides a new means for users to search for products on e-commerce sites by utilizing generative AI. The product search system solves the problem that conventional keyword searches have difficulty in eliciting users' vague needs and finding the optimal product. In the present invention, by narrowing down products in a dialogue format, the user's vague image becomes concrete, making it easier to find the optimal product. First, the user inputs a vague image in a dialogue format, such as "I want a product that is like XX." For example, an input such as "I want a stylish lamp that will suit my living room" is possible. This input is analyzed by the generative AI. Next, the generative AI asks necessary questions in response to the user's input. For example, the generative AI may ask questions such as "What kind of design do you prefer?" or "What is your budget?" This narrows down the products that are most suitable for the user's requirements. Furthermore, by making not only text but also voice dialogue, photos, and explanatory illustrations drawn by the user available, a more intuitive search experience is realized. For example, the user can upload a photo taken with their smartphone, and the generative AI can suggest products based on that photo. This system allows users who are not particular about brands, those with vague needs, and even those unfamiliar with internet searches to easily find the products they are looking for, reducing stress. For example, if a user enters "I want an AI," the generating AI can suggest "smart speaker." Furthermore, the generating AI learns the user's conversation history and can make suggestions that reflect the user's preferences and needs in subsequent searches. This allows users to find products more efficiently. In this way, a conversational search method utilizing generating AI can concretize users' vague needs and make it easier for them to find the most suitable products. As a result, the product search system can concretize users' vague needs and make it easier for them to find the most suitable products.

[0071] The product search system according to this embodiment comprises a reception unit, a questioning unit, a filtering unit, and a suggestion unit. The reception unit receives user input. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception unit can receive text input from the user such as "I want a stylish lamp that would suit my living room." The reception unit can also receive voice input from the user such as "I want a stylish lamp that would suit my living room." Furthermore, the reception unit can also receive uploads of photos taken by the user with a smartphone. For example, the reception unit can receive a photo of the living room taken by the user with a smartphone and suggest products based on that photo. The questioning unit uses a generation AI to ask necessary questions based on the input received by the reception unit. For example, if the user inputs "I want a stylish lamp that would suit my living room," the questioning unit might ask, "What kind of design do you prefer?" The questioning unit may also ask, "What is your budget?" Furthermore, the questioning unit may also ask, "What kind of color do you prefer?" For example, the questioning unit uses a generating AI to ask the user, "What kind of design do you prefer?" based on the user's input. The filtering unit uses the generating AI to narrow down the products based on the information obtained by the questioning unit. For example, if the user answers, "I prefer modern designs," the filtering unit will filter for lamps with modern designs. The filtering unit can also filter for lamps under 10,000 yen if the user answers, "My budget is under 10,000 yen." Furthermore, if the user answers, "I prefer white," the filtering unit can filter for white lamps. For example, the filtering unit uses a generating AI to narrow down lamps with modern designs based on the user's answers. The suggestion unit uses a generating AI to suggest products narrowed down by the filtering unit. For example, the suggestion unit might suggest to the user, "How about this modern design lamp?" The suggestion unit could also suggest, "How about this lamp under 10,000 yen?" Furthermore, the suggestion unit could also suggest, "How about this white lamp?"For example, the suggestion section uses a generation AI to suggest to the user, "How about this modernly designed lamp?" This allows the product search system, according to the embodiment, to concretize the user's vague needs and make it easier for them to find the optimal product.

[0072] The reception desk receives user input. User input includes, but is not limited to, text input, voice input, and image input. Specifically, in the case of text input, users can freely input the characteristics and uses of the desired product using a keyboard or touchscreen. For example, they can input a specific request such as, "I want a stylish lamp that would suit my living room." In the case of voice input, users can communicate their requests by voice through a microphone, and the content is converted into text using voice recognition technology. For example, they can input by voice, "I want a stylish lamp that would suit my living room." In the case of image input, users can upload photos taken with a smartphone or camera. For example, they can upload a photo of their living room, and products can be suggested based on that photo. By supporting these diverse input methods, the reception desk allows users to communicate their requests in the way that is easiest for them. The reception desk also plays a role in appropriately processing the entered data and passing it on to the next step, the questioning desk. This allows for an accurate understanding of user needs and improves the accuracy and efficiency of the entire system. Furthermore, the reception desk also has a function to preprocess the input data and remove noise and input errors. For example, in the case of voice input, it removes background noise and improves the accuracy of voice recognition. Furthermore, in the case of image input, the image resolution is adjusted and the necessary parts are cropped to ensure smoother subsequent processing. This allows the reception unit to efficiently process diverse user inputs and improve the overall system performance.

[0073] The questioning unit uses a generative AI to ask necessary questions based on the input received by the reception unit. Specifically, the generative AI uses natural language processing technology to analyze the user's input and generate appropriate questions. For example, if a user inputs "I want a stylish lamp that would suit my living room," the generative AI understands this and generates a specific question such as "What kind of design do you prefer?" It can also ask questions about important factors in product selection, such as the user's budget and color preferences. For example, it can generate questions such as "What is your budget?" or "What colors do you prefer?" This allows the questioning unit to concretize the user's vague needs and collect more detailed information. Furthermore, the questioning unit can dynamically generate subsequent questions based on the user's answers. For example, if a user answers "I prefer modern designs," the generative AI can use this information to ask additional questions such as "Specifically, what kind of modern designs do you prefer?" This allows the questioning unit to gain a deeper understanding of the user's needs and collect information to suggest the most suitable products. The questioning unit can also analyze the user's answers in real time and adjust the content and order of questions as needed. For example, if a user does not answer a question about their budget, the generating AI can prioritize other questions. This allows the questioning unit to respond flexibly to the user's needs and efficiently gather information.

