system

Abstract

The system according to the embodiment aims to analyze customer data and generate and provide optimal advertisements. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates advertisements based on the analysis results obtained by the analysis unit. The provision unit provides the advertisements generated by the generation unit.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Existing technologies have not yet effectively utilized customer data to generate and deliver personalized advertisements, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze customer data and generate and provide optimal advertisements. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates an advertisement based on the analysis result obtained by the analysis unit. The provision unit provides the advertisement generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze customer data and generate and provide optimal advertisements. [Brief explanation of the drawings]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a system that makes optimal suggestions to customers based on real-time product trends. This system collects and analyzes customer data, generates and provides advertisements, and thereby makes optimal suggestions to customers. For example, when a user checks a recipe, AI checks the ingredients needed and suggests the prices of the ingredients and the total price per store to the user. This allows users to save time researching and shopping around. Furthermore, retailers can learn which products users want by region and hold targeted sales. This allows for reduced advertising costs.

[0029] The proposal system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer data. Examples of customer data include, but are not limited to, purchase history, website browsing history, and survey results. The collection unit can collect, for example, past purchase history, search history, and regional trend data. The collection unit can also estimate a user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the frequency of data collection can be reduced to reduce the burden on the user. The analysis unit analyzes the data collected by the collection unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to, examples. For example, the analysis unit can analyze a user's past purchase history and select an optimal data collection method. The analysis unit can also estimate a user's emotions and adjust the presentation method of the analysis based on the estimated user emotions. For example, if the user is feeling nervous, the system can provide a simple and highly visible analysis result. The generation unit generates an advertisement based on the analysis result obtained by the analysis unit. The advertisements are generated in the form of, for example, text advertisements, banner advertisements, video advertisements, etc., but are not limited to these examples. The generation unit can generate advertisements according to, for example, a region or a date and time. The generation unit can also estimate a user's emotions and adjust the advertisement generation method based on the estimated user's emotions. For example, if the user is relaxed, an advertisement that progresses at a leisurely pace is generated. The provision unit provides the advertisements generated by the generation unit. The advertisements are provided by, for example, email delivery, displaying a banner on a website, sharing on social media, etc., but are not limited to these examples. The provision unit can estimate a user's emotions and adjust the advertisement provision method based on the estimated user's emotions. For example, if the user is relaxed, an advertisement is provided at a leisurely pace. As a result, the recommendation system according to the embodiment can make optimal suggestions to customers by collecting and analyzing customer data, generating and providing advertisements.

[0030] The suggestion system includes an interface for users to check cooking recipes. The interface includes, for example, a search bar for users to search for recipes and a screen for displaying recipe details. For example, when a user enters a cooking recipe into the search bar, the interface displays related recipes. The interface also includes a screen for displaying recipe details, which can display the ingredients and steps of the recipe selected by the user. The interface also includes a function for users to save and share recipes. For example, users can save their favorite recipes and refer to them later. Users can also share recipes on social media. This makes it possible to provide necessary information when users check cooking recipes.

[0031] The proposal system includes a method for displaying information proposed by the AI. Methods for displaying information include, for example, text display, graphical display, and audio output. For example, when the information proposed by the AI ​​is displayed in text, the information is provided to the user visually. Furthermore, by using a graphical display, the information can be provided in a visually easy-to-understand manner. For example, the information can be displayed using graphs or charts. Furthermore, by using audio output, the information can be provided to the user auditorily. For example, the information proposed by the AI ​​can be read aloud. This allows the information proposed by the AI ​​to be displayed appropriately to the user.

[0032] The proposed system provides various advertising formats. The advertising formats include, for example, text advertising, image advertising, and video advertising. For example, text advertising is a format that introduces products and services using short sentences. Image advertising is a format that introduces products and services using visually appealing images. Video advertising is a format that introduces products and services using moving images. This makes it possible to provide users with a variety of advertising formats.

[0033] The collection unit can collect past purchase history, search history, and regional trend data. Past purchase history includes, for example, purchase date and time, purchased items, and purchase amount. The collection unit can collect, for example, data on items purchased by the user in the past. Search history includes, for example, search keywords and search date and time. The collection unit can collect, for example, data on keywords searched for by the user in the past. Regional trend data includes, for example, popular items and event information for each region. The collection unit can collect, for example, information on popular items and events in a specific region. In this way, by collecting past purchase history, search history, and regional trend data, more accurate data can be provided.

[0034] The generation unit can generate advertisements according to region and date and time. Advertisements according to region and date and time include, for example, advertisements related to specific events in each region and advertisements displayed during specific time periods. The generation unit can, for example, generate advertisements related to events held in a specific region. The generation unit can also generate advertisements displayed during specific time periods. For example, an advertisement for a lunch menu can be displayed during the daytime, and an advertisement for a dinner menu can be displayed during the evening. This allows for effective marketing by generating optimal advertisements according to region and date and time.

[0035] The collection unit can analyze the user's past purchase history and select a data collection method. For example, the collection unit prioritizes collection of related data based on products that the user has frequently purchased in the past. The collection unit can also analyze the user's purchase history to determine purchasing trends during specific time periods and collect data during those time periods. Furthermore, the collection unit can also prioritize collection of data related to products in a specific category based on the user's purchase history. This makes it possible to select the optimal data collection method by analyzing the user's past purchase history.

[0036] When collecting data, the collection unit can filter the data based on the user's current lifestyle and areas of interest. For example, if the user is interested in health, the collection unit can prioritize collecting health-related product data. If the user leads a busy life, the collection unit can also collect data on time-saving products and convenient gadgets. Furthermore, if the user plans to attend a specific event, the collection unit can also collect product data related to the event. This allows for more relevant data to be collected by filtering data based on the user's current lifestyle and areas of interest.

[0037] When collecting data, the collection unit can select a collection means according to the user's input method. For example, if the user uses voice input, the collection unit collects data using voice recognition technology. Also, if the user uses text input, the collection unit can collect data using text analysis technology. Furthermore, if the user uses image input, the collection unit can collect data using image recognition technology. This allows for efficient data collection by selecting the optimal collection means according to the user's input method.

[0038] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting data about products that are popular in that area. Furthermore, when the user is traveling, the collection unit can also collect data about recommended products in the area where the user is traveling. Furthermore, when the user is at home, the collection unit can also collect data about sales information at nearby stores. In this way, by collecting highly relevant data by taking into account the user's geographical location information, more appropriate data can be provided.

[0039] When collecting data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit collects data on products that the user has "liked" on social media. The collection unit can also collect product data on brands that the user follows on social media. Furthermore, the collection unit can analyze the content of the user's posts on social media and collect related product data. In this way, related data can be collected by analyzing the user's social media activities.

[0040] When collecting data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit preferentially collects data about products that the user has previously rated highly. The collection unit can also avoid collecting data about products that the user has previously rated poorly. Furthermore, the collection unit can adjust the categories of data to be collected based on the user's past feedback. In this way, the collection method can be customized by reflecting the user's past feedback, and more appropriate data can be collected.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. Furthermore, the analysis unit can determine the priority of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies a purchasing pattern analysis algorithm to purchase history data. The analysis unit can also apply a search behavior analysis algorithm to search history data. Furthermore, the analysis unit can also apply a trend prediction algorithm to regional trend data. In this way, by applying different analysis algorithms depending on the data category, more accurate analysis can be performed.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit corrects the current analysis results based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the current analysis. Furthermore, the analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0044] During analysis, the analysis unit can determine the priority of the analysis based on the time of data submission. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of older data. Furthermore, the analysis unit can adjust the analysis schedule depending on the time of data submission. This allows for efficient analysis by determining the priority of the analysis based on the time of data submission.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can also determine the order of analysis according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Also, if the user does not have technical expertise, the analysis unit can provide analysis results that are easy to understand and avoid technical terms. Furthermore, the analysis unit can adjust the way in which the analysis results are presented according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, more appropriate analysis results can be provided.

