system

Abstract

The system according to this embodiment aims to analyze the user's past and present actions and propose the optimal future actions. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, and a scoring unit. The collection unit collects past and present actions. The analysis unit analyzes the action data collected by the collection unit and discovers potential relationships. The proposal unit proposes future actions based on the relationships discovered by the analysis unit. The scoring unit scores the results of executing the future actions proposed by the proposal unit.

Description

Technical Field

[0005] ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it has not been fully done to propose an optimal future action based on the user's past and current actions, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the user's past and current actions and propose an optimal future action.

Means for Solving the Problems

[0007] The system according to this embodiment can analyze the user's past and present actions and propose the optimal future actions. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The promotion optimization system according to an embodiment of the present invention is a system that optimizes a company's promotions and provides users with new discoveries and special experiences by utilizing generative AI and a knowledge graph. The promotion optimization system uses generative AI and a knowledge graph to discover potential relationships between "past actions" and "current actions" performed on services within the group. Next, the promotion optimization system proposes a "future action" that the user can take to experience serendipity. At this point, the user is not informed of what kind of serendipity it will be. When the user actually takes the "future action," the serendipity is revealed, and the user can gain new discoveries and special experiences, as well as earn a serendipity score. For example, when the user is searching for accommodation on a travel booking site, the promotion optimization system uses generative AI to discover that there is a nearby inn that was the setting for the manga "March Comes in Like a Lion," which the user recently read on an e-book service, and proposes that the user "book this inn." When the user actually stays at this inn, the details of the serendipity are revealed. In this case, the past action is reading "March Comes in Like a Lion" on an e-book service, the current action is searching for accommodation on a travel booking site, and the future action is booking and staying at a particular accommodation. The serendipity score is scored from multiple perspectives using a generation AI. Specifically, it includes happiness, which indicates the joy and satisfaction the user felt; rarity, which indicates the scarcity of the quest; difficulty, which indicates the difficulty of completing the quest; timeliness, which indicates how well the quest is suited to the user's current interests and situation; and novelty, which indicates the ranking of the quest's completion. The user's serendipity score is visualized in the form of rankings or badges. Furthermore, users are seamlessly guided to an open chat where only those who have completed the quest gather, potentially leading to the sharing of emotions and the creation of new communities and friendships among people who have experienced the same serendipity. This system allows companies to conduct promotions at the optimal timing based on users' potential interests and behavioral data, while adding the unique value of serendipity that users experience.The potential relationships discovered by the generative AI allow for unexpected and unforeseen promotional approaches, and the automatic suggestion of quests leads to reduced marketing costs. Users' daily lives become more fortunate and exciting, their attachment to products and services increases through quests, and new communities and friendships are formed through open chats. Reasons for using a knowledge graph include avoiding hallucination by the generative AI due to its external knowledge aspect, and obtaining potential relationships between actions by utilizing the graph structure. In addition, unlike personalized recommendations which immediately suggest products and services to the user, this idea does not reveal detailed information until the quest is completed, but instead provides surprise and a sense of accomplishment, stimulating the user's intellectual curiosity. Furthermore, it has game and community elements that recommendations lack, providing an enjoyable experience. In this way, the promotion optimization system can optimize a company's promotions and provide users with new discoveries and special experiences.

[0029] The promotion optimization system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, and a scoring unit. The collection unit collects past and present actions. Past actions include, but are not limited to, user behavior history, purchase history, and browsing history. Current actions include, but are not limited to, real-time behavior and current interests. The collection unit obtains, for example, user behavior history from a database. The collection unit can also obtain user purchase history from online shopping sites. The collection unit can also obtain user browsing history from a web browser. The analysis unit analyzes the action data collected by the collection unit and discovers potential relationships. The analysis unit analyzes the correlation of action data using, for example, generative AI. The analysis unit can also analyze the causal relationships of action data using generative AI. The analysis unit can also analyze patterns in action data using generative AI. The proposal unit proposes future actions based on the relationships discovered by the analysis unit. The proposal unit, for example, uses generative AI to suggest the most suitable future actions for the user. The proposal unit can also use generative AI to suggest future actions based on the user's interests. Furthermore, the proposal unit can use generative AI to suggest future actions based on the user's behavioral history. The scoring unit scores the results of executing the future actions suggested by the proposal unit. The scoring unit, for example, uses AI to score the results of executing future actions. Furthermore, the scoring unit can use AI to evaluate the results of executing future actions. Furthermore, the scoring unit can use AI to rank the results of executing future actions. As a result, the promotion optimization system according to this embodiment can provide users with new discoveries and special experiences by suggesting and scoring future actions based on the user's past and present actions.

[0030] The data collection unit collects past and present actions. Past actions include, but are not limited to, user activity history, purchase history, and browsing history. Specifically, user activity history includes website visit history, click history, and app usage history. This data is an important indicator of user interests. Purchase history includes detailed information about products and services that the user has purchased in the past, allowing for an understanding of the user's purchasing trends. Browsing history includes information about web pages and products that the user has viewed, allowing for tracking of changes in user interests. Current actions include, but are not limited to, real-time activity and current interests. Real-time activity includes the usage of web pages and apps that the user is currently accessing, and location information. This allows for an immediate understanding of the user's current interests and activity. The data collection unit can, for example, retrieve user activity history from a database. The data collection unit can also retrieve user purchase history from online shopping sites. This includes methods such as retrieving data via APIs or directly querying databases. Furthermore, the data collection unit can also obtain users' browsing history from their web browsers. This includes methods of collecting data using browser extensions and cookies. This allows the data collection unit to gather a wide range of data from diverse data sources and gain a comprehensive understanding of user behavior. In addition, the data collection unit can centrally manage this data and collaborate with other systems and departments as needed. For example, collected data can be stored on a cloud server and made accessible to the analysis and proposal departments. By adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions become possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall performance of the system.

[0031] The analysis unit analyzes action data collected by the data collection unit to discover potential relationships. For example, the analysis unit uses generative AI to analyze the correlations between action data. Specifically, the generative AI receives data such as user behavior history, purchase history, and browsing history as input and analyzes the correlations between this data. For example, it can analyze what products a user who purchased a particular product subsequently viewed, or what actions a user who visited a particular webpage subsequently took. The analysis unit can also use generative AI to analyze the causal relationships of action data. This makes it possible to clarify how a particular action influences other actions. For example, it can analyze how a particular promotion influenced a user's purchasing behavior. Furthermore, the analysis unit can use generative AI to analyze patterns in action data. This makes it possible to understand user behavior patterns and changes in interests. For example, it can analyze the patterns of users who take a particular action at a specific time and propose the most suitable promotion based on that pattern. In addition, the analysis unit can utilize historical data and statistical information to analyze long-term trends and tendencies. This can be used to plan and improve future promotion strategies. For example, by analyzing the effectiveness of past promotions, it is possible to determine which promotions were most effective. This allows the analytics department to quickly and accurately analyze the collected data and gain a deep understanding of user behavior and interests.

[0032] The proposal department proposes future actions based on the relationships discovered by the analysis department. For example, the proposal department uses generative AI to suggest the most suitable future actions for the user. Specifically, the generative AI analyzes the user's interests and behavioral patterns based on data provided by the analysis department and proposes the most suitable promotions and actions. For example, it can suggest accessories or additional products related to a specific product to a user who has purchased that product. The proposal department can also use generative AI to suggest future actions based on the user's interests. This allows for personalized suggestions tailored to the user's current interests. For example, it can suggest new movies and related products related to a specific genre to a user who has recently watched many movies of that genre. The proposal department can also use generative AI to suggest future actions based on the user's behavioral history. This allows for predictions of the user's most likely next actions based on past behavioral patterns and provides suggestions accordingly. For example, it can suggest similar products to a user who has purchased a specific product during a specific season in the past, as that season approaches. Furthermore, the proposal department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the proposal department to consistently provide users with the best possible solutions, thereby improving user satisfaction.

