system

Abstract

The system according to this embodiment aims to lower the barriers to using matching apps and attract more users. [Solution] The system according to the embodiment comprises a learning unit, a creation unit, an evaluation unit, and a probing unit. The learning unit learns the characteristics of the user. The creation unit creates user groups based on the characteristics learned by the learning unit. The evaluation unit engages in conversation while switching the characteristics of the user groups created by the creation unit and evaluates the user's response. The probing unit makes a probing request for matching based on the results evaluated by the evaluation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the hurdle for using a matching app is high and the number of users is limited.

[0005] <了 The system according to the embodiment aims to lower the hurdle for using a matching app and incorporate more users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a creation unit, an evaluation unit, and a probing unit. The learning unit learns the characteristics of users. The creation unit creates user groups based on the characteristics learned by the learning unit. The evaluation unit engages in conversation while switching the characteristics of the user groups created by the creation unit and evaluates the user's response. The probing unit makes a probing request for matching based on the results evaluated by the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can lower the barrier to using matching apps and attract more users. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a 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 matching system according to an embodiment of the present invention is designed to attract "people who want to try a matching app but feel it's too difficult" by using AI to soften the hurdle of "getting a match," which is a major obstacle for conventional matching apps. In this matching system, a user registers with the matching app and begins a conversation with an AI agent. The AI ​​agent learns the user's characteristics (content, tone, frequency, etc.) through the conversation. Once a certain amount of information has been accumulated, the AI ​​agent creates a "user group that seems to be a good match for the user." For example, if user A registers, the AI ​​agent converses with A and learns A's characteristics. Next, the AI ​​agent creates a user group that seems to be a good match for A (for example, users (1) to (10)). In the conversation with A, the AI ​​agent switches between the characteristics of users (1) to (10) as it converses. By assigning weight to the characteristics that A responded well to, the AI ​​agent narrows down the users from (1) to (10). Similarly, with respect to user (1), the AI ​​agent converses with user A to Z as it switches between the characteristics of users A to Z as it narrows down the user. Ultimately, when user A and user (1) form a pair, the AI ​​agent sends a "matching request" to both A and (1). If both accept, the conversation switches from the AI ​​agent to the actual A and (1). This mechanism allows users to be matched with compatible partners without having to interact with a large number of strangers. This mechanism lowers the barrier for users in their 20s and 30s who are hesitant about using dating apps. Users can be matched simply by talking to the AI ​​agent, without getting hurt or having to go through troublesome steps. Also, since matching occurs after a lively conversation, users can connect with compatible partners. For example, if A feels that "I want to try a dating app, but it's too difficult," talking to the AI ​​agent will naturally lead to matching. Through conversations with the AI ​​agent, A can find a partner that suits them.Furthermore, the AI ​​agent learns A's characteristics and creates an optimal user group, allowing A to be matched with the most suitable partner. This mechanism is expected to expand the matching app market. In particular, attracting users who are hesitant to use matching apps is expected to increase market size. Moreover, if the mechanism is successful, global expansion is possible. For example, the AI ​​agent can provide multilingual support and perform matching that takes cultural backgrounds into account, so that it can accommodate users from different cultures and languages. In this way, the present invention utilizes an AI agent to lower the barrier to using matching apps and provide a user-friendly mechanism. Through conversations with the AI ​​agent, users can naturally progress through the matching process and connect with compatible partners. This is expected to expand the matching app market. As a result, the matching system can learn the user's characteristics, create and evaluate the optimal user group, and propose matching, thereby providing a user-friendly matching system.

[0029] The matching system according to this embodiment comprises a learning unit, a creation unit, an evaluation unit, and a prompting unit. The learning unit learns user characteristics. The learning unit learns user characteristics, for example, through conversations with users. The learning unit can learn user characteristics such as age, gender, hobbies, and behavioral patterns. The learning unit can learn user characteristics, for example, using machine learning algorithms. The learning unit can learn the content, tone, and frequency of conversations with users. The learning unit can learn user interests and concerns, for example, through conversations with users. The creation unit creates user groups based on the characteristics learned by the learning unit. The creation unit creates user groups that are likely to be compatible with the user, for example, based on the learned characteristics. The creation unit can create user groups based on the size of the user group and common characteristics. The creation unit can create user groups based on similarities in common hobbies and behavioral patterns, for example. The creation unit conducts conversations while switching the characteristics of the user groups and evaluates the user's response. The evaluation unit conducts conversations while switching the characteristics of the user groups and evaluates the user's response. The evaluation unit evaluates user responses based on specific methods and criteria for switching the characteristics of user groups, for example. The evaluation unit can evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can set the type of user response and the evaluation scale in order to evaluate user responses. The probing unit makes a matching probation based on the results evaluated by the evaluation unit. The probing unit makes a matching probation based on the evaluated results, for example. The probing unit can make a matching probation based on the timing and content of the matching probation. The probing unit can make a matching probation based on the timing and content of the matching probation, for example. If the user accepts, the probing unit switches the conversation partner from the AI ​​agent to an actual user.The prompting unit can switch conversation partners based on specific methods and criteria for switching conversation partners. For example, the prompting unit can switch conversation partners based on specific methods and criteria for switching conversation partners. As a result, the matching system according to the embodiment can learn user characteristics, create and evaluate optimal user groups, and make matching prompts, thereby providing a user-friendly matching system.

[0030] The learning unit learns user characteristics. For example, it learns user characteristics through conversations with users. Specifically, the learning unit uses natural language processing technology to analyze the content of user conversations and extract characteristics such as the user's age, gender, hobbies, and behavioral patterns. For example, it can identify hobbies and interests that users frequently talk about and update the user's profile accordingly. Furthermore, the learning unit can analyze the tone and frequency of the user's conversations and the choice of words they use to understand the user's personality and communication style. As a result, the learning unit can comprehensively learn detailed user characteristics and collect foundational data to provide optimal matching for individual users. The learning unit can continuously learn user characteristics using machine learning algorithms and improve its accuracy over time. For example, if a user starts a new hobby or their behavioral patterns change, the learning unit can quickly detect these changes and update the user's profile. As a result, the learning unit can always achieve highly accurate matching based on the latest information.

[0031] The creation unit creates user groups based on the features learned by the learning unit. Specifically, the creation unit analyzes the learned features and groups users who share common hobbies or behavioral patterns. For example, it can group users with the same hobbies or similar lifestyles together. The creation unit uses an algorithm to create the optimal group based on the size of the user group and the common features. For example, if the group size is too large, the features of individual users may get lost, so it adjusts to an appropriate size. Also, the more common features there are, the better the compatibility between users in the group, so it creates groups while prioritizing common features. Furthermore, the creation unit engages in conversations while switching the features of the user groups and evaluates the users' reactions. This allows the creation unit to optimize the group features based on user reactions and achieve better matching. For example, if a user shows a favorable reaction to a particular group, the features of that group can be strengthened; conversely, if a user shows a negative reaction, the features can be revised. This allows the creation unit to flexibly create groups according to user needs and improve the accuracy of matching.

