system

Abstract

The system according to this embodiment aims to predict the market response to new products and services in advance. [Solution] The system according to the embodiment comprises a construction unit, an input unit, a collection unit, and a prediction unit. The construction unit constructs resident AI agents. The input unit introduces new products and services into the virtual community where the resident AI agents constructed by the construction unit reside. The collection unit collects the resident AI agents' reactions to the new products and services introduced by the input unit. The prediction unit predicts market reactions based on the reactions collected by the collection unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] ,<00​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​The system according to this embodiment comprises a construction unit, an input unit, a collection unit, and a prediction unit. The construction unit constructs resident AI agents. The input unit introduces new products and services into the virtual community inhabited by the resident AI agents constructed by the construction unit. The collection unit collects the resident AI agents' reactions to the new products and services introduced by the input unit. The prediction unit predicts market reactions based on the reactions collected by the collection unit. [Effects of the Invention]

[0007] The system according to this embodiment can predict the market response to new products and services in advance. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that predicts the market response to new services and products in advance by utilizing a virtual community inhabited by resident AI agents that mimic real residents. This system constructs resident AI agents, introduces new products and services into the virtual community, collects the resident AI agents' reactions, and predicts the market response based on those reactions. For example, the resident AI agents are constructed as accurate consumer models based on big data. Next, new products and services are introduced into the virtual community, and the resident AI agents use those products and services. The reactions and word-of-mouth of the resident AI agents spread, and evaluations similar to those in a real market are made. Based on these evaluations, the market response to new services and products can be predicted in advance. For example, a resident AI agent uses a new smartphone and shares their evaluation of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. Based on these evaluations, the market response to new services and products can be predicted in advance. For example, if the evaluation of the new smartphone is high, it can be predicted that it is likely to receive a high evaluation in the actual market as well. Conversely, if the evaluation is low, areas for improvement can be identified, and the product or service can be improved. By utilizing this system, risks in product development can be reduced, and the process of turning ideas into tangible products can be fundamentally improved. This allows the system to predict market reactions to new services and products in advance.

[0029] The system according to this embodiment comprises a construction unit, an input unit, a collection unit, and a prediction unit. The construction unit constructs resident AI agents. The construction unit constructs resident AI agents based on, for example, big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the construction unit to construct resident AI agents that function as realistic consumer models. The input unit introduces new products and services into the virtual community where the resident AI agents constructed by the construction unit live. For example, the input unit introduces new smartphones, applications, food products, etc., into the virtual community. The input unit enables the resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. The collection unit collects the resident AI agents' reactions to the new products and services introduced by the input unit. For example, the collection unit collects the reactions and word-of-mouth from the resident AI agents. The collection unit enables the reactions and word-of-mouth from the resident AI agents to spread, allowing for evaluations similar to those in a real market. The prediction unit predicts market reactions based on the reactions collected by the collection unit. The prediction unit, for example, has resident AI agents use a new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can predict the market response to a new service or product in advance. Thus, the system according to this embodiment can use resident AI agents to predict the market response to a new product or service in advance.

[0030] The development team builds resident AI agents. For example, the development team builds resident AI agents based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the development team to build resident AI agents that function as realistic consumer models. Specifically, the development team first collects a large amount of data and preprocesses it. Preprocessing includes data cleaning, normalization, and feature extraction. Next, using the preprocessed data, machine learning algorithms are applied to train the resident AI agent model. For example, deep learning techniques can be used for this training to learn consumer behavior patterns and preferences with high accuracy. Furthermore, the development team evaluates the trained model and adjusts hyperparameters or retrains the model as needed. Finally, the development team generates resident AI agents that function as realistic consumer models and places them in a virtual community. The resident AI agents can simulate consumer behavior and reactions, and through interaction within the virtual community, they can recreate an environment like a real market.

[0031] The Input Unit introduces new products and services into virtual communities inhabited by resident AI agents built by the Construction Unit. For example, the Input Unit introduces new smartphones, applications, or food products into these virtual communities. Specifically, the Input Unit first prepares information about the new products and services in digital format and places it within the virtual community. This information includes product specifications, usage instructions, price, and convenience. The Input Unit provides this information to the resident AI agents, giving them the opportunity to try out the new products and services. The resident AI agents use the new products and services within the virtual community and share their experiences and evaluations with other agents. The Input Unit monitors these interactions and records the behavior and reactions of the resident AI agents. Furthermore, the Input Unit tracks the adoption rate of the new products and services within the virtual community and analyzes what factors influence the evaluations of the resident AI agents. This allows the Input Unit to predict consumer reactions before launching new products and services into the market, helping to improve products and develop marketing strategies.

[0032] The data collection unit collects the reactions of resident AI agents to new products and services introduced by the input unit. For example, the collection unit collects the reactions and word-of-mouth of resident AI agents. Specifically, the collection unit monitors the behavior logs and statements of resident AI agents within the virtual community in real time and stores this data in a database. The collection unit uses natural language processing technology to analyze the statements of resident AI agents and classify them into positive and negative evaluations. Furthermore, the collection unit analyzes the behavior patterns and purchase history of resident AI agents to evaluate their level of interest in and frequency of use of new products and services. In addition, the collection unit tracks the spread of word-of-mouth among resident AI agents and analyzes what kind of information is transmitted and how. This allows the collection unit to gain a detailed understanding of resident AI agent reactions and obtain evaluations similar to those of a real market. The collected data is used not only by the forecasting unit to predict market reactions, but also to improve products and develop marketing strategies.

[0033] The prediction unit predicts market reactions based on responses collected by the data collection unit. For example, the prediction unit has resident AI agents use a new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can proactively predict market reactions to new services and products. Specifically, the prediction unit analyzes the collected data and predicts market reactions using statistical models and machine learning algorithms. For example, the prediction unit uses regression analysis and clustering methods to analyze the evaluations and behavioral patterns of resident AI agents and predict the reactions of consumer groups with specific attributes. The prediction unit also uses simulation technology to test multiple scenarios and identify the most likely market reaction. Furthermore, the prediction unit can continuously revise its prediction results based on real-time updated data to respond to the latest situations. For example, if evaluations of a new product or service change rapidly, the prediction unit immediately incorporates new data and updates the prediction results. This allows the prediction unit to always provide highly accurate market reaction predictions based on the latest information, supporting quick and appropriate responses.

[0034] The construction unit can build resident AI agents based on big data. For example, the construction unit can build resident AI agents based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the construction unit to build resident AI agents that function as realistic consumer models. Big data includes, but is not limited to, consumer behavior history, purchase history, and social media posts. Some or all of the above processing in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input big data into a generating AI and have the generating AI perform the construction of resident AI agents.