[0033] The scoring unit scores the results of executing future actions proposed by the proposal unit. For example, the scoring unit uses AI to score the results of executing future actions. Specifically, the AI ​​analyzes the user's behavior and reactions after executing the proposed action and evaluates its effectiveness. For example, it can score what actions a user took after purchasing a proposed product, or how effective a proposed promotion was. The scoring unit can also use AI to evaluate the results of future actions. This allows for a quantitative assessment of how beneficial the proposed action was to the user. For example, it can evaluate how much the proposed action influenced user satisfaction and purchase intent. Furthermore, the scoring unit can use AI to rank the results of future actions. This allows for the identification of the most effective action from among multiple proposed actions. For example, it can rank the most effective promotion from among multiple promotions and use the results to plan the next promotion strategy. In addition, the scoring unit provides the scoring results as feedback to the proposal and analysis units, enabling continuous improvement of the overall system's accuracy and effectiveness. This allows the scoring unit to accurately evaluate the effectiveness of the proposed actions and improve the overall system performance.

[0034] The scoring unit can perform scoring from the perspectives of happiness, rarity, difficulty, timeliness, and novelty. For example, the scoring unit can evaluate happiness, which indicates user satisfaction. It can also evaluate rarity, which indicates the scarcity of a quest. Furthermore, it can evaluate difficulty, which indicates the difficulty of completing a quest. For example, the scoring unit can evaluate user satisfaction through surveys. Rarity is evaluated based on the frequency of quest occurrences. Difficulty is evaluated based on the skill level required to complete the quest. This allows for a more detailed evaluation of the user experience by scoring from multiple perspectives. Some or all of the above-described processes in the scoring unit may be performed using AI or not. For example, the scoring unit can input happiness, which indicates user satisfaction, into an AI model and output a score.

[0035] The suggestion unit does not reveal the details of serendipity when proposing future actions to the user. For example, the suggestion unit uses generative AI to suggest future actions to the user. The suggestion unit can also use generative AI to suggest future actions based on the user's interests. Furthermore, the suggestion unit can use generative AI to suggest future actions based on the user's behavioral history. By not revealing the details of serendipity, it is possible to provide the user with surprise and a sense of accomplishment. Some or all of the above processing in the suggestion unit may be performed using generative AI or not. For example, the suggestion unit can input the user's behavioral history into generative AI and output future actions.

[0036] The scoring unit can visualize scoring results in the form of rankings or badges. For example, the scoring unit can display scoring results in a ranking format. It can also display scoring results in a badge format. Furthermore, the scoring unit can display scoring results in a graph format. For example, the scoring unit can display user scores in a ranking format and allow comparison with other users. In the badge format, badges are awarded to users who meet specific conditions. In the graph format, the progress of scores is visually displayed. By visualizing the scoring results, it is possible to increase user motivation. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input scoring results into an AI model and output them in the form of rankings or badges.

[0037] The system includes a guidance unit that directs users who have performed future actions to an open chat. For example, the guidance unit sends a notification to users who have performed future actions, encouraging them to join the open chat. The guidance unit can also provide users who have performed future actions with a link to join the open chat. Furthermore, the guidance unit can explain the overview of the open chat to users who have performed future actions. For example, the guidance unit displays a pop-up notification to users who have performed future actions, encouraging them to join the open chat. The joining link allows users to join the open chat by clicking it. The overview of the open chat is explained to users before they join. This facilitates interaction among users by guiding them to the open chat. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input data on users who have performed future actions into an AI model and output the optimal guidance method.

[0038] The system includes an interaction section that facilitates communication within the open chat. The interaction section can, for example, host events within the open chat. It can also provide topics within the open chat. Furthermore, the interaction section can introduce members within the open chat. For example, the interaction section could host an online meeting as an event within the open chat. Topic provision would offer topics that users might be interested in. Member introductions would introduce new members to other members. This promotes communication within the open chat, potentially leading to the creation of new communities and friendships. Some or all of the above processes in the interaction section may be performed using AI, or not. For example, the interaction section could input user data from the open chat into an AI model and output the optimal method for promoting communication.

[0039] The data collection unit can analyze the user's past action history and select the optimal data collection method. For example, the data collection unit can prioritize collecting actions that the user has frequently performed in the past. The data collection unit can also collect actions performed during specific time periods from the user's past action history. Furthermore, the data collection unit can analyze the user's past action history and select a data collection method based on specific patterns. This allows the optimal data collection method to be selected by analyzing past action history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's past action history into an AI model and output the optimal data collection method.

[0040] The data collection unit can filter actions based on the user's current lifestyle and areas of interest. For example, the unit can prioritize collecting actions related to areas the user is currently interested in. The unit can also collect appropriate actions based on the user's lifestyle (e.g., at work, on vacation). Furthermore, the unit can filter and collect relevant actions based on the user's current activity (e.g., exercising, reading). This allows for the collection of highly relevant data by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the user's lifestyle and areas of interest into an AI model and output the optimal filtering method.

[0041] The data collection unit can prioritize collecting highly relevant actions by considering the user's geographical location information when collecting actions. For example, the data collection unit can prioritize collecting actions related to the user's current location. The data collection unit can also collect actions performed nearby based on the user's geographical location information. Furthermore, the data collection unit can collect highly relevant actions by considering the user's movement history. This allows for the collection of highly relevant actions by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into an AI model and output the optimal action.

[0042] The data collection unit can analyze a user's social media activity and collect relevant actions when collecting actions. For example, the data collection unit can collect relevant actions based on information shared by the user on social media. The data collection unit can also analyze a user's social media activity history and collect relevant actions. Furthermore, the data collection unit can collect relevant actions based on the activity of accounts the user follows. In this way, relevant actions can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media activity data into an AI model and output the optimal action.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the actions during the analysis. For example, the analysis unit will perform a detailed analysis for actions with high importance. Conversely, the analysis unit can also perform a simplified analysis for actions with low importance. Furthermore, the analysis unit can optimally allocate analysis resources according to the importance of the actions. This allows for optimal resource allocation by adjusting the level of detail of the analysis based on the importance of the actions. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit can input action importance data into a generation AI and output the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the action during analysis. For example, the analysis unit can apply a purchasing behavior analysis algorithm to shopping-related actions. It can also apply a travel behavior analysis algorithm to travel-related actions. Furthermore, it can apply a viewing behavior analysis algorithm to entertainment-related actions. By applying different analysis algorithms depending on the category of the action, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input action category data into a generative AI and output the optimal analysis algorithm.

[0045] The analysis unit can determine the priority of the analysis based on the submission date of the actions during the analysis. For example, the analysis unit may prioritize the analysis of recently submitted actions. It can also postpone the analysis of older actions. Furthermore, the analysis unit can optimally allocate analysis resources based on the submission date. This allows for optimal resource allocation by determining the priority of the analysis based on the submission date. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input action submission date data into a generative AI and output the analysis priority.