[0074] The filtering unit uses a generative AI to narrow down products based on the information obtained from the questioning unit. Specifically, the generative AI analyzes the user's answers and compares them with product information in the database to select the most suitable product. For example, if the user answers, "I prefer modern designs," the generative AI searches the database for lamps with modern designs and further narrows down the selection to products that match the criteria. If the user answers, "My budget is under 10,000 yen," the generative AI can narrow down the selection to lamps under 10,000 yen. Furthermore, if the user answers, "I prefer white," the generative AI can narrow down the selection to white lamps. In this way, the filtering unit can efficiently narrow down products based on the user's specific needs. Moreover, the filtering unit can combine multiple conditions to narrow down products. For example, if the user answers, "I want a modern design, my budget is under 10,000 yen, and I prefer white," the generative AI searches the database for products that meet all of these conditions and narrows down the selection to the most suitable product. In addition, the filtering unit can provide more personalized product suggestions by considering the user's past search and purchase history. For example, the system analyzes the design and color trends of products purchased in the past and suggests new products based on that analysis. This allows the filtering function to suggest products that are best suited to the user's preferences and needs. Furthermore, the filtering function can perform filtering based on real-time updated product information, reflecting the latest inventory status and price information. This ensures that users are always provided with the latest information and can be supported in choosing the best product.

[0075] The suggestion department uses generative AI to propose products narrowed down by the filtering department. Specifically, the generative AI selects the most suitable products based on the user's needs and preferences and generates suggestions. For example, it might suggest to the user, "How about this modern-designed lamp?" Depending on the user's budget and color preferences, it can also suggest, "How about this lamp under 10,000 yen?" or "How about this white lamp?" This allows the suggestion department to propose the most suitable products based on the user's specific needs. Furthermore, the suggestion department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. For example, if a user provides feedback that they "don't like" a suggested product, the generative AI adjusts the next suggestion based on that information. The suggestion department can also provide more personalized suggestions by considering the user's past purchase and search history. For example, it can analyze the design and color trends of products purchased in the past and propose new products based on that. This allows the suggestion department to propose products that are best suited to the user's preferences and needs. In addition, the suggestion department can provide suggestions that reflect the latest inventory status and price information based on product information that is updated in real time. This allows us to always provide users with the latest information and support them in choosing the optimal product. Furthermore, the recommendation department has a function to clearly explain product features and benefits to increase user purchasing intent. For example, by providing information such as, "This lamp is energy-efficient and has a long lifespan," it makes it easier for users to choose a product. In this way, the recommendation department can suggest the most suitable product to users and increase their purchasing intent.

[0076] The voice reception unit can accept voice input. For example, the voice reception unit can accept voice input from a user using a microphone. The voice reception unit can also accept voice input using the voice recognition function of a smartphone. For example, the voice reception unit can accept a user inputting "I want a stylish lamp that would suit my living room" using the voice recognition function of their smartphone. This improves user convenience by supporting voice input. Some or all of the above processing in the voice reception unit may be performed using AI, for example, or without AI. For example, the voice reception unit can input the user's voice data into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0077] The image reception unit can accept photographs and illustrations. For example, the image reception unit can accept user uploads of JPEG images. It can also accept user uploads of PNG images. Furthermore, the image reception unit can accept user uploads of hand-drawn illustrations. For example, the image reception unit can accept a user uploading a photo of their living room taken with their smartphone, and then suggest products based on that photo. This allows for a more intuitive search experience by supporting image input. Some or all of the processing described above in the image reception unit may be performed using AI, for example, or not. For example, the image reception unit can input the user-uploaded image data into a generating AI, and have the generating AI generate product suggestions from the image data.

[0078] The learning unit can learn from the conversation history. For example, the learning unit can save the user's past conversation history as a text log. The learning unit can also save the user's past conversation history as an audio recording. Furthermore, based on the user's past conversation history, the learning unit can make suggestions that reflect the user's preferences and needs in subsequent searches. For example, the learning unit's generative AI learns the user's conversation history and makes suggestions that reflect the user's preferences and needs in subsequent searches. In this way, learning from the conversation history makes it possible to make suggestions that reflect the user's preferences and needs in subsequent searches. Some or all of the above processing in the learning unit is performed using the generative AI. For example, the learning unit can input the user's conversation history into the generative AI and have the generative AI perform the learning of the conversation history.

[0079] The questioning unit can ask necessary questions based on user input using generative AI. For example, if the user inputs "I want a stylish lamp that would suit my living room," the questioning unit will ask, "What kind of design do you prefer?" The questioning unit can also ask, "What is your budget?" Furthermore, the questioning unit can ask, "What kind of color do you prefer?" For example, the generative AI in the questioning unit asks, "What kind of design do you prefer?" based on the user's input. This makes it possible to ask questions that clarify the user's vague needs by using generative AI. Some or all of the above processing in the questioning unit is performed using generative AI. For example, the questioning unit can input user input data into the generative AI and have the generative AI generate the necessary questions.

[0080] The filtering unit can use generative AI to narrow down the products that best suit the user's requirements. For example, if the user answers, "I prefer modern designs," the filtering unit will filter for lamps with modern designs. Similarly, if the user answers, "My budget is under 10,000 yen," the filtering unit can filter for lamps under 10,000 yen. Furthermore, if the user answers, "I prefer white," the filtering unit can filter for white lamps. For example, the filtering unit uses generative AI to filter for lamps with modern designs based on the user's answers. This allows for efficient filtering of products that best suit the user's requirements by using generative AI. Some or all of the above processing in the filtering unit is performed using generative AI. For example, the filtering unit can input user response data into the generative AI and have the generative AI perform the product filtering process.

