System

Abstract

The system according to the embodiment aims to allow a user to efficiently meet an ideal person.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a matching unit, and a provision unit. The reception unit receives an input of a feature of an ideal person from a user. The analysis unit analyzes the feature input by the reception unit. The matching unit performs matching from the database based on the feature analyzed by the analysis unit. The providing unit provides the profile of the person proposed by the matching unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of inefficient matching processes for users to meet their ideal partner.

[0005] The system according to the embodiment aims to enable users to efficiently meet their ideal person. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a matching unit, and a provision unit. The reception unit allows a user to input characteristics of an ideal person. The analysis unit analyzes the characteristics input by the reception unit. The matching unit performs matching from a database based on the characteristics analyzed by the analysis unit. The provision unit provides the user with a profile of the person suggested by the matching unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to efficiently meet their ideal person. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A matching system according to an embodiment of the present invention utilizes a generation AI to help users meet their ideal person. In the matching system, a user inputs the characteristics of their ideal person, and a generation AI analyzes those characteristics, performs optimal matching from a database, and provides the user with a profile of the suggested person. For example, the matching system allows a user to input detailed characteristics such as appearance, personality, hobbies, and values. The generation AI analyzes the characteristics of the ideal person in detail based on the user's input and analyzes the profiles of people in the database to identify people who are similar to their ideal person. This allows the user to meet their ideal person. This allows the matching system to efficiently input, analyze, match, and provide characteristics to help users meet their ideal person. For example, when a user inputs detailed characteristics, the generation AI analyzes those characteristics and performs optimal matching, allowing the user to meet someone who is similar to their ideal person.

[0029] A matching system according to an embodiment includes a reception unit, an analysis unit, a matching unit, and a providing unit. The reception unit allows a user to input characteristics of an ideal person. The characteristics input by the user include, but are not limited to, appearance, personality, hobbies, and values. The reception unit allows, for example, a user to input specific elements of appearance (height, weight, hair color, etc.). The reception unit also allows a user to input specific elements of personality (introversion, extroversion, etc.). The reception unit also allows a user to input detailed characteristics of hobbies and values. The analysis unit uses a generative AI to analyze the characteristics input by the reception unit. The analysis is performed using, for example, text analysis, image analysis, data mining, and other methods, but is not limited to these examples. For example, the analysis unit analyzes the user's input content using text analysis. The analysis unit can also analyze the user's input content using image analysis. The analysis unit can also analyze the user's input content using data mining. The matching unit performs matching from a database based on the characteristics analyzed by the analysis unit. Matching is performed using, for example, a similarity calculation, a filtering algorithm, or the like, but is not limited to these examples. For example, the matching unit analyzes the profiles of people in a database using a similarity calculation to identify people who are similar to their ideal person. The matching unit can also identify people who are similar to their ideal person using a filtering algorithm. Furthermore, the matching unit can perform optimal matching by combining multiple analysis methods. The providing unit provides the user with the profile of the person proposed by the matching unit. The provision is performed using, for example, a text format, an image format, a video format, or the like, but is not limited to these examples. For example, the providing unit provides the user with the profile of the proposed person in text format. The providing unit can also provide the user with the profile of the proposed person in image format. Furthermore, the providing unit can also provide the user with the profile of the proposed person in video format. As a result, the matching system according to the embodiment can efficiently input, analyze, match, and provide features to help users find their ideal person.For example, if a user inputs detailed characteristics, the generation AI will analyze those characteristics and perform optimal matching, allowing the user to meet someone who is close to their ideal partner.

[0030] The matching system includes a security unit that protects user privacy and implements security measures. The security unit protects user privacy and implements security measures. Privacy protection includes, but is not limited to, data encryption and anonymization technology. For example, the security unit encrypts and stores user data. The security unit can also anonymize and process user data. The security unit can also perform authentication when accessing user data. Security measures include, but are not limited to, firewalls, antivirus software, and the like. For example, the security unit uses a firewall to prevent unauthorized access from outside. The security unit can also protect the system from malware using antivirus software. Furthermore, the security unit can periodically perform security checks to detect system vulnerabilities and take appropriate measures. This strengthens user privacy protection and security measures. For example, encrypting user data protects it from unauthorized access by third parties. Strengthened security measures also improve system safety, allowing users to use the service with peace of mind.

[0031] The matching system includes an evaluation unit that evaluates the reliability of the proposed person. The evaluation unit evaluates the reliability of the proposed person. The evaluation of reliability includes, for example, past behavioral history, third-party evaluations, etc., but is not limited to these examples. For example, the evaluation unit analyzes the past behavioral history of the proposed person to evaluate reliability. The evaluation unit can also evaluate reliability based on third-party evaluations. Furthermore, the evaluation unit can also verify the profile information of the proposed person to evaluate reliability. This evaluates the reliability of the proposed person, improving the user's sense of security. For example, by confirming that the past behavioral history of the proposed person is reliable, the user can contact that person with peace of mind. Furthermore, by suggesting people with high third-party evaluations, the user can meet highly reliable people.

[0032] The reception unit allows the user to input detailed characteristics of appearance, personality, hobbies, and values. The reception unit allows the user to input detailed characteristics of appearance, personality, hobbies, and values. The detailed characteristics include, but are not limited to, specific elements of appearance (height, weight, hair color, etc.), specific elements of personality (introversion, extroversion, etc.), specific elements of hobbies (sports, music, reading, etc.), and specific elements of values ​​(family-oriented, career-oriented, etc.). For example, the reception unit allows the user to input specific elements of appearance. The reception unit also allows the user to input specific elements of personality. Furthermore, the reception unit also allows the user to input detailed characteristics of hobbies and values. This allows for more accurate matching by the user inputting detailed characteristics. For example, by the user inputting detailed characteristics of appearance, personality, hobbies, and values, the generation AI analyzes the characteristics and performs optimal matching, allowing the user to meet someone who is close to their ideal partner.

[0033] The analysis unit can perform a detailed analysis of the characteristics of an ideal person based on the user's input. The analysis unit uses the generation AI to perform a detailed analysis of the characteristics of an ideal person based on the user's input. Methods of detailed analysis include, but are not limited to, the granularity of the data and the type of analysis algorithm. For example, the analysis unit performs analysis by setting the granularity of the data finely. The analysis unit can also perform analysis by combining multiple analysis algorithms. Furthermore, the analysis unit can combine different analysis methods based on the user's input to derive optimal results. This enables highly accurate matching by performing a detailed analysis of the characteristics of an ideal person based on the user's input. For example, by analyzing the characteristics entered by the user in detail, the generation AI can perform optimal matching, allowing the user to meet someone who is close to their ideal person.

[0034] The matching unit can analyze the profiles of people in the database and identify people who are similar to the ideal person. The matching unit uses a generation AI to analyze the profiles of people in the database and identify people who are similar to the ideal person. Methods for identifying people who are similar to the ideal person include, but are not limited to, similarity scores and filtering conditions. For example, the matching unit can analyze the profiles of people in the database using similarity scores and identify people who are similar to the ideal person. The matching unit can also set filtering conditions to identify people who are similar to the ideal person. Furthermore, the matching unit can combine multiple analysis methods to derive optimal results. This allows people who are similar to the ideal person to be identified by analyzing the profiles of people in the database. For example, the generation AI can analyze the profiles of people in the database based on characteristics entered by a user and identify people who are similar to the ideal person, allowing the user to meet their ideal person.

[0035] The providing unit can provide the profile of the proposed person to the user. The providing unit provides the profile of the proposed person to the user. Methods for providing the profile include, but are not limited to, for example, a text format, an image format, and a video format. For example, the providing unit can provide the profile of the proposed person to the user in a text format. The providing unit can also provide the profile of the proposed person to the user in an image format. Furthermore, the providing unit can also provide the profile of the proposed person to the user in a video format. In this way, by providing the profile of the proposed person to the user, the user can contact a person in which the user is interested. For example, the user can check the profile of the proposed person and contact the person if they are interested, allowing the user to meet their ideal person.

[0036] The reception unit can analyze the user's past input history and provide an auto-completion function to reduce the effort required for input. The reception unit uses a generation AI to analyze the user's past input history and provide an auto-completion function to reduce the effort required for input. The auto-completion function includes, but is not limited to, methods for utilizing the past input history and completion algorithms. For example, the reception unit can automatically display features previously input by the user as candidates. The reception unit can also prioritize suggestions of input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest features to be used in a specific time period based on the user's past input history. This reduces the effort required for input by the user and enables efficient input. For example, by automatically displaying features previously input by the user as candidates, the user can reduce the effort required for inputting the same features again. Furthermore, by prioritized suggestions of input methods previously used by the user, the user can input features in a way that suits them best.

[0037] The reception unit can provide real-time feedback to the user as they enter information, thereby improving the accuracy of the input content. The reception unit uses a generative AI to provide real-time feedback to the user as they enter information, thereby improving the accuracy of the input content. Methods of providing real-time feedback include, but are not limited to, immediate checks of the input content and other forms of feedback. For example, the reception unit can display a confirmation message for the input content in real time as the user enters characteristics. The reception unit can also automatically suggest related characteristics based on the characteristics entered by the user. The reception unit can also provide real-time feedback on the corrections made when the user corrects the input content. This real-time feedback improves the accuracy of the input content and enables more accurate feature input. For example, by displaying a confirmation message for the input content in real time as the user enters characteristics, the user can enter the characteristics while checking the input content. Furthermore, by automatically suggesting related characteristics based on the characteristics entered by the user, the user can enter the characteristics of their ideal partner in more detail.

[0038] The reception unit can automatically generate related questions based on the user's input and collect detailed characteristics. The reception unit uses a generation AI to automatically generate related questions based on the user's input and collect detailed characteristics. Methods for automatically generating related questions include, but are not limited to, question generation algorithms and relevance evaluation criteria. For example, if a user inputs "I like sports," the reception unit can automatically generate a question asking about a specific type of sport. Furthermore, if a user inputs "I have a kind personality," the reception unit can automatically generate a question asking about specific episodes and actions. Furthermore, if a user inputs "I like music," the reception unit can automatically generate a question asking about favorite music genres and artists. This automatic generation of related questions allows for more accurate matching by collecting detailed characteristics. For example, if a user inputs "I like sports," a question asking about a specific type of sport is automatically generated, allowing the user to enter their hobbies in detail. Furthermore, if a user inputs "I have a kind personality," a question asking about specific episodes and actions is automatically generated, allowing the user to enter their personality in detail.

[0039] The reception unit may provide an option to input region-specific characteristics by taking into account the user's geographic location information. The reception unit may use a generation AI to provide an option to input region-specific characteristics by taking into account the user's geographic location information. The option to input region-specific characteristics includes, but is not limited to, hobbies, activities, tourist spots, and events that are specific to the region. For example, if the user lives in a specific region, the reception unit may provide an option to input hobbies and activities that are specific to that region. Furthermore, if the user uses the service while traveling, the reception unit may provide an option to input characteristics related to tourist spots and events in that region. Furthermore, if the user plans to move, the reception unit may provide an option to input information about the new region. This provides an option to input region-specific characteristics by taking into account the geographic location information, enabling more appropriate matching. For example, if the user lives in a specific region, providing an option to input hobbies and activities that are specific to that region allows the user to input characteristics that suit their region. Furthermore, if the user uses the service while traveling, providing an option to input characteristics related to tourist spots and events in that region allows the user to meet their ideal partner at their travel destination.