[0035] The data collection unit can collect the reactions and reviews of resident AI agents. For example, the data collection unit collects the reactions and reviews of resident AI agents. The data collection unit enables the reactions and reviews of resident AI agents to spread, allowing for evaluations similar to those of a real market. For example, the data collection unit allows resident AI agents to use a new smartphone and share their evaluations of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. In this way, the data collection unit can obtain realistic market evaluations by collecting the reactions and reviews of resident AI agents. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the reactions and reviews of resident AI agents into a generating AI and have the generating AI perform the collection of reactions and reviews.

[0036] The prediction unit can predict market reactions based on collected responses. For example, the prediction unit predicts market reactions based on collected responses. For example, a resident AI agent uses a new smartphone and shares its evaluation of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. Based on this evaluation, the prediction unit can predict the market reaction to a new service or product in advance. In this way, the prediction unit can reduce the risks of product development by predicting market reactions based on collected responses. Some or all of the above processing in the prediction unit may be performed using AI, for example, or not using AI. For example, the prediction unit can input collected responses into a generating AI and have the generating AI perform market reaction predictions.

[0037] The input unit can introduce new products and services into the virtual community. For example, the input unit can introduce new smartphones, applications, food products, etc., into the virtual community. The input unit enables resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. In this way, the input unit can obtain the reactions of resident AI agents by introducing new products and services into the virtual community. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input new products and services into a generating AI and have the generating AI execute the introduction into the virtual community.

[0038] The collection unit can collect the responses of resident AI agents in real time. For example, the collection unit collects the responses of resident AI agents in real time. The collection unit enables the spread of the responses and word-of-mouth of resident AI agents, allowing for evaluations similar to those in a real market. As a result, the collection unit enables rapid market evaluation by collecting the responses of resident AI agents in real time. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the responses of resident AI agents into a generating AI and have the generating AI perform real-time response collection.

[0039] The development unit can build resident AI agents by focusing on specific consumer segments from big data. For example, the development unit can build resident AI agents that reflect the behavioral patterns and preferences of young people based on consumer data of young people. It can also build resident AI agents that reflect the behavioral patterns and preferences of the elderly based on consumer data of the elderly. Furthermore, the development unit can build resident AI agents that reflect the behavioral patterns and preferences unique to a specific region based on consumer data of people living in that region. In this way, the development unit can build consumer models that are more tailored to the target by focusing on specific consumer segments. Some or all of the above processing in the development unit may be performed using AI, for example, or not using AI. For example, the development unit can input data of a specific consumer segment into a generation AI and have the generation AI execute the construction of resident AI agents.

[0040] The construction unit can reflect consumer models from different cultures and regions when building resident AI agents. For example, the construction unit can build resident AI agents that reflect Asian-specific cultures and behavioral patterns based on Asian consumer data. It can also build resident AI agents that reflect European-specific cultures and behavioral patterns based on European consumer data. Furthermore, it can build resident AI agents that reflect American-specific cultures and behavioral patterns based on American consumer data. This allows the construction unit to perform global market evaluations by reflecting consumer models from different cultures and regions. Some or all of the above processing in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input consumer data from different cultures and regions into a generation AI and have the generation AI perform the construction of resident AI agents.

[0041] The development unit can incorporate past consumer trends when building resident AI agents. For example, the development unit can build a trend-sensitive resident AI agent based on consumer trend data from the past five years. It can also build a resident AI agent with enhanced responses to popular products based on past hit product data. Furthermore, it can build a resident AI agent that reflects consumer purchasing patterns based on past consumer behavior data. This allows the development unit to build a trend-sensitive consumer model by incorporating past consumer trends. Some or all of the above processes in the development unit may be performed using AI, or not. For example, the development unit can input past consumer trend data into a generation AI and have the generation AI build the resident AI agent.

[0042] The construction unit can adjust the model when building resident AI agents, taking into account the influence of social media. For example, the construction unit can adjust the resident AI agent's responses based on word-of-mouth data on social media. It can also adjust the resident AI agent's behavioral patterns based on trend data on social media. Furthermore, the construction unit can adjust the resident AI agent's preferences based on consumer opinions on social media. In this way, the construction unit can build a more realistic consumer model by taking the influence of social media into account. Some or all of the above processes in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input social media data into a generating AI and have the generating AI perform the model adjustments for the resident AI agent.

[0043] The input unit can customize the input method according to the target consumer group when launching new products or services. For example, the input unit can use social media for promotion of products aimed at young people. It can also use television advertising for promotion of products aimed at the elderly. Furthermore, the input unit can conduct promotions tailored to the characteristics of specific regions for products targeted at those regions. In this way, the input unit can perform more effective promotions by customizing the input method according to the target consumer group. Some or all of the above processes in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input data on the target consumer group into a generating AI and have the generating AI perform the customization of the input method.

[0044] The input unit can simulate different marketing strategies when launching new products or services. For example, it can simulate the effectiveness of online and offline advertising. It can also simulate the effectiveness of discount campaigns and point campaigns. Furthermore, it can simulate the effectiveness of influencer marketing and traditional advertising methods. By simulating different marketing strategies, the input unit can select the optimal strategy. Some or all of the above processes in the input unit may be performed using AI, for example, or not. For example, the input unit can input data for different marketing strategies into a generating AI and have the generating AI run the simulations.

[0045] The input unit can optimize the launch method when introducing new products or services by referring to past market data. For example, the input unit can select the optimal launch method based on past success stories. It can also select a launch method that avoids risks based on past failure stories. Furthermore, the input unit can select the optimal launch timing based on past market trends. In this way, the input unit can select a more effective launch method by referring to past market data. Some or all of the above processes in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input past market data into a generating AI and have the generating AI perform the optimization of the launch method.

[0046] The input unit can adjust its launch strategy when introducing new products or services, taking into account the actions of competitors. For example, the input unit can adjust the timing of its own product launch based on the timing of competitors' new product launches. It can also analyze competitors' marketing strategies and develop counter-strategies. Furthermore, the input unit can adjust its own product pricing strategy by referring to competitors' pricing. In this way, the input unit can develop a more effective launch strategy by taking competitor actions into consideration. Some or all of the above processes in the input unit may be performed using AI, for example, or not using AI. For example, the input unit can input competitor data into a generating AI and have the generating AI perform the adjustment of the launch strategy.

[0047] The data collection unit can prioritize collecting responses from specific consumer groups when collecting responses from resident AI agents. For example, the data collection unit can prioritize collecting responses from younger generations to understand trends. It can also prioritize collecting responses from older generations to understand their needs. Furthermore, the data collection unit can prioritize collecting responses from specific regions to understand region-specific needs. This makes it easier for the data collection unit to understand the needs of target groups by prioritizing the collection of responses from specific consumer groups. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data from specific consumer groups into a generating AI and have the generating AI perform the response collection.

