System

Abstract

To provide a system capable of setting user-specific messages and automatic response messages according to a time zone.SOLUTION: A system according to an embodiment comprises a custom message setting unit, a time schedule setting unit, an automatic response unit, a sharing unit, and a direct message correspondence unit. The custom message setting unit sets a user-specific message. The time schedule setting unit sets an automatic response message which differs according to a day of the week and a time zone. The automatic response unit detects a specific keyword or phrase in a received message, and automatically responds according to the detected results. The sharing unit shares information and links. The direct message correspondence unit responds to the direct message.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not adequately set user-specific messages or automatic response messages according to time periods, and there is room for improvement.

[0005] The system according to the embodiment aims to enable users to set their own messages and auto-reply messages according to time periods. [Means for solving the problem]

[0006] The system according to the embodiment includes a custom message setting unit, a time schedule setting unit, an automatic response unit, a sharing unit, and a direct message handling unit. The custom message setting unit sets a user-specific message. The time schedule setting unit sets different automatic response messages depending on the day of the week and the time period. The automatic response unit detects specific keywords or phrases in received messages and performs an automatic response according to the detected results. The sharing unit shares information and links. The direct message handling unit responds to direct messages. Effect of the Invention

[0007] The system according to the embodiment can enable users to set their own messages and auto-reply messages according to time periods. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed 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 and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The social media autoresponder system according to the embodiment of the present invention provides a customization function that allows a user to set their own greetings and messages, and is a system that allows a user to set different autoresponder messages depending on the day of the week and the time of day. The system can enable autoresponders during non-business hours, for example. The system also has a function of detecting specific keywords and phrases and providing appropriate autoresponder messages accordingly. Furthermore, the system also provides a function of automatically sharing specific information and links and automating replies to direct messages. The system also includes a function of automatically following back new followers and a function of assigning received messages to different autoresponder messages depending on the topic or category. The system also provides a function of collecting information from users and generating personalized autoresponder messages based on the collected information. Furthermore, the system supports integration with CRM systems and customer databases to improve customer engagement. Finally, the system also has a function of evaluating the effectiveness of autoresponders and providing data useful for improving social media strategies. For example, the custom message setting unit and the time schedule setting unit have a function of automatically switching messages set by the user depending on the day of the week and the time of day. This allows the user to set different messages for different time periods. Next, the keyword detection and message classification have a function of analyzing the content of received messages, detecting specific keywords and phrases, and providing corresponding autoresponder messages. This allows users to set responses according to specific topics or categories. Furthermore, to clarify how each function uses AI or generative AI, for example, it is necessary to specifically describe how the AI ​​processes in keyword detection and message classification. For example, it is necessary to clarify how the AI ​​analyzes incoming messages and detects specific keywords or phrases, and how it classifies messages into topics or categories. This allows the social media autoresponder system to provide flexible responses according to the needs of users.

[0029] The social media auto-response system according to the embodiment includes a custom message setting unit, a time schedule setting unit, an automatic response unit, a sharing unit, and a direct message response unit. The custom message setting unit allows the user to set a unique greeting or message. For example, the user can set a message for a specific event or anniversary. The time schedule setting unit allows the user to set different automatic response messages depending on the day of the week or the time period. For example, the automatic response can be enabled during non-business hours. The automatic response unit detects a specific keyword or phrase in a received message and performs an automatic response according to the detected result. For example, an AI analyzes a received message and detects a specific keyword or phrase. The sharing unit automatically shares specific information and links. For example, a link set by a user can be automatically shared. The direct message response unit automatically responds to a direct message. For example, an AI analyzes a direct message and generates an appropriate response. This allows the social media auto-response system to set a user-specific message, set a time schedule, perform an automatic response, share information, and respond to a direct message.

[0030] The custom message setting unit allows users to set their own greetings and messages. For example, users can set messages tailored to specific events or anniversaries. Specifically, users can input and save messages using a text editor through the system's interface. This allows users to pre-set messages tailored to special occasions such as Christmas, New Year, and birthdays, and schedule them to be automatically sent on specific dates and times. The custom message setting unit also has a function for managing multiple message templates, allowing users to select an appropriate template depending on the situation. Furthermore, messages can also include images and links, making it possible to create visually appealing messages. This allows the custom message setting unit to flexibly set messages tailored to individual needs and events, making communication on social media more personalized.