[0040] The reception unit can analyze the user's social media activity and automatically suggest related characteristics. The reception unit uses generative AI to analyze the user's social media activity and automatically suggest related characteristics. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the reception unit can analyze the user's frequent social media posts and suggest related characteristics. The reception unit can also analyze the user's social media friendships and suggest characteristics of common hobbies and interests. Furthermore, the reception unit can suggest related characteristics based on the user's social media activity history. In this way, by analyzing social media activity, related characteristics can be automatically suggested, reducing the effort of input. For example, by analyzing the user's frequent social media posts and suggesting related characteristics, the user can easily enter their hobbies and interests. Furthermore, by analyzing the user's social media friendships and suggesting characteristics of common hobbies and interests, the user can enter the characteristics of their ideal partner in more detail.

[0041] The reception unit can customize the input interface by reflecting the user's past feedback. The reception unit uses a generation AI to customize the input interface by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, survey results and user evaluation comments. For example, the reception unit adjusts the interface design based on feedback previously provided by the user. The reception unit can also improve the input method based on the accuracy of features previously input by the user. Furthermore, the reception unit can analyze the user's past feedback and provide an optimal input interface. In this way, by reflecting past feedback, an optimal input interface is provided for the user, improving input efficiency. For example, by adjusting the interface design based on feedback previously provided by the user, the user can input features using an easy-to-use interface. Furthermore, by improving the input method based on the accuracy of features previously input by the user, the user can input features more accurately.

[0042] The analysis unit can multidimensionally analyze the characteristics of an ideal person based on the user's input. The analysis unit uses a generative AI to multidimensionally analyze the characteristics of an ideal person based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple features and correlation evaluation. For example, the analysis unit multidimensionally analyzes the characteristics entered by the user, such as appearance, personality, hobbies, and values. The analysis unit can also analyze correlations based on the features entered by the user to identify the characteristics of an ideal person. Furthermore, the analysis unit can combine different analysis methods based on the features entered by the user to derive optimal results. This multidimensional analysis allows for more accurate identification of the characteristics of an ideal person. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generative AI can identify the characteristics of an ideal person in detail, allowing the user to meet someone who is close to their ideal person.

[0043] The analysis unit can improve the accuracy of the analysis by referring to the user's past input data. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the user's past input data. Methods for referring to the past input data include, but are not limited to, database structure, data storage period, etc. For example, the analysis unit can improve the accuracy of the analysis by referring to features previously input by the user. The analysis unit can also adjust the analysis algorithm based on the user's past input data. Furthermore, the analysis unit can analyze the user's past input data and select the optimal analysis method. In this way, by referring to the past input data, the accuracy of the analysis can be improved and more appropriate results can be provided. For example, by referring to features previously input by the user to improve the accuracy of the analysis, the generation AI can provide more accurate analysis results, allowing the user to meet someone who is closer to their ideal partner.

[0044] The analysis unit can combine different analysis methods based on the user's input to derive the optimal result. The analysis unit uses the generative AI to combine different analysis methods based on the user's input to derive the optimal result. Methods of combining different analysis methods include, but are not limited to, a combination of machine learning algorithms and hybrid analysis methods. For example, the analysis unit can combine machine learning and statistical analysis to derive the optimal result based on the features entered by the user. The analysis unit can also combine natural language processing and image analysis to derive the optimal result based on the features entered by the user. Furthermore, the analysis unit can combine different analysis methods to derive the optimal result based on the features entered by the user. This combination of different analysis methods can provide more accurate analysis results. For example, by combining machine learning and statistical analysis to derive the optimal result based on the features entered by the user, the generative AI can provide more accurate analysis results, allowing the user to meet someone who is closest to their ideal partner.

[0045] The analysis unit can perform region-specific analysis by taking into account the user's geographic location information. The analysis unit uses a generative AI to perform region-specific analysis by taking into account the user's geographic location information. Methods for performing region-specific analysis include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the analysis unit can perform analysis by taking into account characteristics specific to that region. Furthermore, if the user uses the service while traveling, the analysis unit can also perform analysis by taking into account characteristics related to tourist spots and events in that region. Furthermore, if the user is planning to move, the analysis unit can also perform analysis by taking into account information about the new region. This enables region-specific analysis by taking into account geographic location information, thereby providing more appropriate results. For example, if the user lives in a specific region, performing analysis by taking into account characteristics specific to that region allows the user to meet the ideal person who is suitable for their region. Furthermore, if the user uses the service while traveling, performing analysis by taking into account characteristics related to tourist spots and events in that region allows the user to meet the ideal person at their travel destination.

[0046] The analysis unit can analyze the user's social media activity and incorporate related data into the analysis. The analysis unit uses the generative AI to analyze the user's social media activity and incorporate related data into the analysis. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the analysis unit can analyze the content the user frequently posts on social media and incorporate related data into the analysis. The analysis unit can also analyze the user's social media friendships and incorporate data on common hobbies and interests into the analysis. Furthermore, the analysis unit can incorporate related data into the analysis based on the user's social media activity history. In this way, by analyzing social media activity, the analysis can incorporate related data into the analysis and provide more accurate results. For example, by analyzing the content the user frequently posts on social media and incorporating related data into the analysis, the generative AI can provide more accurate analysis results, allowing the user to meet people who are closer to their ideal partner.

[0047] The analysis unit can customize the analysis algorithm by reflecting the user's past feedback. The analysis unit uses the generation AI to customize the analysis algorithm by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the analysis unit adjusts the analysis algorithm based on feedback previously provided by the user. The analysis unit can also improve the analysis algorithm based on the accuracy of features previously input by the user. Furthermore, the analysis unit can analyze the user's past feedback and provide an optimal analysis algorithm. In this way, by reflecting past feedback, the analysis algorithm can be optimized and more accurate results can be provided. For example, by adjusting the analysis algorithm based on feedback previously provided by the user, the generation AI can provide more accurate analysis results, allowing the user to meet someone who is closer to their ideal partner.

[0048] The matching unit can multidimensionally analyze the profiles of people in the database based on the user's input. The matching unit uses a generation AI to multidimensionally analyze the profiles of people in the database based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple features and correlation evaluation. For example, the matching unit multidimensionally analyzes the characteristics entered by the user, such as appearance, personality, hobbies, and values. The matching unit can also analyze correlations based on the characteristics entered by the user to identify people who are similar to their ideal person. Furthermore, the matching unit can combine different analysis methods based on the characteristics entered by the user to derive optimal results. This multidimensional analysis can provide more accurate matching results. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generation AI can identify people who are similar to their ideal person in detail, allowing the user to meet their ideal person.

[0049] The matching unit can improve the accuracy of matching by referencing the user's past matching results. The matching unit uses the generation AI to improve the accuracy of matching by referencing the user's past matching results. Methods for referencing past matching results include, but are not limited to, database structure, data storage period, etc. For example, the matching unit can improve the accuracy of matching by referencing the characteristics of people the user has matched with in the past. The matching unit can also adjust the matching algorithm based on the user's past matching results. Furthermore, the matching unit can analyze the user's past matching results and select the optimal matching method. In this way, by referencing the past matching results, the accuracy of matching can be improved and more appropriate results can be provided. For example, by referencing the characteristics of people the user has matched with in the past to improve the accuracy of matching, the generation AI can provide more accurate matching results, allowing the user to meet their ideal person.

[0050] The matching unit can combine different matching methods based on the user's input to derive the optimal result. The matching unit uses a generation AI to combine different matching methods based on the user's input to derive the optimal result. Methods of combining different matching methods include, but are not limited to, a combination of machine learning algorithms and a hybrid matching method. For example, the matching unit can combine machine learning and statistical analysis to derive the optimal result based on the features input by the user. The matching unit can also combine natural language processing and image analysis to derive the optimal result based on the features input by the user. Furthermore, the matching unit can combine different matching methods to derive the optimal result based on the features input by the user. This combination of different matching methods can provide more accurate matching results. For example, by combining machine learning and statistical analysis to derive the optimal result based on the features input by the user, the generation AI can provide more accurate matching results, allowing the user to find their ideal partner.

[0051] The matching unit can perform region-specific matching by taking into account the user's geographical location information. The matching unit uses a generation AI to perform region-specific matching by taking into account the user's geographical location information. Methods for performing region-specific matching include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the matching unit can perform matching by taking into account characteristics specific to that region. Furthermore, if the user uses the service while traveling, the matching unit can perform matching by taking into account characteristics related to tourist spots and events in that region. Furthermore, if the user is planning to move, the matching unit can perform matching by taking into account information about the new region. This enables region-specific matching by taking into account the geographical location information, thereby providing more appropriate results. For example, if the user lives in a specific region, matching can be performed by taking into account characteristics specific to that region, allowing the user to meet the ideal person who is suitable for their region. Furthermore, if the user uses the service while traveling, matching can be performed by taking into account characteristics related to tourist spots and events in that region.

[0052] The matching unit can analyze a user's social media activity and incorporate related data into the matching process. The matching unit uses a generation AI to analyze a user's social media activity and incorporate related data into the matching process. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the matching unit can analyze the content that a user frequently posts on social media and incorporate related data into the matching process. The matching unit can also analyze the user's social media friendships and incorporate data on common hobbies and interests into the matching process. Furthermore, the matching unit can incorporate related data into the matching process based on the user's social media activity history. In this way, by analyzing social media activity, related data can be incorporated into the matching process, thereby providing more accurate results. For example, by analyzing the content that a user frequently posts on social media and incorporating related data into the matching process, the generation AI can provide more accurate matching results, allowing the user to meet someone who is closer to their ideal partner.

[0053] The matching unit can customize the matching algorithm by reflecting the user's past feedback. The matching unit uses the generation AI to customize the matching algorithm by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the matching unit adjusts the matching algorithm based on feedback previously provided by the user. The matching unit can also improve the matching algorithm based on the accuracy of features previously input by the user. Furthermore, the matching unit can analyze the user's past feedback and provide an optimal matching algorithm. In this way, by reflecting past feedback, the matching algorithm can be optimized and more accurate results can be provided. For example, by adjusting the matching algorithm based on feedback previously provided by the user, the generation AI can provide more accurate matching results, allowing the user to meet someone who is close to their ideal partner.

[0054] The providing unit can refer to the user's past browsing history to display an optimal profile. The providing unit uses a generation AI to refer to the user's past browsing history to display an optimal profile. Methods for referencing the past browsing history include, but are not limited to, database structure, data storage period, etc. For example, the providing unit can prioritize displaying related profiles based on profiles the user has previously viewed. The providing unit can also suggest profiles that the user may be interested in based on the user's past browsing history. Furthermore, the providing unit can analyze the user's past browsing history and provide an optimal profile display method. This makes it possible to display an optimal profile for the user by referring to the past browsing history. For example, by preferentially displaying related profiles based on profiles the user has previously viewed, the user can more easily find people who match their interests. Furthermore, by suggesting profiles that the user may be interested in based on the user's past browsing history, the user can encounter new people of interest.

[0055] The providing unit can automatically suggest related profiles based on the user's input. The providing unit uses a generation AI to automatically suggest related profiles based on the user's input. Methods for automatically suggesting related profiles include, but are not limited to, proposal algorithms and relevance evaluation criteria. For example, the providing unit can automatically suggest related profiles based on features input by the user. The providing unit can also analyze correlations based on the features input by the user and suggest related profiles. Furthermore, the providing unit can combine different analysis methods to suggest optimal profiles based on the features input by the user. This makes it easier for the user to find people who match their interests by suggesting related profiles based on the input. For example, automatically suggesting related profiles based on the features input by the user makes it easier for the user to find people who match their interests. Furthermore, analyzing correlations based on the features input by the user and suggesting related profiles allows the user to encounter new people of interest.