[0081] The suggestion department can propose products that have been narrowed down using generative AI. For example, the suggestion department might suggest to the user, "How about this modernly designed lamp?" It could also suggest, "How about this lamp under 10,000 yen?" Furthermore, it could suggest, "How about this white lamp?" For example, the generative AI in the suggestion department might suggest to the user, "How about this modernly designed lamp?" In this way, by using generative AI, it is possible to propose the most suitable product to the user. Some or all of the above processing in the suggestion department is performed using generative AI. For example, the suggestion department can input narrowed-down product data into the generative AI and have the generative AI execute the product proposal process.

[0082] The reception unit can estimate the user's emotions and adjust the timing of input acceptance based on the estimated emotions. For example, if the user is stressed, the reception unit can delay the timing of input acceptance to provide time to relax. Alternatively, if the user is excited, the reception unit can quickly accept input to facilitate a smooth conversation. Furthermore, if the user is tired, the reception unit can adjust the timing of input acceptance and start with simple questions. For example, if the reception unit is stressed, it can delay the timing of input acceptance to provide time to relax. By adjusting the timing of input acceptance according to the user's emotions, input can be accepted at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0083] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception desk can suggest relevant input methods by referring to content the user has entered in the past. For example, the reception desk prioritizes suggesting input methods that the user has frequently used in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI select the optimal reception method.

[0084] The reception unit can filter input based on the user's current areas of interest. For example, the reception unit can prioritize input based on product categories the user has recently searched for. The reception unit can also filter input based on topics the user has shown interest in. Furthermore, the reception unit can analyze the user's social media activity and prioritize input related to their areas of interest. For example, the reception unit can prioritize input based on product categories the user has recently searched for. This allows the reception unit to prioritize input that is highly relevant by filtering based on the user's current areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's areas of interest data into a generating AI and have the generating AI perform the filtering process.

[0085] The reception desk can estimate the user's emotions and determine the priority of inputs to be received based on the estimated emotions. For example, if the user is nervous, the reception desk will prioritize important inputs. If the user is relaxed, the reception desk may also prioritize detailed inputs. Furthermore, if the user is in a hurry, the reception desk may prioritize inputs that require quick processing. For example, if the user is nervous, the reception desk will prioritize important inputs. This allows for the prioritization of more appropriate inputs by determining input priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0086] The reception unit can prioritize accepting highly relevant inputs by considering the user's geographical location information. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to products and services in that region. Furthermore, if the user is traveling, the reception unit can prioritize accepting inputs related to their travel destination. Additionally, if the user is at home, the reception unit can prioritize accepting inputs related to information about their home area. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to products and services in that region. This allows for the prioritization of highly relevant inputs by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant inputs.

[0087] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can prioritize accepting inputs related to products or services that the user has recently mentioned on social media. The reception unit can also accept relevant inputs based on the user's interests on social media. Furthermore, the reception unit can prioritize accepting inputs related to brands or topics that the user follows on social media. For example, the reception unit can prioritize accepting inputs related to products or services that the user has recently mentioned on social media. This allows the reception unit to prioritize accepting relevant inputs by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI select relevant inputs.

[0088] The questioning unit can estimate the user's emotions and adjust the wording of the questions based on the estimated emotions. For example, if the user is relaxed, the questioning unit will ask questions in a friendly manner. If the user is tense, the questioning unit can also ask questions in a simple and clear manner. Furthermore, if the user is in a hurry, the questioning unit can ask short questions that can be answered quickly. For example, if the questioning unit is relaxed, the questioning unit will ask questions in a friendly manner. In this way, by adjusting the wording of questions according to the user's emotions, more appropriate questions can be asked. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0089] The questioning unit can adjust the level of detail of a question based on the user's importance. For example, if the user is looking for an important product, the questioning unit will ask detailed questions. Conversely, if the user is looking for a general product, the questioning unit can ask concise questions. Furthermore, if the user is particular about a specific brand, the questioning unit can ask detailed questions related to that brand. For example, if the questioning unit is looking for an important product, it will ask detailed questions. By adjusting the level of detail of questions based on the user's importance, more appropriate questions can be asked. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of the questions.

[0090] The questioning unit can apply different questioning algorithms depending on the user's category when a question is asked. For example, if the user is looking for home appliances, the questioning unit will apply a questioning algorithm specifically for home appliances. Similarly, if the user is looking for fashion items, the questioning unit can apply a questioning algorithm specifically for fashion. Furthermore, if the user is looking for food, the questioning unit can apply a questioning algorithm specifically for food. For example, if the user is looking for home appliances, the questioning unit will apply a questioning algorithm specifically for home appliances. This allows for more appropriate questions to be asked by applying different questioning algorithms depending on the user's category. Some or all of the above processing in the questioning unit may be performed using AI, or not. For example, the questioning unit can input user category data into a generating AI and have the generating AI perform the application of the questioning algorithm.

[0091] The questioning unit can estimate the user's emotions and adjust the length of the questions based on the estimated emotions. For example, if the user is relaxed, the questioning unit will ask detailed questions. If the user is in a hurry, the questioning unit can ask short, to the point. Furthermore, if the user is excited, the questioning unit can ask visually stimulating questions. For example, if the questioning unit is relaxed, it will ask detailed questions. By adjusting the length of questions according to the user's emotions, more appropriate questions can be asked. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0092] The questioning unit can determine the priority of questions based on the timing of user input. For example, the questioning unit can prioritize relevant questions based on the user's most recent input. It can also determine the priority of questions based on the user's input during a specific time period. Furthermore, the questioning unit can prioritize relevant questions by referring to the user's past input. For example, the questioning unit can prioritize relevant questions based on the user's most recent input. This allows for more appropriate questions to be asked by determining the priority of questions based on the timing of user input. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input user input timing data into a generating AI and have the generating AI perform the determination of question priorities.

[0093] The questioning unit can adjust the order of questions based on the user's relevance. For example, if the user has shown interest in a particular product category, the questioning unit will prioritize questions related to that category. Similarly, if the user is interested in a particular brand, the questioning unit can prioritize questions related to that brand. Furthermore, if the user is looking for products in a specific price range, the questioning unit can prioritize questions related to that price range. By adjusting the order of questions based on user relevance, more appropriate questions can be asked. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input user relevance data into a generating AI and have the generating AI adjust the order of questions.