[0031] The time schedule setting unit can set different auto-response messages according to the day of the week and the time period. For example, the auto-response can be enabled during non-business hours. Specifically, the user can use a calendar-style interface to set messages according to specific days of the week and the time period. For example, the auto-response message can be set outside business hours on weekdays or on weekends, so that appropriate responses can be made to followers and customers even when the user is absent. The time schedule setting unit also has a function for setting schedules according to seasons and specific events, and can set special messages during, for example, summer vacations and New Year's holidays. Furthermore, the time schedule setting unit can manage multiple schedules simultaneously, and the user can set multiple auto-response messages according to different conditions. This allows the time schedule setting unit to flexibly set messages according to the time period and situation, and efficiently and effectively manage communication on social media.

[0032] The automatic response unit detects specific keywords or phrases in the received message and responds automatically according to the detected results. For example, AI analyzes the received message and detects specific keywords or phrases. Specifically, it uses natural language processing (NLP) technology to analyze the content of the message and generate an appropriate response based on the pre-set keywords and phrases. For example, if a message is received asking "What are your business hours?", AI detects the keyword "business hours" and automatically replies with a message containing information about the pre-set business hours. AI also has the ability to understand context and can handle complex questions and requests. For example, in response to the message "How do I return an item?", AI can provide detailed information about return policies and procedures. In addition, the automatic response unit learns the user's past response history and is continuously improved to provide more accurate responses. As a result, the automatic response unit can reduce the burden on the user and provide quick and accurate responses, thereby streamlining customer support on social media.

[0033] The sharing unit automatically shares specific information and links. For example, a link set by the user can be automatically shared. Specifically, the user can set information and links to be shared in advance through the system interface, and set them to be automatically shared when specific conditions are met. For example, by automatically sharing new product release information and campaign announcements, timely information can be provided to followers and customers. The sharing unit also has a function of sharing information in response to specific events and actions, and for example, when a user posts using a specific hashtag, related links can be automatically shared. Furthermore, the sharing unit also provides a function of customizing the format and style of the information to be shared, and the user can share information in accordance with the brand image. In this way, the sharing unit allows the user to efficiently and effectively share information and improve engagement on social media.

[0034] The direct message response unit automatically replies to direct messages. For example, AI analyzes direct messages and generates appropriate replies. Specifically, it uses natural language processing (NLP) technology to analyze the contents of direct messages, understands the user's intention, and generates appropriate replies. For example, in response to a message such as "Is the product in stock?", AI checks stock information and automatically replies according to the availability of the product. In addition, the direct message response unit can provide more personalized responses by referring to the user's past message history. For example, for a user who has purchased a specific product in the past, it can suggest related information and recommended products for that product. Furthermore, the direct message response unit has the ability to process multiple messages simultaneously, and can respond quickly even when a large number of messages are sent. As a result, the direct message response unit can reduce the burden on users and provide quick and accurate responses, thereby streamlining customer support on social media.

[0035] The social media automatic response system includes an automatic follow-back unit that automatically follows back new followers. For example, when a new follower is detected, the AI ​​can adjust the timing of the follow-back and follow back at an appropriate timing. This allows for a quick and appropriate follow-back for new followers. A part or all of the above-mentioned processing in the automatic follow-back unit may be performed using AI, or may be performed without using AI. For example, the automatic follow-back unit can select an optimal follow-back method in consideration of attribute information of the new follower. This allows for an optimal follow-back method to be selected based on the attribute information of the new follower.

[0036] The social media auto-response system includes a message classification unit that assigns received messages to different auto-response messages according to topics or categories. The message classification unit analyzes received messages and classifies them according to topics or categories. For example, an AI analyzes received messages, detects specific keywords or phrases, and classifies the messages into topics or categories. This makes it possible to classify received messages according to topics or categories and provide appropriate auto-response messages. Some or all of the above-mentioned processing in the message classification unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the message classification unit can analyze the contents of received messages using a generation AI and detect specific keywords or phrases. This makes it possible to classify received messages according to topics or categories and provide appropriate auto-response messages.