[0047] The generation unit can adjust the level of detail of the generation based on the importance of the data when generating an advertisement. For example, the generation unit generates a detailed advertisement based on data with high importance. The generation unit can also generate a simplified advertisement based on data with low importance. Furthermore, the generation unit can adjust the advertisement generation method according to the importance of the data. In this way, by adjusting the level of detail of the generation based on the importance of the data, advertisements can be generated efficiently.

[0048] The generation unit can apply different generation algorithms depending on the data category when generating an advertisement. For example, the generation unit applies a text generation algorithm to a text advertisement. The generation unit can also apply an image generation algorithm to an image advertisement. The generation unit can also apply a video generation algorithm to a video advertisement. In this way, by applying different generation algorithms depending on the data category, more effective advertisements can be generated.

[0049] When generating an advertisement, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit corrects the current generation result based on the user's past generation results. The generation unit can also extract a specific pattern from the user's past generation results and reflect it in the current generation. Furthermore, the generation unit can also optimize the generation algorithm by referring to the user's past generation results. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0050] When generating advertisements, the generation unit can determine the priority of generation based on the time of data submission. For example, the generation unit generates advertisements preferentially based on the latest data. The generation unit can also generate advertisements later based on older data. Furthermore, the generation unit can adjust the advertisement generation schedule according to the time of data submission. In this way, by determining the priority of generation based on the time of data submission, advertisements can be generated efficiently.

[0051] The generation unit can adjust the order of generation based on the relevance of data when generating advertisements. For example, the generation unit generates advertisements preferentially based on highly relevant data. The generation unit can also generate advertisements later based on less relevant data. Furthermore, the generation unit can also determine the order of advertisement generation according to the relevance of data. In this way, advertisements can be generated efficiently by adjusting the order of generation based on the relevance of data.

[0052] The generation unit may adjust the use of technical terms in the advertisement generation in accordance with the user's level of expertise. For example, if the user has technical expertise, the generation unit may generate an advertisement that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the generation unit may generate an easy-to-understand advertisement that avoids technical terms. Furthermore, the generation unit may adjust the way the advertisement is presented in accordance with the user's level of expertise. As a result, by adjusting the use of technical terms in the advertisement generation in accordance with the user's level of expertise, a more appropriate advertisement can be provided.

[0053] The providing unit can adjust the level of detail of the provision based on the importance of the data when providing an advertisement. For example, the providing unit provides a detailed advertisement based on data with high importance. The providing unit can also provide a simplified advertisement based on data with low importance. Furthermore, the providing unit can adjust the method of providing the advertisement according to the importance of the data. In this way, by adjusting the level of detail of the provision based on the importance of the data, advertisements can be provided efficiently.

[0054] The providing unit can apply different providing algorithms depending on the data category when providing an advertisement. For example, the providing unit applies a text providing algorithm to a text advertisement. The providing unit can also apply an image providing algorithm to an image advertisement. Furthermore, the providing unit can also apply a video providing algorithm to a video advertisement. In this way, by applying different providing algorithms depending on the data category, more effective advertisements can be provided.

[0055] When providing an advertisement, the providing unit can improve the accuracy of the provision by referring to the user's past provision results. The providing unit, for example, corrects the current provision results based on the user's past provision results. The providing unit can also extract specific patterns from the user's past provision results and reflect them in the current provision. Furthermore, the providing unit can also optimize the provision algorithm by referring to the user's past provision results. In this way, the accuracy of the provision can be improved by referring to the user's past provision results.

[0056] The providing unit can determine the priority of advertisement provision based on the time of data submission when providing advertisements. For example, the providing unit provides advertisements preferentially based on the latest data. The providing unit can also provide advertisements later based on older data. Furthermore, the providing unit can adjust the advertisement provision schedule according to the time of data submission. In this way, by determining the priority of advertisement provision based on the time of data submission, advertisements can be provided efficiently.

[0057] The providing unit can adjust the order of advertisement provision based on the relevance of data when providing advertisements. For example, the providing unit provides advertisements preferentially based on highly relevant data. The providing unit can also provide advertisements later based on less relevant data. Furthermore, the providing unit can also determine the order of advertisement provision according to the relevance of data. In this way, advertisements can be provided efficiently by adjusting the order of advertisement provision based on the relevance of data.

[0058] The providing unit can adjust the use of technical terms provided in accordance with the user's level of expertise when providing an advertisement. For example, if the user has technical expertise, the providing unit can provide an advertisement that uses a lot of technical terms. In addition, if the user does not have technical expertise, the providing unit can provide an easy-to-understand advertisement that avoids technical terms. Furthermore, the providing unit can adjust the way the advertisement is expressed in accordance with the user's level of expertise. In this way, by adjusting the use of technical terms provided in accordance with the user's level of expertise, it is possible to provide a more appropriate advertisement.

[0059] When displaying the interface, the user interface can select the optimal display method by referring to the user's past operation history. For example, the user interface can preferentially provide a display method that the user has frequently used in the past. The user interface can also predict and provide a display method to be used during a specific time period based on the user's past operation history. Furthermore, the user interface can also suggest the optimal display method based on the user's past operation history. In this way, the optimal display method can be selected by referring to the user's past operation history.

[0060] The user interface can customize the display content according to the user's current task when the interface is displayed. For example, if the user is shopping, the user interface can prioritize displaying related product information. Also, if the user is cooking, the user interface can prioritize displaying recipes and information on necessary ingredients. Furthermore, if the user is traveling, the user interface can prioritize displaying tourist information and store information for the travel destination. In this way, by customizing the display content according to the user's current task, more appropriate information can be provided.

[0061] The user interface can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the user interface provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the user interface can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the user interface can also provide a simple and highly visible display method. This makes it possible to select the optimal display method by taking into account the user's device information.

[0062] The user interface can make the display content multilingual according to the user's language setting when displaying the interface. For example, the user interface can automatically set the interface language based on the language setting of the user's device. The user interface can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the user interface can display the interface in that language. This makes it possible to provide more appropriate information by making the display content multilingual according to the user's language setting.

[0063] The information display method can adjust the level of detail of the display based on the importance of the data when displaying the information. For example, the information display method displays detailed information for data with high importance. The information display method can also display simplified information for data with low importance. Furthermore, the information display method can determine the priority of the information display according to the importance of the data. As a result, by adjusting the level of detail of the display based on the importance of the data, it is possible to provide information efficiently.

[0064] The information display method can apply different display algorithms depending on the category of data when displaying information. For example, the information display method can apply a purchase pattern display algorithm to purchase history data. The information display method can also apply a search behavior display algorithm to search history data. Furthermore, the information display method can also apply a trend prediction display algorithm to regional trend data. In this way, by applying different display algorithms depending on the category of data, more appropriate information can be provided.

[0065] The information display method can determine the display priority based on the time of data submission when displaying information. The information display method, for example, prioritizes information display based on the latest data. The information display method can also postpone information display based on older data. Furthermore, the information display method can adjust the information display schedule depending on the time of data submission. In this way, by determining the display priority based on the time of data submission, information can be provided efficiently.

[0066] The information display method can adjust the display order based on the relevance of data when displaying information. For example, the information display method prioritizes information display based on highly relevant data. The information display method can also postpone information display based on less relevant data. Furthermore, the information display method can also determine the order of information display according to the relevance of data. As a result, by adjusting the display order based on the relevance of data, information can be provided efficiently.

[0067] The ad format may adjust the level of detail of the format based on the importance of data when selecting the ad format. For example, the ad format may provide a detailed ad format based on data with high importance. The ad format may also provide a simplified ad format based on data with low importance. Furthermore, the ad format may adjust the ad format selection method according to the importance of data. In this way, by adjusting the level of detail of the format based on the importance of data, it is possible to provide advertisements efficiently.