[0094] The filtering unit can estimate the user's emotions and adjust the filtering criteria based on the estimated emotions. For example, if the user is relaxed, the filtering unit can apply detailed filtering criteria. It can also apply concise filtering criteria if the user is in a hurry. Furthermore, if the user is excited, the filtering unit can apply visually stimulating filtering criteria. For example, if the user is relaxed, the filtering unit can apply detailed filtering criteria. This allows for filtering to more appropriate products by adjusting the filtering criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filtering unit may be performed using AI, or not. For example, the filtering unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0095] The filtering unit can improve the accuracy of filtering by considering user relationships during the filtering process. For example, the filtering unit can filter by considering the relevance of products the user has previously purchased. It can also analyze the user's social media activity and filter related products. Furthermore, the filtering unit can filter related products by referring to the purchase history of the user's friends and family. For example, the filtering unit can filter by considering the relevance of products the user has previously purchased. This improves the accuracy of filtering by considering user relationships. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input user relationship data into a generating AI and have the generating AI perform the filtering accuracy improvement.

[0096] The filtering unit can filter products by considering user attribute information. For example, the filtering unit can filter related products based on the user's age and gender. It can also filter related products based on the user's place of residence. Furthermore, it can filter related products based on the user's occupation and hobbies. For example, the filtering unit can filter related products based on the user's age and gender. This allows for the filtering of more appropriate products by considering user attribute information. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input user attribute information data into a generating AI and have the generating AI perform the filtering process.

[0097] The filtering unit can estimate the user's emotions and adjust the order in which the filtering results are displayed based on the estimated emotions. For example, if the user is relaxed, the filtering unit can display results in an order that includes detailed information. If the user is in a hurry, the filtering unit can also display results in an order that includes concise information. Furthermore, if the user is excited, the filtering unit can display results in a visually stimulating order. For example, if the user is relaxed, the filtering unit can display results in an order that includes detailed information. By adjusting the order in which the filtering results are displayed according to the user's emotions, more appropriate products can be displayed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filtering unit may be performed using AI, for example, or not using AI. For example, the filtering unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0098] The filtering unit can filter results while considering the user's geographical distribution. For example, if a user is in a specific region, the filtering unit will prioritize filtering for products related to that region. Furthermore, if a user is traveling, the filtering unit can prioritize filtering for products related to their travel destination. Additionally, if a user is at home, the filtering unit can prioritize filtering for products related to their home area. This allows for the filtering of more appropriate products by considering the user's geographical distribution. Some or all of the above processing in the filtering unit may be performed using AI, or without AI. For example, the filtering unit can input the user's geographical distribution data into a generating AI and have the generating AI perform the filtering process.

[0099] The filtering unit can improve the accuracy of its filtering by referring to the user's relevant literature during the filtering process. For example, the filtering unit can filter related products based on relevant literature the user has read in the past. Furthermore, the filtering unit can improve the accuracy of its filtering by referring to literature related to the user's interests. In addition, the filtering unit can filter related products based on literature the user has shared on social media. For example, the filtering unit can filter related products based on relevant literature the user has read in the past. This allows for improved filtering accuracy by referring to the user's relevant literature. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input the user's relevant literature data into a generating AI and have the generating AI perform the filtering accuracy improvement.

[0100] The suggestion unit can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is relaxed, the suggestion unit will present suggestions in a friendly manner. If the user is tense, the suggestion unit can present suggestions in a simple and clear manner. Furthermore, if the user is in a hurry, the suggestion unit can present short suggestions that can be quickly understood. For example, if the user is relaxed, the suggestion unit will present suggestions in a friendly manner. By adjusting the way suggestions are presented according to the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI, or not using AI. For example, the suggestion unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0101] The suggestion unit can adjust the level of detail in its suggestions based on the importance of the products. For example, if the user is looking for an important product, the suggestion unit will provide a detailed suggestion. It can also provide a concise suggestion if the user is looking for a general product. Furthermore, if the user is particular about a specific brand, the suggestion unit can provide detailed suggestions related to that brand. For example, if the suggestion unit is looking for an important product, it will provide a detailed suggestion. By adjusting the level of detail in suggestions based on the importance of the products, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input user importance data into a generating AI and have the generating AI adjust the level of detail in the suggestions.

[0102] The suggestion unit can apply different suggestion algorithms depending on the product category when making suggestions. For example, if the user is looking for home appliances, the suggestion unit will apply a suggestion algorithm specialized for home appliances. Similarly, if the user is looking for fashion items, the suggestion unit can apply a suggestion algorithm specialized for fashion. Furthermore, if the user is looking for food, the suggestion unit can apply a suggestion algorithm specialized for food. For example, if the user is looking for home appliances, the suggestion unit will apply a suggestion algorithm specialized for home appliances. By applying different suggestion algorithms depending on the product category, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, or not. For example, the suggestion unit can input the user's category data into a generating AI and have the generating AI execute the application of the suggestion algorithm.

[0103] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated emotions. For example, if the user is relaxed, the suggestion unit will provide detailed suggestions. If the user is in a hurry, the suggestion unit can provide short, concise suggestions. Furthermore, if the user is excited, the suggestion unit can provide visually stimulating suggestions. For example, if the user is relaxed, the suggestion unit will provide detailed suggestions. By adjusting the length of suggestions according to the user's emotions, more appropriate suggestions can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0104] The proposal department can prioritize proposals based on the timing of product submission. For example, the proposal department can prioritize relevant proposals based on products the user has recently searched for. It can also prioritize proposals based on products the user has searched for during a specific time period. Furthermore, the proposal department can prioritize relevant proposals by referring to products the user has searched for in the past. For example, the proposal department can prioritize relevant proposals based on products the user has recently searched for. This allows for more appropriate proposals to be made by prioritizing proposals based on the timing of product submission. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input user submission timing data into a generating AI and have the generating AI determine the priority of proposals.