[0046] The analysis unit can adjust the order of analysis based on the relevance of actions during the analysis. For example, the analysis unit can prioritize the analysis of highly relevant actions. It can also postpone the analysis of less relevant actions. Furthermore, the analysis unit can optimally allocate analysis resources based on the relevance of actions. This allows for more efficient analysis by adjusting the order of analysis based on the relevance of actions. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input action relevance data into a generative AI and output the order of analysis.

[0047] The proposal unit can adjust the level of detail of a proposal based on the importance of the action. For example, the proposal unit will provide a detailed proposal for high-importance actions, and a concise proposal for low-importance actions. The proposal unit can also optimally allocate resources to the proposal according to the importance of the action. This allows for optimal resource allocation by adjusting the level of detail of the proposal based on the importance of the action. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit can input action importance data into a generative AI and output the level of detail of the proposal.

[0048] The suggestion unit can apply different suggestion algorithms depending on the action category when making suggestions. For example, the suggestion unit can apply a purchase behavior suggestion algorithm to shopping-related actions. It can also apply a travel behavior suggestion algorithm to travel-related actions. Furthermore, it can apply a viewing behavior suggestion algorithm to entertainment-related actions. By applying different suggestion algorithms depending on the action category, more accurate suggestions become possible. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the suggestion unit can input action category data into a generative AI and output the optimal suggestion algorithm.

[0049] The proposal department can determine the priority of proposals based on the submission timing of actions. For example, the proposal department may prioritize recently submitted actions. It can also postpone older submitted actions. Furthermore, the proposal department can optimally allocate resources to proposals based on submission timing. This allows for optimal resource allocation by prioritizing proposals based on submission timing. Some or all of the above processing in the proposal department may be performed using or without a generative AI. For example, the proposal department can input action submission timing data into a generative AI and output a proposal priority.

[0050] The proposal unit can adjust the order of proposals based on the relevance of the actions during the proposal process. For example, the proposal unit can prioritize proposing highly relevant actions. It can also postpone less relevant actions. Furthermore, the proposal unit can optimally allocate resources for proposals based on the relevance of the actions. This allows for more efficient proposals by adjusting the order of proposals based on the relevance of the actions. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit can input action relevance data into a generative AI and output the order of proposals.

[0051] The scoring unit can adjust the level of detail in the scoring based on the degree of action completion. For example, the scoring unit will perform detailed scoring for actions with a high degree of completion. Conversely, the scoring unit can also perform simplified scoring for actions with a low degree of completion. Furthermore, the scoring unit can optimally allocate scoring resources according to the degree of action completion. This allows for optimal resource allocation by adjusting the level of detail in the scoring unit based on the degree of action completion. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action completion data into an AI model and output the level of detail in the scoring.

[0052] The scoring unit can apply different scoring algorithms depending on the category of the action during scoring. For example, the scoring unit can apply a purchasing behavior scoring algorithm to shopping-related actions. It can also apply a travel behavior scoring algorithm to travel-related actions. Furthermore, it can apply a viewing behavior scoring algorithm to entertainment-related actions. By applying different scoring algorithms depending on the category of the action, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action category data into an AI model and output the optimal scoring algorithm.

[0053] The scoring unit can determine the scoring priority based on the submission date of actions during the scoring process. For example, the scoring unit may prioritize recently submitted actions. It can also postpone older submitted actions. Furthermore, the scoring unit can optimally allocate scoring resources based on the submission date. This allows for optimal resource allocation by determining the scoring priority based on the submission date. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action submission date data into an AI model and output the scoring priority.

[0054] The scoring unit can adjust the scoring order based on the relevance of actions during the scoring process. For example, the scoring unit can prioritize scoring actions with high relevance. It can also postpone scoring actions with low relevance. Furthermore, the scoring unit can optimally allocate scoring resources based on the relevance of actions. This allows for more efficient scoring by adjusting the scoring order based on the relevance of actions. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action relevance data into an AI model and output the scoring order.

[0055] The guidance unit can select the optimal guidance method by referring to the user's past chat history during guidance. For example, the guidance unit can guide the user to a relevant open chat based on the content of chats the user has participated in in the past. The guidance unit can also guide the user to an open chat related to a topic of interest based on the user's past chat history. Furthermore, the guidance unit can analyze the user's past chat history and select the optimal guidance method. This allows the optimal guidance method to be selected by referring to past chat history. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input the user's past chat history data into an AI model and output the optimal guidance method.

[0056] The guidance unit can select the optimal guidance method by considering the user's device information during guidance. For example, if the user is using a smartphone, the guidance unit provides a guidance method that matches the screen size. If the user is using a tablet, the guidance unit can also provide a guidance method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the guidance unit can provide a concise and highly visible guidance method. This allows the system to select the optimal guidance method by considering device information. Some or all of the above processing in the guidance unit may be performed using AI, or without AI. For example, the guidance unit can input the user's device information into an AI model and output the optimal guidance method.

[0057] The interaction unit can select the optimal interaction method by referring to the user's past interaction history when facilitating interaction. For example, the interaction unit can provide relevant interaction methods based on the content of interactions the user has participated in in the past. The interaction unit can also provide interaction methods related to topics of interest based on the user's past interaction history. Furthermore, the interaction unit can analyze the user's past interaction history and select the optimal interaction method. This allows the optimal interaction method to be selected by referring to past interaction history. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input the user's past interaction history data into an AI model and output the optimal interaction method.

[0058] The interaction unit can select the optimal interaction method by considering the user's geographical location information when facilitating interaction. For example, the interaction unit can provide interaction methods related to the user's current location. It can also provide nearby interaction events based on the user's geographical location information. Furthermore, the interaction unit can provide highly relevant interaction methods by considering the user's travel history. In this way, the optimal interaction method can be selected by considering geographical location information. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input the user's geographical location information into an AI model and output the optimal interaction method.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] A promotion optimization system can prioritize providing highly relevant promotions by considering the user's geographical location. For example, it can prioritize promotions related to the user's current location. It can also provide information on nearby events and sales based on the user's geographical location. Furthermore, it can provide highly relevant promotions by considering the user's travel history. In this way, by considering the user's geographical location, highly relevant promotions can be provided. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's geographical location information into an AI model and output the optimal promotions.

[0061] A promotion optimization system can analyze a user's social media activity and provide relevant promotions. For example, it can provide relevant promotions based on information shared by the user on social media. It can also analyze a user's social media activity history and provide relevant promotions. Furthermore, it can provide relevant promotions based on the activity of accounts the user follows. In this way, relevant promotions can be provided by analyzing social media activity. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user social media activity data into an AI model and output the optimal promotion.

[0062] A promotion optimization system can analyze a user's past action history and select the optimal promotion method. For example, it can prioritize promoting actions that a user has frequently performed in the past. It can also promote actions performed during specific time periods based on the user's past action history. Furthermore, it can analyze the user's past action history and select promotion methods based on specific patterns. In this way, the optimal promotion method can be selected by analyzing past action history. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's past action history into an AI model and output the optimal promotion method.

[0063] A promotion optimization system can filter promotions based on a user's current lifestyle and areas of interest. For example, it can prioritize promotions related to areas of interest the user is currently interested in. It can also provide appropriate promotions according to the user's lifestyle (e.g., at work, on vacation). Furthermore, it can filter and provide relevant promotions based on the user's current activities (e.g., exercising, reading). This allows for the provision of highly relevant promotions by filtering based on the user's lifestyle and areas of interest. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input data on the user's lifestyle and areas of interest into an AI model and output the optimal filtering method.