[0048] The data collection unit can compare responses from resident AI agents at different times of day and in different situations. For example, it can compare responses in the morning and evening to understand differences based on the time of day. It can also compare responses on weekdays and weekends to understand differences based on the day of the week. Furthermore, it can compare responses before and after specific events to understand differences based on the situation. This allows the data collection unit to gain a more detailed understanding of consumer behavior patterns by comparing responses at different times of day and in different situations. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data from different times of day and situations into a generating AI and have the generating AI perform the response comparison.

[0049] The data collection unit can collect social media posts at the same time as collecting responses from resident AI agents. For example, the data collection unit can collect social media posts simultaneously with the responses of resident AI agents. The data collection unit can also analyze social media posts and compare them with the responses of resident AI agents. Furthermore, the data collection unit can grasp social media trends and reflect them in the responses of resident AI agents. This allows the data collection unit to conduct a broader market assessment by collecting social media posts as well. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media data into a generating AI and have the generating AI collect the posts.

[0050] The data collection unit can compare real-time responses with past responses when collecting responses from resident AI agents. For example, the data collection unit can compare real-time responses with past responses to understand changes in trends. The data collection unit can also analyze the differences between real-time responses and past responses. Furthermore, the data collection unit can collect real-time responses and integrate and analyze them with past responses. This allows the data collection unit to understand changes in trends by comparing real-time responses with past responses. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input real-time response data and past response data into a generating AI and have the generating AI perform the comparison.

[0051] The forecasting unit can make predictions that prioritize the responses of specific consumer groups when forecasting market reactions. For example, the forecasting unit can forecast market reactions by prioritizing the responses of younger generations. It can also forecast market reactions by prioritizing the responses of older generations. Furthermore, the forecasting unit can forecast market reactions by prioritizing the responses of consumer groups in specific regions. This improves the forecasting unit's accuracy for target groups by prioritizing the responses of specific consumer groups. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input data on specific consumer groups into a generating AI and have the generating AI perform a prediction that prioritizes responses.

[0052] The forecasting unit can broaden the scope of its predictions by simulating different scenarios when forecasting market reactions. For example, the forecasting unit can predict market reactions by simulating scenarios that take into account changes in economic conditions. It can also predict market reactions by simulating scenarios that take into account the actions of competitors. Furthermore, it can predict market reactions by simulating scenarios that take into account changes in consumer preferences. In this way, the forecasting unit can make more multifaceted market reaction predictions by simulating different scenarios. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input data for different scenarios into a generating AI and have the generating AI execute the simulations.

[0053] The forecasting unit can improve the accuracy of its forecasts by referring to past market data when predicting market reactions. For example, the forecasting unit can improve the accuracy of its forecasts based on past success stories. It can also make predictions to avoid risks based on past failure stories. Furthermore, the forecasting unit can improve the accuracy of its forecasts based on past market trends. In this way, the forecasting unit improves the accuracy of its forecasts by referring to past market data. Some or all of the above processes in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input past market data into a generating AI and have the generating AI perform the task of improving the accuracy of the forecast.

[0054] The forecasting unit can make market response predictions while taking into account the actions of competitors. For example, the forecasting unit can predict market response based on the timing of new product launches by competitors. The forecasting unit can also analyze the marketing strategies of competitors and make predictions to counter them. Furthermore, the forecasting unit can predict market response by referring to the pricing of competitors. In this way, the forecasting unit can make more realistic market response predictions by taking into account the actions of competitors. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or not using AI. For example, the forecasting unit can input competitor data into a generating AI and have the generating AI execute the prediction.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The development unit can learn the behavioral patterns of resident AI agents and generate personalized agents based on the user's past behavioral history. For example, it can adjust the preferences and behavioral patterns of resident AI agents based on data of products and services that the user has frequently purchased in the past. It can also make the agent more active during times when the user is active at a particular time. Furthermore, if the user shows interest in a particular event or campaign, that information can be reflected in the agent. In this way, the development unit can generate more personalized resident AI agents based on the user's past behavioral history.

[0057] The data collection unit can collect audio and image data along with the responses of resident AI agents. For example, it can collect audio responses when a resident AI agent uses a new smartphone and analyze that audio data. It can also collect image data of the resident AI agent's facial expressions and actions when using a new application. Furthermore, it can simultaneously collect audio and images when a resident AI agent describes their experience using a specific product and analyze them comprehensively. As a result, the data collection unit can perform a more detailed market evaluation by collecting audio and image data together.

[0058] The forecasting unit can predict responses for different market segments based on collected response data. For example, it can analyze response data separately for young people and older people to predict responses for each market segment. It can also compare response data from consumers in urban and rural areas to predict market responses for each region. Furthermore, it can predict responses for niche market segments based on response data from consumer groups with specific occupations or hobbies. As a result, the forecasting unit can develop more targeted marketing strategies by predicting responses for different market segments.

[0059] The input unit can incorporate user feedback in real time when launching new products or services. For example, if a user provides feedback on the design of a new smartphone, the design can be immediately adjusted based on that feedback. Similarly, if a user gives their opinion on the functionality of a new application, the functionality can be improved based on that opinion. Furthermore, if a user evaluates the taste of a new food product, the taste can be adjusted based on that evaluation. In this way, the input unit can respond to market needs more quickly by incorporating user feedback in real time.

[0060] The development unit can learn the behavioral patterns of resident AI agents and generate personalized agents based on the user's past behavioral history. For example, it can adjust the preferences and behavioral patterns of resident AI agents based on data of products and services that the user has frequently purchased in the past. It can also make the agent more active during times when the user is active at a particular time. Furthermore, if the user shows interest in a particular event or campaign, that information can be reflected in the agent. In this way, the development unit can generate more personalized resident AI agents based on the user's past behavioral history.

[0061] The data collection unit can collect audio and image data along with the responses of resident AI agents. For example, it can collect audio responses when a resident AI agent uses a new smartphone and analyze that audio data. It can also collect image data of the resident AI agent's facial expressions and actions when using a new application. Furthermore, it can simultaneously collect audio and images when a resident AI agent describes their experience using a specific product and analyze them comprehensively. As a result, the data collection unit can perform a more detailed market evaluation by collecting audio and image data together.

[0062] The forecasting unit can predict responses for different market segments based on collected response data. For example, it can analyze response data separately for young people and older people to predict responses for each market segment. It can also compare response data from consumers in urban and rural areas to predict market responses for each region. Furthermore, it can predict responses for niche market segments based on response data from consumer groups with specific occupations or hobbies. As a result, the forecasting unit can develop more targeted marketing strategies by predicting responses for different market segments.