[0068] When selecting an ad format, different formats can be applied depending on the data category. For example, a text format can be applied to a text ad. Also, an image format can be applied to an image ad. Furthermore, a video format can be applied to a video ad. Thus, by applying different formats depending on the data category, more effective ads can be provided.

[0069] When selecting an ad format, the ad format can be optimized by referring to the user's past ad format selection history. For example, the ad format corrects the current ad format based on the user's past ad format selection history. The ad format can also extract specific patterns from the user's past ad format selection history and reflect them in the current ad format. Furthermore, the ad format can also optimize the ad format selection algorithm by referring to the user's past ad format selection history. In this way, by referring to the user's past ad format selection history, the format can be optimized and more effective ads can be provided.

[0070] When selecting an ad format, the priority of the ad format can be determined based on the time of data submission. For example, the ad format can provide an ad format preferentially based on the latest data. Alternatively, the ad format can provide an ad format later based on older data. Furthermore, the ad format can adjust the ad format provision schedule depending on the time of data submission. In this way, by determining the priority of the format based on the time of data submission, ads can be provided efficiently.

[0071] When selecting an ad format, the order of the ad formats can be adjusted based on the relevance of data. For example, the ad format can provide an ad format preferentially based on highly relevant data. Alternatively, the ad format can provide an ad format later based on less relevant data. Furthermore, the ad format can determine the order of providing the ad formats according to the relevance of data. In this way, adjusting the order of formats based on the relevance of data allows for efficient advertisement provision.

[0072] When selecting an ad format, the ad format may adjust the use of technical terms in the format according to the user's level of expertise. For example, if the user has technical expertise, the ad format may provide an ad format that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the ad format may provide an easy-to-understand ad format that avoids technical terms. Furthermore, the ad format may adjust the way the ad format is expressed according to the user's level of expertise. As a result, by adjusting the use of technical terms in the format according to the user's level of expertise, more appropriate ads can be provided.

[0073] When collecting purchase history, search history, and regional trend data, the collection algorithm can be optimized by referring to past history data. When collecting purchase history, search history, and regional trend data, for example, current data collection can be optimized based on the user's past purchase history. Furthermore, when collecting purchase history, search history, and regional trend data, current data collection can be optimized based on the user's past search history. Furthermore, when collecting purchase history, search history, and regional trend data, current data collection can be optimized based on the regional trend data. In this way, by referring to past history data, the collection algorithm can be optimized and more appropriate data can be collected.

[0074] When collecting purchase history, search history, and regional trend data, the collected data can be updated by reflecting user feedback. When collecting purchase history, search history, and regional trend data, the collected data can be updated, for example, based on user feedback. In addition, when collecting purchase history, search history, and regional trend data, specific patterns can be extracted from user feedback and reflected in the collected data. Furthermore, when collecting purchase history, search history, and regional trend data, the collection algorithm can be optimized by referring to user feedback. In this way, the collected data can be updated by reflecting user feedback, and more appropriate data can be collected.

[0075] When collecting purchase history, search history, and regional trend data, the collected data can be weighted based on the time when the history data was submitted. When collecting purchase history, search history, and regional trend data, data collection can be prioritized based on, for example, the most recent history data. Also, when collecting purchase history, search history, and regional trend data, data collection can be postponed based on older history data. Furthermore, when collecting purchase history, search history, and regional trend data, the weighting of the collected data can be adjusted depending on the time when the history data was submitted. In this way, by weighting the collected data based on the time when the history data was submitted, more appropriate data can be collected.

[0076] When collecting purchase history, search history, and regional trend data, information from different data sources can be integrated to enrich the collected data. For example, when collecting purchase history, search history, and regional trend data, purchase history data and search history data can be integrated to enrich the collected data. In addition, when collecting purchase history, search history, and regional trend data, regional trend data and social media data can be integrated to enrich the collected data. Furthermore, when collecting purchase history, search history, and regional trend data, information from different data sources can be integrated to improve the accuracy of the collected data. In this way, by integrating information from different data sources, the collected data can be enriched and more appropriate data can be collected.

[0077] When generating advertisements according to region and date and time, the generation algorithm can be optimized by referring to region and date and time data when generating advertisements. When generating advertisements according to region and date and time, the optimal advertisement is generated based on, for example, regional trend data. When generating advertisements according to region and date and time, it is also possible to generate advertisements according to time periods based on date and time data. Furthermore, when generating advertisements according to region and date and time, it is also possible to integrate region and date and time data to generate the optimal advertisement. In this way, by referring to region and date and time data, the generation algorithm can be optimized and more effective advertisements can be generated.

[0078] When generating advertisements according to region and date and time, it is possible to update the generated data by reflecting user feedback when generating advertisements. When generating advertisements according to region and date and time, it is possible to update the generated data based on user feedback, for example. Furthermore, when generating advertisements according to region and date and time, it is also possible to extract specific patterns from user feedback and reflect them in the generated data. Furthermore, when generating advertisements according to region and date and time, it is also possible to optimize the generation algorithm by referring to user feedback. In this way, it is possible to update the generated data by reflecting user feedback and generate more effective advertisements.

[0079] When generating advertisements according to region and date and time, the generated data can be weighted based on the time of submission of the region and date and time data. When generating advertisements according to region and date and time, for example, advertisements can be generated preferentially based on the latest region data. Furthermore, when generating advertisements according to region and date and time, advertisements can be generated later based on older region data. Furthermore, when generating advertisements according to region and date and time, the weighting of the generated data can be adjusted based on the time of submission of the region and date and time data. In this way, by weighting the generated data based on the time of submission of the region and date and time data, more effective advertisements can be generated.

[0080] When generating advertisements according to region and date and time, information from different data sources can be integrated to enrich the generated data. When generating advertisements according to region and date and time, for example, regional trend data and social media data can be integrated to enrich the generated data. When generating advertisements according to region and date and time, purchase history data and search history data can also be integrated to enrich the generated data. Furthermore, when generating advertisements according to region and date and time, information from different data sources can be integrated to improve the accuracy of the generated data. In this way, by integrating information from different data sources, the generated data can be enriched and more effective advertisements can be generated.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The recommendation system can introduce interactive elements to increase users' purchasing motivation. For example, when a user selects a specific product, the system displays a quiz or survey related to that product, allowing the user to earn points by answering it. In addition, each time a user completes a specific action, the system can award badges or titles, enhancing the user's sense of accomplishment. Furthermore, the system can allow users to receive additional rewards by sharing with friends. This can increase user engagement and encourage purchasing motivation.

[0083] The recommendation system can customize its suggestions taking into account the user's health condition. For example, if the user is connected to a health management app, it can suggest healthy ingredients and recipes based on that data. Also, if the user has specific allergies, it can take that information into account and suggest products that do not contain allergens. Furthermore, it can suggest appropriate nutritional supplement products based on the user's exercise habits. This allows it to make optimal suggestions based on the user's health condition.

[0084] The recommendation system can predict future purchases based on a user's purchasing history and make suggestions in advance. For example, it can identify products that a user purchases regularly and send reminders when those products will be needed. It can also suggest products similar to those the user has previously purchased, providing an opportunity to try new products. Furthermore, it can analyze a user's purchasing patterns and make suggestions tailored to specific events or seasons. This can improve the user's purchasing experience.

[0085] The proposed system can enhance users' purchasing behavior with gamification elements. For example, users can earn points every time they purchase a specific product and use those points to receive rewards. Users can also earn badges and titles by completing specific missions. Furthermore, users can increase their purchasing motivation by competing with their friends. This makes users' purchasing behavior more fun and increases their engagement.