[0064] The promotion optimization system can select the optimal promotion method by considering the user's device information. For example, if the user is using a smartphone, it can provide a promotion method that is adapted to the screen size. If the user is using a tablet, it can provide a promotion method optimized for the larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible promotion method. In this way, the optimal promotion method can be selected by considering device information. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's device information into an AI model and output the optimal promotion method.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The data collection unit collects past and current actions. Past actions include the user's behavioral history, purchase history, browsing history, etc., while current actions include real-time behavior and current interests. The data collection unit obtains this data from databases, online shopping sites, web browsers, etc. Step 2: The analysis unit analyzes the action data collected by the collection unit and discovers potential relationships. The analysis unit uses generative AI to analyze the correlations, causal relationships, and patterns in the action data. Step 3: The proposal department proposes future actions based on the relationships discovered by the analysis department. The proposal department uses generative AI to propose the optimal future actions for the user, making suggestions based on the user's interests and behavioral history. Step 4: The scoring unit scores the results of executing the future actions proposed by the proposal unit. The scoring unit uses AI to score, evaluate, and rank the results of executing the future actions.

[0067] (Example of form 2) The promotion optimization system according to an embodiment of the present invention is a system that optimizes a company's promotions and provides users with new discoveries and special experiences by utilizing generative AI and a knowledge graph. The promotion optimization system uses generative AI and a knowledge graph to discover potential relationships between "past actions" and "current actions" performed on services within the group. Next, the promotion optimization system proposes a "future action" that the user can take to experience serendipity. At this point, the user is not informed of what kind of serendipity it will be. When the user actually takes the "future action," the serendipity is revealed, and the user can gain new discoveries and special experiences, as well as earn a serendipity score. For example, when the user is searching for accommodation on a travel booking site, the promotion optimization system uses generative AI to discover that there is a nearby inn that was the setting for the manga "March Comes in Like a Lion," which the user recently read on an e-book service, and proposes that the user "book this inn." When the user actually stays at this inn, the details of the serendipity are revealed. In this case, the past action is reading "March Comes in Like a Lion" on an e-book service, the current action is searching for accommodation on a travel booking site, and the future action is booking and staying at a particular accommodation. The serendipity score is scored from multiple perspectives using a generation AI. Specifically, it includes happiness, which indicates the joy and satisfaction the user felt; rarity, which indicates the scarcity of the quest; difficulty, which indicates the difficulty of completing the quest; timeliness, which indicates how well the quest is suited to the user's current interests and situation; and novelty, which indicates the ranking of the quest's completion. The user's serendipity score is visualized in the form of rankings or badges. Furthermore, users are seamlessly guided to an open chat where only those who have completed the quest gather, potentially leading to the sharing of emotions and the creation of new communities and friendships among people who have experienced the same serendipity. This system allows companies to conduct promotions at the optimal timing based on users' potential interests and behavioral data, while adding the unique value of serendipity that users experience.The potential relationships discovered by the generative AI allow for unexpected and unforeseen promotional approaches, and the automatic suggestion of quests leads to reduced marketing costs. Users' daily lives become more fortunate and exciting, their attachment to products and services increases through quests, and new communities and friendships are formed through open chats. Reasons for using a knowledge graph include avoiding hallucination by the generative AI due to its external knowledge aspect, and obtaining potential relationships between actions by utilizing the graph structure. In addition, unlike personalized recommendations which immediately suggest products and services to the user, this idea does not reveal detailed information until the quest is completed, but instead provides surprise and a sense of accomplishment, stimulating the user's intellectual curiosity. Furthermore, it has game and community elements that recommendations lack, providing an enjoyable experience. In this way, the promotion optimization system can optimize a company's promotions and provide users with new discoveries and special experiences.

[0068] The promotion optimization system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, and a scoring unit. The collection unit collects past and present actions. Past actions include, but are not limited to, user behavior history, purchase history, and browsing history. Current actions include, but are not limited to, real-time behavior and current interests. The collection unit obtains, for example, user behavior history from a database. The collection unit can also obtain user purchase history from online shopping sites. The collection unit can also obtain user browsing history from a web browser. The analysis unit analyzes the action data collected by the collection unit and discovers potential relationships. The analysis unit analyzes the correlation of action data using, for example, generative AI. The analysis unit can also analyze the causal relationships of action data using generative AI. The analysis unit can also analyze patterns in action data using generative AI. The proposal unit proposes future actions based on the relationships discovered by the analysis unit. The proposal unit, for example, uses generative AI to suggest the most suitable future actions for the user. The proposal unit can also use generative AI to suggest future actions based on the user's interests. Furthermore, the proposal unit can use generative AI to suggest future actions based on the user's behavioral history. The scoring unit scores the results of executing the future actions suggested by the proposal unit. The scoring unit, for example, uses AI to score the results of executing future actions. Furthermore, the scoring unit can use AI to evaluate the results of executing future actions. Furthermore, the scoring unit can use AI to rank the results of executing future actions. As a result, the promotion optimization system according to this embodiment can provide users with new discoveries and special experiences by suggesting and scoring future actions based on the user's past and present actions.

[0069] The data collection unit collects past and present actions. Past actions include, but are not limited to, user activity history, purchase history, and browsing history. Specifically, user activity history includes website visit history, click history, and app usage history. This data is an important indicator of user interests. Purchase history includes detailed information about products and services that the user has purchased in the past, allowing for an understanding of the user's purchasing trends. Browsing history includes information about web pages and products that the user has viewed, allowing for tracking of changes in user interests. Current actions include, but are not limited to, real-time activity and current interests. Real-time activity includes the usage of web pages and apps that the user is currently accessing, and location information. This allows for an immediate understanding of the user's current interests and activity. The data collection unit can, for example, retrieve user activity history from a database. The data collection unit can also retrieve user purchase history from online shopping sites. This includes methods such as retrieving data via APIs or directly querying databases. Furthermore, the data collection unit can also obtain users' browsing history from their web browsers. This includes methods of collecting data using browser extensions and cookies. This allows the data collection unit to gather a wide range of data from diverse data sources and gain a comprehensive understanding of user behavior. In addition, the data collection unit can centrally manage this data and collaborate with other systems and departments as needed. For example, collected data can be stored on a cloud server and made accessible to the analysis and proposal departments. By adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions become possible. As a result, the data collection unit can collect data efficiently and effectively, improving the overall performance of the system.

[0070] The analysis unit analyzes action data collected by the data collection unit to discover potential relationships. For example, the analysis unit uses generative AI to analyze the correlations between action data. Specifically, the generative AI receives data such as user behavior history, purchase history, and browsing history as input and analyzes the correlations between this data. For example, it can analyze what products a user who purchased a particular product subsequently viewed, or what actions a user who visited a particular webpage subsequently took. The analysis unit can also use generative AI to analyze the causal relationships of action data. This makes it possible to clarify how a particular action influences other actions. For example, it can analyze how a particular promotion influenced a user's purchasing behavior. Furthermore, the analysis unit can use generative AI to analyze patterns in action data. This makes it possible to understand user behavior patterns and changes in interests. For example, it can analyze the patterns of users who take a particular action at a specific time and propose the most suitable promotion based on that pattern. In addition, the analysis unit can utilize historical data and statistical information to analyze long-term trends and tendencies. This can be used to plan and improve future promotion strategies. For example, by analyzing the effectiveness of past promotions, it is possible to determine which promotions were most effective. This allows the analytics department to quickly and accurately analyze the collected data and gain a deep understanding of user behavior and interests.