[0105] The suggestion unit can adjust the order of suggestions based on the relevance of the products. For example, if a user has shown interest in a particular product category, the suggestion unit will prioritize suggestions related to that category. Similarly, if a user is interested in a particular brand, the suggestion unit can prioritize suggestions related to that brand. Furthermore, if a user is looking for products in a specific price range, the suggestion unit can prioritize suggestions related to that price range. For example, if a user has shown interest in a particular product category, the suggestion unit will prioritize suggestions related to that category. By adjusting the order of suggestions based on the relevance of the products, more appropriate suggestions can be made. Some or all of the above processing in the suggestion unit may be performed using AI, or not. For example, the suggestion unit can input user relevance data into a generating AI and have the generating AI adjust the order of suggestions.

[0106] The voice reception unit can estimate the user's emotions and adjust the method of receiving voice input based on the estimated emotions. For example, if the user is nervous, the voice reception unit can receive voice input in a calm voice. It can also receive voice input in a cheerful voice if the user is relaxed. Furthermore, if the user is in a hurry, the voice reception unit can receive voice input quickly. For example, if the voice reception unit is nervous, it can receive voice input in a calm voice. By adjusting the method of receiving voice input according to the user's emotions, more appropriate voice input can be received. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice reception unit may be performed using AI, or not using AI. For example, the voice reception unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0107] The voice reception unit can select the optimal reception method by referring to the user's past voice input history when voice input is received. For example, the voice reception unit may prioritize suggesting voice input methods that the user has frequently used in the past. The voice reception unit can also predict and suggest voice input methods to be used during specific time periods based on the user's past voice input history. Furthermore, the voice reception unit can suggest relevant voice input methods by referring to content that the user has previously entered. For example, the voice reception unit may prioritize suggesting voice input methods that the user has frequently used in the past. This allows the optimal voice input method to be selected by referring to the user's past voice input history. Some or all of the above processing in the voice reception unit may be performed using AI, for example, or without AI. For example, the voice reception unit can input the user's past voice input history data into a generating AI and have the generating AI select the optimal reception method.

[0108] The voice reception unit can estimate the user's emotions and prioritize voice input based on the estimated emotions. For example, if the user is nervous, the voice reception unit will prioritize important voice input. It can also prioritize detailed voice input if the user is relaxed. Furthermore, if the user is in a hurry, the voice reception unit can prioritize voice input that requires quick processing. For example, if the user is nervous, the voice reception unit will prioritize important voice input. This allows for prioritizing more appropriate voice input based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice reception unit may be performed using AI, or not. For example, the voice reception unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0109] The voice reception unit can select the optimal reception method when a voice input is received, taking into account the user's device information. For example, if the user is using a smartphone, the voice reception unit can suggest a voice input method optimized for smartphones. Furthermore, if the user is using a tablet, the voice reception unit can suggest a voice input method optimized for tablets. In addition, if the user is using a smartwatch, the voice reception unit can suggest a voice input method optimized for smartwatches. For example, if the user is using a smartphone, the voice reception unit can suggest a voice input method optimized for smartphones. This allows the optimal voice input method to be selected by considering the user's device information. Some or all of the above processing in the voice reception unit may be performed using AI, or without AI. For example, the voice reception unit can input user device information data into a generating AI and have the generating AI select the optimal reception method.

[0110] The image reception unit can estimate the user's emotions and adjust the image input reception method based on the estimated user emotions. For example, if the user is nervous, the image reception unit can accept image input with a calm color scheme interface. It can also accept image input with a bright color scheme interface if the user is relaxed. Furthermore, if the user is in a hurry, the image reception unit can accept image input quickly. For example, if the user is nervous, the image reception unit can accept image input with a calm color scheme interface. By adjusting the image input reception method according to the user's emotions, more appropriate image input can be received. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image reception unit may be performed using AI, or not using AI. For example, the image reception unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0111] The image reception unit can select the optimal reception method by referring to the user's past image input history when an image is input. For example, the image reception unit may prioritize suggesting image input methods that the user has frequently used in the past. The image reception unit can also predict and suggest image input methods to be used during specific time periods based on the user's past image input history. Furthermore, the image reception unit can suggest relevant image input methods by referring to content that the user has previously entered. For example, the image reception unit may prioritize suggesting image input methods that the user has frequently used in the past. This allows the optimal image input method to be selected by referring to the user's past image input history. Some or all of the above processing in the image reception unit may be performed using AI, for example, or without AI. For example, the image reception unit can input the user's past image input history data into a generating AI and have the generating AI select the optimal reception method.

[0112] The image reception unit can estimate the user's emotions and determine the priority of image inputs based on the estimated emotions. For example, if the user is nervous, the image reception unit will prioritize important image inputs. It can also prioritize detailed image inputs if the user is relaxed. Furthermore, if the user is in a hurry, the image reception unit can prioritize image inputs that require quick processing. For example, if the user is nervous, the image reception unit will prioritize important image inputs. By prioritizing image inputs according to the user's emotions, more appropriate image inputs can be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLMs) or multimodal generation AIs. Some or all of the above-described processing in the image reception unit may be performed using AI, or not. For example, the image reception unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0113] The image reception unit can select the optimal reception method when an image is input, taking into account the user's device information. For example, if the user is using a smartphone, the image reception unit can suggest an image input method optimized for smartphones. Furthermore, if the user is using a tablet, the image reception unit can suggest an image input method optimized for tablets. In addition, if the user is using a desktop, the image reception unit can suggest an image input method optimized for desktops. For example, if the user is using a smartphone, the image reception unit can suggest an image input method optimized for smartphones. This allows the optimal image input method to be selected by considering the user's device information. Some or all of the above processing in the image reception unit may be performed using AI, or without AI. For example, the image reception unit can input user device information data into a generating AI and have the generating AI select the optimal reception method.