[0056] The providing unit can improve the accuracy of profile display by reflecting user feedback. The providing unit uses the generation AI to reflect user feedback and improve the accuracy of profile display. Methods of reflecting feedback include, but are not limited to, a method of collecting feedback and timing of reflection. For example, the providing unit can improve the accuracy of profile display based on feedback provided by the user. The providing unit can also adjust the display algorithm based on user feedback. Furthermore, the providing unit can analyze user feedback and provide an optimal profile display method. In this way, by reflecting feedback, the accuracy of profile display is improved and user satisfaction is increased. For example, by improving the accuracy of profile display based on user feedback, the user can more easily find people who match their interests. Furthermore, by adjusting the display algorithm based on user feedback, the user can receive more accurate profile display.

[0057] The providing unit can display a region-specific profile by taking into account the user's geographic location information. The providing unit uses a generation AI to display a region-specific profile by taking into account the user's geographic location information. Methods for displaying a region-specific profile include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the providing unit can display a profile with characteristics unique to that region. Furthermore, if the user uses the service while traveling, the providing unit can display a profile related to tourist attractions and events in that region. Furthermore, if the user is planning to move, the providing unit can display a profile with information about the new region. This allows for more appropriate matching by displaying a region-specific profile by taking into account the geographic location information. For example, if the user lives in a specific region, displaying a profile with characteristics unique to that region allows the user to meet the ideal person who suits their region. Furthermore, if the user uses the service while traveling, displaying a profile related to tourist attractions and events in that region allows the user to meet the ideal person at their travel destination.

[0058] The providing unit can analyze the user's social media activity and suggest related profiles. The providing unit uses a generative AI to analyze the user's social media activity and suggest related profiles. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the providing unit can analyze the content the user frequently posts on social media and suggest related profiles. The providing unit can also analyze the user's social media friendships and suggest profiles with common hobbies and interests. Furthermore, the providing unit can suggest related profiles based on the user's social media activity history. In this way, analyzing social media activity can suggest related profiles, making it easier for the user to find people who match the user's interests. For example, analyzing the content the user frequently posts on social media and suggesting related profiles can make it easier for the user to find people who match their interests. Furthermore, analyzing the user's social media friendships and suggesting profiles with common hobbies and interests can allow the user to meet new people of interest.

[0059] The providing unit can customize the profile display by reflecting the user's past feedback. The providing unit uses a generation AI to customize the profile display by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the providing unit adjusts the design of the profile display based on feedback previously provided by the user. The providing unit can also improve the display method based on the accuracy of profiles previously viewed by the user. Furthermore, the providing unit can analyze the user's past feedback and provide an optimal profile display method. In this way, by reflecting past feedback, an optimal profile display is provided to the user and satisfaction is improved. For example, by adjusting the design of the profile display based on feedback previously provided by the user, the user can view the profile using an easy-to-use interface. Furthermore, by improving the display method based on the accuracy of profiles previously viewed by the user, the user can receive a more accurate profile display.

[0060] The security unit can refer to the user's past security history to provide optimal security measures. The security unit uses a generation AI to refer to the user's past security history to provide optimal security measures. Methods for referring to past security history include, but are not limited to, database structure, data storage period, etc. For example, the security unit can refer to security risks the user has encountered in the past and provide optimal measures. The security unit can also adjust security algorithms based on the user's past security history. Furthermore, the security unit can analyze the user's past security history and provide optimal security measures. In this way, by referring to past security history, optimal security measures are provided and risks are reduced. For example, by referring to security risks the user has encountered in the past and providing optimal measures, the user can take appropriate measures against similar risks. Furthermore, by adjusting security algorithms based on the user's past security history, the user can receive more effective security measures.

[0061] The security unit can automatically evaluate security risks based on user input. The security unit uses generative AI to automatically evaluate security risks based on user input. Methods for automatically evaluating security risks include, but are not limited to, risk assessment algorithms and evaluation criteria. For example, the security unit automatically evaluates security risks based on features input by the user. The security unit can also analyze correlations based on the features input by the user to identify security risks. Furthermore, the security unit can combine different analysis methods based on the features input by the user to perform an optimal security risk assessment. This allows security risks to be evaluated based on input content, enabling early identification of risks and countermeasures to be taken. For example, automatically evaluating security risks based on features input by the user allows users to quickly identify potential risks and take appropriate countermeasures. Furthermore, analyzing correlations based on the features input by the user to identify security risks allows users to understand the details of the risks and take effective countermeasures.

[0062] The security unit can improve security measures by reflecting user feedback. The security unit uses generative AI to improve security measures by reflecting user feedback. Methods of reflecting feedback include, but are not limited to, methods of collecting feedback and timing of reflection. For example, the security unit improves security measures based on feedback provided by the user. The security unit can also adjust security algorithms based on user feedback. Furthermore, the security unit can analyze user feedback and provide optimal security measures. In this way, by reflecting feedback, security measures are optimized and risks are reduced. For example, by improving security measures based on user feedback, users can receive more effective security measures. Furthermore, by adjusting security algorithms based on user feedback, users can receive security measures that suit them.

[0063] The security unit can provide region-specific security measures by taking into account the user's geographic location information. The security unit uses a generative AI to provide region-specific security measures by taking into account the user's geographic location information. Methods for providing region-specific security measures include, but are not limited to, risk characteristics for each region and region-specific threats. For example, if the user lives in a specific region, the security unit can provide measures by taking into account security risks specific to that region. Furthermore, if the user uses the service while traveling, the security unit can provide measures related to security risks in that region. Furthermore, if the user plans to move, the security unit can provide measures by taking into account security information for the new region. In this way, region-specific security measures are provided by taking into account the geographic location information, thereby reducing risks. For example, if the user lives in a specific region, measures can be provided by taking into account security risks specific to that region, allowing the user to receive security measures appropriate for the region. Furthermore, if the user uses the service while traveling, measures related to security risks in that region can be provided, allowing the user to use the service with peace of mind even while traveling.

[0064] The security unit can analyze a user's social media activity and evaluate associated security risks. The security unit uses generative AI to analyze the user's social media activity and evaluate associated security risks. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the security unit can analyze the user's frequent social media posts and evaluate associated security risks. The security unit can also analyze the user's social media friendships and evaluate common security risks. Furthermore, the security unit can evaluate associated security risks based on the user's social media activity history. In this way, analyzing social media activity can evaluate associated security risks and take countermeasures. For example, by analyzing the user's frequent social media posts and evaluating related security risks, the user can identify potential risks early and take appropriate countermeasures. Furthermore, by analyzing the user's social media friendships and evaluating common security risks, the user can understand the details of the risks and take effective countermeasures.

[0065] The security unit can customize security measures by reflecting the user's past feedback. The security unit uses a generative AI to customize security measures by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the security unit customizes security measures based on feedback provided by the user in the past. The security unit can also improve measures based on security risks the user has encountered in the past. Furthermore, the security unit can analyze the user's past feedback and provide optimal security measures. In this way, security measures are optimized and risks are reduced by reflecting past feedback. For example, by customizing security measures based on feedback provided by the user in the past, the user can receive security measures that are tailored to them. Furthermore, by improving measures based on security risks the user has encountered in the past, the user can take appropriate measures against similar risks.

[0066] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation history. The evaluation unit uses the generation AI to improve the accuracy of the evaluation by referring to the user's past evaluation history. Methods for referring to the past evaluation history include, but are not limited to, database structure, data storage period, etc. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the user's past evaluation history. Furthermore, the evaluation unit can analyze the user's past evaluation history and select the optimal evaluation method. In this way, by referring to the past evaluation history, the accuracy of the evaluation can be improved and more appropriate results can be provided. For example, by referring to the user's past evaluations and improving the accuracy of the evaluation, the generation AI can provide more accurate evaluation results, allowing the user to meet someone who is closer to their ideal partner.

[0067] The evaluation unit can multidimensionally analyze the evaluation criteria based on the user's input. The evaluation unit uses the generation AI to multidimensionally analyze the evaluation criteria based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple evaluation criteria and correlation evaluation. For example, the evaluation unit multidimensionally analyzes the evaluation criteria based on the features input by the user. The evaluation unit can also analyze correlations and identify evaluation criteria based on the features input by the user. Furthermore, the evaluation unit can combine different analysis methods to derive optimal evaluation criteria based on the features input by the user. This multidimensional analysis can provide more accurate evaluation criteria. For example, by multidimensionally analyzing the evaluation criteria based on the features input by the user, the generation AI can provide more accurate evaluation criteria, allowing the user to meet someone who is closer to their ideal partner.

[0068] The evaluation unit can improve the evaluation criteria by reflecting user feedback. The evaluation unit uses a generative AI to improve the evaluation criteria by reflecting user feedback. Methods of reflecting feedback include, but are not limited to, methods of collecting feedback and timing of reflection. For example, the evaluation unit improves the evaluation criteria based on feedback provided by the user. The evaluation unit can also adjust the evaluation algorithm based on user feedback. Furthermore, the evaluation unit can analyze user feedback and provide optimal evaluation criteria. In this way, by reflecting feedback, the evaluation criteria can be optimized and more appropriate results can be provided. For example, by improving the evaluation criteria based on user feedback, the user can receive more accurate evaluation results. Furthermore, by adjusting the evaluation algorithm based on user feedback, the user can receive evaluation criteria that suit them.

[0069] The evaluation unit can provide region-specific evaluation criteria by taking into account the user's geographic location information. The evaluation unit uses a generation AI to provide region-specific evaluation criteria by taking into account the user's geographic location information. Methods for providing region-specific evaluation criteria include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the evaluation unit can provide evaluation criteria specific to that region. Furthermore, if the user uses the service while traveling, the evaluation unit can provide evaluation criteria related to tourist attractions and events in that region. Furthermore, if the user is planning to move, the evaluation unit can provide evaluation criteria that take into account information about the new region. In this way, by taking geographic location information into account, region-specific evaluation criteria can be provided and more appropriate results can be provided. For example, if the user lives in a specific region, providing region-specific evaluation criteria allows the user to receive evaluation results appropriate for the region. Furthermore, if the user uses the service while traveling, providing evaluation criteria related to tourist attractions and events in that region allows the user to receive appropriate evaluation results even at the travel destination.

[0070] The evaluation unit can analyze the user's social media activity and incorporate related evaluation data. The evaluation unit can use the generation AI to analyze the user's social media activity and incorporate related evaluation data. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the evaluation unit can analyze the content the user frequently posts on social media and incorporate related evaluation data. The evaluation unit can also analyze the user's social media friendships and incorporate evaluation data based on shared hobbies and interests. Furthermore, the evaluation unit can incorporate related evaluation data based on the user's social media activity history. In this way, by analyzing social media activity, the generation AI can incorporate related evaluation data and provide more accurate results. For example, by analyzing the content the user frequently posts on social media and incorporating related evaluation data, the generation AI can provide more accurate evaluation results, allowing the user to meet someone who is closer to their ideal partner.