[0032] The evaluation unit conducts conversations while switching the characteristics of the user group and evaluates the user's response. Specifically, the evaluation unit observes the user's response through conversation while changing the characteristics of the user group. For example, it evaluates how the user responds to a specific topic and makes an evaluation based on the type and intensity of that response. The evaluation unit can set evaluation scales to quantitatively evaluate the user's response. For example, it can classify the user's response into three categories: positive, negative, and neutral, and score the frequency and intensity of each response. Furthermore, the evaluation unit can analyze the user's response in real time and provide rapid feedback of the evaluation results. This allows the evaluation unit to perform rapid evaluations based on the user's response and provide appropriate information to the creation and consultation units. The evaluation unit can use machine learning algorithms to evaluate the user's response. For example, it can analyze the user's facial expressions, tone of voice, and word choice to infer the user's emotions and intentions. This allows the evaluation unit to evaluate the user's response more accurately and improve the accuracy of matching. Furthermore, the evaluation unit can utilize past evaluation data to analyze patterns in user responses and predict future responses. This allows the evaluation unit to conduct long-term evaluations based on user responses, improving the overall reliability and accuracy of the system.

[0033] The Prompt Unit makes matching inquiries based on the evaluation results from the Evaluation Unit. Specifically, the Prompt Unit proposes the most suitable match to the user based on the evaluation results. For example, if a user shows a favorable reaction to a particular group, it can propose matching with members of that group. The Prompt Unit adjusts the timing and content of matching inquiries to make suggestions at the optimal time for the user. For example, it may make inquiries during times when the user is relaxed or when they feel like actively communicating. Furthermore, if the user accepts, the Prompt Unit switches the conversation partner from the AI ​​agent to an actual user. Specifically, when a user accepts a match, the Prompt Unit initiates a procedure to end the conversation with the AI ​​agent and start a conversation with an actual user. This allows the user to smoothly begin communication with an actual user based on the information obtained through the conversation with the AI ​​agent. The Prompt Unit can switch conversation partners based on specific methods and criteria. For example, with the user's consent, it may share information about the conversation partner and switch at the appropriate time. This allows the matching unit to propose the optimal match to the user and facilitate smooth communication. Furthermore, the matching unit can collect user feedback and continuously improve the accuracy of the matching and the content of the suggestions. As a result, the matching unit can provide a user-friendly matching system and improve user satisfaction.

[0034] The learning unit can learn user characteristics through conversations with users. For example, the learning unit can learn user characteristics through conversations with users. The learning unit can learn the content, tone, and frequency of user conversations. For example, the learning unit can learn user interests and concerns through conversations with users. The learning unit can use machine learning algorithms to learn user characteristics. For example, the learning unit can use machine learning algorithms to learn user characteristics through conversations with users. The learning unit can use generative AI to learn user characteristics. For example, the learning unit can use generative AI to learn user characteristics through conversations with users. This allows the learning unit to grasp user characteristics more accurately by learning them through conversations with users.

[0035] The creation unit can create user groups that are likely to be compatible with a user based on learned features. For example, the creation unit can create user groups that are likely to be compatible with a user based on learned features. The creation unit can create user groups based on the size of the user group or common features. For example, the creation unit can create user groups based on similarities in shared hobbies or behavioral patterns. The creation unit can use machine learning algorithms to create user groups. For example, the creation unit can use machine learning algorithms to create user groups based on learned features. The creation unit can use generative AI to create user groups. For example, the creation unit can use generative AI to create user groups based on learned features. This allows the creation unit to match compatible users by creating user groups based on learned features.

[0036] The evaluation unit can conduct conversations while switching the characteristics of user groups and evaluate user responses. The evaluation unit can, for example, conduct conversations while switching the characteristics of user groups and evaluate user responses. The evaluation unit can evaluate user responses based on specific methods and criteria for switching the characteristics of user groups. The evaluation unit can evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can, for example, evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can use machine learning algorithms to evaluate user responses. The evaluation unit can use generative AI to evaluate user responses. This makes it easier for the evaluation unit to evaluate user responses by conducting conversations while switching the characteristics of user groups.

[0037] The probing unit can make matching inquiries based on the evaluated results. The probing unit can, for example, make matching inquiries based on the evaluated results. The probing unit can make matching inquiries based on the timing and content of the matching inquiries. The probing unit can, for example, make matching inquiries based on the timing and content of the matching inquiries. The probing unit can use machine learning algorithms to make matching inquiries. The probing unit can, for example, use machine learning algorithms to make matching inquiries based on the evaluated results. The probing unit can use generative AI to make matching inquiries. The probing unit can, for example, use generative AI to make matching inquiries based on the evaluated results. This allows the probing unit to make matching inquiries based on the evaluated results, enabling matching at the optimal time for the user.

[0038] The prompting unit can switch the conversation partner from an AI agent to a real user if the user accepts. The prompting unit can switch conversation partners based on specific methods and criteria for doing so. The prompting unit can use machine learning algorithms to switch conversation partners. The prompting unit can use generative AI to switch conversation partners. This allows the prompting unit to achieve smooth matching by switching conversation partners upon user acceptance.

[0039] The learning unit can analyze the user's past conversation history and select the optimal learning method. For example, the learning unit can customize the learning method based on words and phrases the user has frequently used in the past. The learning unit can prioritize incorporating topics the user has shown interest in in the past into the learning content. The learning unit can select and reuse methods that were highly effective from the user's past conversation history. This allows the learning unit to select the optimal learning method by analyzing the user's past conversation history. The learning unit can use generative AI to analyze past conversation history. For example, the learning unit can input the user's past conversation history into the generative AI and have the generative AI select the optimal learning method.

[0040] The learning unit can customize learning content based on the user's interests and preferences during the learning process. For example, the learning unit can incorporate content related to the user's hobbies. The learning unit can reflect the latest news and topics that the user is interested in into the learning content. The learning unit can structure learning content based on themes that the user has shown interest in in the past. In this way, the learning unit enhances the effectiveness of learning by customizing learning content based on the user's interests and preferences. The learning unit can use generative AI to customize learning content. For example, the learning unit can input the user's interests and preferences into the generative AI and have the generative AI perform the customization of learning content.

[0041] The learning unit can prioritize learning highly relevant information by considering the user's geographical location during the learning process. For example, the learning unit can prioritize learning information related to the area where the user is currently located. If the user is traveling, the learning unit can learn information about the culture and history of the place they are visiting. The learning unit can incorporate the latest news and event information of the area where the user lives into its learning content. In this way, the learning unit can prioritize learning highly relevant information by considering the user's geographical location. The learning unit can use generative AI to consider geographical location. For example, the learning unit can input the user's geographical location information into the generative AI and have the generative AI select highly relevant information.

[0042] The learning unit can analyze the user's social media activity and learn relevant information during the learning process. For example, the learning unit can customize the learning content based on articles and posts shared by the user on social media. The learning unit can learn information related to topics of accounts that the user follows. The learning unit can reflect themes that the user has shown interest in on social media in its learning content. In this way, the learning unit can learn relevant information by analyzing the user's social media activity. The learning unit can use generative AI to analyze social media activity. For example, the learning unit can input the user's social media activity into the generative AI and have the generative AI select relevant information.