[0063] The input unit can incorporate user feedback in real time when launching new products or services. For example, if a user provides feedback on the design of a new smartphone, the design can be immediately adjusted based on that feedback. Similarly, if a user gives their opinion on the functionality of a new application, the functionality can be improved based on that opinion. Furthermore, if a user evaluates the taste of a new food product, the taste can be adjusted based on that evaluation. In this way, the input unit can respond to market needs more quickly by incorporating user feedback in real time.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The development team builds a resident AI agent. The development team builds the resident AI agent based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the development team to build a resident AI agent that functions as a realistic consumer model. Step 2: The Input Unit introduces new products and services into the virtual community where the resident AI agents, built by the Construction Unit, reside. The Input Unit introduces new smartphones, applications, food items, etc., into the virtual community. The Input Unit enables the resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. Step 3: The collection unit collects the reactions of resident AI agents to the new products and services introduced by the input unit. The collection unit collects the reactions and word-of-mouth from resident AI agents. The collection unit enables the reactions and word-of-mouth from resident AI agents to spread, allowing for evaluations similar to those in a real market. Step 4: The prediction unit predicts market reaction based on the responses collected by the collection unit. The prediction unit has resident AI agents use the new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can predict the market reaction to the new service or product in advance.

[0066] (Example of form 2) The system according to an embodiment of the present invention is a system that predicts the market response to new services and products in advance by utilizing a virtual community inhabited by resident AI agents that mimic real residents. This system constructs resident AI agents, introduces new products and services into the virtual community, collects the resident AI agents' reactions, and predicts the market response based on those reactions. For example, the resident AI agents are constructed as accurate consumer models based on big data. Next, new products and services are introduced into the virtual community, and the resident AI agents use those products and services. The reactions and word-of-mouth of the resident AI agents spread, and evaluations similar to those in a real market are made. Based on these evaluations, the market response to new services and products can be predicted in advance. For example, a resident AI agent uses a new smartphone and shares their evaluation of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. Based on these evaluations, the market response to new services and products can be predicted in advance. For example, if the evaluation of the new smartphone is high, it can be predicted that it is likely to receive a high evaluation in the actual market as well. Conversely, if the evaluation is low, areas for improvement can be identified, and the product or service can be improved. By utilizing this system, risks in product development can be reduced, and the process of turning ideas into tangible products can be fundamentally improved. This allows the system to predict market reactions to new services and products in advance.

[0067] The system according to this embodiment comprises a construction unit, an input unit, a collection unit, and a prediction unit. The construction unit constructs resident AI agents. The construction unit constructs resident AI agents based on, for example, big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the construction unit to construct resident AI agents that function as realistic consumer models. The input unit introduces new products and services into the virtual community where the resident AI agents constructed by the construction unit live. For example, the input unit introduces new smartphones, applications, food products, etc., into the virtual community. The input unit enables the resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. The collection unit collects the resident AI agents' reactions to the new products and services introduced by the input unit. For example, the collection unit collects the reactions and word-of-mouth from the resident AI agents. The collection unit enables the reactions and word-of-mouth from the resident AI agents to spread, allowing for evaluations similar to those in a real market. The prediction unit predicts market reactions based on the reactions collected by the collection unit. The prediction unit, for example, has resident AI agents use a new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can predict the market response to a new service or product in advance. Thus, the system according to this embodiment can use resident AI agents to predict the market response to a new product or service in advance.

[0068] The development team builds resident AI agents. For example, the development team builds resident AI agents based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the development team to build resident AI agents that function as realistic consumer models. Specifically, the development team first collects a large amount of data and preprocesses it. Preprocessing includes data cleaning, normalization, and feature extraction. Next, using the preprocessed data, machine learning algorithms are applied to train the resident AI agent model. For example, deep learning techniques can be used for this training to learn consumer behavior patterns and preferences with high accuracy. Furthermore, the development team evaluates the trained model and adjusts hyperparameters or retrains the model as needed. Finally, the development team generates resident AI agents that function as realistic consumer models and places them in a virtual community. The resident AI agents can simulate consumer behavior and reactions, and through interaction within the virtual community, they can recreate an environment like a real market.

[0069] The Input Unit introduces new products and services into virtual communities inhabited by resident AI agents built by the Construction Unit. For example, the Input Unit introduces new smartphones, applications, or food products into these virtual communities. Specifically, the Input Unit first prepares information about the new products and services in digital format and places it within the virtual community. This information includes product specifications, usage instructions, price, and convenience. The Input Unit provides this information to the resident AI agents, giving them the opportunity to try out the new products and services. The resident AI agents use the new products and services within the virtual community and share their experiences and evaluations with other agents. The Input Unit monitors these interactions and records the behavior and reactions of the resident AI agents. Furthermore, the Input Unit tracks the adoption rate of the new products and services within the virtual community and analyzes what factors influence the evaluations of the resident AI agents. This allows the Input Unit to predict consumer reactions before launching new products and services into the market, helping to improve products and develop marketing strategies.

[0070] The data collection unit collects the reactions of resident AI agents to new products and services introduced by the input unit. For example, the collection unit collects the reactions and word-of-mouth of resident AI agents. Specifically, the collection unit monitors the behavior logs and statements of resident AI agents within the virtual community in real time and stores this data in a database. The collection unit uses natural language processing technology to analyze the statements of resident AI agents and classify them into positive and negative evaluations. Furthermore, the collection unit analyzes the behavior patterns and purchase history of resident AI agents to evaluate their level of interest in and frequency of use of new products and services. In addition, the collection unit tracks the spread of word-of-mouth among resident AI agents and analyzes what kind of information is transmitted and how. This allows the collection unit to gain a detailed understanding of resident AI agent reactions and obtain evaluations similar to those of a real market. The collected data is used not only by the forecasting unit to predict market reactions, but also to improve products and develop marketing strategies.

[0071] The prediction unit predicts market reactions based on responses collected by the data collection unit. For example, the prediction unit has resident AI agents use a new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can proactively predict market reactions to new services and products. Specifically, the prediction unit analyzes the collected data and predicts market reactions using statistical models and machine learning algorithms. For example, the prediction unit uses regression analysis and clustering methods to analyze the evaluations and behavioral patterns of resident AI agents and predict the reactions of consumer groups with specific attributes. The prediction unit also uses simulation technology to test multiple scenarios and identify the most likely market reaction. Furthermore, the prediction unit can continuously revise its prediction results based on real-time updated data to respond to the latest situations. For example, if evaluations of a new product or service change rapidly, the prediction unit immediately incorporates new data and updates the prediction results. This allows the prediction unit to always provide highly accurate market reaction predictions based on the latest information, supporting quick and appropriate responses.