[0071] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback. The evaluation unit uses a generation AI to customize the evaluation criteria by reflecting the user's past feedback. Methods of reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the evaluation unit customizes the evaluation criteria based on feedback provided by the user in the past. The evaluation unit can also improve the evaluation criteria based on the accuracy of the user's past evaluations. Furthermore, the evaluation unit can analyze the user's past feedback and provide optimal evaluation criteria. In this way, by reflecting past feedback, the evaluation criteria can be optimized and more appropriate results can be provided. For example, by customizing the evaluation criteria based on feedback provided by the user in the past, the user can receive evaluation criteria that suit them. Furthermore, by improving the evaluation criteria based on the accuracy of the user's past evaluations, the user can receive more accurate evaluation results.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The reception unit can automatically generate related questions based on the characteristics input by the user and collect detailed characteristics. For example, if the user inputs "I like sports," the reception unit can automatically generate questions asking about specific types of sports. If the user inputs "I have a kind personality," the reception unit can automatically generate questions asking about specific episodes and actions. If the user inputs "I like music," the reception unit can automatically generate questions asking about favorite music genres and artists. By automatically generating related questions, detailed characteristics can be collected and more accurate matching can be achieved. For example, if the user inputs "I like sports," the reception unit can automatically generate questions asking about specific types of sports, allowing the user to enter their hobbies in detail. If the user inputs "I have a kind personality," the reception unit can automatically generate questions asking about specific episodes and actions, allowing the user to enter their personality in detail.

[0074] The analysis unit can multidimensionally analyze the characteristics of an ideal person based on the user's input. For example, it multidimensionally analyzes characteristics such as appearance, personality, hobbies, and values ​​entered by the user. It can also analyze correlations based on the characteristics entered by the user to identify the characteristics of an ideal person. It can also combine different analysis methods based on the characteristics entered by the user to derive optimal results. This multidimensional analysis allows for more accurate identification of the characteristics of an ideal person. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generative AI can identify the characteristics of an ideal person in detail, allowing the user to meet someone who is close to their ideal person.

[0075] The matching unit can improve the accuracy of matching by referring to the user's past matching results. For example, it can improve the accuracy of matching by referring to the characteristics of people the user has matched with in the past. It can also adjust the matching algorithm based on the user's past matching results. It can also analyze the user's past matching results and select the optimal matching method. In this way, by referring to past matching results, it can improve the accuracy of matching and provide more appropriate results. For example, by referring to the characteristics of people the user has matched with in the past and improving the accuracy of matching, the generation AI can provide more accurate matching results, allowing the user to meet their ideal person.

[0076] The providing unit can refer to the user's past browsing history to display the most appropriate profile. For example, based on profiles the user has viewed in the past, related profiles can be preferentially displayed. Also, based on the user's past browsing history, profiles that may be of interest can be suggested. Furthermore, the providing unit can analyze the user's past browsing history and provide an optimal profile display method. This makes it possible to display the most appropriate profile for the user by referring to the past browsing history. For example, by preferentially displaying related profiles based on profiles the user has viewed in the past, the user can easily find people who match their interests. Also, by suggesting profiles that may be of interest based on the user's past browsing history, the user can encounter new people of interest.

[0077] The security unit can provide optimal security measures by referring to the user's past security history. For example, the security unit can provide optimal measures by referring to security risks the user has encountered in the past. The security unit can also adjust security algorithms based on the user's past security history. Furthermore, the security unit can analyze the user's past security history and provide optimal security measures. In this way, optimal security measures are provided and risks are reduced by referring to the past security history. For example, by referring to security risks the user has encountered in the past and providing optimal measures, the user can take appropriate measures against similar risks. Furthermore, by adjusting security algorithms based on the user's past security history, the user can receive more effective security measures.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The reception unit allows the user to input the characteristics of their ideal partner. The characteristics input by the user include appearance (height, weight, hair color, etc.), personality (introvert, extrovert, etc.), hobbies, values, etc. Step 2: The analysis unit uses the generation AI to analyze the features input by the reception unit. The analysis is performed using methods such as text analysis, image analysis, and data mining. Step 3: The matching unit performs matching from the database based on the features analyzed by the analysis unit. Matching is performed using methods such as similarity calculation and filtering algorithms. Step 4: The providing unit provides the user with the profile of the person proposed by the matching unit in a format such as text, image, or video.

[0080] (Example 2) A matching system according to an embodiment of the present invention utilizes a generation AI to help users meet their ideal person. In the matching system, a user inputs the characteristics of their ideal person, and a generation AI analyzes those characteristics, performs optimal matching from a database, and provides the user with a profile of the suggested person. For example, the matching system allows a user to input detailed characteristics such as appearance, personality, hobbies, and values. The generation AI analyzes the characteristics of the ideal person in detail based on the user's input and analyzes the profiles of people in the database to identify people who are similar to their ideal person. This allows the user to meet their ideal person. This allows the matching system to efficiently input, analyze, match, and provide characteristics to help users meet their ideal person. For example, when a user inputs detailed characteristics, the generation AI analyzes those characteristics and performs optimal matching, allowing the user to meet someone who is similar to their ideal person.

[0081] A matching system according to an embodiment includes a reception unit, an analysis unit, a matching unit, and a providing unit. The reception unit allows a user to input characteristics of an ideal person. The characteristics input by the user include, but are not limited to, appearance, personality, hobbies, and values. The reception unit allows, for example, a user to input specific elements of appearance (height, weight, hair color, etc.). The reception unit also allows a user to input specific elements of personality (introversion, extroversion, etc.). The reception unit also allows a user to input detailed characteristics of hobbies and values. The analysis unit uses a generative AI to analyze the characteristics input by the reception unit. The analysis is performed using, for example, text analysis, image analysis, data mining, and other methods, but is not limited to these examples. For example, the analysis unit analyzes the user's input content using text analysis. The analysis unit can also analyze the user's input content using image analysis. The analysis unit can also analyze the user's input content using data mining. The matching unit performs matching from a database based on the characteristics analyzed by the analysis unit. Matching is performed using, for example, a similarity calculation, a filtering algorithm, or the like, but is not limited to these examples. For example, the matching unit analyzes the profiles of people in a database using a similarity calculation to identify people who are similar to their ideal person. The matching unit can also identify people who are similar to their ideal person using a filtering algorithm. Furthermore, the matching unit can perform optimal matching by combining multiple analysis methods. The providing unit provides the user with the profile of the person proposed by the matching unit. The provision is performed using, for example, a text format, an image format, a video format, or the like, but is not limited to these examples. For example, the providing unit provides the user with the profile of the proposed person in text format. The providing unit can also provide the user with the profile of the proposed person in image format. Furthermore, the providing unit can also provide the user with the profile of the proposed person in video format. As a result, the matching system according to the embodiment can efficiently input, analyze, match, and provide features to help users find their ideal person.For example, if a user inputs detailed characteristics, the generation AI will analyze those characteristics and perform optimal matching, allowing the user to meet someone who is close to their ideal partner.

[0082] The matching system includes a security unit that protects user privacy and implements security measures. The security unit protects user privacy and implements security measures. Privacy protection includes, but is not limited to, data encryption and anonymization technology. For example, the security unit encrypts and stores user data. The security unit can also anonymize and process user data. The security unit can also perform authentication when accessing user data. Security measures include, but are not limited to, firewalls, antivirus software, and the like. For example, the security unit uses a firewall to prevent unauthorized access from outside. The security unit can also protect the system from malware using antivirus software. Furthermore, the security unit can periodically perform security checks to detect system vulnerabilities and take appropriate measures. This strengthens user privacy protection and security measures. For example, encrypting user data protects it from unauthorized access by third parties. Strengthened security measures also improve system safety, allowing users to use the service with peace of mind.

[0083] The matching system includes an evaluation unit that evaluates the reliability of the proposed person. The evaluation unit evaluates the reliability of the proposed person. The evaluation of reliability includes, for example, past behavioral history, third-party evaluations, etc., but is not limited to these examples. For example, the evaluation unit analyzes the past behavioral history of the proposed person to evaluate reliability. The evaluation unit can also evaluate reliability based on third-party evaluations. Furthermore, the evaluation unit can also verify the profile information of the proposed person to evaluate reliability. This evaluates the reliability of the proposed person, improving the user's sense of security. For example, by confirming that the past behavioral history of the proposed person is reliable, the user can contact that person with peace of mind. Furthermore, by suggesting people with high third-party evaluations, the user can meet highly reliable people.

[0084] The reception unit allows the user to input detailed characteristics of appearance, personality, hobbies, and values. The reception unit allows the user to input detailed characteristics of appearance, personality, hobbies, and values. The detailed characteristics include, but are not limited to, specific elements of appearance (height, weight, hair color, etc.), specific elements of personality (introversion, extroversion, etc.), specific elements of hobbies (sports, music, reading, etc.), and specific elements of values ​​(family-oriented, career-oriented, etc.). For example, the reception unit allows the user to input specific elements of appearance. The reception unit also allows the user to input specific elements of personality. Furthermore, the reception unit also allows the user to input detailed characteristics of hobbies and values. This allows for more accurate matching by the user inputting detailed characteristics. For example, by the user inputting detailed characteristics of appearance, personality, hobbies, and values, the generation AI analyzes the characteristics and performs optimal matching, allowing the user to meet someone who is close to their ideal partner.

[0085] The analysis unit can perform a detailed analysis of the characteristics of an ideal person based on the user's input. The analysis unit uses the generation AI to perform a detailed analysis of the characteristics of an ideal person based on the user's input. Methods of detailed analysis include, but are not limited to, the granularity of the data and the type of analysis algorithm. For example, the analysis unit performs analysis by setting the granularity of the data finely. The analysis unit can also perform analysis by combining multiple analysis algorithms. Furthermore, the analysis unit can combine different analysis methods based on the user's input to derive optimal results. This enables highly accurate matching by performing a detailed analysis of the characteristics of an ideal person based on the user's input. For example, by analyzing the characteristics entered by the user in detail, the generation AI can perform optimal matching, allowing the user to meet someone who is close to their ideal person.

[0086] The matching unit can analyze the profiles of people in the database and identify people who are similar to the ideal person. The matching unit uses a generation AI to analyze the profiles of people in the database and identify people who are similar to the ideal person. Methods for identifying people who are similar to the ideal person include, but are not limited to, similarity scores and filtering conditions. For example, the matching unit can analyze the profiles of people in the database using similarity scores and identify people who are similar to the ideal person. The matching unit can also set filtering conditions to identify people who are similar to the ideal person. Furthermore, the matching unit can combine multiple analysis methods to derive optimal results. This allows people who are similar to the ideal person to be identified by analyzing the profiles of people in the database. For example, the generation AI can analyze the profiles of people in the database based on characteristics entered by a user and identify people who are similar to the ideal person, allowing the user to meet their ideal person.

[0087] The providing unit can provide the profile of the proposed person to the user. The providing unit provides the profile of the proposed person to the user. Methods for providing the profile include, but are not limited to, for example, a text format, an image format, and a video format. For example, the providing unit can provide the profile of the proposed person to the user in a text format. The providing unit can also provide the profile of the proposed person to the user in an image format. Furthermore, the providing unit can also provide the profile of the proposed person to the user in a video format. In this way, by providing the profile of the proposed person to the user, the user can contact a person in which the user is interested. For example, the user can check the profile of the proposed person and contact the person if they are interested, allowing the user to meet their ideal person.

[0088] The reception unit can estimate the user's emotions and customize the interface for inputting the characteristics of an ideal person based on the estimated user emotions. The reception unit can estimate the user's emotions using a generative AI and customize the interface for inputting the characteristics of an ideal person based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression analysis, voice analysis, and text analysis. For example, the reception unit can estimate the user's emotions using facial expression analysis. The reception unit can also estimate the user's emotions using voice analysis. The reception unit can also estimate the user's emotions using text analysis. Methods for customizing the interface based on emotions include, but are not limited to, changing the interface design, providing input options, prioritizing voice input, and the like. For example, if the user is nervous, the reception unit can provide a simple and intuitive interface to reduce the effort required for input. If the user is relaxed, the reception unit can provide detailed input options and suggest a customizable interface. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to enable quick feature input. This reduces the effort required for input and improves the user experience by providing an interface that responds to the user's emotions. For example, if the user is nervous, a simple and intuitive interface reduces the effort required for input and allows the user to enter characteristics without stress. On the other hand, if the user is relaxed, detailed input options are provided, allowing the user to enter the characteristics of their ideal partner in detail.