[0043] The creation unit can create optimal user groups by referring to the user's past matching history during creation. For example, the creation unit can create optimal user groups based on the characteristics of people the user has matched with in the past. The creation unit can create user groups considering the characteristics of people the user has liked in the past. The creation unit can prioritize including compatible users in the group based on the user's past matching history. In this way, the creation unit can create optimal user groups by referring to the user's past matching history. The creation unit can use a generation AI to refer to past matching history. For example, the creation unit can input the user's past matching history into the generation AI and have the generation AI create the optimal user groups.

[0044] The creation unit can customize user groups based on the user's current lifestyle and areas of interest during creation. For example, the creation unit can include users related to areas the user is currently interested in. The creation unit can create user groups that match the user's lifestyle (work, hobbies, etc.). The creation unit can include users related to communities and events the user is currently participating in. In this way, the creation unit can create the optimal group for the user by customizing the user group based on the user's current lifestyle and areas of interest. The creation unit can use generative AI to take lifestyle and areas of interest into consideration. For example, the creation unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the user group.

[0045] The creation unit can prioritize creating highly relevant user groups by considering the user's geographical location information during creation. For example, the creation unit can include users related to the region the user is currently in. If the user is traveling, the creation unit can include users related to the region they are visiting. The creation unit can also prioritize including users in the region where the user lives. In this way, the creation unit can prioritize creating highly relevant user groups by considering the user's geographical location information. The creation unit can use a generation AI to consider geographical location information. For example, the creation unit can input the user's geographical location information into the generation AI and have the generation AI create highly relevant user groups.

[0046] The creation unit can analyze a user's social media activity and create relevant user groups during the creation process. For example, the creation unit can include users related to accounts the user follows on social media. The creation unit can include users related to content the user has shared on social media. The creation unit can include users related to themes the user has shown interest in on social media. In this way, the creation unit can create relevant user groups by analyzing a user's social media activity. The creation unit can use generative AI to analyze social media activity. For example, the creation unit can input a user's social media activity into the generative AI and have the generative AI create relevant user groups.

[0047] The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluations based on features that the user has preferred in the past. The evaluation unit can adjust the evaluation criteria based on the user's past response history. The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. In this way, the evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. The evaluation unit can use a generative AI to refer to past response history. For example, the evaluation unit can input the user's past response history into the generative AI and have the generative AI perform the task of improving the accuracy of the evaluation.

[0048] The evaluation unit can customize the evaluation content based on the user's current lifestyle and areas of interest during the evaluation process. For example, the evaluation unit can provide evaluation content related to the user's current areas of interest. The evaluation unit can provide evaluation content that is appropriate for the user's lifestyle (work, hobbies, etc.). The evaluation unit can provide evaluation content related to the communities and events the user is currently participating in. In this way, the evaluation unit can provide the optimal evaluation for the user by customizing the evaluation content based on the user's current lifestyle and areas of interest. The evaluation unit can use generative AI to take lifestyle and areas of interest into consideration. For example, the evaluation unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the evaluation content.

[0049] The evaluation unit can prioritize highly relevant evaluations by considering the user's geographical location during the evaluation process. For example, the evaluation unit can provide evaluations related to the area the user is currently in. If the user is traveling, the evaluation unit can provide evaluations related to the area they are visiting. The evaluation unit can also prioritize providing evaluations for the area where the user lives. In this way, the evaluation unit can prioritize highly relevant evaluations by considering the user's geographical location. The evaluation unit can use a generative AI to consider geographical location. For example, the evaluation unit can input the user's geographical location into the generative AI and have the generative AI select highly relevant evaluations.

[0050] The evaluation unit can analyze a user's social media activity and perform relevant evaluations during the evaluation process. For example, the evaluation unit can customize evaluation content based on articles and posts shared by the user on social media. The evaluation unit can provide evaluation content related to topics of accounts the user follows. The evaluation unit can provide evaluation content related to themes the user has shown interest in on social media. In this way, the evaluation unit can perform relevant evaluations by analyzing the user's social media activity. The evaluation unit can use generative AI to analyze social media activity. For example, the evaluation unit can input the user's social media activity into the generative AI and have the generative AI select relevant evaluation content.

[0051] The probing unit can select the optimal probing method by referring to the user's past matching history when probing. For example, the probing unit can select the optimal probing method based on the probing method the user has preferred in the past. The probing unit can select a probing method with a high success rate from the user's past matching history. The probing unit can select the optimal probing method by referring to probing methods that the user has found more acceptable in the past. In this way, the probing unit can select the optimal probing method by referring to the user's past matching history. The probing unit can use a generation AI to refer to past matching history. For example, the probing unit can input the user's past matching history into a generation AI and have the generation AI select the optimal probing method.

[0052] The prompting unit can customize the content of the prompt based on the user's current lifestyle and areas of interest. For example, the prompting unit can provide prompts related to areas the user is currently interested in. The prompting unit can provide prompts that are appropriate to the user's lifestyle (work, hobbies, etc.). The prompting unit can provide prompts related to communities and events the user is currently participating in. In this way, the prompting unit can make the most appropriate prompts for the user by customizing the prompts based on the user's current lifestyle and areas of interest. The prompting unit can use generative AI to take into account the user's lifestyle and areas of interest. For example, the prompting unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the prompts.

[0053] The prompting unit can prioritize highly relevant prompts by considering the user's geographical location information during the prompting process. For example, the prompting unit can provide prompts related to the user's current location. If the user is traveling, the prompting unit can provide prompts related to the destination region. The prompting unit can prioritize prompts for the user's residential area. In this way, the prompting unit can prioritize highly relevant prompts by considering the user's geographical location information. The prompting unit can use a generation AI to consider geographical location information. For example, the prompting unit can input the user's geographical location information into the generation AI and have the generation AI select highly relevant prompts.

[0054] The prompting unit can analyze the user's social media activity and make relevant prompts when making a prompt. For example, the prompting unit can customize the prompt based on articles and posts the user has shared on social media. The prompting unit can provide prompts related to topics of accounts the user follows. The prompting unit can provide prompts related to themes the user has shown interest in on social media. In this way, the prompting unit can make relevant prompts by analyzing the user's social media activity. The prompting unit can use generative AI to analyze social media activity. For example, the prompting unit can input the user's social media activity into the generative AI and have the generative AI select relevant prompts.

[0055] The contact unit can select the optimal contact timing by referring to the user's calendar information when making a contact. For example, the contact unit can refer to appointments registered in the user's calendar and make a contact during an available time. The contact unit can provide contact content related to a specific event based on the user's calendar information. Based on the user's calendar information, the contact unit can select the optimal contact timing that matches the appointment. In this way, the contact unit can select the optimal contact timing by referring to the user's calendar information. The contact unit can use a generation AI to refer to the calendar information. For example, the contact unit can input the user's calendar information into the generation AI and have the generation AI select the optimal contact timing.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The creation unit can analyze a user's past behavior history and create user groups based on their behavior patterns. For example, if a user was active during a specific time period in the past, other users who were active during that time period can be included in the group. If a user frequently participates in a specific event, users related to that event can be included in the group. If a user has a specific hobby, users related to that hobby can be included in the group. In this way, the creation unit can create optimal user groups based on the user's behavior patterns.