[0086] The proposed system can provide personalized coupons based on a user's purchasing history. For example, it can provide coupons related to products that a user has purchased in the past. Also, if a user frequently purchases products in a particular category, it can provide discount coupons for products in that category. Furthermore, it can provide special coupons for users' birthdays or anniversaries. This can increase the user's purchasing motivation and encourage repeat purchases.

[0087] The processing flow of the first embodiment will be briefly explained below.

[0088] Step 1: The collection unit collects customer data. Customer data includes purchase history, website browsing history, survey results, etc. The collection unit can collect past purchase history, search history, and regional trend data. The collection unit also estimates the user's emotions and adjusts the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the frequency of data collection can be reduced to reduce the burden on the user. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed using statistical analysis and machine learning algorithms. The analysis unit analyzes the user's past purchase history and can select the optimal data collection method. The analysis unit also estimates the user's emotions and adjusts the way the analysis is presented based on the estimated user emotions. For example, if the user is nervous, it will provide simple, highly visible analysis results. Step 3: The generation unit generates advertisements based on the analysis results obtained by the analysis unit. The advertisements are generated in the form of text advertisements, banner advertisements, video advertisements, etc. The generation unit can generate advertisements according to the region and date and time. The generation unit also estimates the user's emotions and adjusts the method of advertisement generation based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates an advertisement that progresses at a leisurely pace. Step 4: The serving unit serves the advertisement generated by the generating unit. The serving unit serves the advertisement by email, displaying a banner on a website, sharing on social media, etc. The serving unit estimates the user's emotions and adjusts the method of serving advertisements based on the estimated user emotions. For example, if the user is relaxed, the serving unit serves advertisements at a leisurely pace.

[0089] (Example 2) A system according to an embodiment of the present invention is a system that makes optimal suggestions to customers based on real-time product trends. This system collects and analyzes customer data, generates and provides advertisements, and thereby makes optimal suggestions to customers. For example, when a user checks a recipe, AI checks the ingredients needed and suggests the prices of the ingredients and the total price per store to the user. This allows users to save time researching and shopping around. Furthermore, retailers can learn which products users want by region and hold targeted sales. This allows for reduced advertising costs.

[0090] The proposal system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects customer data. Examples of customer data include, but are not limited to, purchase history, website browsing history, and survey results. The collection unit can collect, for example, past purchase history, search history, and regional trend data. The collection unit can also estimate a user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the frequency of data collection can be reduced to reduce the burden on the user. The analysis unit analyzes the data collected by the collection unit. The analysis can be performed using, for example, statistical analysis or a machine learning algorithm, but is not limited to, examples. For example, the analysis unit can analyze a user's past purchase history and select an optimal data collection method. The analysis unit can also estimate a user's emotions and adjust the presentation method of the analysis based on the estimated user emotions. For example, if the user is feeling nervous, the system can provide a simple and highly visible analysis result. The generation unit generates an advertisement based on the analysis result obtained by the analysis unit. The advertisements are generated in the form of, for example, text advertisements, banner advertisements, video advertisements, etc., but are not limited to these examples. The generation unit can generate advertisements according to, for example, a region or a date and time. The generation unit can also estimate a user's emotions and adjust the advertisement generation method based on the estimated user's emotions. For example, if the user is relaxed, an advertisement that progresses at a leisurely pace is generated. The provision unit provides the advertisements generated by the generation unit. The advertisements are provided by, for example, email delivery, displaying a banner on a website, sharing on social media, etc., but are not limited to these examples. The provision unit can estimate a user's emotions and adjust the advertisement provision method based on the estimated user's emotions. For example, if the user is relaxed, an advertisement is provided at a leisurely pace. As a result, the recommendation system according to the embodiment can make optimal suggestions to customers by collecting and analyzing customer data, generating and providing advertisements.

[0091] The suggestion system includes an interface for users to check cooking recipes. The interface includes, for example, a search bar for users to search for recipes and a screen for displaying recipe details. For example, when a user enters a cooking recipe into the search bar, the interface displays related recipes. The interface also includes a screen for displaying recipe details, which can display the ingredients and steps of the recipe selected by the user. The interface also includes a function for users to save and share recipes. For example, users can save their favorite recipes and refer to them later. Users can also share recipes on social media. This makes it possible to provide necessary information when users check cooking recipes.

[0092] The proposal system includes a method for displaying information proposed by the AI. Methods for displaying information include, for example, text display, graphical display, and audio output. For example, when the information proposed by the AI ​​is displayed in text, the information is provided to the user visually. Furthermore, by using a graphical display, the information can be provided in a visually easy-to-understand manner. For example, the information can be displayed using graphs or charts. Furthermore, by using audio output, the information can be provided to the user auditorily. For example, the information proposed by the AI ​​can be read aloud. This allows the information proposed by the AI ​​to be displayed appropriately to the user.

[0093] The proposed system provides various advertising formats. The advertising formats include, for example, text advertising, image advertising, and video advertising. For example, text advertising is a format that introduces products and services using short sentences. Image advertising is a format that introduces products and services using visually appealing images. Video advertising is a format that introduces products and services using moving images. This makes it possible to provide users with a variety of advertising formats.

[0094] The collection unit can collect past purchase history, search history, and regional trend data. Past purchase history includes, for example, purchase date and time, purchased items, and purchase amount. The collection unit can collect, for example, data on items purchased by the user in the past. Search history includes, for example, search keywords and search date and time. The collection unit can collect, for example, data on keywords searched for by the user in the past. Regional trend data includes, for example, popular items and event information for each region. The collection unit can collect, for example, information on popular items and events in a specific region. In this way, by collecting past purchase history, search history, and regional trend data, more accurate data can be provided.

[0095] The generation unit can generate advertisements according to region and date and time. Advertisements according to region and date and time include, for example, advertisements related to specific events in each region and advertisements displayed during specific time periods. The generation unit can, for example, generate advertisements related to events held in a specific region. The generation unit can also generate advertisements displayed during specific time periods. For example, an advertisement for a lunch menu can be displayed during the daytime, and an advertisement for a dinner menu can be displayed during the evening. This allows for effective marketing by generating optimal advertisements according to region and date and time.

[0096] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the user's burden. Furthermore, if the user is relaxed, the collection unit can increase the frequency of data collection to collect more detailed data. Furthermore, if the user is in a hurry, the collection unit can quickly collect data to immediately obtain the necessary information. This reduces the user's burden by adjusting the timing of data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The collection unit can analyze the user's past purchase history and select a data collection method. For example, the collection unit prioritizes collection of related data based on products that the user has frequently purchased in the past. The collection unit can also analyze the user's purchase history to determine purchasing trends during specific time periods and collect data during those time periods. Furthermore, the collection unit can also prioritize collection of data related to products in a specific category based on the user's purchase history. This makes it possible to select the optimal data collection method by analyzing the user's past purchase history.

[0098] When collecting data, the collection unit can filter the data based on the user's current lifestyle and areas of interest. For example, if the user is interested in health, the collection unit can prioritize collecting health-related product data. If the user leads a busy life, the collection unit can also collect data on time-saving products and convenient gadgets. Furthermore, if the user plans to attend a specific event, the collection unit can also collect product data related to the event. This allows for more relevant data to be collected by filtering data based on the user's current lifestyle and areas of interest.

[0099] When collecting data, the collection unit can select a collection means according to the user's input method. For example, if the user uses voice input, the collection unit collects data using voice recognition technology. Also, if the user uses text input, the collection unit can collect data using text analysis technology. Furthermore, if the user uses image input, the collection unit can collect data using image recognition technology. This allows for efficient data collection by selecting the optimal collection means according to the user's input method.