[0089] The reception unit can analyze the user's past input history and provide an auto-completion function to reduce the effort required for input. The reception unit uses a generation AI to analyze the user's past input history and provide an auto-completion function to reduce the effort required for input. The auto-completion function includes, but is not limited to, methods for utilizing the past input history and completion algorithms. For example, the reception unit can automatically display features previously input by the user as candidates. The reception unit can also prioritize suggestions of input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest features to be used in a specific time period based on the user's past input history. This reduces the effort required for input by the user and enables efficient input. For example, by automatically displaying features previously input by the user as candidates, the user can reduce the effort required for inputting the same features again. Furthermore, by prioritized suggestions of input methods previously used by the user, the user can input features in a way that suits them best.

[0090] The reception unit can provide real-time feedback to the user as they enter information, thereby improving the accuracy of the input content. The reception unit uses a generative AI to provide real-time feedback to the user as they enter information, thereby improving the accuracy of the input content. Methods of providing real-time feedback include, but are not limited to, immediate checks of the input content and other forms of feedback. For example, the reception unit can display a confirmation message for the input content in real time as the user enters characteristics. The reception unit can also automatically suggest related characteristics based on the characteristics entered by the user. The reception unit can also provide real-time feedback on the corrections made when the user corrects the input content. This real-time feedback improves the accuracy of the input content and enables more accurate feature input. For example, by displaying a confirmation message for the input content in real time as the user enters characteristics, the user can enter the characteristics while checking the input content. Furthermore, by automatically suggesting related characteristics based on the characteristics entered by the user, the user can enter the characteristics of their ideal partner in more detail.

[0091] The reception unit can automatically generate related questions based on the user's input and collect detailed characteristics. The reception unit uses a generation AI to automatically generate related questions based on the user's input and collect detailed characteristics. Methods for automatically generating related questions include, but are not limited to, question generation algorithms and relevance evaluation criteria. For example, if a user inputs "I like sports," the reception unit can automatically generate a question asking about a specific type of sport. Furthermore, if a user inputs "I have a kind personality," the reception unit can automatically generate a question asking about specific episodes and actions. Furthermore, if a user inputs "I like music," the reception unit can automatically generate a question asking about favorite music genres and artists. This automatic generation of related questions allows for more accurate matching by collecting detailed characteristics. For example, if a user inputs "I like sports," a question asking about a specific type of sport is automatically generated, allowing the user to enter their hobbies in detail. Furthermore, if a user inputs "I have a kind personality," a question asking about specific episodes and actions is automatically generated, allowing the user to enter their personality in detail.

[0092] The reception unit can estimate the user's emotions and adjust the priority of input content based on the estimated user emotions. The reception unit can estimate the user's emotions using a generation AI and adjust the priority of input content based on the estimated user emotions. Methods for adjusting the priority of input content include, but are not limited to, importance scores and the user's emotional state. For example, if the user is nervous, the reception unit can provide an interface that allows the user to input important characteristics first. Also, if the user is relaxed, the reception unit can provide an interface that allows the user to input detailed characteristics first. Furthermore, if the user is in a hurry, the reception unit can provide an interface that allows the user to input the most important characteristics first. In this way, by adjusting the priority of input content according to the user's emotions, the important characteristics can be input first. For example, if the user is nervous, an interface that allows the user to input important characteristics first can be provided, allowing the user to input important characteristics without stress. Also, if the user is relaxed, an interface that allows the user to input detailed characteristics can be provided, allowing the user to input the characteristics of their ideal partner in detail.

[0093] The reception unit may provide an option to input region-specific characteristics by taking into account the user's geographic location information. The reception unit may use a generation AI to provide an option to input region-specific characteristics by taking into account the user's geographic location information. The option to input region-specific characteristics includes, but is not limited to, hobbies, activities, tourist spots, and events that are specific to the region. For example, if the user lives in a specific region, the reception unit may provide an option to input hobbies and activities that are specific to that region. Furthermore, if the user uses the service while traveling, the reception unit may provide an option to input characteristics related to tourist spots and events in that region. Furthermore, if the user plans to move, the reception unit may provide an option to input information about the new region. This provides an option to input region-specific characteristics by taking into account the geographic location information, enabling more appropriate matching. For example, if the user lives in a specific region, providing an option to input hobbies and activities that are specific to that region allows the user to input characteristics that suit their region. Furthermore, if the user uses the service while traveling, providing an option to input characteristics related to tourist spots and events in that region allows the user to meet their ideal partner at their travel destination.

[0094] The reception unit can analyze the user's social media activity and automatically suggest related characteristics. The reception unit uses generative AI to analyze the user's social media activity and automatically suggest related characteristics. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the reception unit can analyze the user's frequent social media posts and suggest related characteristics. The reception unit can also analyze the user's social media friendships and suggest characteristics of common hobbies and interests. Furthermore, the reception unit can suggest related characteristics based on the user's social media activity history. In this way, by analyzing social media activity, related characteristics can be automatically suggested, reducing the effort of input. For example, by analyzing the user's frequent social media posts and suggesting related characteristics, the user can easily enter their hobbies and interests. Furthermore, by analyzing the user's social media friendships and suggesting characteristics of common hobbies and interests, the user can enter the characteristics of their ideal partner in more detail.

[0095] The reception unit can customize the input interface by reflecting the user's past feedback. The reception unit uses a generation AI to customize the input interface by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, survey results and user evaluation comments. For example, the reception unit adjusts the interface design based on feedback previously provided by the user. The reception unit can also improve the input method based on the accuracy of features previously input by the user. Furthermore, the reception unit can analyze the user's past feedback and provide an optimal input interface. In this way, by reflecting past feedback, an optimal input interface is provided for the user, improving input efficiency. For example, by adjusting the interface design based on feedback previously provided by the user, the user can input features using an easy-to-use interface. Furthermore, by improving the input method based on the accuracy of features previously input by the user, the user can input features more accurately.

[0096] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. The analysis unit uses a generative AI to estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. Methods for adjusting the analysis algorithm include, but are not limited to, parameter adjustment and algorithm selection. For example, if the user is nervous, the analysis unit uses a simple and intuitive analysis algorithm. Alternatively, if the user is relaxed, the analysis unit can use a detailed analysis algorithm. Furthermore, if the user is in a hurry, the analysis unit can use an algorithm that provides analysis results quickly. This allows for more appropriate analysis results to be provided by adjusting the analysis algorithm according to the user's emotions. For example, if the user is nervous, a simple and intuitive analysis algorithm can be used, allowing the user to receive analysis results without stress. Alternatively, if the user is relaxed, a detailed analysis algorithm can be used, allowing the user to receive more detailed analysis results.

[0097] The analysis unit can multidimensionally analyze the characteristics of an ideal person based on the user's input. The analysis unit uses a generative AI to multidimensionally analyze the characteristics of an ideal person based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple features and correlation evaluation. For example, the analysis unit multidimensionally analyzes the characteristics entered by the user, such as appearance, personality, hobbies, and values. The analysis unit can also analyze correlations based on the features entered by the user to identify the characteristics of an ideal person. Furthermore, the analysis unit can combine different analysis methods based on the features entered by the user to derive optimal results. This multidimensional analysis allows for more accurate identification of the characteristics of an ideal person. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generative AI can identify the characteristics of an ideal person in detail, allowing the user to meet someone who is close to their ideal person.

[0098] The analysis unit can improve the accuracy of the analysis by referring to the user's past input data. The analysis unit uses the generation AI to improve the accuracy of the analysis by referring to the user's past input data. Methods for referring to the past input data include, but are not limited to, database structure, data storage period, etc. For example, the analysis unit can improve the accuracy of the analysis by referring to features previously input by the user. The analysis unit can also adjust the analysis algorithm based on the user's past input data. Furthermore, the analysis unit can analyze the user's past input data and select the optimal analysis method. In this way, by referring to the past input data, the accuracy of the analysis can be improved and more appropriate results can be provided. For example, by referring to features previously input by the user to improve the accuracy of the analysis, the generation AI can provide more accurate analysis results, allowing the user to meet someone who is closer to their ideal partner.

[0099] The analysis unit can combine different analysis methods based on the user's input to derive the optimal result. The analysis unit uses the generative AI to combine different analysis methods based on the user's input to derive the optimal result. Methods of combining different analysis methods include, but are not limited to, a combination of machine learning algorithms and hybrid analysis methods. For example, the analysis unit can combine machine learning and statistical analysis to derive the optimal result based on the features entered by the user. The analysis unit can also combine natural language processing and image analysis to derive the optimal result based on the features entered by the user. Furthermore, the analysis unit can combine different analysis methods to derive the optimal result based on the features entered by the user. This combination of different analysis methods can provide more accurate analysis results. For example, by combining machine learning and statistical analysis to derive the optimal result based on the features entered by the user, the generative AI can provide more accurate analysis results, allowing the user to meet someone who is closest to their ideal partner.

[0100] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The analysis unit uses a generative AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. Methods for adjusting the display method of the analysis results include, but are not limited to, graph display, text display, and interactive display. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. Also, if the user is relaxed, the analysis unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This allows the user to understand the analysis results more clearly by providing a display method that corresponds to the user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided, allowing the user to understand the analysis results without stress. Also, if the user is relaxed, a display method including detailed information can be provided, allowing the user to understand the analysis results in detail.

[0101] The analysis unit can perform region-specific analysis by taking into account the user's geographic location information. The analysis unit uses a generative AI to perform region-specific analysis by taking into account the user's geographic location information. Methods for performing region-specific analysis include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the analysis unit can perform analysis by taking into account characteristics specific to that region. Furthermore, if the user uses the service while traveling, the analysis unit can also perform analysis by taking into account characteristics related to tourist spots and events in that region. Furthermore, if the user is planning to move, the analysis unit can also perform analysis by taking into account information about the new region. This enables region-specific analysis by taking into account geographic location information, thereby providing more appropriate results. For example, if the user lives in a specific region, performing analysis by taking into account characteristics specific to that region allows the user to meet the ideal person who is suitable for their region. Furthermore, if the user uses the service while traveling, performing analysis by taking into account characteristics related to tourist spots and events in that region allows the user to meet the ideal person at their travel destination.

[0102] The analysis unit can analyze the user's social media activity and incorporate related data into the analysis. The analysis unit uses the generative AI to analyze the user's social media activity and incorporate related data into the analysis. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the analysis unit can analyze the content the user frequently posts on social media and incorporate related data into the analysis. The analysis unit can also analyze the user's social media friendships and incorporate data on common hobbies and interests into the analysis. Furthermore, the analysis unit can incorporate related data into the analysis based on the user's social media activity history. In this way, by analyzing social media activity, the analysis can incorporate related data into the analysis and provide more accurate results. For example, by analyzing the content the user frequently posts on social media and incorporating related data into the analysis, the generative AI can provide more accurate analysis results, allowing the user to meet people who are closer to their ideal partner.

[0103] The analysis unit can customize the analysis algorithm by reflecting the user's past feedback. The analysis unit uses the generation AI to customize the analysis algorithm by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the analysis unit adjusts the analysis algorithm based on feedback previously provided by the user. The analysis unit can also improve the analysis algorithm based on the accuracy of features previously input by the user. Furthermore, the analysis unit can analyze the user's past feedback and provide an optimal analysis algorithm. In this way, by reflecting past feedback, the analysis algorithm can be optimized and more accurate results can be provided. For example, by adjusting the analysis algorithm based on feedback previously provided by the user, the generation AI can provide more accurate analysis results, allowing the user to meet someone who is closer to their ideal partner.