[0072] The construction unit can build resident AI agents based on big data. For example, the construction unit can build resident AI agents based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the construction unit to build resident AI agents that function as realistic consumer models. Big data includes, but is not limited to, consumer behavior history, purchase history, and social media posts. Some or all of the above processing in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input big data into a generating AI and have the generating AI perform the construction of resident AI agents.

[0073] The data collection unit can collect the reactions and reviews of resident AI agents. For example, the data collection unit collects the reactions and reviews of resident AI agents. The data collection unit enables the reactions and reviews of resident AI agents to spread, allowing for evaluations similar to those of a real market. For example, the data collection unit allows resident AI agents to use a new smartphone and share their evaluations of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. In this way, the data collection unit can obtain realistic market evaluations by collecting the reactions and reviews of resident AI agents. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the reactions and reviews of resident AI agents into a generating AI and have the generating AI perform the collection of reactions and reviews.

[0074] The prediction unit can predict market reactions based on collected responses. For example, the prediction unit predicts market reactions based on collected responses. For example, a resident AI agent uses a new smartphone and shares its evaluation of its usability and design. This evaluation influences other resident AI agents, and word-of-mouth spreads. Based on this evaluation, the prediction unit can predict the market reaction to a new service or product in advance. In this way, the prediction unit can reduce the risks of product development by predicting market reactions based on collected responses. Some or all of the above processing in the prediction unit may be performed using AI, for example, or not using AI. For example, the prediction unit can input collected responses into a generating AI and have the generating AI perform market reaction predictions.

[0075] The input unit can introduce new products and services into the virtual community. For example, the input unit can introduce new smartphones, applications, food products, etc., into the virtual community. The input unit enables resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. In this way, the input unit can obtain the reactions of resident AI agents by introducing new products and services into the virtual community. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input new products and services into a generating AI and have the generating AI execute the introduction into the virtual community.

[0076] The collection unit can collect the responses of resident AI agents in real time. For example, the collection unit collects the responses of resident AI agents in real time. The collection unit enables the spread of the responses and word-of-mouth of resident AI agents, allowing for evaluations similar to those in a real market. As a result, the collection unit enables rapid market evaluation by collecting the responses of resident AI agents in real time. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the responses of resident AI agents into a generating AI and have the generating AI perform real-time response collection.

[0077] The build unit can estimate the user's emotions and adjust the behavior patterns of the resident AI agent based on the estimated user emotions. For example, if the user is stressed, the build unit can make the resident AI agent behave calmly and take relaxing actions. It can also make the resident AI agent behave more actively and show energetic responses if the user is excited. Furthermore, if the user is sad, the build unit can make the resident AI agent behave gently and take comforting actions. In this way, the build unit can realize a more realistic consumer model by adjusting the behavior patterns of the resident AI agent according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI 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 build unit may be performed using AI, or not. For example, the build unit can input user emotion data into the generative AI and have the generative AI perform emotion-based behavior pattern adjustments.

[0078] The development unit can build resident AI agents by focusing on specific consumer segments from big data. For example, the development unit can build resident AI agents that reflect the behavioral patterns and preferences of young people based on consumer data of young people. It can also build resident AI agents that reflect the behavioral patterns and preferences of the elderly based on consumer data of the elderly. Furthermore, the development unit can build resident AI agents that reflect the behavioral patterns and preferences unique to a specific region based on consumer data of people living in that region. In this way, the development unit can build consumer models that are more tailored to the target by focusing on specific consumer segments. Some or all of the above processing in the development unit may be performed using AI, for example, or not using AI. For example, the development unit can input data of a specific consumer segment into a generation AI and have the generation AI execute the construction of resident AI agents.

[0079] The construction unit can reflect consumer models from different cultures and regions when building resident AI agents. For example, the construction unit can build resident AI agents that reflect Asian-specific cultures and behavioral patterns based on Asian consumer data. It can also build resident AI agents that reflect European-specific cultures and behavioral patterns based on European consumer data. Furthermore, it can build resident AI agents that reflect American-specific cultures and behavioral patterns based on American consumer data. This allows the construction unit to perform global market evaluations by reflecting consumer models from different cultures and regions. Some or all of the above processing in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input consumer data from different cultures and regions into a generation AI and have the generation AI perform the construction of resident AI agents.

[0080] The construction unit can estimate the user's emotions and simulate the resident AI agent's response based on the estimated user emotions. For example, if the user is happy, the construction unit can simulate the resident AI agent to also show a happy response. The construction unit can also simulate the resident AI agent to respond calmly if the user is angry. Furthermore, the construction unit can simulate the resident AI agent to show an empathetic response if the user is sad. This allows the construction unit to perform more realistic market evaluations by simulating the resident AI agent's response according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input user emotion data into a generative AI and have the generative AI perform a simulation of an emotion-based response.

[0081] The development unit can incorporate past consumer trends when building resident AI agents. For example, the development unit can build a trend-sensitive resident AI agent based on consumer trend data from the past five years. It can also build a resident AI agent with enhanced responses to popular products based on past hit product data. Furthermore, it can build a resident AI agent that reflects consumer purchasing patterns based on past consumer behavior data. This allows the development unit to build a trend-sensitive consumer model by incorporating past consumer trends. Some or all of the above processes in the development unit may be performed using AI, or not. For example, the development unit can input past consumer trend data into a generation AI and have the generation AI build the resident AI agent.

[0082] The construction unit can adjust the model when building resident AI agents, taking into account the influence of social media. For example, the construction unit can adjust the resident AI agent's responses based on word-of-mouth data on social media. It can also adjust the resident AI agent's behavioral patterns based on trend data on social media. Furthermore, the construction unit can adjust the resident AI agent's preferences based on consumer opinions on social media. In this way, the construction unit can build a more realistic consumer model by taking the influence of social media into account. Some or all of the above processes in the construction unit may be performed using AI, for example, or not using AI. For example, the construction unit can input social media data into a generating AI and have the generating AI perform the model adjustments for the resident AI agent.

[0083] The input unit can estimate the user's emotions and adjust the timing of new product or service launches based on those emotions. For example, if the user is excited, the input unit can accelerate the launch of a new product. Conversely, if the user is relaxed, the input unit can maintain the normal launch timing. Furthermore, if the user is feeling anxious, the input unit can delay the launch. This allows the input unit to achieve more effective market entry by adjusting the launch 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 input unit may be performed using AI, or not. For example, the input unit can input user emotion data into the generative AI and have the generative AI perform emotion-based adjustments to launch timing.

[0084] The input unit can customize the input method according to the target consumer group when launching new products or services. For example, the input unit can use social media for promotion of products aimed at young people. It can also use television advertising for promotion of products aimed at the elderly. Furthermore, the input unit can conduct promotions tailored to the characteristics of specific regions for products targeted at those regions. In this way, the input unit can perform more effective promotions by customizing the input method according to the target consumer group. Some or all of the above processes in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input data on the target consumer group into a generating AI and have the generating AI perform the customization of the input method.