[0100] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, if the user is excited, the collection unit can prioritize collecting data related to the latest trending products. Furthermore, if the user is relaxed, the collection unit can prioritize collecting data related to products that the user uses on a daily basis. Furthermore, if the user is stressed, the collection unit can prioritize collecting data related to products that have a relaxing effect. This allows for more appropriate data to be collected by prioritizing the data to be collected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting data about products that are popular in that area. Furthermore, when the user is traveling, the collection unit can also collect data about recommended products in the area where the user is traveling. Furthermore, when the user is at home, the collection unit can also collect data about sales information at nearby stores. In this way, by collecting highly relevant data by taking into account the user's geographical location information, more appropriate data can be provided.

[0102] When collecting data, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit collects data on products that the user has "liked" on social media. The collection unit can also collect product data on brands that the user follows on social media. Furthermore, the collection unit can analyze the content of the user's posts on social media and collect related product data. In this way, related data can be collected by analyzing the user's social media activities.

[0103] When collecting data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit preferentially collects data about products that the user has previously rated highly. The collection unit can also avoid collecting data about products that the user has previously rated poorly. Furthermore, the collection unit can adjust the categories of data to be collected based on the user's past feedback. In this way, the collection method can be customized by reflecting the user's past feedback, and more appropriate data can be collected.

[0104] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide simple, highly visible analysis results. The analysis unit can also provide detailed analysis results if the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can provide concise analysis results that focus on the main points. This allows for adjusting the way the analysis is presented according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on data with high importance. The analysis unit can also perform a simplified analysis on data with low importance. Furthermore, the analysis unit can determine the priority of the analysis according to the importance of the data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data.

[0106] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit applies a purchasing pattern analysis algorithm to purchase history data. The analysis unit can also apply a search behavior analysis algorithm to search history data. Furthermore, the analysis unit can also apply a trend prediction algorithm to regional trend data. In this way, by applying different analysis algorithms depending on the data category, more accurate analysis can be performed.

[0107] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit corrects the current analysis results based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results and reflect them in the current analysis. Furthermore, the analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0108] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short, to-the-point analysis result. Alternatively, if the user is relaxed, the analysis unit can provide a longer analysis result with detailed explanations. Furthermore, if the user is excited, the analysis unit can provide an analysis result with visually stimulating effects. This allows for adjusting the length of the analysis according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0109] During analysis, the analysis unit can determine the priority of the analysis based on the time of data submission. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of older data. Furthermore, the analysis unit can adjust the analysis schedule depending on the time of data submission. This allows for efficient analysis by determining the priority of the analysis based on the time of data submission.

[0110] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can also determine the order of analysis according to the relevance of the data. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the data.

[0111] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Also, if the user does not have technical expertise, the analysis unit can provide analysis results that are easy to understand and avoid technical terms. Furthermore, the analysis unit can adjust the way in which the analysis results are presented according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, more appropriate analysis results can be provided.

[0112] The generation unit can estimate the user's emotions and adjust the advertisement generation method based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate an advertisement that progresses at a leisurely pace. If the user is in a hurry, the generation unit can also generate an advertisement that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can also generate an advertisement that adds a visually stimulating effect. In this way, by adjusting the advertisement generation method according to the user's emotions, more effective advertisements can be generated. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0113] The generation unit can adjust the level of detail of the generation based on the importance of the data when generating an advertisement. For example, the generation unit generates a detailed advertisement based on data with high importance. The generation unit can also generate a simplified advertisement based on data with low importance. Furthermore, the generation unit can adjust the advertisement generation method according to the importance of the data. In this way, by adjusting the level of detail of the generation based on the importance of the data, advertisements can be generated efficiently.

[0114] The generation unit can apply different generation algorithms depending on the data category when generating an advertisement. For example, the generation unit applies a text generation algorithm to a text advertisement. The generation unit can also apply an image generation algorithm to an image advertisement. The generation unit can also apply a video generation algorithm to a video advertisement. In this way, by applying different generation algorithms depending on the data category, more effective advertisements can be generated.

[0115] When generating an advertisement, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit corrects the current generation result based on the user's past generation results. The generation unit can also extract a specific pattern from the user's past generation results and reflect it in the current generation. Furthermore, the generation unit can also optimize the generation algorithm by referring to the user's past generation results. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0116] The generation unit can estimate the user's emotions and adjust the length of the advertisement to be generated based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate a short, to-the-point advertisement. If the user is relaxed, the generation unit can also generate a longer advertisement with detailed explanations. Furthermore, if the user is excited, the generation unit can also generate an advertisement with visually stimulating effects. This allows for more effective advertisements to be provided by adjusting the length of the advertisement to be generated according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] When generating advertisements, the generation unit can determine the priority of generation based on the time of data submission. For example, the generation unit generates advertisements preferentially based on the latest data. The generation unit can also generate advertisements later based on older data. Furthermore, the generation unit can adjust the advertisement generation schedule according to the time of data submission. In this way, by determining the priority of generation based on the time of data submission, advertisements can be generated efficiently.

[0118] The generation unit can adjust the order of generation based on the relevance of data when generating advertisements. For example, the generation unit generates advertisements preferentially based on highly relevant data. The generation unit can also generate advertisements later based on less relevant data. Furthermore, the generation unit can also determine the order of advertisement generation according to the relevance of data. In this way, advertisements can be generated efficiently by adjusting the order of generation based on the relevance of data.

[0119] The generation unit may adjust the use of technical terms in the advertisement generation in accordance with the user's level of expertise. For example, if the user has technical expertise, the generation unit may generate an advertisement that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the generation unit may generate an easy-to-understand advertisement that avoids technical terms. Furthermore, the generation unit may adjust the way the advertisement is presented in accordance with the user's level of expertise. As a result, by adjusting the use of technical terms in the advertisement generation in accordance with the user's level of expertise, a more appropriate advertisement can be provided.

[0120] The providing unit can estimate the user's emotions and adjust the method of providing advertisements based on the estimated user emotions. For example, if the user is relaxed, the providing unit can provide advertisements at a leisurely pace. Also, if the user is in a hurry, the providing unit can provide advertisements quickly. Furthermore, if the user is excited, the providing unit can provide advertisements with visually stimulating effects. This allows for more effective advertisements to be provided by adjusting the method of providing advertisements according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0121] The providing unit can adjust the level of detail of the provision based on the importance of the data when providing an advertisement. For example, the providing unit provides a detailed advertisement based on data with high importance. The providing unit can also provide a simplified advertisement based on data with low importance. Furthermore, the providing unit can adjust the method of providing the advertisement according to the importance of the data. In this way, by adjusting the level of detail of the provision based on the importance of the data, advertisements can be provided efficiently.

[0122] The providing unit can apply different providing algorithms depending on the data category when providing an advertisement. For example, the providing unit applies a text providing algorithm to a text advertisement. The providing unit can also apply an image providing algorithm to an image advertisement. Furthermore, the providing unit can also apply a video providing algorithm to a video advertisement. In this way, by applying different providing algorithms depending on the data category, more effective advertisements can be provided.

[0123] When providing an advertisement, the providing unit can improve the accuracy of the provision by referring to the user's past provision results. The providing unit, for example, corrects the current provision results based on the user's past provision results. The providing unit can also extract specific patterns from the user's past provision results and reflect them in the current provision. Furthermore, the providing unit can also optimize the provision algorithm by referring to the user's past provision results. In this way, the accuracy of the provision can be improved by referring to the user's past provision results.

[0124] The providing unit can estimate the user's emotions and adjust the length of the advertisement to be provided based on the estimated user's emotions. For example, if the user is in a hurry, the providing unit can provide a short, to-the-point advertisement. If the user is relaxed, the providing unit can also provide a longer advertisement with detailed explanations. Furthermore, if the user is excited, the providing unit can also provide an advertisement with a visually stimulating effect. This allows for more effective advertisements to be provided by adjusting the length of the advertisement to be provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0125] The providing unit can determine the priority of advertisement provision based on the time of data submission when providing advertisements. For example, the providing unit provides advertisements preferentially based on the latest data. The providing unit can also provide advertisements later based on older data. Furthermore, the providing unit can adjust the advertisement provision schedule according to the time of data submission. In this way, by determining the priority of advertisement provision based on the time of data submission, advertisements can be provided efficiently.