[0104] The matching unit can estimate the user's emotions and adjust the matching algorithm based on the estimated user emotions. The matching unit uses a generation AI to estimate the user's emotions and adjust the matching algorithm based on the estimated user emotions. Methods for adjusting the matching algorithm include, but are not limited to, parameter adjustment and algorithm selection. For example, if the user is nervous, the matching unit can use a simple and intuitive matching algorithm. Alternatively, if the user is relaxed, the matching unit can use a detailed matching algorithm. Furthermore, if the user is in a hurry, the matching unit can use an algorithm that provides matching results quickly. This allows for more appropriate matching results by providing a matching algorithm that corresponds to the user's emotions. For example, if the user is nervous, a simple and intuitive matching algorithm can be used, allowing the user to receive matching results without stress. Alternatively, if the user is relaxed, a detailed matching algorithm can be used, allowing the user to receive more detailed matching results.

[0105] The matching unit can multidimensionally analyze the profiles of people in the database based on the user's input. The matching unit uses a generation AI to multidimensionally analyze the profiles of people in the database based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple features and correlation evaluation. For example, the matching unit multidimensionally analyzes the characteristics entered by the user, such as appearance, personality, hobbies, and values. The matching unit can also analyze correlations based on the characteristics entered by the user to identify people who are similar to their ideal person. Furthermore, the matching unit can combine different analysis methods based on the characteristics entered by the user to derive optimal results. This multidimensional analysis can provide more accurate matching results. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generation AI can identify people who are similar to their ideal person in detail, allowing the user to meet their ideal person.

[0106] The matching unit can improve the accuracy of matching by referencing the user's past matching results. The matching unit uses the generation AI to improve the accuracy of matching by referencing the user's past matching results. Methods for referencing past matching results include, but are not limited to, database structure, data storage period, etc. For example, the matching unit can improve the accuracy of matching by referencing the characteristics of people the user has matched with in the past. The matching unit can also adjust the matching algorithm based on the user's past matching results. Furthermore, the matching unit can analyze the user's past matching results and select the optimal matching method. In this way, by referencing the past matching results, the accuracy of matching can be improved and more appropriate results can be provided. For example, by referencing the characteristics of people the user has matched with in the past to improve the accuracy of matching, the generation AI can provide more accurate matching results, allowing the user to meet their ideal person.

[0107] The matching unit can combine different matching methods based on the user's input to derive the optimal result. The matching unit uses a generation AI to combine different matching methods based on the user's input to derive the optimal result. Methods of combining different matching methods include, but are not limited to, a combination of machine learning algorithms and a hybrid matching method. For example, the matching unit can combine machine learning and statistical analysis to derive the optimal result based on the features input by the user. The matching unit can also combine natural language processing and image analysis to derive the optimal result based on the features input by the user. Furthermore, the matching unit can combine different matching methods to derive the optimal result based on the features input by the user. This combination of different matching methods can provide more accurate matching results. For example, by combining machine learning and statistical analysis to derive the optimal result based on the features input by the user, the generation AI can provide more accurate matching results, allowing the user to find their ideal partner.

[0108] The matching unit can estimate the user's emotions and adjust the display method of the matching results based on the estimated user emotions. The matching unit uses a generation AI to estimate the user's emotions and adjust the display method of the matching results based on the estimated user emotions. Methods for adjusting the display method of the matching results include, but are not limited to, graph display, text display, and interactive display. For example, if the user is nervous, the matching unit can provide a simple, highly visible display method. Also, if the user is relaxed, the matching unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the matching unit can provide a display method that focuses on the main points. This allows the user to understand the matching results more clearly by providing a display method that corresponds to the user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided, allowing the user to understand the matching results without stress. Also, if the user is relaxed, a display method including detailed information can be provided, allowing the user to understand the matching results in detail.

[0109] The matching unit can perform region-specific matching by taking into account the user's geographical location information. The matching unit uses a generation AI to perform region-specific matching by taking into account the user's geographical location information. Methods for performing region-specific matching include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the matching unit can perform matching by taking into account characteristics specific to that region. Furthermore, if the user uses the service while traveling, the matching unit can perform matching by taking into account characteristics related to tourist spots and events in that region. Furthermore, if the user is planning to move, the matching unit can perform matching by taking into account information about the new region. This enables region-specific matching by taking into account the geographical location information, thereby providing more appropriate results. For example, if the user lives in a specific region, matching can be performed by taking into account characteristics specific to that region, allowing the user to meet the ideal person who is suitable for their region. Furthermore, if the user uses the service while traveling, matching can be performed by taking into account characteristics related to tourist spots and events in that region.

[0110] The matching unit can analyze a user's social media activity and incorporate related data into the matching process. The matching unit uses a generation AI to analyze a user's social media activity and incorporate related data into the matching process. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the matching unit can analyze the content that a user frequently posts on social media and incorporate related data into the matching process. The matching unit can also analyze the user's social media friendships and incorporate data on common hobbies and interests into the matching process. Furthermore, the matching unit can incorporate related data into the matching process based on the user's social media activity history. In this way, by analyzing social media activity, related data can be incorporated into the matching process, thereby providing more accurate results. For example, by analyzing the content that a user frequently posts on social media and incorporating related data into the matching process, the generation AI can provide more accurate matching results, allowing the user to meet someone who is closer to their ideal partner.

[0111] The matching unit can customize the matching algorithm by reflecting the user's past feedback. The matching unit uses the generation AI to customize the matching algorithm by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the matching unit adjusts the matching algorithm based on feedback previously provided by the user. The matching unit can also improve the matching algorithm based on the accuracy of features previously input by the user. Furthermore, the matching unit can analyze the user's past feedback and provide an optimal matching algorithm. In this way, by reflecting past feedback, the matching algorithm can be optimized and more accurate results can be provided. For example, by adjusting the matching algorithm based on feedback previously provided by the user, the generation AI can provide more accurate matching results, allowing the user to meet someone who is close to their ideal partner.

[0112] The providing unit can estimate the user's emotions and adjust the profile display method based on the estimated user emotions. The providing unit can estimate the user's emotions using a generation AI and adjust the profile display method based on the estimated user emotions. Methods for adjusting the profile display method include, but are not limited to, graph display, text display, and interactive display. For example, if the user is nervous, the providing unit can provide a simple, highly visible display method. Also, if the user is relaxed, the providing unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the providing unit can provide a display method that focuses on the main points. This allows the user to understand the profile more deeply by providing a display method that corresponds to the user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided, allowing the user to understand the profile without stress. Also, if the user is relaxed, a display method including detailed information can be provided, allowing the user to understand the profile in detail.

[0113] The providing unit can refer to the user's past browsing history to display an optimal profile. The providing unit uses a generation AI to refer to the user's past browsing history to display an optimal profile. Methods for referencing the past browsing history include, but are not limited to, database structure, data storage period, etc. For example, the providing unit can prioritize displaying related profiles based on profiles the user has previously viewed. The providing unit can also suggest profiles that the user may be interested in based on the user's past browsing history. Furthermore, the providing unit can analyze the user's past browsing history and provide an optimal profile display method. This makes it possible to display an optimal profile for the user by referring to the past browsing history. For example, by preferentially displaying related profiles based on profiles the user has previously viewed, the user can more easily find people who match their interests. Furthermore, by suggesting profiles that the user may be interested in based on the user's past browsing history, the user can encounter new people of interest.

[0114] The providing unit can automatically suggest related profiles based on the user's input. The providing unit uses a generation AI to automatically suggest related profiles based on the user's input. Methods for automatically suggesting related profiles include, but are not limited to, proposal algorithms and relevance evaluation criteria. For example, the providing unit can automatically suggest related profiles based on features input by the user. The providing unit can also analyze correlations based on the features input by the user and suggest related profiles. Furthermore, the providing unit can combine different analysis methods to suggest optimal profiles based on the features input by the user. This makes it easier for the user to find people who match their interests by suggesting related profiles based on the input. For example, automatically suggesting related profiles based on the features input by the user makes it easier for the user to find people who match their interests. Furthermore, analyzing correlations based on the features input by the user and suggesting related profiles allows the user to encounter new people of interest.

[0115] The providing unit can improve the accuracy of profile display by reflecting user feedback. The providing unit uses the generation AI to reflect user feedback and improve the accuracy of profile display. Methods of reflecting feedback include, but are not limited to, a method of collecting feedback and timing of reflection. For example, the providing unit can improve the accuracy of profile display based on feedback provided by the user. The providing unit can also adjust the display algorithm based on user feedback. Furthermore, the providing unit can analyze user feedback and provide an optimal profile display method. In this way, by reflecting feedback, the accuracy of profile display is improved and user satisfaction is increased. For example, by improving the accuracy of profile display based on user feedback, the user can more easily find people who match their interests. Furthermore, by adjusting the display algorithm based on user feedback, the user can receive more accurate profile display.

[0116] The providing unit can estimate the user's emotions and prioritize profiles based on the estimated user emotions. The providing unit can estimate the user's emotions using a generation AI and prioritize profiles based on the estimated user emotions. Methods for prioritizing profiles include, but are not limited to, importance scores and the user's emotional state. For example, if the user is nervous, the providing unit can prioritize displaying profiles with important features. Also, if the user is relaxed, the providing unit can prioritize displaying profiles with detailed features. Furthermore, if the user is in a hurry, the providing unit can prioritize displaying profiles with the most important features. In this way, important profiles can be prioritized by providing priorities according to the user's emotions. For example, if the user is nervous, profiles with important features can be prioritized, allowing the user to view important profiles without stress. Also, if the user is relaxed, profiles with detailed features can be prioritized, allowing the user to view profiles in detail.

[0117] The providing unit can display a region-specific profile by taking into account the user's geographic location information. The providing unit uses a generation AI to display a region-specific profile by taking into account the user's geographic location information. Methods for displaying a region-specific profile include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the providing unit can display a profile with characteristics unique to that region. Furthermore, if the user uses the service while traveling, the providing unit can display a profile related to tourist attractions and events in that region. Furthermore, if the user is planning to move, the providing unit can display a profile with information about the new region. This allows for more appropriate matching by displaying a region-specific profile by taking into account the geographic location information. For example, if the user lives in a specific region, displaying a profile with characteristics unique to that region allows the user to meet the ideal person who suits their region. Furthermore, if the user uses the service while traveling, displaying a profile related to tourist attractions and events in that region allows the user to meet the ideal person at their travel destination.

[0118] The providing unit can analyze the user's social media activity and suggest related profiles. The providing unit uses a generative AI to analyze the user's social media activity and suggest related profiles. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the providing unit can analyze the content the user frequently posts on social media and suggest related profiles. The providing unit can also analyze the user's social media friendships and suggest profiles with common hobbies and interests. Furthermore, the providing unit can suggest related profiles based on the user's social media activity history. In this way, analyzing social media activity can suggest related profiles, making it easier for the user to find people who match the user's interests. For example, analyzing the content the user frequently posts on social media and suggesting related profiles can make it easier for the user to find people who match their interests. Furthermore, analyzing the user's social media friendships and suggesting profiles with common hobbies and interests can allow the user to meet new people of interest.