[0058] The creation process can create user groups while considering the user's geographical location. For example, if a user lives in a specific region, other users living in that region can be included in the group. If a user is traveling, users related to the region they are visiting can be included in the group. If a user is attending a specific event, users related to that event can be included in the group. In this way, the creation process can create highly relevant user groups by considering the user's geographical location.

[0059] The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. For example, it can improve the accuracy of its evaluations based on features the user has preferred in the past. It can adjust the evaluation criteria based on the user's past response history. It can improve the accuracy of its evaluations by referring to the user's past response history. In this way, the evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history.

[0060] The contact unit can analyze a user's social media activity and make relevant contacts. For example, it can customize contact content based on articles and posts the user has shared on social media. It can provide contact content related to topics on accounts the user follows. It can provide contact content related to themes the user has shown interest in on social media. In this way, the contact unit can make relevant contacts by analyzing the user's social media activity.

[0061] The learning unit can analyze the user's past conversation history and select the optimal learning method. For example, it can customize the learning method based on words and phrases the user has used frequently in the past. It can also prioritize incorporating topics the user has shown interest in in the past into the learning content. From the user's past conversation history, it can select and reuse methods that were highly effective in learning. In this way, the learning unit can select the optimal learning method by analyzing the user's past conversation history.

[0062] The contact unit can select the optimal contact timing by referring to the user's calendar information. For example, it can refer to appointments registered in the user's calendar and contact them during their free time. Based on the user's calendar information, it can provide contact content related to a specific event. Based on the user's calendar information, it can select the optimal contact timing that matches their schedule. In this way, the contact unit can select the optimal contact timing by referring to the user's calendar information.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The learning unit learns user characteristics. For example, through conversations with the user, it learns the user's age, gender, hobbies, behavioral patterns, conversation content, tone of voice, frequency, interests, etc. The learning unit can learn these characteristics using machine learning algorithms. Step 2: The creation unit creates user groups based on the features learned by the learning unit. For example, it creates user groups that are likely to be compatible with the user based on the learned features, and also creates user groups based on similarities in common hobbies and behavioral patterns. Step 3: The evaluation unit conducts conversations while switching the characteristics of the user groups created by the creation unit, and evaluates the users' responses. For example, it sets the types of user responses and evaluation scales based on specific methods and criteria for switching the characteristics of the user groups, and then evaluates the users' responses. Step 4: The probing unit makes a matching proposition based on the evaluation results from the evaluation unit. For example, based on the evaluation results, it determines the timing and content of the matching proposition, and if the user accepts, it switches the conversation partner from the AI ​​agent to an actual user.

[0065] (Example of form 2) The matching system according to an embodiment of the present invention is designed to attract "people who want to try a matching app but feel it's too difficult" by using AI to soften the hurdle of "getting a match," which is a major obstacle for conventional matching apps. In this matching system, a user registers with the matching app and begins a conversation with an AI agent. The AI ​​agent learns the user's characteristics (content, tone, frequency, etc.) through the conversation. Once a certain amount of information has been accumulated, the AI ​​agent creates a "user group that seems to be a good match for the user." For example, if user A registers, the AI ​​agent converses with A and learns A's characteristics. Next, the AI ​​agent creates a user group that seems to be a good match for A (for example, users (1) to (10)). In the conversation with A, the AI ​​agent switches between the characteristics of users (1) to (10) as it converses. By assigning weight to the characteristics that A responded well to, the AI ​​agent narrows down the users from (1) to (10). Similarly, with respect to user (1), the AI ​​agent converses with user A to Z as it switches between the characteristics of users A to Z as it narrows down the user. Ultimately, when user A and user (1) form a pair, the AI ​​agent sends a "matching request" to both A and (1). If both accept, the conversation switches from the AI ​​agent to the actual A and (1). This mechanism allows users to be matched with compatible partners without having to interact with a large number of strangers. This mechanism lowers the barrier for users in their 20s and 30s who are hesitant about using dating apps. Users can be matched simply by talking to the AI ​​agent, without getting hurt or having to go through troublesome steps. Also, since matching occurs after a lively conversation, users can connect with compatible partners. For example, if A feels that "I want to try a dating app, but it's too difficult," talking to the AI ​​agent will naturally lead to matching. Through conversations with the AI ​​agent, A can find a partner that suits them.Furthermore, the AI ​​agent learns A's characteristics and creates an optimal user group, allowing A to be matched with the most suitable partner. This mechanism is expected to expand the matching app market. In particular, attracting users who are hesitant to use matching apps is expected to increase market size. Moreover, if the mechanism is successful, global expansion is possible. For example, the AI ​​agent can provide multilingual support and perform matching that takes cultural backgrounds into account, so that it can accommodate users from different cultures and languages. In this way, the present invention utilizes an AI agent to lower the barrier to using matching apps and provide a user-friendly mechanism. Through conversations with the AI ​​agent, users can naturally progress through the matching process and connect with compatible partners. This is expected to expand the matching app market. As a result, the matching system can learn the user's characteristics, create and evaluate the optimal user group, and propose matching, thereby providing a user-friendly matching system.

[0066] The matching system according to this embodiment comprises a learning unit, a creation unit, an evaluation unit, and a prompting unit. The learning unit learns user characteristics. The learning unit learns user characteristics, for example, through conversations with users. The learning unit can learn user characteristics such as age, gender, hobbies, and behavioral patterns. The learning unit can learn user characteristics, for example, using machine learning algorithms. The learning unit can learn the content, tone, and frequency of conversations with users. The learning unit can learn user interests and concerns, for example, through conversations with users. The creation unit creates user groups based on the characteristics learned by the learning unit. The creation unit creates user groups that are likely to be compatible with the user, for example, based on the learned characteristics. The creation unit can create user groups based on the size of the user group and common characteristics. The creation unit can create user groups based on similarities in common hobbies and behavioral patterns, for example. The creation unit conducts conversations while switching the characteristics of the user groups and evaluates the user's response. The evaluation unit conducts conversations while switching the characteristics of the user groups and evaluates the user's response. The evaluation unit evaluates user responses based on specific methods and criteria for switching the characteristics of user groups, for example. The evaluation unit can evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can set the type of user response and the evaluation scale in order to evaluate user responses. The probing unit makes a matching probation based on the results evaluated by the evaluation unit. The probing unit makes a matching probation based on the evaluated results, for example. The probing unit can make a matching probation based on the timing and content of the matching probation. The probing unit can make a matching probation based on the timing and content of the matching probation, for example. If the user accepts, the probing unit switches the conversation partner from the AI ​​agent to an actual user.The prompting unit can switch conversation partners based on specific methods and criteria for switching conversation partners. For example, the prompting unit can switch conversation partners based on specific methods and criteria for switching conversation partners. As a result, the matching system according to the embodiment can learn user characteristics, create and evaluate optimal user groups, and make matching prompts, thereby providing a user-friendly matching system.