[0071] The proposal department proposes future actions based on the relationships discovered by the analysis department. For example, the proposal department uses generative AI to suggest the most suitable future actions for the user. Specifically, the generative AI analyzes the user's interests and behavioral patterns based on data provided by the analysis department and proposes the most suitable promotions and actions. For example, it can suggest accessories or additional products related to a specific product to a user who has purchased that product. The proposal department can also use generative AI to suggest future actions based on the user's interests. This allows for personalized suggestions tailored to the user's current interests. For example, it can suggest new movies and related products related to a specific genre to a user who has recently watched many movies of that genre. The proposal department can also use generative AI to suggest future actions based on the user's behavioral history. This allows for predictions of the user's most likely next actions based on past behavioral patterns and provides suggestions accordingly. For example, it can suggest similar products to a user who has purchased a specific product during a specific season in the past, as that season approaches. Furthermore, the proposal department can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. This allows the proposal department to consistently provide users with the best possible solutions, thereby improving user satisfaction.

[0072] The scoring unit scores the results of executing future actions proposed by the proposal unit. For example, the scoring unit uses AI to score the results of executing future actions. Specifically, the AI ​​analyzes the user's behavior and reactions after executing the proposed action and evaluates its effectiveness. For example, it can score what actions a user took after purchasing a proposed product, or how effective a proposed promotion was. The scoring unit can also use AI to evaluate the results of future actions. This allows for a quantitative assessment of how beneficial the proposed action was to the user. For example, it can evaluate how much the proposed action influenced user satisfaction and purchase intent. Furthermore, the scoring unit can use AI to rank the results of future actions. This allows for the identification of the most effective action from among multiple proposed actions. For example, it can rank the most effective promotion from among multiple promotions and use the results to plan the next promotion strategy. In addition, the scoring unit provides the scoring results as feedback to the proposal and analysis units, enabling continuous improvement of the overall system's accuracy and effectiveness. This allows the scoring unit to accurately evaluate the effectiveness of the proposed actions and improve the overall system performance.

[0073] The scoring unit can perform scoring from the perspectives of happiness, rarity, difficulty, timeliness, and novelty. For example, the scoring unit can evaluate happiness, which indicates user satisfaction. It can also evaluate rarity, which indicates the scarcity of a quest. Furthermore, it can evaluate difficulty, which indicates the difficulty of completing a quest. For example, the scoring unit can evaluate user satisfaction through surveys. Rarity is evaluated based on the frequency of quest occurrences. Difficulty is evaluated based on the skill level required to complete the quest. This allows for a more detailed evaluation of the user experience by scoring from multiple perspectives. Some or all of the above-described processes in the scoring unit may be performed using AI or not. For example, the scoring unit can input happiness, which indicates user satisfaction, into an AI model and output a score.

[0074] The suggestion unit does not reveal the details of serendipity when proposing future actions to the user. For example, the suggestion unit uses generative AI to suggest future actions to the user. The suggestion unit can also use generative AI to suggest future actions based on the user's interests. Furthermore, the suggestion unit can use generative AI to suggest future actions based on the user's behavioral history. By not revealing the details of serendipity, it is possible to provide the user with surprise and a sense of accomplishment. Some or all of the above processing in the suggestion unit may be performed using generative AI or not. For example, the suggestion unit can input the user's behavioral history into generative AI and output future actions.

[0075] The scoring unit can visualize scoring results in the form of rankings or badges. For example, the scoring unit can display scoring results in a ranking format. It can also display scoring results in a badge format. Furthermore, the scoring unit can display scoring results in a graph format. For example, the scoring unit can display user scores in a ranking format and allow comparison with other users. In the badge format, badges are awarded to users who meet specific conditions. In the graph format, the progress of scores is visually displayed. By visualizing the scoring results, it is possible to increase user motivation. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input scoring results into an AI model and output them in the form of rankings or badges.

[0076] The system includes a guidance unit that directs users who have performed future actions to an open chat. For example, the guidance unit sends a notification to users who have performed future actions, encouraging them to join the open chat. The guidance unit can also provide users who have performed future actions with a link to join the open chat. Furthermore, the guidance unit can explain the overview of the open chat to users who have performed future actions. For example, the guidance unit displays a pop-up notification to users who have performed future actions, encouraging them to join the open chat. The joining link allows users to join the open chat by clicking it. The overview of the open chat is explained to users before they join. This facilitates interaction among users by guiding them to the open chat. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input data on users who have performed future actions into an AI model and output the optimal guidance method.

[0077] The system includes an interaction section that facilitates communication within the open chat. The interaction section can, for example, host events within the open chat. It can also provide topics within the open chat. Furthermore, the interaction section can introduce members within the open chat. For example, the interaction section could host an online meeting as an event within the open chat. Topic provision would offer topics that users might be interested in. Member introductions would introduce new members to other members. This promotes communication within the open chat, potentially leading to the creation of new communities and friendships. Some or all of the above processes in the interaction section may be performed using AI, or not. For example, the interaction section could input user data from the open chat into an AI model and output the optimal method for promoting communication.

[0078] The data collection unit can estimate the user's emotions and adjust the timing of data collection for past and present actions based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing and collect data when the user is relaxed. The data collection unit can also perform urgent data collection if the user is excited, reflecting real-time actions. Furthermore, if the user is tired, the data collection unit can adjust the collection timing to collect data after the user has rested. This allows for more appropriate data collection by adjusting the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and output the data collection timing.

[0079] The data collection unit can analyze the user's past action history and select the optimal data collection method. For example, the data collection unit can prioritize collecting actions that the user has frequently performed in the past. The data collection unit can also collect actions performed during specific time periods from the user's past action history. Furthermore, the data collection unit can analyze the user's past action history and select a data collection method based on specific patterns. This allows the optimal data collection method to be selected by analyzing past action history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's past action history into an AI model and output the optimal data collection method.

[0080] The data collection unit can filter actions based on the user's current lifestyle and areas of interest. For example, the unit can prioritize collecting actions related to areas the user is currently interested in. The unit can also collect appropriate actions based on the user's lifestyle (e.g., at work, on vacation). Furthermore, the unit can filter and collect relevant actions based on the user's current activity (e.g., exercising, reading). This allows for the collection of highly relevant data by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on the user's lifestyle and areas of interest into an AI model and output the optimal filtering method.

[0081] The data collection unit can estimate the user's emotions and determine the priority of actions to collect based on the estimated emotions. For example, if the user is relaxed, the data collection unit will prioritize collecting actions related to relaxation. Similarly, if the user is excited, the data collection unit can prioritize collecting actions related to excitement. Furthermore, if the user is stressed, the data collection unit can prioritize collecting actions related to stress reduction. This allows for more appropriate data collection by prioritizing actions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and output action priorities.

[0082] The data collection unit can prioritize collecting highly relevant actions by considering the user's geographical location information when collecting actions. For example, the data collection unit can prioritize collecting actions related to the user's current location. The data collection unit can also collect actions performed nearby based on the user's geographical location information. Furthermore, the data collection unit can collect highly relevant actions by considering the user's movement history. This allows for the collection of highly relevant actions by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's geographical location information into an AI model and output the optimal action.

[0083] The data collection unit can analyze a user's social media activity and collect relevant actions when collecting actions. For example, the data collection unit can collect relevant actions based on information shared by the user on social media. The data collection unit can also analyze a user's social media activity history and collect relevant actions. Furthermore, the data collection unit can collect relevant actions based on the activity of accounts the user follows. In this way, relevant actions can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media activity data into an AI model and output the optimal action.