[0119] The providing unit can customize the profile display by reflecting the user's past feedback. The providing unit uses a generation AI to customize the profile display by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the providing unit adjusts the design of the profile display based on feedback previously provided by the user. The providing unit can also improve the display method based on the accuracy of profiles previously viewed by the user. Furthermore, the providing unit can analyze the user's past feedback and provide an optimal profile display method. In this way, by reflecting past feedback, an optimal profile display is provided to the user and satisfaction is improved. For example, by adjusting the design of the profile display based on feedback previously provided by the user, the user can view the profile using an easy-to-use interface. Furthermore, by improving the display method based on the accuracy of profiles previously viewed by the user, the user can receive a more accurate profile display.

[0120] The security unit can estimate the user's emotions and adjust security measures based on the estimated user emotions. The security unit uses generative AI to estimate the user's emotions and adjust security measures based on the estimated user emotions. Methods for adjusting security measures include, but are not limited to, parameter adjustment and countermeasure selection. For example, if the user is nervous, the security unit can provide simple and intuitive security measures. Also, if the user is relaxed, the security unit can provide detailed security measures. Furthermore, if the user is in a hurry, the security unit can quickly provide security measures. This increases the sense of security by providing security measures that correspond to the user's emotions. For example, if the user is nervous, simple and intuitive security measures can be provided, allowing the user to accept the security measures without stress. Also, if the user is relaxed, detailed security measures can be provided, allowing the user to understand the security measures in detail.

[0121] The security unit can refer to the user's past security history to provide optimal security measures. The security unit uses a generation AI to refer to the user's past security history to provide optimal security measures. Methods for referring to past security history include, but are not limited to, database structure, data storage period, etc. For example, the security unit can refer to security risks the user has encountered in the past and provide optimal measures. The security unit can also adjust security algorithms based on the user's past security history. Furthermore, the security unit can analyze the user's past security history and provide optimal security measures. In this way, by referring to past security history, optimal security measures are provided and risks are reduced. For example, by referring to security risks the user has encountered in the past and providing optimal measures, the user can take appropriate measures against similar risks. Furthermore, by adjusting security algorithms based on the user's past security history, the user can receive more effective security measures.

[0122] The security unit can automatically evaluate security risks based on user input. The security unit uses generative AI to automatically evaluate security risks based on user input. Methods for automatically evaluating security risks include, but are not limited to, risk assessment algorithms and evaluation criteria. For example, the security unit automatically evaluates security risks based on features input by the user. The security unit can also analyze correlations based on the features input by the user to identify security risks. Furthermore, the security unit can combine different analysis methods based on the features input by the user to perform an optimal security risk assessment. This allows security risks to be evaluated based on input content, enabling early identification of risks and countermeasures to be taken. For example, automatically evaluating security risks based on features input by the user allows users to quickly identify potential risks and take appropriate countermeasures. Furthermore, analyzing correlations based on the features input by the user to identify security risks allows users to understand the details of the risks and take effective countermeasures.

[0123] The security unit can improve security measures by reflecting user feedback. The security unit uses generative AI to improve security measures by reflecting user feedback. Methods of reflecting feedback include, but are not limited to, methods of collecting feedback and timing of reflection. For example, the security unit improves security measures based on feedback provided by the user. The security unit can also adjust security algorithms based on user feedback. Furthermore, the security unit can analyze user feedback and provide optimal security measures. In this way, by reflecting feedback, security measures are optimized and risks are reduced. For example, by improving security measures based on user feedback, users can receive more effective security measures. Furthermore, by adjusting security algorithms based on user feedback, users can receive security measures that suit them.

[0124] The security unit can estimate the user's emotions and prioritize security measures based on the estimated user emotions. The security unit uses a generative AI to estimate the user's emotions and prioritize security measures based on the estimated user emotions. Methods for prioritizing security measures include, but are not limited to, importance scores and the user's emotional state. For example, if the user is nervous, the security unit can prioritize providing important security measures. Also, if the user is relaxed, the security unit can prioritize providing detailed security measures. Furthermore, if the user is in a hurry, the security unit can prioritize providing the most important security measures. In this way, by providing priorities according to the user's emotions, important security measures can be implemented first. For example, if the user is nervous, important security measures can be prioritized, allowing the user to receive important measures without stress. Also, if the user is relaxed, detailed security measures can be prioritized, making it easier for the user to understand the details of the measures.

[0125] The security unit can provide region-specific security measures by taking into account the user's geographic location information. The security unit uses a generative AI to provide region-specific security measures by taking into account the user's geographic location information. Methods for providing region-specific security measures include, but are not limited to, risk characteristics for each region and region-specific threats. For example, if the user lives in a specific region, the security unit can provide measures by taking into account security risks specific to that region. Furthermore, if the user uses the service while traveling, the security unit can provide measures related to security risks in that region. Furthermore, if the user plans to move, the security unit can provide measures by taking into account security information for the new region. In this way, region-specific security measures are provided by taking into account the geographic location information, thereby reducing risks. For example, if the user lives in a specific region, measures can be provided by taking into account security risks specific to that region, allowing the user to receive security measures appropriate for the region. Furthermore, if the user uses the service while traveling, measures related to security risks in that region can be provided, allowing the user to use the service with peace of mind even while traveling.

[0126] The security unit can analyze a user's social media activity and evaluate associated security risks. The security unit uses generative AI to analyze the user's social media activity and evaluate associated security risks. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the security unit can analyze the user's frequent social media posts and evaluate associated security risks. The security unit can also analyze the user's social media friendships and evaluate common security risks. Furthermore, the security unit can evaluate associated security risks based on the user's social media activity history. In this way, analyzing social media activity can evaluate associated security risks and take countermeasures. For example, by analyzing the user's frequent social media posts and evaluating related security risks, the user can identify potential risks early and take appropriate countermeasures. Furthermore, by analyzing the user's social media friendships and evaluating common security risks, the user can understand the details of the risks and take effective countermeasures.

[0127] The security unit can customize security measures by reflecting the user's past feedback. The security unit uses a generative AI to customize security measures by reflecting the user's past feedback. Methods for reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the security unit customizes security measures based on feedback provided by the user in the past. The security unit can also improve measures based on security risks the user has encountered in the past. Furthermore, the security unit can analyze the user's past feedback and provide optimal security measures. In this way, security measures are optimized and risks are reduced by reflecting past feedback. For example, by customizing security measures based on feedback provided by the user in the past, the user can receive security measures that are tailored to them. Furthermore, by improving measures based on security risks the user has encountered in the past, the user can take appropriate measures against similar risks.

[0128] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated user emotions. The evaluation unit uses a generative AI to estimate the user's emotions and adjust the evaluation criteria based on the estimated user emotions. Methods for adjusting the evaluation criteria include, but are not limited to, parameter adjustment and criterion selection. For example, if the user is nervous, the evaluation unit uses simple and intuitive evaluation criteria. Alternatively, if the user is relaxed, the evaluation unit can use detailed evaluation criteria. Furthermore, if the user is in a hurry, the evaluation unit can use criteria that provide evaluation results quickly. This allows for more appropriate evaluation results by providing evaluation criteria that correspond to the user's emotions. For example, if the user is nervous, simple and intuitive evaluation criteria can be used, allowing the user to receive the evaluation results without stress. Alternatively, if the user is relaxed, detailed evaluation criteria can be used, allowing the user to understand the evaluation results in detail.

[0129] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation history. The evaluation unit uses the generation AI to improve the accuracy of the evaluation by referring to the user's past evaluation history. Methods for referring to the past evaluation history include, but are not limited to, database structure, data storage period, etc. For example, the evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation history. The evaluation unit can also adjust the evaluation algorithm based on the user's past evaluation history. Furthermore, the evaluation unit can analyze the user's past evaluation history and select the optimal evaluation method. In this way, by referring to the past evaluation history, the accuracy of the evaluation can be improved and more appropriate results can be provided. For example, by referring to the user's past evaluations and improving the accuracy of the evaluation, the generation AI can provide more accurate evaluation results, allowing the user to meet someone who is closer to their ideal partner.

[0130] The evaluation unit can multidimensionally analyze the evaluation criteria based on the user's input. The evaluation unit uses the generation AI to multidimensionally analyze the evaluation criteria based on the user's input. Methods of multidimensional analysis include, but are not limited to, simultaneous analysis of multiple evaluation criteria and correlation evaluation. For example, the evaluation unit multidimensionally analyzes the evaluation criteria based on the features input by the user. The evaluation unit can also analyze correlations and identify evaluation criteria based on the features input by the user. Furthermore, the evaluation unit can combine different analysis methods to derive optimal evaluation criteria based on the features input by the user. This multidimensional analysis can provide more accurate evaluation criteria. For example, by multidimensionally analyzing the evaluation criteria based on the features input by the user, the generation AI can provide more accurate evaluation criteria, allowing the user to meet someone who is closer to their ideal partner.

[0131] The evaluation unit can improve the evaluation criteria by reflecting user feedback. The evaluation unit uses a generative AI to improve the evaluation criteria by reflecting user feedback. Methods of reflecting feedback include, but are not limited to, methods of collecting feedback and timing of reflection. For example, the evaluation unit improves the evaluation criteria based on feedback provided by the user. The evaluation unit can also adjust the evaluation algorithm based on user feedback. Furthermore, the evaluation unit can analyze user feedback and provide optimal evaluation criteria. In this way, by reflecting feedback, the evaluation criteria can be optimized and more appropriate results can be provided. For example, by improving the evaluation criteria based on user feedback, the user can receive more accurate evaluation results. Furthermore, by adjusting the evaluation algorithm based on user feedback, the user can receive evaluation criteria that suit them.

[0132] The evaluation unit can estimate the user's emotions and adjust the display method of the evaluation results based on the estimated user emotions. The evaluation unit can estimate the user's emotions using a generation AI and adjust the display method of the evaluation results based on the estimated user emotions. Methods for adjusting the display method of the evaluation results include, but are not limited to, graph display, text display, and interactive display. For example, if the user is nervous, the evaluation unit can provide a simple, highly visible display method. Also, if the user is relaxed, the evaluation unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the evaluation unit can provide a display method that focuses on the main points. This allows the user to understand the evaluation results more clearly by providing a display method that corresponds to the user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided, allowing the user to understand the evaluation results without stress. Also, if the user is relaxed, a display method including detailed information can be provided, allowing the user to understand the evaluation results in detail.

[0133] The evaluation unit can provide region-specific evaluation criteria by taking into account the user's geographic location information. The evaluation unit uses a generation AI to provide region-specific evaluation criteria by taking into account the user's geographic location information. Methods for providing region-specific evaluation criteria include, but are not limited to, data characteristics for each region and region-specific trends. For example, if the user lives in a specific region, the evaluation unit can provide evaluation criteria specific to that region. Furthermore, if the user uses the service while traveling, the evaluation unit can provide evaluation criteria related to tourist attractions and events in that region. Furthermore, if the user is planning to move, the evaluation unit can provide evaluation criteria that take into account information about the new region. In this way, by taking geographic location information into account, region-specific evaluation criteria can be provided and more appropriate results can be provided. For example, if the user lives in a specific region, providing region-specific evaluation criteria allows the user to receive evaluation results appropriate for the region. Furthermore, if the user uses the service while traveling, providing evaluation criteria related to tourist attractions and events in that region allows the user to receive appropriate evaluation results even at the travel destination.

[0134] The evaluation unit can analyze the user's social media activity and incorporate related evaluation data. The evaluation unit can use the generation AI to analyze the user's social media activity and incorporate related evaluation data. Methods for analyzing social media activity include, but are not limited to, analyzing post content and follower analysis. For example, the evaluation unit can analyze the content the user frequently posts on social media and incorporate related evaluation data. The evaluation unit can also analyze the user's social media friendships and incorporate evaluation data based on shared hobbies and interests. Furthermore, the evaluation unit can incorporate related evaluation data based on the user's social media activity history. In this way, by analyzing social media activity, the generation AI can incorporate related evaluation data and provide more accurate results. For example, by analyzing the content the user frequently posts on social media and incorporating related evaluation data, the generation AI can provide more accurate evaluation results, allowing the user to meet someone who is closer to their ideal partner.