[0067] The learning unit learns user characteristics. For example, it learns user characteristics through conversations with users. Specifically, the learning unit uses natural language processing technology to analyze the content of user conversations and extract characteristics such as the user's age, gender, hobbies, and behavioral patterns. For example, it can identify hobbies and interests that users frequently talk about and update the user's profile accordingly. Furthermore, the learning unit can analyze the tone and frequency of the user's conversations and the choice of words they use to understand the user's personality and communication style. As a result, the learning unit can comprehensively learn detailed user characteristics and collect foundational data to provide optimal matching for individual users. The learning unit can continuously learn user characteristics using machine learning algorithms and improve its accuracy over time. For example, if a user starts a new hobby or their behavioral patterns change, the learning unit can quickly detect these changes and update the user's profile. As a result, the learning unit can always achieve highly accurate matching based on the latest information.

[0068] The creation unit creates user groups based on the features learned by the learning unit. Specifically, the creation unit analyzes the learned features and groups users who share common hobbies or behavioral patterns. For example, it can group users with the same hobbies or similar lifestyles together. The creation unit uses an algorithm to create the optimal group based on the size of the user group and the common features. For example, if the group size is too large, the features of individual users may get lost, so it adjusts to an appropriate size. Also, the more common features there are, the better the compatibility between users in the group, so it creates groups while prioritizing common features. Furthermore, the creation unit engages in conversations while switching the features of the user groups and evaluates the users' reactions. This allows the creation unit to optimize the group features based on user reactions and achieve better matching. For example, if a user shows a favorable reaction to a particular group, the features of that group can be strengthened; conversely, if a user shows a negative reaction, the features can be revised. This allows the creation unit to flexibly create groups according to user needs and improve the accuracy of matching.

[0069] The evaluation unit conducts conversations while switching the characteristics of the user group and evaluates the user's response. Specifically, the evaluation unit observes the user's response through conversation while changing the characteristics of the user group. For example, it evaluates how the user responds to a specific topic and makes an evaluation based on the type and intensity of that response. The evaluation unit can set evaluation scales to quantitatively evaluate the user's response. For example, it can classify the user's response into three categories: positive, negative, and neutral, and score the frequency and intensity of each response. Furthermore, the evaluation unit can analyze the user's response in real time and provide rapid feedback of the evaluation results. This allows the evaluation unit to perform rapid evaluations based on the user's response and provide appropriate information to the creation and consultation units. The evaluation unit can use machine learning algorithms to evaluate the user's response. For example, it can analyze the user's facial expressions, tone of voice, and word choice to infer the user's emotions and intentions. This allows the evaluation unit to evaluate the user's response more accurately and improve the accuracy of matching. Furthermore, the evaluation unit can utilize past evaluation data to analyze patterns in user responses and predict future responses. This allows the evaluation unit to conduct long-term evaluations based on user responses, improving the overall reliability and accuracy of the system.

[0070] The Prompt Unit makes matching inquiries based on the evaluation results from the Evaluation Unit. Specifically, the Prompt Unit proposes the most suitable match to the user based on the evaluation results. For example, if a user shows a favorable reaction to a particular group, it can propose matching with members of that group. The Prompt Unit adjusts the timing and content of matching inquiries to make suggestions at the optimal time for the user. For example, it may make inquiries during times when the user is relaxed or when they feel like actively communicating. Furthermore, if the user accepts, the Prompt Unit switches the conversation partner from the AI ​​agent to an actual user. Specifically, when a user accepts a match, the Prompt Unit initiates a procedure to end the conversation with the AI ​​agent and start a conversation with an actual user. This allows the user to smoothly begin communication with an actual user based on the information obtained through the conversation with the AI ​​agent. The Prompt Unit can switch conversation partners based on specific methods and criteria. For example, with the user's consent, it may share information about the conversation partner and switch at the appropriate time. This allows the matching unit to propose the optimal match to the user and facilitate smooth communication. Furthermore, the matching unit can collect user feedback and continuously improve the accuracy of the matching and the content of the suggestions. As a result, the matching unit can provide a user-friendly matching system and improve user satisfaction.

[0071] The learning unit can learn user characteristics through conversations with users. For example, the learning unit can learn user characteristics through conversations with users. The learning unit can learn the content, tone, and frequency of user conversations. For example, the learning unit can learn user interests and concerns through conversations with users. The learning unit can use machine learning algorithms to learn user characteristics. For example, the learning unit can use machine learning algorithms to learn user characteristics through conversations with users. The learning unit can use generative AI to learn user characteristics. For example, the learning unit can use generative AI to learn user characteristics through conversations with users. This allows the learning unit to grasp user characteristics more accurately by learning them through conversations with users.

[0072] The creation unit can create user groups that are likely to be compatible with a user based on learned features. For example, the creation unit can create user groups that are likely to be compatible with a user based on learned features. The creation unit can create user groups based on the size of the user group or common features. For example, the creation unit can create user groups based on similarities in shared hobbies or behavioral patterns. The creation unit can use machine learning algorithms to create user groups. For example, the creation unit can use machine learning algorithms to create user groups based on learned features. The creation unit can use generative AI to create user groups. For example, the creation unit can use generative AI to create user groups based on learned features. This allows the creation unit to match compatible users by creating user groups based on learned features.

[0073] The evaluation unit can conduct conversations while switching the characteristics of user groups and evaluate user responses. The evaluation unit can, for example, conduct conversations while switching the characteristics of user groups and evaluate user responses. The evaluation unit can evaluate user responses based on specific methods and criteria for switching the characteristics of user groups. The evaluation unit can evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can, for example, evaluate user responses based on the type of user response and the evaluation scale. The evaluation unit can use machine learning algorithms to evaluate user responses. The evaluation unit can use generative AI to evaluate user responses. This makes it easier for the evaluation unit to evaluate user responses by conducting conversations while switching the characteristics of user groups.

[0074] The probing unit can make matching inquiries based on the evaluated results. The probing unit can, for example, make matching inquiries based on the evaluated results. The probing unit can make matching inquiries based on the timing and content of the matching inquiries. The probing unit can, for example, make matching inquiries based on the timing and content of the matching inquiries. The probing unit can use machine learning algorithms to make matching inquiries. The probing unit can, for example, use machine learning algorithms to make matching inquiries based on the evaluated results. The probing unit can use generative AI to make matching inquiries. The probing unit can, for example, use generative AI to make matching inquiries based on the evaluated results. This allows the probing unit to make matching inquiries based on the evaluated results, enabling matching at the optimal time for the user.

[0075] The prompting unit can switch the conversation partner from an AI agent to a real user if the user accepts. The prompting unit can switch conversation partners based on specific methods and criteria for doing so. The prompting unit can use machine learning algorithms to switch conversation partners. The prompting unit can use generative AI to switch conversation partners. This allows the prompting unit to achieve smooth matching by switching conversation partners upon user acceptance.

[0076] The learning unit can estimate the user's emotions and adjust the learning pace based on the estimated emotions. For example, if the user is nervous, the learning unit can slow down the learning pace to help the user relax. If the user is excited, the learning unit can speed up the learning pace to keep the user interested. If the user is tired, the learning unit can adjust the learning pace to allow the user to continue learning without strain. In this way, the learning unit can allow the user to continue learning without strain by adjusting the learning pace 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0077] The learning unit can analyze the user's past conversation history and select the optimal learning method. For example, the learning unit can customize the learning method based on words and phrases the user has frequently used in the past. The learning unit can prioritize incorporating topics the user has shown interest in in the past into the learning content. The learning unit can select and reuse methods that were highly effective from the user's past conversation history. This allows the learning unit to select the optimal learning method by analyzing the user's past conversation history. The learning unit can use generative AI to analyze past conversation history. For example, the learning unit can input the user's past conversation history into the generative AI and have the generative AI select the optimal learning method.