[0114] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit can select detailed training data. It can also select concise training data if the user is in a hurry. Furthermore, if the user is excited, the learning unit can select visually stimulating training data. For example, if the user is relaxed, the learning unit can select detailed training data. This allows for the selection of more appropriate training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using AI, or not. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0115] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also extract specific patterns from past learning data and optimize the learning algorithm. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. For example, the learning unit can select the optimal learning algorithm based on past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0116] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated emotions. For example, the learning unit will learn more frequently if the user is relaxed. It can also reduce the frequency of learning if the user is in a hurry. Furthermore, it can adjust the frequency of learning if the user is excited. For example, the learning unit will learn more frequently if the user is relaxed. This allows for more appropriate learning by adjusting the frequency of learning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0117] The learning unit can weight the training data based on the timing of user input during training. For example, the learning unit can weight the training data based on data recently entered by the user. It can also weight the training data based on data entered by the user during a specific time period. Furthermore, the learning unit can weight the training data by referring to data entered by the user in the past. For example, the learning unit can weight the training data based on data recently entered by the user. This allows for more appropriate training by weighting the training data based on the timing of user input. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user input timing data into a generating AI and have the generating AI perform the training data weighting.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The product search system can also include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit collects and analyzes data on products and services that the user has purchased in the past. For example, it can understand the user's purchasing trends based on information such as the category, price range, and brand of products the user has purchased in the past. This allows the system to suggest products similar to or related to products the user has purchased in the past. For example, if the user has purchased home appliances in the past, the system can suggest new products in the same category or related accessories. Also, if the user prefers a particular brand, the system can suggest new products from that brand or other products from the same brand. Furthermore, the purchase history analysis unit can analyze the user's purchase frequency and timing and suggest products at the appropriate time. For example, if a user regularly purchases a product, the system can predict when that product will need to be repurchased and suggest it as a reminder. This makes it possible to provide more personalized product suggestions by utilizing the user's purchase history.

[0120] The product search system can also include a social media analysis unit that analyzes users' social media activity. This unit analyzes information users share on social media, accounts they follow, and posts they like. For example, if a user mentions a specific brand or product on social media, the system can collect information related to that brand or product and incorporate it into its recommendations. This enables product suggestions based on user interests. For instance, if a user shows interest in fashion items on social media, the system can suggest the latest fashion items and products that are in line with current trends. It can also suggest products recommended by influencers the user follows. Furthermore, the social media analysis unit can analyze the user's social media activity patterns and suggest products at the optimal time. For example, if a user tends to use social media at night, the system can tailor product suggestions to that time. This allows for more effective product suggestions by leveraging users' social media activity.

[0121] The product search system may further include an emotion timing adjustment unit that estimates the user's emotions and adjusts the timing of product suggestions based on the estimated emotions. The emotion timing adjustment unit estimates emotions from the user's facial expressions, voice, text input, etc., and makes product suggestions at the appropriate time. For example, if the user is stressed, the timing of suggestions may be delayed to give the user time to relax. Also, if the user is excited, product suggestions may be made quickly to facilitate a smooth conversation. Furthermore, if the user is tired, the system may start with simple questions and gradually provide more detailed suggestions. For example, if the user is stressed, the timing of suggestions may be delayed to give the user time to relax. By adjusting the timing of product suggestions according to the user's emotions, products can be suggested at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emotion timing adjustment unit may be performed using AI, for example, or without using AI. For example, the emotion timing adjustment unit can input the user's facial expression data into the generating AI and have the generating AI perform emotion estimation.

[0122] The product search system can also include a health monitoring unit that monitors the user's health status. This unit collects and analyzes health data such as the user's heart rate, blood pressure, and sleep patterns. For example, if the user is using a smartwatch, health data can be obtained from that device. This allows the system to make product recommendations based on the user's health status. For instance, if the user is stressed, the system can suggest products with relaxing effects or products that help relieve stress. Similarly, if the user is not getting enough exercise, fitness-related products can be suggested. Furthermore, based on the user's sleep patterns, the system can suggest products that support comfortable sleep. For example, if the user is sleep-deprived, sleep aids or products with relaxing effects can be suggested. This enables product recommendations that take the user's health status into consideration.

[0123] The product search system may further include an emotion content adjustment unit that estimates the user's emotions and adjusts the content of product suggestions based on the estimated emotions. The emotion content adjustment unit estimates emotions from the user's facial expressions, voice, text input, etc., and makes appropriate product suggestions. For example, if the user is relaxed, it may suggest detailed product descriptions or multiple options. If the user is in a hurry, it may also suggest concise product descriptions or just one optimal option. Furthermore, if the user is excited, it may also make visually stimulating product suggestions. For example, if the user is relaxed, it may suggest detailed product descriptions or multiple options. By adjusting the content of product suggestions according to the user's emotions, more appropriate product suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the emotion content adjustment unit may be performed using AI, for example, or not using AI. For example, the emotion content adjustment unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0124] The product search system may further include a purchase intent adjustment unit that estimates the user's purchase intent and adjusts the frequency of product suggestions based on the estimated intent. The purchase intent adjustment unit estimates the user's purchase intent from the user's past purchase history, current search behavior, and dialogue content, and makes product suggestions at an appropriate frequency. For example, if the user shows high purchase intent, product suggestions are made frequently to encourage purchase. Conversely, if the user shows low purchase intent, the frequency of suggestions can be reduced to lessen the user's burden. Furthermore, if the user shows strong interest in a particular product, suggestions related to that product can be prioritized. For example, if the user shows high purchase intent, product suggestions are made frequently to encourage purchase. By adjusting the frequency of product suggestions according to the user's purchase intent, more effective product suggestions become possible. Purchase intent estimation is achieved using a purchase intent estimation function, for example, using a purchase intent engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the purchase intent adjustment unit may be performed using AI, for example, or without using AI. For example, the purchase intent adjustment unit can input user dialogue data into a generating AI and have the generating AI perform the estimation of purchase intent.