[0085] The input unit can simulate different marketing strategies when launching new products or services. For example, it can simulate the effectiveness of online and offline advertising. It can also simulate the effectiveness of discount campaigns and point campaigns. Furthermore, it can simulate the effectiveness of influencer marketing and traditional advertising methods. By simulating different marketing strategies, the input unit can select the optimal strategy. Some or all of the above processes in the input unit may be performed using AI, for example, or not. For example, the input unit can input data for different marketing strategies into a generating AI and have the generating AI run the simulations.

[0086] The input unit can estimate the user's emotions and determine the order in which new products and services will be introduced based on those estimated emotions. For example, if the user is excited, the input unit will introduce the most anticipated product first. If the user is relaxed, the input unit can also introduce products in order. Furthermore, if the user is feeling anxious, the input unit can introduce products that provide a sense of security first. This allows the input unit to determine the order of introduction according to the user's emotions, enabling more effective market entry. 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 input unit may be performed using AI, or not. For example, the input unit can input user emotion data into a generative AI and have the generative AI perform the emotion-based introduction order determination.

[0087] The input unit can optimize the launch method when introducing new products or services by referring to past market data. For example, the input unit can select the optimal launch method based on past success stories. It can also select a launch method that avoids risks based on past failure stories. Furthermore, the input unit can select the optimal launch timing based on past market trends. In this way, the input unit can select a more effective launch method by referring to past market data. Some or all of the above processes in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input past market data into a generating AI and have the generating AI perform the optimization of the launch method.

[0088] The input unit can adjust its launch strategy when introducing new products or services, taking into account the actions of competitors. For example, the input unit can adjust the timing of its own product launch based on the timing of competitors' new product launches. It can also analyze competitors' marketing strategies and develop counter-strategies. Furthermore, the input unit can adjust its own product pricing strategy by referring to competitors' pricing. In this way, the input unit can develop a more effective launch strategy by taking competitor actions into consideration. Some or all of the above processes in the input unit may be performed using AI, for example, or not using AI. For example, the input unit can input competitor data into a generating AI and have the generating AI perform the adjustment of the launch strategy.

[0089] The data collection unit can estimate the user's emotions and adjust the method of collecting responses from the resident AI agent based on the estimated user emotions. For example, if the user is excited, the data collection unit can quickly collect responses from the resident AI agent. If the user is relaxed, the data collection unit can also collect responses from the resident AI agent in a normal manner. Furthermore, if the user is feeling anxious, the data collection unit can carefully collect responses from the resident AI agent. This allows the data collection unit to perform more accurate market evaluations by adjusting the response collection method according to the user's emotions. 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, 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, for example, or not using AI. For example, the data collection unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the response collection method based on emotions.

[0090] The data collection unit can prioritize collecting responses from specific consumer groups when collecting responses from resident AI agents. For example, the data collection unit can prioritize collecting responses from younger generations to understand trends. It can also prioritize collecting responses from older generations to understand their needs. Furthermore, the data collection unit can prioritize collecting responses from specific regions to understand region-specific needs. This makes it easier for the data collection unit to understand the needs of target groups by prioritizing the collection of responses from specific consumer groups. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data from specific consumer groups into a generating AI and have the generating AI perform the response collection.

[0091] The data collection unit can compare responses from resident AI agents at different times of day and in different situations. For example, it can compare responses in the morning and evening to understand differences based on the time of day. It can also compare responses on weekdays and weekends to understand differences based on the day of the week. Furthermore, it can compare responses before and after specific events to understand differences based on the situation. This allows the data collection unit to gain a more detailed understanding of consumer behavior patterns by comparing responses at different times of day and in different situations. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data from different times of day and situations into a generating AI and have the generating AI perform the response comparison.

[0092] The data collection unit can estimate the user's emotions and adjust the analysis method of the collected responses based on the estimated user emotions. For example, if the user is excited, the data collection unit may prioritize positive responses in its analysis. It can also perform a balanced analysis if the user is relaxed. Furthermore, if the user is anxious, the data collection unit may prioritize negative responses in its analysis. This allows the data collection unit to perform more accurate market evaluations by adjusting the analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 have the generative AI adjust the response analysis method based on the emotions.

[0093] The data collection unit can collect social media posts at the same time as collecting responses from resident AI agents. For example, the data collection unit can collect social media posts simultaneously with the responses of resident AI agents. The data collection unit can also analyze social media posts and compare them with the responses of resident AI agents. Furthermore, the data collection unit can grasp social media trends and reflect them in the responses of resident AI agents. This allows the data collection unit to conduct a broader market assessment by collecting social media posts as well. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media data into a generating AI and have the generating AI collect the posts.

[0094] The data collection unit can compare real-time responses with past responses when collecting responses from resident AI agents. For example, the data collection unit can compare real-time responses with past responses to understand changes in trends. The data collection unit can also analyze the differences between real-time responses and past responses. Furthermore, the data collection unit can collect real-time responses and integrate and analyze them with past responses. This allows the data collection unit to understand changes in trends by comparing real-time responses with past responses. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input real-time response data and past response data into a generating AI and have the generating AI perform the comparison.

[0095] The prediction unit can estimate the user's emotions and adjust the accuracy of market response predictions based on the estimated user emotions. For example, if the user is excited, the prediction unit can improve the accuracy of predicting positive market responses. It can also make balanced market response predictions if the user is relaxed. Furthermore, if the user is anxious, the prediction unit can improve the accuracy of predicting negative market responses. This allows the prediction unit to make more accurate market response predictions by adjusting the prediction accuracy 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 prediction unit may be performed using AI, or not. For example, the prediction unit can input user emotion data into the generative AI and have the generative AI perform emotion-based prediction accuracy adjustments.

[0096] The forecasting unit can make predictions that prioritize the responses of specific consumer groups when forecasting market reactions. For example, the forecasting unit can forecast market reactions by prioritizing the responses of younger generations. It can also forecast market reactions by prioritizing the responses of older generations. Furthermore, the forecasting unit can forecast market reactions by prioritizing the responses of consumer groups in specific regions. This improves the forecasting unit's accuracy for target groups by prioritizing the responses of specific consumer groups. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input data on specific consumer groups into a generating AI and have the generating AI perform a prediction that prioritizes responses.

[0097] The forecasting unit can broaden the scope of its predictions by simulating different scenarios when forecasting market reactions. For example, the forecasting unit can predict market reactions by simulating scenarios that take into account changes in economic conditions. It can also predict market reactions by simulating scenarios that take into account the actions of competitors. Furthermore, it can predict market reactions by simulating scenarios that take into account changes in consumer preferences. In this way, the forecasting unit can make more multifaceted market reaction predictions by simulating different scenarios. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input data for different scenarios into a generating AI and have the generating AI execute the simulations.