[0078] The learning unit can customize learning content based on the user's interests and preferences during the learning process. For example, the learning unit can incorporate content related to the user's hobbies. The learning unit can reflect the latest news and topics that the user is interested in into the learning content. The learning unit can structure learning content based on themes that the user has shown interest in in the past. In this way, the learning unit enhances the effectiveness of learning by customizing learning content based on the user's interests and preferences. The learning unit can use generative AI to customize learning content. For example, the learning unit can input the user's interests and preferences into the generative AI and have the generative AI perform the customization of learning content.

[0079] The learning unit can estimate the user's emotions and determine learning priorities based on those emotions. For example, if the user is stressed, the learning unit will prioritize learning content that promotes relaxation. If the user is excited, the learning unit can prioritize learning content that is interesting. If the user is tired, the learning unit can prioritize learning content that is easy to understand. In this way, the learning unit can determine learning priorities according to the user's emotions, allowing the user to continue learning without difficulty. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The learning unit can prioritize learning highly relevant information by considering the user's geographical location during the learning process. For example, the learning unit can prioritize learning information related to the area where the user is currently located. If the user is traveling, the learning unit can learn information about the culture and history of the place they are visiting. The learning unit can incorporate the latest news and event information of the area where the user lives into its learning content. In this way, the learning unit can prioritize learning highly relevant information by considering the user's geographical location. The learning unit can use generative AI to consider geographical location. For example, the learning unit can input the user's geographical location information into the generative AI and have the generative AI select highly relevant information.

[0081] The learning unit can analyze the user's social media activity and learn relevant information during the learning process. For example, the learning unit can customize the learning content based on articles and posts shared by the user on social media. The learning unit can learn information related to topics of accounts that the user follows. The learning unit can reflect themes that the user has shown interest in on social media in its learning content. In this way, the learning unit can learn relevant information by analyzing the user's social media activity. The learning unit can use generative AI to analyze social media activity. For example, the learning unit can input the user's social media activity into the generative AI and have the generative AI select relevant information.

[0082] The creation unit can estimate the user's emotions and adjust how user groups are created based on the estimated emotions. For example, if the user is tense, the creation unit can create a relaxed user group. If the user is excited, the creation unit can create an active user group. If the user is tired, the creation unit can create a calm user group. In this way, the creation unit can create the optimal group for the user by adjusting how user groups are created 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The creation unit can create optimal user groups by referring to the user's past matching history during creation. For example, the creation unit can create optimal user groups based on the characteristics of people the user has matched with in the past. The creation unit can create user groups considering the characteristics of people the user has liked in the past. The creation unit can prioritize including compatible users in the group based on the user's past matching history. In this way, the creation unit can create optimal user groups by referring to the user's past matching history. The creation unit can use a generation AI to refer to past matching history. For example, the creation unit can input the user's past matching history into the generation AI and have the generation AI create the optimal user groups.

[0084] The creation unit can customize user groups based on the user's current lifestyle and areas of interest during creation. For example, the creation unit can include users related to areas the user is currently interested in. The creation unit can create user groups that match the user's lifestyle (work, hobbies, etc.). The creation unit can include users related to communities and events the user is currently participating in. In this way, the creation unit can create the optimal group for the user by customizing the user group based on the user's current lifestyle and areas of interest. The creation unit can use generative AI to take lifestyle and areas of interest into consideration. For example, the creation unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the user group.

[0085] The creation unit can estimate the user's emotions and determine the priority of user groups based on the estimated emotions. For example, if the user is stressed, the creation unit can prioritize relaxing user groups. If the user is excited, the creation unit can prioritize active user groups. If the user is tired, the creation unit can prioritize calm user groups. In this way, the creation unit can prioritize creating the optimal group for the user by determining the priority of user groups according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The creation unit can prioritize creating highly relevant user groups by considering the user's geographical location information during creation. For example, the creation unit can include users related to the region the user is currently in. If the user is traveling, the creation unit can include users related to the region they are visiting. The creation unit can also prioritize including users in the region where the user lives. In this way, the creation unit can prioritize creating highly relevant user groups by considering the user's geographical location information. The creation unit can use a generation AI to consider geographical location information. For example, the creation unit can input the user's geographical location information into the generation AI and have the generation AI create highly relevant user groups.

[0087] The creation unit can analyze a user's social media activity and create relevant user groups during the creation process. For example, the creation unit can include users related to accounts the user follows on social media. The creation unit can include users related to content the user has shared on social media. The creation unit can include users related to themes the user has shown interest in on social media. In this way, the creation unit can create relevant user groups by analyzing a user's social media activity. The creation unit can use generative AI to analyze social media activity. For example, the creation unit can input a user's social media activity into the generative AI and have the generative AI create relevant user groups.

[0088] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is tense, the evaluation unit can relax the evaluation criteria to help the user relax. If the user is excited, the evaluation unit can tighten the evaluation criteria to keep the user interested. If the user is tired, the evaluation unit can adjust the evaluation criteria to allow the user to evaluate comfortably. In this way, the evaluation unit can allow the user to evaluate comfortably by adjusting the evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluations based on features that the user has preferred in the past. The evaluation unit can adjust the evaluation criteria based on the user's past response history. The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. In this way, the evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. The evaluation unit can use a generative AI to refer to past response history. For example, the evaluation unit can input the user's past response history into the generative AI and have the generative AI perform the task of improving the accuracy of the evaluation.

[0090] The evaluation unit can customize the evaluation content based on the user's current lifestyle and areas of interest during the evaluation process. For example, the evaluation unit can provide evaluation content related to the user's current areas of interest. The evaluation unit can provide evaluation content that is appropriate for the user's lifestyle (work, hobbies, etc.). The evaluation unit can provide evaluation content related to the communities and events the user is currently participating in. In this way, the evaluation unit can provide the optimal evaluation for the user by customizing the evaluation content based on the user's current lifestyle and areas of interest. The evaluation unit can use generative AI to take lifestyle and areas of interest into consideration. For example, the evaluation unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the evaluation content.

[0091] The evaluation unit can estimate the user's emotions and determine the priority of evaluations based on the estimated emotions. For example, if the user is stressed, the evaluation unit will prioritize relaxing evaluations. If the user is excited, the evaluation unit can prioritize interesting evaluations. If the user is tired, the evaluation unit can prioritize simple and easy-to-understand evaluations. In this way, the evaluation unit can prioritize evaluations according to the user's emotions and provide the user with the most optimal evaluation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The evaluation unit can prioritize highly relevant evaluations by considering the user's geographical location during the evaluation process. For example, the evaluation unit can provide evaluations related to the area the user is currently in. If the user is traveling, the evaluation unit can provide evaluations related to the area they are visiting. The evaluation unit can also prioritize providing evaluations for the area where the user lives. In this way, the evaluation unit can prioritize highly relevant evaluations by considering the user's geographical location. The evaluation unit can use a generative AI to consider geographical location. For example, the evaluation unit can input the user's geographical location into the generative AI and have the generative AI select highly relevant evaluations.