[0125] The product search system may also include a lifestyle analysis unit that analyzes the user's lifestyle. The lifestyle analysis unit collects and analyzes data such as the user's lifestyle habits, hobbies, and interests. For example, if the user is interested in fitness, it can suggest fitness-related products. If the user enjoys cooking, it can also suggest kitchenware and recipe books. Furthermore, if the user likes to travel, it can suggest travel-related products and services. For example, if the user is interested in fitness, it can suggest fitness-related products. This enables product suggestions based on the user's lifestyle. Some or all of the above processing in the lifestyle analysis unit may be performed using AI, for example, or without AI. For example, the lifestyle analysis unit can input the user's lifestyle data into a generating AI and have the generating AI perform the lifestyle analysis.

[0126] The product search system may further include an emotion order adjustment unit that estimates the user's emotions and adjusts the order of product suggestions based on the estimated emotions. The emotion order adjustment unit estimates emotions from the user's facial expressions, voice, text input, etc., and suggests products in an appropriate order. For example, if the user is relaxed, products may be suggested in an order that includes detailed information. If the user is in a hurry, products may be suggested in an order that includes concise information. Furthermore, if the user is excited, products may be suggested in a visually stimulating order. For example, if the user is relaxed, products may be suggested in an order that includes detailed information. By adjusting the order of product suggestions according to the user's emotions, more appropriate product suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emotion order adjustment unit may be performed using AI, for example, or without AI. For example, the emotion order adjustment unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0127] The product search system may further include a geographic information suggestion unit that makes product suggestions while considering the user's geographic location. The geographic information suggestion unit suggests relevant products and services based on the user's current location and past travel history. For example, if the user is in a specific region, it can suggest products and services related to that region. Also, if the user is traveling, it can suggest products and services related to their travel destination. Furthermore, if the user is at home, it can suggest products and services related to information around their home. For example, if the user is in a specific region, it can suggest products and services related to that region. This makes it possible to make product suggestions that take the user's geographic location into account. Some or all of the above processing in the geographic information suggestion unit may be performed using AI, for example, or without AI. For example, the geographic information suggestion unit can input the user's geographic location data into a generating AI and have the generating AI execute suggestions for relevant products and services.

[0128] The product search system may further include an emotion expression adjustment unit that estimates the user's emotions and adjusts the way product suggestions are presented based on the estimated emotions. The emotion expression adjustment unit estimates emotions from the user's facial expressions, voice, text input, etc., and presents product suggestions in an appropriate manner. For example, if the user is relaxed, product suggestions are presented in a friendly manner. If the user is tense, product suggestions can be presented in a simple and clear manner. Furthermore, if the user is in a hurry, short suggestions that can be quickly understood can be presented. For example, if the user is relaxed, product suggestions are presented in a friendly manner. By adjusting the way product suggestions are presented according to the user's emotions, more appropriate product suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the emotion expression adjustment unit may be performed using AI, for example, or without AI. For example, the emotion expression adjustment unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The reception desk accepts user input. User input includes text input, voice input, and image input. For example, the desk accepts users to type "I want a stylish lamp that would suit my living room" in text, to voice the same message, or to upload a photo of their living room taken with their smartphone. Step 2: The questioning unit uses a generation AI to ask necessary questions based on the input received by the reception unit. For example, if a user inputs "I want a stylish lamp that would suit my living room," the unit will ask questions such as "What kind of design do you prefer?", "What is your budget?", and "What color do you prefer?". Step 3: The filtering section uses a generation AI to narrow down the products based on the information obtained from the question section. For example, if the user answers "I prefer modern designs," the filter will narrow down to lamps with modern designs; if they answer "My budget is under 10,000 yen," the filter will narrow down to lamps under 10,000 yen; and if they answer "I prefer white," the filter will narrow down to white lamps. Step 4: The suggestion department uses generation AI to propose products that have been narrowed down by the filtering department. For example, it might suggest to the user, "How about this modern design lamp?", "How about this lamp under 10,000 yen?", or "How about this white lamp?".