[0084] The analysis unit can estimate the user's emotions and adjust the analysis method of action data based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide deep insights. If the user is in a hurry, the analysis unit can perform a concise analysis and provide results quickly. If the user is excited, the analysis unit can provide visually appealing analysis results. By adjusting the analysis method based on the user's emotions, more appropriate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using or without generative AI. For example, the analysis unit can input user emotion data into a generative AI and output an analysis method.

[0085] The analysis unit can adjust the level of detail of the analysis based on the importance of the actions during the analysis. For example, the analysis unit will perform a detailed analysis for actions with high importance. Conversely, the analysis unit can also perform a simplified analysis for actions with low importance. Furthermore, the analysis unit can optimally allocate analysis resources according to the importance of the actions. This allows for optimal resource allocation by adjusting the level of detail of the analysis based on the importance of the actions. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit can input action importance data into a generation AI and output the level of detail of the analysis.

[0086] The analysis unit can apply different analysis algorithms depending on the category of the action during analysis. For example, the analysis unit can apply a purchasing behavior analysis algorithm to shopping-related actions. It can also apply a travel behavior analysis algorithm to travel-related actions. Furthermore, it can apply a viewing behavior analysis algorithm to entertainment-related actions. By applying different analysis algorithms depending on the category of the action, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input action category data into a generative AI and output the optimal analysis algorithm.

[0087] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can also provide a display method that gets straight to the point. By adjusting the display method based on the user's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI or not. For example, the analysis unit can input user emotion data into a generative AI and output the optimal display method.

[0088] The analysis unit can determine the priority of the analysis based on the submission date of the actions during the analysis. For example, the analysis unit may prioritize the analysis of recently submitted actions. It can also postpone the analysis of older actions. Furthermore, the analysis unit can optimally allocate analysis resources based on the submission date. This allows for optimal resource allocation by determining the priority of the analysis based on the submission date. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input action submission date data into a generative AI and output the analysis priority.

[0089] The analysis unit can adjust the order of analysis based on the relevance of actions during the analysis. For example, the analysis unit can prioritize the analysis of highly relevant actions. It can also postpone the analysis of less relevant actions. Furthermore, the analysis unit can optimally allocate analysis resources based on the relevance of actions. This allows for more efficient analysis by adjusting the order of analysis based on the relevance of actions. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit can input action relevance data into a generative AI and output the order of analysis.

[0090] The suggestion unit can estimate the user's emotions and adjust how it suggests future actions based on those emotions. For example, if the user is relaxed, the suggestion unit can provide detailed suggestions. If the user is in a hurry, it can provide concise suggestions. If the user is excited, it can provide visually appealing suggestions. By adjusting the suggestion method based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using generative AI or not. For example, the suggestion unit can input user emotion data into a generative AI and output the optimal suggestion method.

[0091] The proposal unit can adjust the level of detail of a proposal based on the importance of the action. For example, the proposal unit will provide a detailed proposal for high-importance actions, and a concise proposal for low-importance actions. The proposal unit can also optimally allocate resources to the proposal according to the importance of the action. This allows for optimal resource allocation by adjusting the level of detail of the proposal based on the importance of the action. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit can input action importance data into a generative AI and output the level of detail of the proposal.

[0092] The suggestion unit can apply different suggestion algorithms depending on the action category when making suggestions. For example, the suggestion unit can apply a purchase behavior suggestion algorithm to shopping-related actions. It can also apply a travel behavior suggestion algorithm to travel-related actions. Furthermore, it can apply a viewing behavior suggestion algorithm to entertainment-related actions. By applying different suggestion algorithms depending on the action category, more accurate suggestions become possible. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the suggestion unit can input action category data into a generative AI and output the optimal suggestion algorithm.

[0093] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the user is relaxed, the suggestion unit will provide a detailed suggestion. If the user is in a hurry, the suggestion unit can provide a concise suggestion. If the user is excited, the suggestion unit can provide a visually appealing suggestion. By adjusting the length of the suggestion based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using or without a generative AI. For example, the suggestion unit can input user emotion data into a generative AI and output the length of the suggestion.

[0094] The proposal department can determine the priority of proposals based on the submission timing of actions. For example, the proposal department may prioritize recently submitted actions. It can also postpone older submitted actions. Furthermore, the proposal department can optimally allocate resources to proposals based on submission timing. This allows for optimal resource allocation by prioritizing proposals based on submission timing. Some or all of the above processing in the proposal department may be performed using or without a generative AI. For example, the proposal department can input action submission timing data into a generative AI and output a proposal priority.

[0095] The proposal unit can adjust the order of proposals based on the relevance of the actions during the proposal process. For example, the proposal unit can prioritize proposing highly relevant actions. It can also postpone less relevant actions. Furthermore, the proposal unit can optimally allocate resources for proposals based on the relevance of the actions. This allows for more efficient proposals by adjusting the order of proposals based on the relevance of the actions. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit can input action relevance data into a generative AI and output the order of proposals.

[0096] The scoring unit can estimate the user's emotions and adjust the scoring criteria based on the estimated emotions. For example, if the user is relaxed, the scoring unit can provide a detailed score. If the user is in a hurry, the scoring unit can provide a concise score. If the user is excited, the scoring unit can provide a visually appealing score. By adjusting the scoring criteria based on the user's emotions, more appropriate scoring becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input user emotion data into a generative AI and output scoring criteria.

[0097] The scoring unit can adjust the level of detail in the scoring based on the degree of action completion. For example, the scoring unit will perform detailed scoring for actions with a high degree of completion. Conversely, the scoring unit can also perform simplified scoring for actions with a low degree of completion. Furthermore, the scoring unit can optimally allocate scoring resources according to the degree of action completion. This allows for optimal resource allocation by adjusting the level of detail in the scoring unit based on the degree of action completion. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action completion data into an AI model and output the level of detail in the scoring.

[0098] The scoring unit can apply different scoring algorithms depending on the category of the action during scoring. For example, the scoring unit can apply a purchasing behavior scoring algorithm to shopping-related actions. It can also apply a travel behavior scoring algorithm to travel-related actions. Furthermore, it can apply a viewing behavior scoring algorithm to entertainment-related actions. By applying different scoring algorithms depending on the category of the action, more accurate scoring becomes possible. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action category data into an AI model and output the optimal scoring algorithm.

[0099] The scoring unit can estimate the user's emotions and adjust the display method of the scoring results based on the estimated emotions. For example, if the user is nervous, the scoring unit can provide a simple and highly visible display method. If the user is relaxed, the scoring unit can also provide a display method that includes detailed information. If the user is in a hurry, the scoring unit can also provide a display method that gets straight to the point. By adjusting the display method based on the user's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input user emotion data into a generative AI and output the optimal display method.

[0100] The scoring unit can determine the scoring priority based on the submission date of actions during the scoring process. For example, the scoring unit may prioritize recently submitted actions. It can also postpone older submitted actions. Furthermore, the scoring unit can optimally allocate scoring resources based on the submission date. This allows for optimal resource allocation by determining the scoring priority based on the submission date. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action submission date data into an AI model and output the scoring priority.

[0101] The scoring unit can adjust the scoring order based on the relevance of actions during the scoring process. For example, the scoring unit can prioritize scoring actions with high relevance. It can also postpone scoring actions with low relevance. Furthermore, the scoring unit can optimally allocate scoring resources based on the relevance of actions. This allows for more efficient scoring by adjusting the scoring order based on the relevance of actions. Some or all of the above processing in the scoring unit may be performed using AI or not. For example, the scoring unit can input action relevance data into an AI model and output the scoring order.