[0093] The evaluation unit can analyze a user's social media activity and perform relevant evaluations during the evaluation process. For example, the evaluation unit can customize evaluation content based on articles and posts shared by the user on social media. The evaluation unit can provide evaluation content related to topics of accounts the user follows. The evaluation unit can provide evaluation content related to themes the user has shown interest in on social media. In this way, the evaluation unit can perform relevant evaluations by analyzing the user's social media activity. The evaluation unit can use generative AI to analyze social media activity. For example, the evaluation unit can input the user's social media activity into the generative AI and have the generative AI select relevant evaluation content.

[0094] The persuasion unit can estimate the user's emotions and adjust the timing of its persuasion based on the estimated emotions. For example, if the user is tense, the persuasion unit will persuasion at a time when the user can relax. If the user is excited, the persuasion unit can persuasion at a time when the user can find it interesting. If the user is tired, the persuasion unit can persuasion at a time when the user can easily accept it. In this way, the persuasion unit can adjust the timing of its persuasion according to the user's emotions, thereby providing the optimal timing for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The probing unit can select the optimal probing method by referring to the user's past matching history when probing. For example, the probing unit can select the optimal probing method based on the probing method the user has preferred in the past. The probing unit can select a probing method with a high success rate from the user's past matching history. The probing unit can select the optimal probing method by referring to probing methods that the user has found more acceptable in the past. In this way, the probing unit can select the optimal probing method by referring to the user's past matching history. The probing unit can use a generation AI to refer to past matching history. For example, the probing unit can input the user's past matching history into a generation AI and have the generation AI select the optimal probing method.

[0096] The prompting unit can customize the content of the prompt based on the user's current lifestyle and areas of interest. For example, the prompting unit can provide prompts related to areas the user is currently interested in. The prompting unit can provide prompts that are appropriate to the user's lifestyle (work, hobbies, etc.). The prompting unit can provide prompts related to communities and events the user is currently participating in. In this way, the prompting unit can make the most appropriate prompts for the user by customizing the prompts based on the user's current lifestyle and areas of interest. The prompting unit can use generative AI to take into account the user's lifestyle and areas of interest. For example, the prompting unit can input the user's lifestyle and areas of interest into the generative AI and have the generative AI perform the customization of the prompts.

[0097] The prompting unit can estimate the user's emotions and determine the priority of prompts based on the estimated emotions. For example, if the user is stressed, the prompting unit will prioritize prompts that promote relaxation. If the user is excited, the prompting unit can prioritize prompts that pique their interest. If the user is tired, the prompting unit can prioritize prompts that are simple and easy to understand. In this way, the prompting unit can prioritize prompts that are optimal for the user by determining the priority of prompts according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The prompting unit can prioritize highly relevant prompts by considering the user's geographical location information during the prompting process. For example, the prompting unit can provide prompts related to the user's current location. If the user is traveling, the prompting unit can provide prompts related to the destination region. The prompting unit can prioritize prompts for the user's residential area. In this way, the prompting unit can prioritize highly relevant prompts by considering the user's geographical location information. The prompting unit can use a generation AI to consider geographical location information. For example, the prompting unit can input the user's geographical location information into the generation AI and have the generation AI select highly relevant prompts.

[0099] The prompting unit can analyze the user's social media activity and make relevant prompts when making a prompt. For example, the prompting unit can customize the prompt based on articles and posts the user has shared on social media. The prompting unit can provide prompts related to topics of accounts the user follows. The prompting unit can provide prompts related to themes the user has shown interest in on social media. In this way, the prompting unit can make relevant prompts by analyzing the user's social media activity. The prompting unit can use generative AI to analyze social media activity. For example, the prompting unit can input the user's social media activity into the generative AI and have the generative AI select relevant prompts.

[0100] The contact unit can select the optimal contact timing by referring to the user's calendar information when making a contact. For example, the contact unit can refer to appointments registered in the user's calendar and make a contact during an available time. The contact unit can provide contact content related to a specific event based on the user's calendar information. Based on the user's calendar information, the contact unit can select the optimal contact timing that matches the appointment. In this way, the contact unit can select the optimal contact timing by referring to the user's calendar information. The contact unit can use a generation AI to refer to the calendar information. For example, the contact unit can input the user's calendar information into the generation AI and have the generation AI select the optimal contact timing.

[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 learning unit can estimate the user's emotions and adjust the conversation content based on those estimates. For example, if the user is feeling down, the learning unit can offer words of encouragement or positive topics. If the user is excited, the learning unit can offer topics that maintain that excitement. If the user is tired, the learning unit can offer topics that help them relax. In this way, the learning unit can increase user satisfaction by providing conversation content that matches the user's emotions.

[0103] The creation unit can analyze a user's past behavior history and create user groups based on their behavior patterns. For example, if a user was active during a specific time period in the past, other users who were active during that time period can be included in the group. If a user frequently participates in a specific event, users related to that event can be included in the group. If a user has a specific hobby, users related to that hobby can be included in the group. In this way, the creation unit can create optimal user groups based on the user's behavior patterns.

[0104] The evaluation unit can estimate the user's emotions and adjust the evaluation feedback based on those emotions. For example, if the user is feeling anxious, the evaluation unit can provide feedback in gentle language. If the user is confident, the evaluation unit can point out specific areas for improvement. If the user is tired, the evaluation unit can provide concise and easy-to-understand feedback. In this way, the evaluation unit can increase user acceptance by providing feedback that is tailored to the user's emotions.

[0105] The persuasive unit can estimate the user's emotions and adjust the content of the persuasion based on those emotions. For example, if the user is tense, the persuasive unit can use content that helps them relax. If the user is excited, the persuasive unit can use content that helps maintain that excitement. If the user is tired, the persuasive unit can use content that is simple and easy to understand. In this way, the persuasive unit can increase user acceptance by providing content that matches the user's emotions.

[0106] The learning unit can estimate the user's emotions and adjust the learning pace based on those emotions. For example, if the user is nervous, the learning pace can be slowed down to help the user relax. If the user is excited, the learning pace can be increased to keep the user interested. If the user is tired, the learning pace can be adjusted to allow the user to continue learning without difficulty. In this way, the learning unit can adjust the learning pace according to the user's emotions, allowing the user to continue learning without difficulty.

[0107] The creation process can create user groups while considering the user's geographical location. For example, if a user lives in a specific region, other users living in that region can be included in the group. If a user is traveling, users related to the region they are visiting can be included in the group. If a user is attending a specific event, users related to that event can be included in the group. In this way, the creation process can create highly relevant user groups by considering the user's geographical location.

[0108] The evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history. For example, it can improve the accuracy of its evaluations based on features the user has preferred in the past. It can adjust the evaluation criteria based on the user's past response history. It can improve the accuracy of its evaluations by referring to the user's past response history. In this way, the evaluation unit can improve the accuracy of its evaluations by referring to the user's past response history.