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0133] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the reception unit, questioning unit, filtering unit, suggestion unit, voice reception unit, image reception unit, learning unit, and emotion estimation function, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives text input, voice input, and image input from the user. The questioning unit is implemented by the specific processing unit 290 of the data processing unit 12 and asks necessary questions based on the user's input using a generating AI. The filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and narrows down products using a generating AI. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests the narrowed-down products using a generating AI. The voice reception unit receives voice input using the microphone 38B of the smart device 14. The image reception unit receives image input using the camera 42 of the smart device 14. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the dialogue history. The emotion estimation function is implemented by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions. The correspondence between each part and the device and control unit is not limited to the example described above and can be modified in various ways.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the reception unit, questioning unit, filtering unit, suggestion unit, voice reception unit, image reception unit, learning unit, and emotion estimation function, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives text input, voice input, and image input from the user. The questioning unit is implemented by the identification processing unit 290 of the data processing unit 12 and asks necessary questions based on the user's input using a generating AI. The filtering unit is implemented by the identification processing unit 290 of the data processing unit 12 and narrows down products using a generating AI. The suggestion unit is implemented by the identification processing unit 290 of the data processing unit 12 and suggests the narrowed-down products using a generating AI. The voice reception unit receives voice input using the microphone 238 of the smart glasses 214. The image reception unit receives image input using the camera 42 of the smart glasses 214. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns the dialogue history. The emotion estimation function is implemented by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions. The correspondence between each part and the device and control unit is not limited to the example described above and can be modified in various ways.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0153] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0154] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0157] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0158] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0159] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0160] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0161] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0165] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0166] Each of the multiple elements described above, including the reception unit, questioning unit, filtering unit, suggestion unit, voice reception unit, image reception unit, learning unit, and emotion estimation function, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives text input, voice input, and image input from the user. The questioning unit is implemented by the specific processing unit 290 of the data processing unit 12 and asks necessary questions based on the user's input using a generation AI. The filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and narrows down products using a generation AI. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests the narrowed-down products using a generation AI. The voice reception unit receives voice input using the microphone 238 of the headset terminal 314. The image reception unit receives image input using the camera 42 of the headset terminal 314. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the dialogue history. The emotion estimation function is implemented by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions. The correspondence between each part and the device and control unit is not limited to the example described above and can be modified in various ways.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0169] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0170] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0171] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0173] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0174] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0175] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0176] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0177] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0178] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0179] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0180] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0181] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] Each of the multiple elements described above, including the reception unit, questioning unit, filtering unit, suggestion unit, voice reception unit, image reception unit, learning unit, and emotion estimation function, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives text input, voice input, and image input from the user. The questioning unit is implemented by the specific processing unit 290 of the data processing unit 12 and asks necessary questions based on the user's input using a generating AI. The filtering unit is implemented by the specific processing unit 290 of the data processing unit 12 and narrows down products using a generating AI. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests the narrowed-down products using a generating AI. The voice reception unit receives voice input using the microphone 238 of the robot 414. The image reception unit receives image input using the camera 42 of the robot 414. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the dialogue history. The emotion estimation function is implemented by the specific processing unit 290 of the data processing device 12, which estimates the user's emotions. The correspondence between each part and the device and control unit is not limited to the example described above and can be modified in various ways.

[0184] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0186] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0187] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0188] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0191] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0192] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0193] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0194] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0195] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0196] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0197] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0199] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0200] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0201] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0202] (Note 1) A reception area that receives user input, A questioning unit that asks necessary questions based on the input received by the reception unit, A filtering unit that narrows down the products based on the information obtained by the aforementioned questioning unit, The system includes a suggestion unit that proposes products narrowed down by the aforementioned narrowing unit. A system characterized by the following features. (Note 2) It is equipped with a voice input receiving unit. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features an image reception section that accepts photos and illustrations. The system described in Appendix 1, characterized by the features described herein. (Note 4) It has a learning unit that learns from the dialogue history. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned question section is, Using generative AI, the system asks necessary questions based on user input. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned narrowing section is, Use generative AI to narrow down the products that best suit the user's needs. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned proposal section is, We propose products that have been narrowed down using generational AI. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is Analyze the user's past input history to select the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving input, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is It estimates the user's emotions and determines the priority of input to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving input, the system prioritizes accepting inputs that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving input, the system analyzes the user's social media activity and accepts relevant input. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned question section is, The system estimates the user's emotions and adjusts the wording of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned question section is, When asking a question, adjust the level of detail based on the user's importance to the question. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned question section is, When asking a question, apply a different question algorithm depending on the user's category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned question section is, The system estimates the user's emotions and adjusts the length of the questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned question section is, When asking questions, prioritize the questions based on when the user entered the information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned question section is, When asking questions, adjust the order of questions based on user relevance. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned narrowing section is, It estimates the user's emotions and adjusts the filtering criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned narrowing section is, When filtering results, the system improves the accuracy of the filtering process by considering the relationships between users. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned narrowing section is, When filtering results, the system takes user attribute information into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned narrowing section is, It estimates the user's sentiment and adjusts the order in which the filtered results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned narrowing section is, When filtering results, the system takes into account the geographical distribution of users. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned narrowing section is, When narrowing down results, the system improves the accuracy of the filtering process by referencing relevant literature from the user. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, When submitting proposals, prioritize them based on when the products are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned voice reception unit is The system estimates the user's emotions and adjusts the voice input acceptance method based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned voice reception unit is During voice input, the system selects the optimal input method by referring to the user's past voice input history. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned voice reception unit is It estimates the user's emotions and determines the priority of voice input based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned voice reception unit is When voice input is used, the system selects the optimal input method considering the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned image receiving unit is The system estimates the user's emotions and adjusts the image input acceptance method based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned image receiving unit is When an image is entered, the system selects the optimal submission method by referring to the user's past image entry history. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned image receiving unit is It estimates the user's emotions and determines the priority of image input based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned image receiving unit is When an image is input, the system selects the optimal reception method considering the user's device information. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned learning unit, During training, the training data is weighted based on when the user input occurred. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that receives user input, A questioning unit that asks necessary questions based on the input received by the reception unit, A filtering unit that narrows down the products based on the information obtained by the aforementioned questioning unit, The system includes a suggestion unit that proposes products narrowed down by the aforementioned narrowing unit. A system characterized by the following features.

2. It is equipped with a voice input receiving unit. The system according to feature 1.

3. It features an image reception section that accepts photos and illustrations. The system according to feature 1.

4. It has a learning unit that learns from the dialogue history. The system according to feature 1.

5. The aforementioned question section is, Using generative AI, the system asks necessary questions based on user input. The system according to feature 1.

6. The aforementioned narrowing section is, Use generative AI to narrow down the products that best suit the user's needs. The system according to feature 1.

7. The aforementioned proposal section is, We propose products that have been narrowed down using generational AI. The system according to feature 1.

8. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system according to feature 1.

9. The aforementioned reception unit is Analyze the user's past input history to select the optimal reception method. The system according to feature 1.

10. The aforementioned reception unit is When receiving input, filtering is performed based on the user's current areas of interest. The system according to feature 1.

Images