[0126] The providing unit can adjust the order of advertisement provision based on the relevance of data when providing advertisements. For example, the providing unit provides advertisements preferentially based on highly relevant data. The providing unit can also provide advertisements later based on less relevant data. Furthermore, the providing unit can also determine the order of advertisement provision according to the relevance of data. In this way, advertisements can be provided efficiently by adjusting the order of advertisement provision based on the relevance of data.

[0127] The providing unit can adjust the use of technical terms provided in accordance with the user's level of expertise when providing an advertisement. For example, if the user has technical expertise, the providing unit can provide an advertisement that uses a lot of technical terms. In addition, if the user does not have technical expertise, the providing unit can provide an easy-to-understand advertisement that avoids technical terms. Furthermore, the providing unit can adjust the way the advertisement is expressed in accordance with the user's level of expertise. In this way, by adjusting the use of technical terms provided in accordance with the user's level of expertise, it is possible to provide a more appropriate advertisement.

[0128] The user interface can estimate a user's emotions and adjust the interface display method based on the estimated user emotions. For example, if the user is nervous, the user interface can provide an interface with calm colors to reduce visual stress. Furthermore, if the user is having fun, the user interface can provide an interface with bright colors to make input work more enjoyable. Furthermore, if the user is tired, the user interface can provide a simple, highly visible interface to make input work easier. This allows for a more appropriate display by adjusting the interface display method 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 can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0129] When displaying the interface, the user interface can select the optimal display method by referring to the user's past operation history. For example, the user interface can preferentially provide a display method that the user has frequently used in the past. The user interface can also predict and provide a display method to be used during a specific time period based on the user's past operation history. Furthermore, the user interface can also suggest the optimal display method based on the user's past operation history. In this way, the optimal display method can be selected by referring to the user's past operation history.

[0130] The user interface can customize the display content according to the user's current task when the interface is displayed. For example, if the user is shopping, the user interface can prioritize displaying related product information. Also, if the user is cooking, the user interface can prioritize displaying recipes and information on necessary ingredients. Furthermore, if the user is traveling, the user interface can prioritize displaying tourist information and store information for the travel destination. In this way, by customizing the display content according to the user's current task, more appropriate information can be provided.

[0131] The user interface can estimate the user's emotions and adjust the interface's operation procedures based on the estimated user's emotions. For example, if the user is nervous, the user interface can provide simple and intuitive operation procedures. Furthermore, if the user is relaxed, the user interface can provide detailed operation procedures. Furthermore, if the user is in a hurry, the user interface can provide quick operation procedures. This allows the interface's operation procedures to be adjusted according to the user's emotions, thereby providing more appropriate operation procedures. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0132] The user interface can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the user interface provides a display method that matches the screen size. Furthermore, if the user is using a tablet, the user interface can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the user interface can also provide a simple and highly visible display method. This makes it possible to select the optimal display method by taking into account the user's device information.

[0133] The user interface can make the display content multilingual according to the user's language setting when displaying the interface. For example, the user interface can automatically set the interface language based on the language setting of the user's device. The user interface can also provide a language switching function when the user uses multiple languages. Furthermore, if the user selects a specific language, the user interface can display the interface in that language. This makes it possible to provide more appropriate information by making the display content multilingual according to the user's language setting.

[0134] The information display method can estimate a user's emotion and adjust the information display method based on the estimated user's emotion. For example, when the user is nervous, the information display method can provide a simple, highly visible information display. Furthermore, when the user is relaxed, the information display method can also provide a detailed information display. Furthermore, when the user is in a hurry, the information display method can also provide a concise information display that focuses on the main points. In this way, by adjusting the information display method according to the user's emotion, more appropriate information can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0135] The information display method can adjust the level of detail of the display based on the importance of the data when displaying the information. For example, the information display method displays detailed information for data with high importance. The information display method can also display simplified information for data with low importance. Furthermore, the information display method can determine the priority of the information display according to the importance of the data. As a result, by adjusting the level of detail of the display based on the importance of the data, it is possible to provide information efficiently.

[0136] The information display method can apply different display algorithms depending on the category of data when displaying information. For example, the information display method can apply a purchase pattern display algorithm to purchase history data. The information display method can also apply a search behavior display algorithm to search history data. Furthermore, the information display method can also apply a trend prediction display algorithm to regional trend data. In this way, by applying different display algorithms depending on the category of data, more appropriate information can be provided.

[0137] The information display method can estimate a user's emotion and adjust the length of the information display based on the estimated user emotion. For example, when the user is in a hurry, the information display method can provide a short, to-the-point information display. Furthermore, when the user is relaxed, the information display method can provide a longer information display including detailed explanations. Furthermore, when the user is excited, the information display method can provide an information display with a visually stimulating effect. This allows for more appropriate information to be provided by adjusting the length of the information display according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0138] The information display method can determine the display priority based on the time of data submission when displaying information. The information display method, for example, prioritizes information display based on the latest data. The information display method can also postpone information display based on older data. Furthermore, the information display method can adjust the information display schedule depending on the time of data submission. In this way, by determining the display priority based on the time of data submission, information can be provided efficiently.

[0139] The information display method can adjust the display order based on the relevance of data when displaying information. For example, the information display method prioritizes information display based on highly relevant data. The information display method can also postpone information display based on less relevant data. Furthermore, the information display method can also determine the order of information display according to the relevance of data. As a result, by adjusting the display order based on the relevance of data, information can be provided efficiently.

[0140] The ad format can estimate a user's emotions and adjust the ad format based on the estimated user emotions. For example, if the user is relaxed, the ad format can provide a leisurely ad format. If the user is in a hurry, the ad format can also provide a short, to-the-point ad format. Furthermore, if the user is excited, the ad format can also provide an ad format with visually stimulating effects. This allows for more effective advertising by adjusting the ad format according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0141] The ad format may adjust the level of detail of the format based on the importance of data when selecting the ad format. For example, the ad format may provide a detailed ad format based on data with high importance. The ad format may also provide a simplified ad format based on data with low importance. Furthermore, the ad format may adjust the ad format selection method according to the importance of data. In this way, by adjusting the level of detail of the format based on the importance of data, it is possible to provide advertisements efficiently.

[0142] When selecting an ad format, different formats can be applied depending on the data category. For example, a text format can be applied to a text ad. Also, an image format can be applied to an image ad. Furthermore, a video format can be applied to a video ad. Thus, by applying different formats depending on the data category, more effective ads can be provided.

[0143] When selecting an ad format, the ad format can be optimized by referring to the user's past ad format selection history. For example, the ad format corrects the current ad format based on the user's past ad format selection history. The ad format can also extract specific patterns from the user's past ad format selection history and reflect them in the current ad format. Furthermore, the ad format can also optimize the ad format selection algorithm by referring to the user's past ad format selection history. In this way, by referring to the user's past ad format selection history, the format can be optimized and more effective ads can be provided.

[0144] The ad format can estimate the user's emotions and adjust the length of the ad format based on the estimated user emotions. For example, if the user is in a hurry, the ad format can provide a short, to-the-point ad format. Alternatively, if the user is relaxed, the ad format can provide a longer ad format with detailed explanations. Furthermore, if the user is excited, the ad format can provide an ad format with visually stimulating effects. This allows for more effective advertisements to be provided by adjusting the length of the ad format according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0145] When selecting an ad format, the priority of the ad format can be determined based on the time of data submission. For example, the ad format can provide an ad format preferentially based on the latest data. Alternatively, the ad format can provide an ad format later based on older data. Furthermore, the ad format can adjust the ad format provision schedule depending on the time of data submission. In this way, by determining the priority of the format based on the time of data submission, ads can be provided efficiently.