[0109] The contact unit can analyze a user's social media activity and make relevant contacts. For example, it can customize contact content based on articles and posts the user has shared on social media. It can provide contact content related to topics on accounts the user follows. It can provide contact content related to themes the user has shown interest in on social media. In this way, the contact unit can make relevant contacts by analyzing the user's social media activity.

[0110] The learning unit can analyze the user's past conversation history and select the optimal learning method. For example, it can customize the learning method based on words and phrases the user has used frequently in the past. It can also prioritize incorporating topics the user has shown interest in in the past into the learning content. From the user's past conversation history, it can select and reuse methods that were highly effective in learning. In this way, the learning unit can select the optimal learning method by analyzing the user's past conversation history.

[0111] The contact unit can select the optimal contact timing by referring to the user's calendar information. For example, it can refer to appointments registered in the user's calendar and contact them during their free time. Based on the user's calendar information, it can provide contact content related to a specific event. Based on the user's calendar information, it can select the optimal contact timing that matches their schedule. In this way, the contact unit can select the optimal contact timing by referring to the user's calendar information.

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

[0113] Step 1: The learning unit learns user characteristics. For example, through conversations with the user, it learns the user's age, gender, hobbies, behavioral patterns, conversation content, tone of voice, frequency, interests, etc. The learning unit can learn these characteristics using machine learning algorithms. Step 2: The creation unit creates user groups based on the features learned by the learning unit. For example, it creates user groups that are likely to be compatible with the user based on the learned features, and also creates user groups based on similarities in common hobbies and behavioral patterns. Step 3: The evaluation unit conducts conversations while switching the characteristics of the user groups created by the creation unit, and evaluates the users' responses. For example, it sets the types of user responses and evaluation scales based on specific methods and criteria for switching the characteristics of the user groups, and then evaluates the users' responses. Step 4: The probing unit makes a matching proposition based on the evaluation results from the evaluation unit. For example, based on the evaluation results, it determines the timing and content of the matching proposition, and if the user accepts, it switches the conversation partner from the AI ​​agent to an actual user.

[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 learning unit, creation unit, evaluation unit, and probing unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and learns the user's characteristics through conversation with the user. The creation unit is implemented by the identification processing unit 290 of the data processing device 12 and creates user groups based on the learned characteristics. The evaluation unit is implemented by the control unit 46A of the smart device 14 and evaluates the user's response by engaging in conversation while switching the characteristics of the user group. The probing unit is implemented by the identification processing unit 290 of the data processing device 12 and makes matching inquiries based on the evaluated results. 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 learning unit, creation unit, evaluation unit, and probing unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and learns the user's characteristics through conversation with the user. The creation unit is implemented by the identification processing unit 290 of the data processing device 12 and creates user groups based on the learned characteristics. The evaluation unit is implemented by the control unit 46A of the smart glasses 214 and evaluates the user's response by engaging in conversation while switching the characteristics of the user group. The probing unit is implemented by the identification processing unit 290 of the data processing device 12 and performs matching probing based on the evaluated results. 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.

[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 learning unit, creation unit, evaluation unit, and probing unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and learns the user's characteristics through conversation with the user. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and creates user groups based on the learned characteristics. The evaluation unit is implemented by the control unit 46A of the headset terminal 314 and evaluates the user's response while engaging in conversation while switching the characteristics of the user group. The probing unit is implemented by the identification processing unit 290 of the data processing unit 12 and makes matching inquiries based on the evaluated results. 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.

[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 learning unit, creation unit, evaluation unit, and tapping unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and learns the user's characteristics through conversation with the user. The creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and creates user groups based on the learned characteristics. The evaluation unit is implemented by the control unit 46A of the robot 414 and evaluates the user's response by engaging in conversation while switching the characteristics of the user group. The tapping unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs matching taps based on the evaluated results. 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.

[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) A learning unit that learns user characteristics, A creation unit that creates user groups based on the features learned by the learning unit, An evaluation unit conducts conversations while switching the characteristics of the user group created by the creation unit and evaluates the user's response. The system includes a tapping unit that performs matching inquiries based on the results evaluated by the evaluation unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Learn user characteristics through conversations with users. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned creation unit, Based on learned features, create user groups that are likely to be a good match for the user. The system described in Appendix 1, characterized by the features described herein. (Note 4) The evaluation unit, The conversation is conducted while switching between user group characteristics, and user responses are evaluated. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned tapping section is Based on the evaluation results, we will initiate a matching inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned tapping section is If the user accepts, the conversation partner will switch from the AI ​​agent to a real user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, Analyze the user's past conversation history and select the optimal learning method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During learning, the learning content is customized based on the user's interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, It estimates the user's emotions and determines learning priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, During learning, the system prioritizes learning highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During learning, the system analyzes users' social media activity and learns relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned creation unit, We estimate user sentiment and adjust how user groups are created based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned creation unit, During creation, the system references the user's past matching history to create the most suitable user group. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned creation unit, When creating a user group, customize it based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned creation unit, It estimates user sentiment and determines the priority of user groups based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned creation unit, When creating user groups, prioritize creating highly relevant user groups by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned creation unit, During creation, analyze users' social media activity and create relevant user groups. The system described in Appendix 1, characterized by the features described herein. (Note 19) The evaluation unit, It estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit, During evaluation, we improve the accuracy of the evaluation by referring to the user's past response history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit, During the evaluation process, the evaluation content is customized based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit, It estimates the user's emotions and determines the priority of evaluations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit, During the evaluation process, the system prioritizes evaluations that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit, During the evaluation process, we analyze users' social media activity and conduct relevant assessments. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned tapping section is The system estimates the user's emotions and adjusts the timing of the outreach based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned tapping section is When making an initial contact, the system selects the most suitable contact method by referring to the user's past matching history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned tapping section is When making an initial contact, the content of the inquiry is customized based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned tapping section is The system estimates the user's emotions and determines the priority of inquiries based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned tapping section is When making initial contacts, the system prioritizes contacts that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned tapping section is When making initial contact, we analyze the user's social media activity and make relevant inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned tapping section is When making an inquiry, the system selects the optimal timing by referring to the user's calendar information. 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. A learning unit that learns user characteristics, A creation unit creates a user group based on the features learned by the learning unit, An evaluation unit conducts conversations while switching the characteristics of the user group created by the creation unit and evaluates the user's response. The system includes a tapping unit that performs matching inquiries based on the results evaluated by the evaluation unit. A system characterized by the following features.

2. The aforementioned learning unit, Learn user characteristics through conversations with users. The system according to feature 1.

3. The aforementioned creation unit, Based on learned features, create user groups that are likely to be a good match for the user. The system according to feature 1.

4. The evaluation unit, The conversation is conducted while switching between user group characteristics, and user responses are evaluated. The system according to feature 1.

5. The aforementioned tapping section is Based on the evaluation results, we will initiate a matching inquiry. The system according to feature 1.

6. The aforementioned tapping section is If the user accepts, the conversation partner will switch from the AI ​​agent to a real user. The system according to feature 1.

7. The aforementioned learning unit, It estimates the user's emotions and adjusts the learning speed based on the estimated emotions. The system according to feature 1.

8. The aforementioned learning unit, Analyze the user's past conversation history and select the optimal learning method. The system according to feature 1.

Images