[0037] The social media auto-response system includes a collection unit that collects user information and a generation unit that generates an auto-response message based on the collected information. The collection unit collects user information. For example, it can collect profile information and behavioral history of the user. The generation unit generates an auto-response message based on the collected information. For example, an AI can analyze the collected information and generate an optimal auto-response message for the user. This makes it possible to collect user information and generate an individualized auto-response message. A part or all of the above-mentioned processing in the collection unit and the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can analyze the behavioral history of the user using the generation AI, and the generation unit can generate an individualized auto-response message using the generation AI. This makes it possible to collect user information and generate an individualized auto-response message.

[0038] The social media autoresponder system includes an integration unit that supports integration with a CRM system or a customer database. For example, the integration unit can use AI to analyze data in a CRM system or a customer database and perform integration. This can support integration with a CRM system or a customer database and improve customer engagement. Some or all of the above-mentioned processing in the integration unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the integration unit can use a generation AI to analyze data in a CRM system or a customer database and perform integration. This can support integration with a CRM system or a customer database and improve customer engagement.

[0039] The social media automatic response system includes an evaluation unit that evaluates the effect of the automatic response, and a provision unit that provides the evaluation result. The evaluation unit evaluates the effect of the automatic response. For example, an AI can analyze the effect of the automatic response and generate an evaluation result. The provision unit provides the evaluation result. For example, an AI can analyze the evaluation result and provide it to a user. This makes it possible to evaluate the effect of the automatic response and provide the result. A part or all of the above-mentioned processing in the evaluation unit and the provision unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the evaluation unit can analyze the effect of the automatic response using a generation AI, and the provision unit can provide the evaluation result using a generation AI. This makes it possible to evaluate the effect of the automatic response and provide the result.

[0040] The generation unit can acquire the geographical location information of the user and customize the auto-response message based on the acquired geographical location information of the user. For example, an AI can analyze the geographical location information of the user and generate an auto-response message including information related to the area. This allows the auto-response message to be customized based on the geographical location information of the user. A part or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the geographical location information of the user using the generation AI and customize the auto-response message. This allows the auto-response message to be customized based on the geographical location information of the user.

[0041] The automatic response unit can include advertising or promotional information in the automatic response message. For example, when the AI ​​generates the automatic response message, the advertising or promotional information can be inserted. This allows the advertising or promotional information to be included in the automatic response message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze advertising or promotional information using the generation AI and appropriately insert it into the automatic response message. This allows the advertising or promotional information to be included in the automatic response message.

[0042] The automatic response unit can predict the optimal response time based on the user's time zone or activity pattern. For example, the AI ​​can analyze the user's past activity pattern and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's activity pattern using the generation AI and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern.

[0043] The automatic response unit can select a response message for a specific keyword from multiple templates set by the user. For example, the AI ​​can detect a specific keyword and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific keyword using the generation AI and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user.

[0044] The automatic response unit can generate an automatic response message related to a message including a specific hashtag. For example, an AI can detect a specific hashtag and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific hashtag using the generation AI and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag.

[0045] The custom message setting unit can analyze the user's past message history and propose an optimal custom message. For example, an AI can analyze the user's past message history and propose similar or related messages. This makes it possible to analyze the user's past message history and propose an optimal custom message. A part or all of the above-mentioned processing in the custom message setting unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the custom message setting unit can analyze the user's past message history using a generation AI and propose an optimal custom message. This makes it possible to analyze the user's past message history and propose an optimal custom message.

[0046] The custom message setting unit can customize the message based on the user's current activity status when setting the custom message. For example, the AI ​​can analyze the user's current activity status and suggest a business-oriented message, a relaxing message, or a message related to an event. This allows the message to be customized based on the user's current activity status. A part or all of the above-mentioned processing in the custom message setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the custom message setting unit can analyze the user's current activity status using the generation AI and customize the message. This allows the message to be customized based on the user's current activity status.

[0047] The time schedule setting unit can analyze the user's past activity patterns and propose an optimal time schedule. For example, the AI ​​can analyze the user's past activity patterns and set an automatic response to the time period when the user was most active or the time period when the user received the most messages. This makes it possible to analyze the user's past activity patterns and propose an optimal time schedule. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's past activity patterns using the generation AI and propose an optimal time schedule. This makes it possible to analyze the user's past activity patterns and propose an optimal time schedule.