[0146] When selecting an ad format, the order of the ad formats can be adjusted based on the relevance of data. For example, the ad format can provide an ad format preferentially based on highly relevant data. Alternatively, the ad format can provide an ad format later based on less relevant data. Furthermore, the ad format can determine the order of providing the ad formats according to the relevance of data. In this way, adjusting the order of formats based on the relevance of data allows for efficient advertisement provision.

[0147] When selecting an ad format, the ad format may adjust the use of technical terms in the format according to the user's level of expertise. For example, if the user has technical expertise, the ad format may provide an ad format that uses a lot of technical terms. Alternatively, if the user does not have technical expertise, the ad format may provide an easy-to-understand ad format that avoids technical terms. Furthermore, the ad format may adjust the way the ad format is expressed according to the user's level of expertise. As a result, by adjusting the use of technical terms in the format according to the user's level of expertise, more appropriate ads can be provided.

[0148] The collection of purchase history, search history, and regional trend data can estimate a user's emotions and adjust the data collection method based on the estimated user emotions. For example, detailed data can be collected when a user is relaxed. Furthermore, the collection of purchase history, search history, and regional trend data can also be used to quickly collect data when a user is in a hurry. Furthermore, the collection of purchase history, search history, and regional trend data can also be used to collect visually stimulating data when a user is excited. This allows for more appropriate data collection by adjusting the data collection method 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 can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0149] When collecting purchase history, search history, and regional trend data, the collection algorithm can be optimized by referring to past history data. When collecting purchase history, search history, and regional trend data, for example, current data collection can be optimized based on the user's past purchase history. Furthermore, when collecting purchase history, search history, and regional trend data, current data collection can be optimized based on the user's past search history. Furthermore, when collecting purchase history, search history, and regional trend data, current data collection can be optimized based on the regional trend data. In this way, by referring to past history data, the collection algorithm can be optimized and more appropriate data can be collected.

[0150] When collecting purchase history, search history, and regional trend data, the collected data can be updated by reflecting user feedback. When collecting purchase history, search history, and regional trend data, the collected data can be updated, for example, based on user feedback. In addition, when collecting purchase history, search history, and regional trend data, specific patterns can be extracted from user feedback and reflected in the collected data. Furthermore, when collecting purchase history, search history, and regional trend data, the collection algorithm can be optimized by referring to user feedback. In this way, the collected data can be updated by reflecting user feedback, and more appropriate data can be collected.

[0151] The collection of purchase history, search history, and regional trend data can be adjusted based on the estimated user emotion by estimating the user's emotion. For example, when a user is relaxed, data collection can be performed more frequently. Furthermore, when a user is in a hurry, data collection can be reduced in frequency to quickly collect data. Furthermore, when a user is excited, data collection can be increased in frequency to collect more detailed data. This allows for more appropriate data to be collected by adjusting the collection frequency according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0152] When collecting purchase history, search history, and regional trend data, the collected data can be weighted based on the time when the history data was submitted. When collecting purchase history, search history, and regional trend data, data collection can be prioritized based on, for example, the most recent history data. Also, when collecting purchase history, search history, and regional trend data, data collection can be postponed based on older history data. Furthermore, when collecting purchase history, search history, and regional trend data, the weighting of the collected data can be adjusted depending on the time when the history data was submitted. In this way, by weighting the collected data based on the time when the history data was submitted, more appropriate data can be collected.

[0153] When collecting purchase history, search history, and regional trend data, information from different data sources can be integrated to enrich the collected data. For example, when collecting purchase history, search history, and regional trend data, purchase history data and search history data can be integrated to enrich the collected data. In addition, when collecting purchase history, search history, and regional trend data, regional trend data and social media data can be integrated to enrich the collected data. Furthermore, when collecting purchase history, search history, and regional trend data, information from different data sources can be integrated to improve the accuracy of the collected data. In this way, by integrating information from different data sources, the collected data can be enriched and more appropriate data can be collected.

[0154] Advertisement generation according to region and date and time can estimate a user's emotions and adjust the ad generation method based on the estimated user emotions. Advertisement generation according to region and date and time can, for example, generate an advertisement that progresses at a leisurely pace if the user is relaxed. Advertisement generation according to region and date and time can also generate an advertisement that emphasizes the shortest route if the user is in a hurry. Advertisement generation according to region and date and time can also generate an advertisement with a visually stimulating effect if the user is excited. This allows for more effective advertisements to be generated by adjusting the ad generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0155] When generating advertisements according to region and date and time, the generation algorithm can be optimized by referring to region and date and time data when generating advertisements. When generating advertisements according to region and date and time, the optimal advertisement is generated based on, for example, regional trend data. When generating advertisements according to region and date and time, it is also possible to generate advertisements according to time periods based on date and time data. Furthermore, when generating advertisements according to region and date and time, it is also possible to integrate region and date and time data to generate the optimal advertisement. In this way, by referring to region and date and time data, the generation algorithm can be optimized and more effective advertisements can be generated.

[0156] When generating advertisements according to region and date and time, it is possible to update the generated data by reflecting user feedback when generating advertisements. When generating advertisements according to region and date and time, it is possible to update the generated data based on user feedback, for example. Furthermore, when generating advertisements according to region and date and time, it is also possible to extract specific patterns from user feedback and reflect them in the generated data. Furthermore, when generating advertisements according to region and date and time, it is also possible to optimize the generation algorithm by referring to user feedback. In this way, it is possible to update the generated data by reflecting user feedback and generate more effective advertisements.

[0157] Ad generation according to region and date and time can estimate the user's emotions and adjust the frequency of advertisement generation based on the estimated user emotions. Ad generation according to region and date and time can, for example, generate advertisements frequently when the user is relaxed. Ad generation according to region and date and time can also reduce the frequency of advertisement generation to generate advertisements quickly when the user is in a hurry. Ad generation according to region and date and time can also increase the frequency of advertisement generation to generate more detailed advertisements when the user is excited. This allows for more effective advertisements to be generated by adjusting the frequency of advertisement generation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0158] When generating advertisements according to region and date and time, the generated data can be weighted based on the time of submission of the region and date and time data. When generating advertisements according to region and date and time, for example, advertisements can be generated preferentially based on the latest region data. Furthermore, when generating advertisements according to region and date and time, advertisements can be generated later based on older region data. Furthermore, when generating advertisements according to region and date and time, the weighting of the generated data can be adjusted based on the time of submission of the region and date and time data. In this way, by weighting the generated data based on the time of submission of the region and date and time data, more effective advertisements can be generated.

[0159] When generating advertisements according to region and date and time, information from different data sources can be integrated to enrich the generated data. When generating advertisements according to region and date and time, for example, regional trend data and social media data can be integrated to enrich the generated data. When generating advertisements according to region and date and time, purchase history data and search history data can also be integrated to enrich the generated data. Furthermore, when generating advertisements according to region and date and time, information from different data sources can be integrated to improve the accuracy of the generated data. In this way, by integrating information from different data sources, the generated data can be enriched and more effective advertisements can be generated. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects customer data using the camera 42 and microphone 38B of the smart device 14 and processes the data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advertisements based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart device 14 and provides the generated advertisements to the user. The interface, for example, uses the display 40A of the smart device 14 to display a screen for the user to check cooking recipes. The method of displaying information includes, for example, displaying text or outputting audio using the display 40A and speaker 40B of the smart device 14. The advertisements are, for example, displayed as text advertisements, image advertisements, or video advertisements using the display 40A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects customer data using the camera 42 and microphone 238 of the smart glasses 214 and processes the data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advertisements based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides the generated advertisements to the user. The interface, for example, displays a screen on the display of the smart glasses 214 for the user to check cooking recipes. The method of displaying information includes, for example, displaying text or outputting audio using the display and speaker 240 of the smart glasses 214. The advertisement format includes, for example, displaying text advertisements, image advertisements, and video advertisements using the display of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit collects customer data using the camera 42 and microphone 238 of the headset terminal 314 and processes the data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advertisements based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the headset terminal 314 and provides the generated advertisements to the user. The interface, for example, uses the display 343 of the headset terminal 314 to display a screen that allows the user to check cooking recipes. The information is displayed, for example, by text display or audio output using the display 343 or speaker 240 of the headset terminal 314. The advertisements may be in the form of text advertisements, image advertisements, or video advertisements, for example, displayed on the display 343 of the headset terminal 314 . === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects customer data using the camera 42 and microphone 238 of the robot 414 and processes the data using the control unit 46A. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected data using statistical analysis or machine learning algorithms. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates advertisements based on the analysis results. The provision unit is realized, for example, by the control unit 46A of the robot 414 and provides the generated advertisements to the user. The interface, for example, displays a screen on the display of the robot 414 for the user to check cooking recipes. The method of displaying information includes, for example, displaying text or outputting audio using the display or speaker 240 of the robot 414. The advertisements are, for example, displayed in the form of text advertisements, image advertisements, or video advertisements using the display of the robot 414.