[0102] The guidance unit can estimate the user's emotions and adjust the method of guiding the user to the open chat based on the estimated emotions. For example, if the user is relaxed, the guidance unit will provide guidance that includes detailed explanations. If the user is in a hurry, the guidance unit can provide concise guidance. If the user is excited, the guidance unit can provide visually appealing guidance. By adjusting the guidance method based on the user's emotions, more appropriate guidance becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input user emotion data into a generative AI and output the optimal guidance method.

[0103] The guidance unit can select the optimal guidance method by referring to the user's past chat history during guidance. For example, the guidance unit can guide the user to a relevant open chat based on the content of chats the user has participated in in the past. The guidance unit can also guide the user to an open chat related to a topic of interest based on the user's past chat history. Furthermore, the guidance unit can analyze the user's past chat history and select the optimal guidance method. This allows the optimal guidance method to be selected by referring to past chat history. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input the user's past chat history data into an AI model and output the optimal guidance method.

[0104] The guidance unit can estimate the user's emotions and determine guidance priorities based on the estimated emotions. For example, if the user is relaxed, the guidance unit can provide guidance that includes detailed explanations. If the user is in a hurry, the guidance unit can provide concise guidance. If the user is excited, the guidance unit can provide visually appealing guidance. By determining guidance priorities based on the user's emotions, more appropriate guidance becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the guidance unit may be performed using AI or not. For example, the guidance unit can input user emotion data into a generative AI and output guidance priorities.

[0105] The guidance unit can select the optimal guidance method by considering the user's device information during guidance. For example, if the user is using a smartphone, the guidance unit provides a guidance method that matches the screen size. If the user is using a tablet, the guidance unit can also provide a guidance method optimized for a larger screen. Furthermore, if the user is using a smartwatch, the guidance unit can provide a concise and highly visible guidance method. This allows the system to select the optimal guidance method by considering device information. Some or all of the above processing in the guidance unit may be performed using AI, or without AI. For example, the guidance unit can input the user's device information into an AI model and output the optimal guidance method.

[0106] The interaction unit can estimate the user's emotions and adjust the interaction facilitation method based on the estimated emotions. For example, if the user is relaxed, the interaction unit can provide detailed interaction facilitation methods. If the user is in a hurry, the interaction unit can provide concise interaction facilitation methods. If the user is excited, the interaction unit can provide visually appealing interaction facilitation methods. By adjusting the interaction facilitation method based on the user's emotions, more appropriate interactions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input user emotion data into a generative AI and output the optimal interaction facilitation method.

[0107] The interaction unit can select the optimal interaction method by referring to the user's past interaction history when facilitating interaction. For example, the interaction unit can provide relevant interaction methods based on the content of interactions the user has participated in in the past. The interaction unit can also provide interaction methods related to topics of interest based on the user's past interaction history. Furthermore, the interaction unit can analyze the user's past interaction history and select the optimal interaction method. This allows the optimal interaction method to be selected by referring to past interaction history. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input the user's past interaction history data into an AI model and output the optimal interaction method.

[0108] The interaction unit can estimate the user's emotions and determine the priority of interactions based on those emotions. For example, if the user is relaxed, the interaction unit can provide detailed interaction facilitation methods. If the user is in a hurry, the interaction unit can provide concise interaction facilitation methods. If the user is excited, the interaction unit can provide visually appealing interaction facilitation methods. This allows for more appropriate interactions by determining the priority of interactions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input user emotion data into a generative AI and output interaction priorities.

[0109] The interaction unit can select the optimal interaction method by considering the user's geographical location information when facilitating interaction. For example, the interaction unit can provide interaction methods related to the user's current location. It can also provide nearby interaction events based on the user's geographical location information. Furthermore, the interaction unit can provide highly relevant interaction methods by considering the user's travel history. In this way, the optimal interaction method can be selected by considering geographical location information. Some or all of the above processing in the interaction unit may be performed using AI or not. For example, the interaction unit can input the user's geographical location information into an AI model and output the optimal interaction method.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] A promotion optimization system can estimate a user's emotions and adjust the timing of promotions based on those emotions. For example, if a user is stressed, the promotion notification can be delayed until the user is relaxed. Conversely, if a user is excited, the promotion can be notified immediately to encourage real-time action. Furthermore, if a user is tired, the promotion notification can be adjusted until the user has rested. This allows for more effective promotions by adjusting the timing of promotions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user emotion data into a generative AI and output the timing of promotions.

[0112] A promotion optimization system can prioritize providing highly relevant promotions by considering the user's geographical location. For example, it can prioritize promotions related to the user's current location. It can also provide information on nearby events and sales based on the user's geographical location. Furthermore, it can provide highly relevant promotions by considering the user's travel history. In this way, by considering the user's geographical location, highly relevant promotions can be provided. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's geographical location information into an AI model and output the optimal promotions.

[0113] A promotion optimization system can analyze a user's social media activity and provide relevant promotions. For example, it can provide relevant promotions based on information shared by the user on social media. It can also analyze a user's social media activity history and provide relevant promotions. Furthermore, it can provide relevant promotions based on the activity of accounts the user follows. In this way, relevant promotions can be provided by analyzing social media activity. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user social media activity data into an AI model and output the optimal promotion.

[0114] A promotion optimization system can estimate a user's emotions and adjust the content of a promotion based on those emotions. For example, if a user is relaxed, it can provide detailed promotional content. If a user is in a hurry, it can provide concise promotional content. Furthermore, if a user is excited, it can provide visually appealing promotional content. By adjusting the content of a promotion based on the user's emotions, more effective promotions become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user emotion data into a generative AI and output promotional content.

[0115] A promotion optimization system can analyze a user's past action history and select the optimal promotion method. For example, it can prioritize promoting actions that a user has frequently performed in the past. It can also promote actions performed during specific time periods based on the user's past action history. Furthermore, it can analyze the user's past action history and select promotion methods based on specific patterns. In this way, the optimal promotion method can be selected by analyzing past action history. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's past action history into an AI model and output the optimal promotion method.

[0116] A promotion optimization system can estimate a user's emotions and prioritize promotions based on those emotions. For example, if a user is relaxed, it can prioritize promotions related to relaxation. Similarly, if a user is excited, it can prioritize promotions related to excitement. Furthermore, if a user is stressed, it can prioritize promotions related to stress reduction. This allows for more effective promotions by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user emotion data into a generative AI and output promotion priorities.

[0117] A promotion optimization system can filter promotions based on a user's current lifestyle and areas of interest. For example, it can prioritize promotions related to areas of interest the user is currently interested in. It can also provide appropriate promotions according to the user's lifestyle (e.g., at work, on vacation). Furthermore, it can filter and provide relevant promotions based on the user's current activities (e.g., exercising, reading). This allows for the provision of highly relevant promotions by filtering based on the user's lifestyle and areas of interest. Some or all of the above processes in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input data on the user's lifestyle and areas of interest into an AI model and output the optimal filtering method.

[0118] A promotion optimization system can estimate a user's emotions and adjust how promotions are displayed based on those emotions. For example, if a user is feeling anxious, it can provide a simple and highly visible display. If a user is relaxed, it can provide a display that includes detailed information. Furthermore, if a user is in a hurry, it can provide a display that gets straight to the point. By adjusting the display method based on the user's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user emotion data into a generative AI and output the optimal display method.

[0119] The promotion optimization system can select the optimal promotion method by considering the user's device information. For example, if the user is using a smartphone, it can provide a promotion method that is adapted to the screen size. If the user is using a tablet, it can provide a promotion method optimized for the larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible promotion method. In this way, the optimal promotion method can be selected by considering device information. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input the user's device information into an AI model and output the optimal promotion method.