[0135] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback. The evaluation unit uses a generation AI to customize the evaluation criteria by reflecting the user's past feedback. Methods of reflecting past feedback include, but are not limited to, the method of collecting feedback and the timing of reflection. For example, the evaluation unit customizes the evaluation criteria based on feedback provided by the user in the past. The evaluation unit can also improve the evaluation criteria based on the accuracy of the user's past evaluations. Furthermore, the evaluation unit can analyze the user's past feedback and provide optimal evaluation criteria. In this way, by reflecting past feedback, the evaluation criteria can be optimized and more appropriate results can be provided. For example, by customizing the evaluation criteria based on feedback provided by the user in the past, the user can receive evaluation criteria that suit them. Furthermore, by improving the evaluation criteria based on the accuracy of the user's past evaluations, the user can receive more accurate evaluation results. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, matching unit, provision unit, security unit, and evaluation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and allows the user to input the characteristics of their ideal person. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes the input characteristics using a generation AI. The matching unit is realized by the identification processing unit 290 of the data processing device 12 and performs matching from a database based on the analyzed characteristics. The provision unit is realized by the control unit 46A of the smart device 14 and provides the user with a profile of the proposed person. The security unit is realized by the identification processing unit 290 of the data processing device 12 and protects the user's privacy and takes security measures. The evaluation unit is realized by the identification processing unit 290 of the data processing device 12 and evaluates the reliability of the proposed person. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, matching unit, provision unit, security unit, and evaluation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and allows the user to input the characteristics of their ideal person. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes the input characteristics using a generation AI. The matching unit is realized by the identification processing unit 290 of the data processing device 12 and performs matching from a database based on the analyzed characteristics. The provision unit is realized by the control unit 46A of the smart glasses 214 and provides the user with a profile of the suggested person. The security unit is realized by the identification processing unit 290 of the data processing device 12 and performs user privacy protection and security measures. The evaluation unit is realized by the identification processing unit 290 of the data processing device 12 and evaluates the reliability of the suggested person. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, matching unit, provision unit, security unit, and evaluation unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314, and allows the user to input the characteristics of their ideal person. The analysis unit is realized by the identification processing unit 290 of the data processing device 12, and analyzes the input characteristics using a generation AI. The matching unit is realized by the identification processing unit 290 of the data processing device 12, and performs matching from a database based on the analyzed characteristics. The provision unit is realized by the control unit 46A of the headset-type terminal 314, and provides the user with a profile of the proposed person. The security unit is realized by the identification processing unit 290 of the data processing device 12, and protects the user's privacy and implements security measures. The evaluation unit is realized by the identification processing unit 290 of the data processing device 12, and evaluates the reliability of the proposed person. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, matching unit, provision unit, security unit, and evaluation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and allows the user to input the characteristics of their ideal person. The analysis unit is realized by the identification processing unit 290 of the data processing device 12 and analyzes the input characteristics using a generation AI. The matching unit is realized by the identification processing unit 290 of the data processing device 12 and performs matching from a database based on the analyzed characteristics. The provision unit is realized by the control unit 46A of the robot 414 and provides the user with a profile of the proposed person. The security unit is realized by the identification processing unit 290 of the data processing device 12 and implements user privacy protection and security measures. The evaluation unit is realized by the identification processing unit 290 of the data processing device 12 and evaluates the reliability of the proposed person.

[0136] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0137] The reception unit can automatically generate related questions based on the characteristics input by the user and collect detailed characteristics. For example, if the user inputs "I like sports," the reception unit can automatically generate questions asking about specific types of sports. If the user inputs "I have a kind personality," the reception unit can automatically generate questions asking about specific episodes and actions. If the user inputs "I like music," the reception unit can automatically generate questions asking about favorite music genres and artists. By automatically generating related questions, detailed characteristics can be collected and more accurate matching can be achieved. For example, if the user inputs "I like sports," the reception unit can automatically generate questions asking about specific types of sports, allowing the user to enter their hobbies in detail. If the user inputs "I have a kind personality," the reception unit can automatically generate questions asking about specific episodes and actions, allowing the user to enter their personality in detail.

[0138] The analysis unit can multidimensionally analyze the characteristics of an ideal person based on the user's input. For example, it multidimensionally analyzes characteristics such as appearance, personality, hobbies, and values ​​entered by the user. It can also analyze correlations based on the characteristics entered by the user to identify the characteristics of an ideal person. It can also combine different analysis methods based on the characteristics entered by the user to derive optimal results. This multidimensional analysis allows for more accurate identification of the characteristics of an ideal person. For example, by multidimensionally analyzing the characteristics entered by the user, such as appearance, personality, hobbies, and values, the generative AI can identify the characteristics of an ideal person in detail, allowing the user to meet someone who is close to their ideal person.

[0139] The matching unit can improve the accuracy of matching by referring to the user's past matching results. For example, it can improve the accuracy of matching by referring to the characteristics of people the user has matched with in the past. It can also adjust the matching algorithm based on the user's past matching results. It can also analyze the user's past matching results and select the optimal matching method. In this way, by referring to past matching results, it can improve the accuracy of matching and provide more appropriate results. For example, by referring to the characteristics of people the user has matched with in the past and improving the accuracy of matching, the generation AI can provide more accurate matching results, allowing the user to meet their ideal person.

[0140] The providing unit can refer to the user's past browsing history to display the most appropriate profile. For example, based on profiles the user has viewed in the past, related profiles can be preferentially displayed. Also, based on the user's past browsing history, profiles that may be of interest can be suggested. Furthermore, the providing unit can analyze the user's past browsing history and provide an optimal profile display method. This makes it possible to display the most appropriate profile for the user by referring to the past browsing history. For example, by preferentially displaying related profiles based on profiles the user has viewed in the past, the user can easily find people who match their interests. Also, by suggesting profiles that may be of interest based on the user's past browsing history, the user can encounter new people of interest.

[0141] The security unit can provide optimal security measures by referring to the user's past security history. For example, the security unit can provide optimal measures by referring to security risks the user has encountered in the past. The security unit can also adjust security algorithms based on the user's past security history. Furthermore, the security unit can analyze the user's past security history and provide optimal security measures. In this way, optimal security measures are provided and risks are reduced by referring to the past security history. For example, by referring to security risks the user has encountered in the past and providing optimal measures, the user can take appropriate measures against similar risks. Furthermore, by adjusting security algorithms based on the user's past security history, the user can receive more effective security measures.

[0142] The reception unit can estimate the user's emotions and customize an interface for inputting the characteristics of an ideal person based on the estimated user's emotions. For example, if the user is nervous, a simple and intuitive interface can be provided to reduce the effort required for input. Also, if the user is relaxed, detailed input options can be provided and a customizable interface can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to enable quick input of characteristics. In this way, by providing an interface that corresponds to the user's emotions, the effort required for input can be reduced and the user experience can be improved. For example, if the user is nervous, a simple and intuitive interface can be provided to reduce the effort required for input, allowing the user to input characteristics without stress. Also, if the user is relaxed, detailed input options can be provided to allow the user to input the characteristics of their ideal person in detail.

[0143] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user's emotions. For example, if the user is nervous, a simple and intuitive analysis algorithm can be used. On the other hand, if the user is relaxed, a detailed analysis algorithm can be used. Furthermore, if the user is in a hurry, an algorithm that provides analysis results quickly can be used. In this way, by adjusting the analysis algorithm according to the user's emotions, more appropriate analysis results can be provided. For example, if the user is nervous, a simple and intuitive analysis algorithm can be used, allowing the user to receive analysis results without stress. On the other hand, if the user is relaxed, a detailed analysis algorithm can be used, allowing the user to receive more detailed analysis results.

[0144] The matching unit can estimate the user's emotions and adjust the matching algorithm based on the estimated user's emotions. For example, if the user is nervous, a simple and intuitive matching algorithm can be used. On the other hand, if the user is relaxed, a detailed matching algorithm can be used. Furthermore, if the user is in a hurry, an algorithm that provides matching results quickly can be used. In this way, by providing a matching algorithm according to the user's emotions, more appropriate matching results can be provided. For example, if the user is nervous, a simple and intuitive matching algorithm can be used, allowing the user to receive matching results without stress. On the other hand, if the user is relaxed, a detailed matching algorithm can be used, allowing the user to receive more detailed matching results.

[0145] The providing unit can estimate the user's emotions and adjust the profile display method based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. Also, if the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, by providing a display method according to the user's emotions, the user can better understand the profile. For example, if the user is nervous, a simple, highly visible display method can be provided, allowing the user to understand the profile without stress. Also, if the user is relaxed, a display method including detailed information can be provided, allowing the user to understand the profile in detail.

[0146] The security unit can estimate the user's emotions and adjust security measures based on the estimated user emotions. For example, if the user is nervous, simple and intuitive security measures can be provided. If the user is relaxed, detailed security measures can be provided. Furthermore, if the user is in a hurry, security measures can be provided quickly. In this way, security measures can be provided according to the user's emotions, thereby increasing the sense of security. For example, if the user is nervous, simple and intuitive security measures can be provided, allowing the user to accept the security measures without stress. Furthermore, if the user is relaxed, detailed security measures can be provided, allowing the user to understand the security measures in detail.

[0147] The processing flow of the second embodiment will be briefly explained below.

[0148] Step 1: The reception unit allows the user to input the characteristics of their ideal partner. The characteristics input by the user include appearance (height, weight, hair color, etc.), personality (introvert, extrovert, etc.), hobbies, values, etc. Step 2: The analysis unit uses the generation AI to analyze the features input by the reception unit. The analysis is performed using methods such as text analysis, image analysis, and data mining. Step 3: The matching unit performs matching from the database based on the features analyzed by the analysis unit. Matching is performed using methods such as similarity calculation and filtering algorithms. Step 4: The providing unit provides the user with the profile of the person proposed by the matching unit in a format such as text, image, or video.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0154] 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.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0170] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0177] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0179] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0186] 7, a 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.

[0187] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0188] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0189] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0191] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0192] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0193] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0194] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0196] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0199] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0200] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0201] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0202] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0204] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0205] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0206] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0209] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0210] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0211] 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.

[0212] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0213] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0214] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0215] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0217] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0218] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0219] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0220] [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit where a user inputs characteristics of an ideal person; an analysis unit that analyzes the characteristics input by the reception unit; a matching unit that performs matching from a database based on the features analyzed by the analysis unit; a providing unit that provides a user with a profile of the person suggested by the matching unit. A system characterized by:

2. Equipped with a security department that protects user privacy and takes security measures 2. The system of claim 1.

3. Equipped with an evaluation unit that evaluates the reliability of the proposed person 2. The system of claim 1.

4. The reception unit Users enter detailed characteristics about their appearance, personality, hobbies, and values 2. The system of claim 1.

5. The analysis unit Analyze the characteristics of your ideal partner in detail based on your input 2. The system of claim 1.

6. The matching unit Analyze the profiles of people in the database and identify those who are close to your ideal match 2. The system of claim 1.

7. The providing unit Providing the user with suggested person profiles 2. The system of claim 1.

8. The reception unit Estimate the user's emotions and customize the interface for inputting the characteristics of the ideal person based on the estimated user emotions.

2. The system of claim 1.

Images