[0160] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0161] The recommendation system can introduce interactive elements to increase users' purchasing motivation. For example, when a user selects a specific product, the system displays a quiz or survey related to that product, allowing the user to earn points by answering it. In addition, each time a user completes a specific action, the system can award badges or titles, enhancing the user's sense of accomplishment. Furthermore, the system can allow users to receive additional rewards by sharing with friends. This can increase user engagement and encourage purchasing motivation.

[0162] The recommendation system can customize its suggestions taking into account the user's health condition. For example, if the user is connected to a health management app, it can suggest healthy ingredients and recipes based on that data. Also, if the user has specific allergies, it can take that information into account and suggest products that do not contain allergens. Furthermore, it can suggest appropriate nutritional supplement products based on the user's exercise habits. This allows it to make optimal suggestions based on the user's health condition.

[0163] The recommendation system can predict future purchases based on a user's purchasing history and make suggestions in advance. For example, it can identify products that a user purchases regularly and send reminders when those products will be needed. It can also suggest products similar to those the user has previously purchased, providing an opportunity to try new products. Furthermore, it can analyze a user's purchasing patterns and make suggestions tailored to specific events or seasons. This can improve the user's purchasing experience.

[0164] The proposed system can enhance users' purchasing behavior with gamification elements. For example, users can earn points every time they purchase a specific product and use those points to receive rewards. Users can also earn badges and titles by completing specific missions. Furthermore, users can increase their purchasing motivation by competing with their friends. This makes users' purchasing behavior more fun and increases their engagement.

[0165] The proposed system can provide personalized coupons based on a user's purchasing history. For example, it can provide coupons related to products that a user has purchased in the past. Also, if a user frequently purchases products in a particular category, it can provide discount coupons for products in that category. Furthermore, it can provide special coupons for users' birthdays or anniversaries. This can increase the user's purchasing motivation and encourage repeat purchases.

[0166] The recommendation system can estimate the user's emotions and adjust the recommendations based on the estimated emotions. For example, if the user is feeling stressed, it can suggest products and services that have a relaxing effect. If the user is excited, it can suggest products related to active activities. Furthermore, if the user is sad, it can suggest products related to entertainment and hobbies to lift the user's spirits. This allows it to make optimal recommendations based on the user's emotions.

[0167] The proposed system can estimate the user's emotions and adjust the interface design based on the estimated emotions. For example, if the user is relaxed, it can provide an interface with calm colors. If the user is excited, it can provide an interface with bright and lively colors. Furthermore, if the user is tired, it can provide a simple, highly visible interface. This makes it possible to provide the optimal interface according to the user's emotions.

[0168] The proposed system can estimate a user's emotions and adjust the way advertisements are displayed based on the estimated emotions. For example, if a user is relaxed, an advertisement that progresses at a leisurely pace can be displayed. If a user is in a hurry, an advertisement that is short and to the point can be displayed. Furthermore, if a user is excited, an advertisement that adds visually stimulating effects can be displayed. This allows the system to provide the most appropriate advertisement according to the user's emotions.

[0169] The proposed system can estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is relaxed, notifications can be displayed slowly. If the user is in a hurry, notifications can be displayed immediately. Furthermore, if the user is excited, notifications can be displayed with visually stimulating effects. This allows the system to provide optimal notifications according to the user's emotions.

[0170] The proposed system can estimate the user's emotions and adjust the content of recommendations based on the estimated emotions. For example, if the user is relaxed, it can recommend products and services that have a relaxing effect. If the user is excited, it can recommend products related to active activities. Furthermore, if the user is sad, it can recommend products related to entertainment and hobbies to lift the user's spirits. This allows it to make optimal recommendations according to the user's emotions.

[0171] The processing flow of the second embodiment will be briefly explained below.

[0172] Step 1: The collection unit collects customer data. Customer data includes purchase history, website browsing history, survey results, etc. The collection unit can collect past purchase history, search history, and regional trend data. The collection unit also estimates the user's emotions and adjusts the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the frequency of data collection can be reduced to reduce the burden on the user. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed using statistical analysis and machine learning algorithms. The analysis unit analyzes the user's past purchase history and can select the optimal data collection method. The analysis unit also estimates the user's emotions and adjusts the way the analysis is presented based on the estimated user emotions. For example, if the user is nervous, it will provide simple, highly visible analysis results. Step 3: The generation unit generates advertisements based on the analysis results obtained by the analysis unit. The advertisements are generated in the form of text advertisements, banner advertisements, video advertisements, etc. The generation unit can generate advertisements according to the region and date and time. The generation unit also estimates the user's emotions and adjusts the method of advertisement generation based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates an advertisement that progresses at a leisurely pace. Step 4: The serving unit serves the advertisement generated by the generating unit. The serving unit serves the advertisement by email, displaying a banner on a website, sharing on social media, etc. The serving unit estimates the user's emotions and adjusts the method of serving advertisements based on the estimated user emotions. For example, if the user is relaxed, the serving unit serves advertisements at a leisurely pace.

[0173] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0175] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0176] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0177] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0178] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0179] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0180] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0181] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0182] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0183] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0184] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0185] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0186] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0187] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0188] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0189] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0190] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0191] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0192] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0193] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0194] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0195] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0196] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0197] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0198] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0199] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0200] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0201] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0202] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0203] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0204] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0205] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0206] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0207] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0208] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0209] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0210] 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.

[0211] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0212] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0213] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0214] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0215] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0216] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0217] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0218] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0219] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0220] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0221] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0222] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0223] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0224] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0225] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0226] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0227] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0228] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0229] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0230] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0231] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0232] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0233] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0234] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0235] 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.

[0236] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0237] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0238] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0239] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0240] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0241] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0242] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0243] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0244] [Explanation of symbols]

[0245] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects customer data; an analysis unit that analyzes the data collected by the collection unit; a generation unit that generates an advertisement based on the analysis result obtained by the analysis unit; a providing unit that provides the advertisement generated by the generating unit; Equipped with A system characterized by:

2. Provides an interface for users to check cooking recipes 2. The system of claim 1.

3. Equipping the device with a method for displaying information suggested by AI 2. The system of claim 1.

4. Offering advertising formats 2. The system of claim 1.

5. The collecting unit Collect past purchase history, search history, and local trend data 2. The system of claim 1.

6. The generation unit Generate ads based on location and time 2. The system of claim 1.

7. The collecting unit Estimate user emotions and determine the timing of data collection based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit Analyze users' past purchase history and select data collection methods 2. The system of claim 1.

9. The collecting unit Filtering data collection based on the user's current life situation and interests 2. The system of claim 1.

Images