[0098] The prediction unit can estimate the user's emotions and adjust how the prediction results are displayed based on the estimated emotions. For example, if the user is excited, the prediction unit can highlight positive prediction results. It can also display balanced prediction results if the user is relaxed. Furthermore, if the user is anxious, the prediction unit can highlight negative prediction results. This allows the prediction unit to provide more effective information by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 prediction unit may be performed using AI, or not. For example, the prediction unit can input user emotion data into the generative AI and have the generative AI adjust the display method based on the emotions.

[0099] The forecasting unit can improve the accuracy of its forecasts by referring to past market data when predicting market reactions. For example, the forecasting unit can improve the accuracy of its forecasts based on past success stories. It can also make predictions to avoid risks based on past failure stories. Furthermore, the forecasting unit can improve the accuracy of its forecasts based on past market trends. In this way, the forecasting unit improves the accuracy of its forecasts by referring to past market data. Some or all of the above processes in the forecasting unit may be performed using AI, for example, or without AI. For example, the forecasting unit can input past market data into a generating AI and have the generating AI perform the task of improving the accuracy of the forecast.

[0100] The forecasting unit can make market response predictions while taking into account the actions of competitors. For example, the forecasting unit can predict market response based on the timing of new product launches by competitors. The forecasting unit can also analyze the marketing strategies of competitors and make predictions to counter them. Furthermore, the forecasting unit can predict market response by referring to the pricing of competitors. In this way, the forecasting unit can make more realistic market response predictions by taking into account the actions of competitors. Some or all of the above processing in the forecasting unit may be performed using AI, for example, or not using AI. For example, the forecasting unit can input competitor data into a generating AI and have the generating AI execute the prediction.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The development unit can learn the behavioral patterns of resident AI agents and generate personalized agents based on the user's past behavioral history. For example, it can adjust the preferences and behavioral patterns of resident AI agents based on data of products and services that the user has frequently purchased in the past. It can also make the agent more active during times when the user is active at a particular time. Furthermore, if the user shows interest in a particular event or campaign, that information can be reflected in the agent. In this way, the development unit can generate more personalized resident AI agents based on the user's past behavioral history.

[0103] The data collection unit can collect audio and image data along with the responses of resident AI agents. For example, it can collect audio responses when a resident AI agent uses a new smartphone and analyze that audio data. It can also collect image data of the resident AI agent's facial expressions and actions when using a new application. Furthermore, it can simultaneously collect audio and images when a resident AI agent describes their experience using a specific product and analyze them comprehensively. As a result, the data collection unit can perform a more detailed market evaluation by collecting audio and image data together.

[0104] The forecasting unit can predict responses for different market segments based on collected response data. For example, it can analyze response data separately for young people and older people to predict responses for each market segment. It can also compare response data from consumers in urban and rural areas to predict market responses for each region. Furthermore, it can predict responses for niche market segments based on response data from consumer groups with specific occupations or hobbies. As a result, the forecasting unit can develop more targeted marketing strategies by predicting responses for different market segments.

[0105] The input unit can incorporate user feedback in real time when launching new products or services. For example, if a user provides feedback on the design of a new smartphone, the design can be immediately adjusted based on that feedback. Similarly, if a user gives their opinion on the functionality of a new application, the functionality can be improved based on that opinion. Furthermore, if a user evaluates the taste of a new food product, the taste can be adjusted based on that evaluation. In this way, the input unit can respond to market needs more quickly by incorporating user feedback in real time.

[0106] The data collection unit can perform sentiment analysis and track changes in emotions when collecting responses from resident AI agents. For example, it can analyze changes in emotions when resident AI agents use a new smartphone, understanding the difference in emotions before and after use. It can also track changes in emotions when resident AI agents use a new application and analyze fluctuations in emotions during use. Furthermore, it can track changes in emotions when resident AI agents describe their experience using a specific product, and use that sentiment data to conduct market evaluations. This allows the data collection unit to perform more detailed market evaluations by conducting sentiment analysis.

[0107] The development unit can learn the behavioral patterns of resident AI agents and generate personalized agents based on the user's past behavioral history. For example, it can adjust the preferences and behavioral patterns of resident AI agents based on data of products and services that the user has frequently purchased in the past. It can also make the agent more active during times when the user is active at a particular time. Furthermore, if the user shows interest in a particular event or campaign, that information can be reflected in the agent. In this way, the development unit can generate more personalized resident AI agents based on the user's past behavioral history.

[0108] The data collection unit can collect audio and image data along with the responses of resident AI agents. For example, it can collect audio responses when a resident AI agent uses a new smartphone and analyze that audio data. It can also collect image data of the resident AI agent's facial expressions and actions when using a new application. Furthermore, it can simultaneously collect audio and images when a resident AI agent describes their experience using a specific product and analyze them comprehensively. As a result, the data collection unit can perform a more detailed market evaluation by collecting audio and image data together.

[0109] The forecasting unit can predict responses for different market segments based on collected response data. For example, it can analyze response data separately for young people and older people to predict responses for each market segment. It can also compare response data from consumers in urban and rural areas to predict market responses for each region. Furthermore, it can predict responses for niche market segments based on response data from consumer groups with specific occupations or hobbies. As a result, the forecasting unit can develop more targeted marketing strategies by predicting responses for different market segments.

[0110] The input unit can incorporate user feedback in real time when launching new products or services. For example, if a user provides feedback on the design of a new smartphone, the design can be immediately adjusted based on that feedback. Similarly, if a user gives their opinion on the functionality of a new application, the functionality can be improved based on that opinion. Furthermore, if a user evaluates the taste of a new food product, the taste can be adjusted based on that evaluation. In this way, the input unit can respond to market needs more quickly by incorporating user feedback in real time.