[0048] The time schedule setting unit can customize the schedule based on the user's current living situation when setting the time schedule. For example, the AI ​​can analyze the user's current living situation and set an automatic response for business, an automatic response with a relaxed content, or an automatic response related to an event. This makes it possible to customize the schedule based on the user's current living situation. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's current living situation using the generation AI and customize the schedule. This makes it possible to customize the schedule based on the user's current living situation.

[0049] The automatic response unit can adjust the level of detail of the response based on the importance of the received message when automatically responding. For example, the AI ​​can analyze the importance of the received message and provide a detailed response to an important message and a concise response to a general message. This makes it possible to adjust the level of detail of the response based on the importance of the received message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the importance of the received message using the generation AI and adjust the level of detail of the response. This makes it possible to adjust the level of detail of the response based on the importance of the received message.

[0050] The automatic response unit can apply different response algorithms depending on the category of the message when automatically responding. For example, the AI ​​can analyze the category of the message and provide a business-oriented response to a business-related message and a personal response to a personal message. This makes it possible to apply the optimal response algorithm depending on the category of the message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the category of the message using the generation AI and apply different response algorithms. This makes it possible to apply the optimal response algorithm depending on the category of the message.

[0051] The sharing unit can adjust the level of detail of the sharing based on the importance of the information to be shared at the time of sharing. For example, the AI ​​can analyze the importance of the information to be shared, and important information can be shared in detail, and general information can be shared briefly. This makes it possible to adjust the level of detail of the sharing based on the importance of the information. Some or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the importance of the information to be shared using the generation AI, and adjust the level of detail of the sharing. This makes it possible to adjust the level of detail of the sharing based on the importance of the information.

[0052] The sharing unit can apply different sharing algorithms depending on the category of information when sharing. For example, an AI can analyze the category of information, and perform business-oriented sharing for business-related information and personal sharing for personal information. This makes it possible to apply the optimal sharing algorithm depending on the category of information. Some or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the category of information using the generation AI, and apply different sharing algorithms. This makes it possible to apply the optimal sharing algorithm depending on the category of information.

[0053] When responding to a direct message, the direct message response unit can adjust the level of detail of the response based on the importance of the message. For example, an AI can analyze the importance of the message and provide a detailed response to an important message and a concise response to a general message. This makes it possible to adjust the level of detail of the response based on the importance of the message. Some or all of the above-mentioned processing in the direct message response unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the direct message response unit can analyze the importance of the message using a generation AI and adjust the level of detail of the response. This makes it possible to adjust the level of detail of the response based on the importance of the message.

[0054] The direct message response unit can apply different response algorithms depending on the category of the message when responding to the direct message. For example, the AI ​​can analyze the category of the message and provide a business-oriented response to a business-related message and a personal response to a personal message. This allows the optimal response algorithm to be applied depending on the category of the message. Some or all of the above-mentioned processing in the direct message response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the direct message response unit can analyze the category of the message using the generation AI and apply different response algorithms. This allows the optimal response algorithm to be applied depending on the category of the message.

[0055] The automatic follow-back unit can select the optimal follow-back method in consideration of the attribute information of the new follower when following back. For example, AI can analyze the attribute information of the new follower, perform business-related follow-back for business-related followers, and perform personal follow-back for personal followers. This allows the optimal follow-back method to be selected based on the attribute information of the new follower. A part or all of the above-mentioned processing in the automatic follow-back unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic follow-back unit can analyze the attribute information of the new follower using the generation AI, and select the optimal follow-back method. This allows the optimal follow-back method to be selected based on the attribute information of the new follower.

[0056] The message classification unit can improve the accuracy of classification by taking into account the interrelationships between messages when classifying messages. For example, the AI ​​can analyze the interrelationships between messages, provide a detailed response to an important message, and provide a concise response to a general message. This can improve the accuracy of classification by taking into account the interrelationships between messages. Some or all of the above-mentioned processing in the message classification unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the message classification unit can analyze the interrelationships between messages using the generation AI, and improve the accuracy of classification. This can improve the accuracy of classification by taking into account the interrelationships between messages.