[0120] A promotion optimization system can estimate a user's emotions and prioritize promotions based on those emotions. For example, if a user is relaxed, it can prioritize promotions related to relaxation. Similarly, if a user is excited, it can prioritize promotions related to excitement. Furthermore, if a user is stressed, it can prioritize promotions related to stress reduction. This allows for more effective promotions by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the promotion optimization system may be performed using AI or not. For example, the promotion optimization system can input user emotion data into a generative AI and output promotion priorities.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The data collection unit collects past and current actions. Past actions include the user's behavioral history, purchase history, browsing history, etc., while current actions include real-time behavior and current interests. The data collection unit obtains this data from databases, online shopping sites, web browsers, etc. Step 2: The analysis unit analyzes the action data collected by the collection unit and discovers potential relationships. The analysis unit uses generative AI to analyze the correlations, causal relationships, and patterns in the action data. Step 3: The proposal department proposes future actions based on the relationships discovered by the analysis department. The proposal department uses generative AI to propose the optimal future actions for the user, making suggestions based on the user's interests and behavioral history. Step 4: The scoring unit scores the results of executing the future actions proposed by the proposal unit. The scoring unit uses AI to score, evaluate, and rank the results of executing the future actions.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scoring unit, guidance unit, and interaction unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit acquires the user's behavior history by the control unit 46A of the smart device 14 and analyzes it by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the correlation of action data using generated AI. The proposal unit is implemented in the identification processing unit 290 of the data processing unit 12 and proposes the optimal future action to the user. The scoring unit is implemented in the identification processing unit 290 of the data processing unit 12 and scores the execution results of future actions. The guidance unit is implemented in the identification processing unit 46A of the smart device 14 and sends a notification to the user who has performed a future action to encourage them to join the open chat. The interaction unit is implemented in the identification processing unit 46A of the smart device 14 and hosts an event within the open chat. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scoring unit, guidance unit, and interaction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit acquires the user's behavior history by the control unit 46A of the smart glasses 214 and analyzes it by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the correlation of action data using generated AI. The proposal unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and proposes the optimal future action to the user. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and scores the execution result of the future action. The guidance unit is implemented, for example, by the control unit 46A of the smart glasses 214 and sends a notification to the user who has performed the future action, prompting them to join the open chat. The interaction unit is implemented, for example, by the control unit 46A of the smart glasses 214 and hosts an event within the open chat. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scoring unit, guidance unit, and communication unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit acquires the user's behavior history by the control unit 46A of the headset terminal 314 and analyzes it by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented in the identification processing unit 290 of the data processing unit 12 and analyzes the correlation of action data using generated AI. The proposal unit is implemented in the identification processing unit 290 of the data processing unit 12 and proposes the optimal future action to the user. The scoring unit is implemented in the identification processing unit 290 of the data processing unit 12 and scores the execution results of future actions. The guidance unit is implemented in the identification processing unit 46A of the headset terminal 314 and sends a notification to the user who has performed a future action to encourage them to join the open chat. The communication unit is implemented in the identification processing unit 46A of the headset terminal 314 and hosts events within the open chat. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scoring unit, guidance unit, and interaction unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit acquires the user's behavior history by the control unit 46A of the robot 414 and analyzes it by the identification processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and analyzes the correlation of action data using generated AI. The proposal unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and proposes the optimal future action to the user. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and scores the execution results of future actions. The guidance unit is implemented, for example, by the control unit 46A of the robot 414 and sends a notification to the user who performed the future action, prompting them to join the open chat. The interaction unit is implemented, for example, by the control unit 46A of the robot 414 and hosts an event within the open chat. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A collection department that collects past and present actions, An analysis unit analyzes the action data collected by the aforementioned collection unit and discovers potential relationships, Based on the relationships discovered by the aforementioned analysis unit, the proposal unit proposes future actions, The system includes a scoring unit that scores the results of executing the future actions proposed by the proposal unit. A system characterized by the following features. (Note 2) The scoring unit is, The scoring is based on factors such as happiness level, rarity, difficulty, timeliness, and novelty. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned proposal section is, When suggesting future actions to users, do not reveal the details of serendipity. The system described in Appendix 1, characterized by the features described herein. (Note 4) The scoring unit is, Visualize scoring results in the form of rankings and badges. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned system, It includes a guidance system that directs users who have taken future actions to an open chat. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned system, It includes a communication section to facilitate interaction within the open chat. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting past and current actions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the user's past action history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting actions, filtering is performed based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and determines the priority of actions to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting actions, the system prioritizes collecting highly relevant actions by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting actions, the system analyzes users' social media activity and collects relevant actions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis method of action data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the action. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the action. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the analysis priority is determined based on when the actions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the actions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, It estimates the user's emotions and adjusts how future actions are suggested based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the importance of the action. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When making a proposal, different proposal algorithms are applied depending on the category of the action. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, When submitting a proposal, prioritize the proposals based on when the action will be submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, When making a proposal, adjust the order of the proposals based on the relevance of the actions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The scoring unit is, The system estimates the user's emotions and adjusts the scoring criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The scoring unit is, When scoring, adjust the level of detail in the scoring based on the degree of action completion. The system described in Appendix 1, characterized by the features described herein. (Note 27) The scoring unit is, When scoring, different scoring algorithms are applied depending on the category of the action. The system described in Appendix 1, characterized by the features described herein. (Note 28) The scoring unit is, The system estimates the user's emotions and adjusts how the scoring results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The scoring unit is, When scoring, priority is determined based on when the actions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The scoring unit is, When scoring, adjust the scoring order based on the relevance of the actions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned induction unit is The system estimates the user's emotions and adjusts how to guide them to open chats based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned induction unit is During the guidance process, the system will refer to the user's past chat history to select the most appropriate guidance method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned induction unit is It estimates the user's emotions and determines the priority of guidance based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned induction unit is During guidance, the optimal guidance method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned AC unit is It estimates the user's emotions and adjusts the interaction facilitation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned AC unit is When promoting interaction, the system selects the most suitable interaction method by referring to the user's past interaction history. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned AC unit is It estimates the user's emotions and determines the priority of interactions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned AC unit is When promoting interaction, the system selects the optimal interaction method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection department that collects past and present actions, An analysis unit analyzes the action data collected by the aforementioned collection unit and discovers potential relationships, Based on the relationships discovered by the aforementioned analysis unit, the proposal unit proposes future actions, The system includes a scoring unit that scores the results of executing the future actions proposed by the proposal unit. A system characterized by the following features.

2. The scoring unit is, The scoring is based on factors such as happiness level, rarity, difficulty, timeliness, and novelty. The system according to feature 1.

3. The aforementioned proposal section is, When suggesting future actions to users, do not reveal the details of serendipity. The system according to feature 1.

4. The scoring unit is, Visualize scoring results in the form of rankings and badges. The system according to feature 1.

5. The aforementioned system, It includes a guidance system that directs users who have taken future actions to an open chat. The system according to feature 1.

6. The aforementioned system, It includes a communication section to facilitate interaction within the open chat. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting past and current actions based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the user's past action history and select the optimal data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting actions, filtering is performed based on the user's current lifestyle and areas of interest. The system according to feature 1.

10. The aforementioned collection unit is It estimates the user's emotions and determines the priority of actions to collect based on the estimated user emotions. The system according to feature 1.

Images