[0111] The data collection unit can perform sentiment analysis and track changes in emotions when collecting responses from resident AI agents. For example, it can analyze changes in emotions when resident AI agents use a new smartphone, understanding the difference in emotions before and after use. It can also track changes in emotions when resident AI agents use a new application and analyze fluctuations in emotions during use. Furthermore, it can track changes in emotions when resident AI agents describe their experience using a specific product, and use that sentiment data to conduct market evaluations. This allows the data collection unit to perform more detailed market evaluations by conducting sentiment analysis.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The development team builds a resident AI agent. The development team builds the resident AI agent based on big data. Big data includes consumer behavior history, purchase history, and social media posts. This allows the development team to build a resident AI agent that functions as a realistic consumer model. Step 2: The Input Unit introduces new products and services into the virtual community where the resident AI agents, built by the Construction Unit, reside. The Input Unit introduces new smartphones, applications, food items, etc., into the virtual community. The Input Unit enables the resident AI agents to use these products and services and share their experiences and evaluations within the virtual community. Step 3: The collection unit collects the reactions of resident AI agents to the new products and services introduced by the input unit. The collection unit collects the reactions and word-of-mouth from resident AI agents. The collection unit enables the reactions and word-of-mouth from resident AI agents to spread, allowing for evaluations similar to those in a real market. Step 4: The prediction unit predicts market reaction based on the responses collected by the collection unit. The prediction unit has resident AI agents use the new smartphone and share their evaluations of its usability and design. These evaluations influence other resident AI agents, spreading word-of-mouth. Based on these evaluations, the prediction unit can predict the market reaction to the new service or product in advance.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the construction unit, input unit, collection unit, and prediction unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the construction unit is implemented by the specific processing unit 290 of the data processing unit 12 and constructs resident AI agents based on big data. The input unit is implemented by, for example, the control unit 46A of the smart device 14 and introduces new products and services to the virtual community. The collection unit is implemented by, for example, the control unit 46A of the smart device 14 and collects the responses of the resident AI agents. The prediction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and predicts market reactions based on the collected responses. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the construction unit, input unit, collection unit, and prediction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the construction unit is implemented by the specific processing unit 290 of the data processing unit 12, which constructs resident AI agents based on big data. The input unit is implemented, for example, by the control unit 46A of the smart glasses 214, which introduces new products and services to the virtual community. The collection unit is implemented, for example, by the control unit 46A of the smart glasses 214, which collects the responses of the resident AI agents. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which predicts market reactions based on the collected responses. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the construction unit, input unit, collection unit, and prediction unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the construction unit is implemented by the specific processing unit 290 of the data processing unit 12, which constructs resident AI agents based on big data. The input unit is implemented by, for example, the control unit 46A of the headset terminal 314, which introduces new products and services to the virtual community. The collection unit is implemented by, for example, the control unit 46A of the headset terminal 314, which collects the responses of the resident AI agents. The prediction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which predicts market reactions based on the collected responses. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The 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.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS 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).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] 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.

[0158] 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.

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

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

[0161] In 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.

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

[0163] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0165] The data processing system 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.

[0166] Each of the multiple elements described above, including the construction unit, input unit, collection unit, and prediction unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the construction unit is implemented by the specific processing unit 290 of the data processing unit 12, which constructs resident AI agents based on big data. The input unit is implemented by, for example, the control unit 46A of the robot 414, which introduces new products and services into the virtual community. The collection unit is implemented by, for example, the control unit 46A of the robot 414, which collects the responses of the resident AI agents. The prediction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which predicts market reactions based on the collected responses. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) The construction department builds resident AI agents, The aforementioned construction unit has an input unit that introduces new products and services to a virtual community inhabited by resident AI agents, A collection unit collects the reactions of resident AI agents to new products and services introduced by the aforementioned input unit, The system includes a prediction unit that predicts market reactions based on the reactions collected by the collection unit. A system characterized by the following features. (Note 2) The aforementioned construction unit is Building resident AI agents based on big data The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Collect the reactions and reviews of resident AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 4) The prediction unit, Market response forecast based on collected feedback The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned input section is Launch new products and services into a virtual community. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is Collect the responses of resident AI agents in real time. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned construction unit is It estimates the user's emotions and adjusts the behavior patterns of the resident AI agent based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned construction unit is We will build a resident AI agent by focusing on specific consumer segments from big data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned construction unit is When building resident AI agents, reflect consumer models from different cultures and regions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned construction unit is It estimates the user's emotions and simulates the resident AI agent's response based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned construction unit is When building resident AI agents, reflect past consumer trends. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned construction unit is When building resident AI agents, adjust the model to take into account the influence of social media. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned input section is We estimate user emotions and adjust the timing of new product and service launches based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned input section is When launching new products or services, customize the launch method according to the target consumer group. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned input section is Simulate different marketing strategies when launching new products or services. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned input section is We estimate user emotions and determine the order in which to launch new products and services based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned input section is When launching new products or services, we optimize the launch method by referring to past market data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned input section is When launching new products or services, adjust your launch strategy by considering the actions of your competitors. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned collection unit is It estimates the user's emotions and adjusts the method of collecting responses from resident AI agents based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned collection unit is When collecting responses from resident AI agents, prioritize collecting responses from specific consumer groups. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned collection unit is When collecting responses from resident AI agents, compare responses at different times of day and in different situations. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned collection unit is We estimate user emotions and adjust the analysis method of collected responses based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned collection unit is When collecting responses from resident AI agents, social media posts will also be collected. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned collection unit is When collecting responses from resident AI agents, compare real-time responses with past responses. The system described in Appendix 1, characterized by the features described herein. (Note 25) The prediction unit, We estimate user sentiment and adjust the accuracy of market response forecasts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The prediction unit, When forecasting market reactions, we prioritize the responses of specific consumer groups. The system described in Appendix 1, characterized by the features described herein. (Note 27) The prediction unit, When forecasting market reactions, simulate different scenarios to broaden the scope of the forecast. The system described in Appendix 1, characterized by the features described herein. (Note 28) The prediction unit, It estimates the user's emotions and adjusts how the prediction results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The prediction unit, When forecasting market response, we improve the accuracy of our predictions by referring to historical market data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The prediction unit, When forecasting market response, we take into account the actions of our competitors. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0186] 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. The construction department will build the resident AI agent, The input unit introduces new products and services into the virtual community inhabited by the resident AI agents constructed by the aforementioned construction unit, A collection unit collects the reactions of resident AI agents to new products and services introduced by the aforementioned input unit, The system includes a prediction unit that predicts market reactions based on the reactions collected by the collection unit. A system characterized by the following features.

2. The aforementioned construction unit is Building resident AI agents based on big data The system according to feature 1.

3. The aforementioned collection unit is Collect the reactions and reviews of resident AI agents. The system according to feature 1.

4. The prediction unit, Market response forecast based on collected feedback The system according to feature 1.

5. The aforementioned input section is Launch new products and services into a virtual community. The system according to feature 1.

6. The aforementioned collection unit is Collect the responses of resident AI agents in real time. The system according to feature 1.

7. The aforementioned construction unit is It estimates the user's emotions and adjusts the behavior patterns of the resident AI agent based on the estimated user emotions. The system according to feature 1.

8. The aforementioned construction unit is We will build a resident AI agent by focusing on specific consumer segments from big data. The system according to feature 1.

9. The aforementioned construction unit is When building resident AI agents, reflect consumer models from different cultures and regions. The system according to feature 1.

Images