[0057] The collection unit can adjust the level of detail of the collection based on the importance of the information to be collected at the time of collection. For example, the AI ​​can analyze the importance of the information to be collected, and important information can be collected in detail, and general information can be collected briefly. This makes it possible to adjust the level of detail of the collection based on the importance of the information. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can analyze the importance of the information to be collected using the generation AI, and adjust the level of detail of the collection. This makes it possible to adjust the level of detail of the collection based on the importance of the information.

[0058] The generation unit can adjust the level of detail of the generation based on the importance of the automatic response to be generated at the time of generation. For example, the importance of the automatic response to be generated by the AI ​​can be analyzed, and detailed generation can be performed for important responses and concise generation can be performed for general responses. This makes it possible to adjust the level of detail of the generation based on the importance of the automatic response. A part or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the importance of the automatic response to be generated using the generation AI, and adjust the level of detail of the generation. This makes it possible to adjust the level of detail of the generation based on the importance of the automatic response.

[0059] During integration, the integration unit can adjust the level of detail of the integration based on the importance of the system to be integrated. For example, the AI ​​can analyze the importance of the system to be integrated, and perform detailed integration for important systems and simple integration for general systems. This makes it possible to adjust the level of detail of the integration based on the importance of the systems. Some or all of the above-mentioned processing in the integration unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the integration unit can analyze the importance of the system to be integrated using the generation AI, and adjust the level of detail of the integration. This makes it possible to adjust the level of detail of the integration based on the importance of the systems.

[0060] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the data to be evaluated during the evaluation. For example, the importance of the data to be evaluated by the AI ​​can be analyzed, and a detailed evaluation can be performed on important data and a brief evaluation can be performed on general data. This makes it possible to adjust the level of detail of the evaluation based on the importance of the data. Some or all of the above-mentioned processing in the evaluation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the importance of the data to be evaluated using the generation AI, and adjust the level of detail of the evaluation. This makes it possible to adjust the level of detail of the evaluation based on the importance of the data.

[0061] The providing unit can adjust the level of detail of the information provided based on the importance of the information to be provided at the time of providing. For example, the AI ​​can analyze the importance of the information to be provided, and provide important information in detail and general information in a concise manner. This makes it possible to adjust the level of detail of the information provided based on the importance of the information. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the importance of the information to be provided using the generation AI, and adjust the level of detail of the information provided. This makes it possible to adjust the level of detail of the information provided based on the importance of the information.

[0062] The providing unit can determine the priority of provision based on the time of information submission at the time of information provision. For example, an AI can analyze the time of information submission and provide the latest information preferentially. This makes it possible to determine the priority of provision based on the time of information submission. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the time of information submission using the generation AI and determine the priority of provision. This makes it possible to determine the priority of provision based on the time of information submission.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The custom message setting unit can analyze the user's past message history and propose an optimal custom message. For example, an AI can analyze the user's past message history and propose similar or related messages. This makes it possible to analyze the user's past message history and propose an optimal custom message. A part or all of the above-mentioned processing in the custom message setting unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the custom message setting unit can analyze the user's past message history using a generation AI and propose an optimal custom message. This makes it possible to analyze the user's past message history and propose an optimal custom message.

[0065] The automatic response unit can predict the optimal response time based on the user's time zone or activity pattern. For example, the AI ​​can analyze the user's past activity pattern and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's activity pattern using the generation AI and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern.

[0066] The automatic response unit can select a response message for a specific keyword from multiple templates set by the user. For example, the AI ​​can detect a specific keyword and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific keyword using the generation AI and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user.

[0067] The automatic response unit can generate an automatic response message related to a message including a specific hashtag. For example, an AI can detect a specific hashtag and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific hashtag using the generation AI and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag.

[0068] The automatic response unit can include advertising or promotional information in the automatic response message. For example, when the AI ​​generates the automatic response message, the advertising or promotional information can be inserted. This allows the advertising or promotional information to be included in the automatic response message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze advertising or promotional information using the generation AI and appropriately insert it into the automatic response message. This allows the advertising or promotional information to be included in the automatic response message.

[0069] The process flow of the first embodiment will be briefly described below.

[0070] Step 1: The custom message setting section allows users to set their own greetings and messages. For example, users can set messages tailored to specific events or anniversaries. Step 2: The time schedule setting section can set different auto-reply messages according to the day of the week and the time of day. For example, the auto-reply can be enabled during non-business hours. Step 3: The automatic response unit detects specific keywords or phrases in the received message and performs an automatic response based on the detected results. For example, AI analyzes the received message and detects specific keywords or phrases. Step 4: The sharing section automatically shares certain information and links. For example, a link set by the user can be automatically shared. Step 5: The direct message response unit automatically responds to direct messages. For example, AI analyzes direct messages and generates appropriate replies.

[0071] (Example 2) The social media autoresponder system according to the embodiment of the present invention provides a customization function that allows a user to set their own greetings and messages, and is a system that allows a user to set different autoresponder messages depending on the day of the week and the time of day. The system can enable autoresponders during non-business hours, for example. The system also has a function of detecting specific keywords and phrases and providing appropriate autoresponder messages accordingly. Furthermore, the system also provides a function of automatically sharing specific information and links and automating replies to direct messages. The system also includes a function of automatically following back new followers and a function of assigning received messages to different autoresponder messages depending on the topic or category. The system also provides a function of collecting information from users and generating personalized autoresponder messages based on the collected information. Furthermore, the system supports integration with CRM systems and customer databases to improve customer engagement. Finally, the system also has a function of evaluating the effectiveness of autoresponders and providing data useful for improving social media strategies. For example, the custom message setting unit and the time schedule setting unit have a function of automatically switching messages set by the user depending on the day of the week and the time of day. This allows the user to set different messages for different time periods. Next, the keyword detection and message classification have a function of analyzing the content of received messages, detecting specific keywords and phrases, and providing corresponding autoresponder messages. This allows users to set responses according to specific topics or categories. Furthermore, to clarify how each function uses AI or generative AI, for example, it is necessary to specifically describe how the AI ​​processes in keyword detection and message classification. For example, it is necessary to clarify how the AI ​​analyzes incoming messages and detects specific keywords or phrases, and how it classifies messages into topics or categories. This allows the social media autoresponder system to provide flexible responses according to the needs of users.

[0072] The social media auto-response system according to the embodiment includes a custom message setting unit, a time schedule setting unit, an automatic response unit, a sharing unit, and a direct message response unit. The custom message setting unit allows the user to set a unique greeting or message. For example, the user can set a message for a specific event or anniversary. The time schedule setting unit allows the user to set different automatic response messages depending on the day of the week or the time period. For example, the automatic response can be enabled during non-business hours. The automatic response unit detects a specific keyword or phrase in a received message and performs an automatic response according to the detected result. For example, an AI analyzes a received message and detects a specific keyword or phrase. The sharing unit automatically shares specific information and links. For example, a link set by a user can be automatically shared. The direct message response unit automatically responds to a direct message. For example, an AI analyzes a direct message and generates an appropriate response. This allows the social media auto-response system to set a user-specific message, set a time schedule, perform an automatic response, share information, and respond to a direct message.

[0073] The custom message setting unit allows users to set their own greetings and messages. For example, users can set messages tailored to specific events or anniversaries. Specifically, users can input and save messages using a text editor through the system's interface. This allows users to pre-set messages tailored to special occasions such as Christmas, New Year, and birthdays, and schedule them to be automatically sent on specific dates and times. The custom message setting unit also has a function for managing multiple message templates, allowing users to select an appropriate template depending on the situation. Furthermore, messages can also include images and links, making it possible to create visually appealing messages. This allows the custom message setting unit to flexibly set messages tailored to individual needs and events, making communication on social media more personalized.

[0074] The time schedule setting unit can set different auto-response messages according to the day of the week and the time period. For example, the auto-response can be enabled during non-business hours. Specifically, the user can use a calendar-style interface to set messages according to specific days of the week and the time period. For example, the auto-response message can be set outside business hours on weekdays or on weekends, so that appropriate responses can be made to followers and customers even when the user is absent. The time schedule setting unit also has a function for setting schedules according to seasons and specific events, and can set special messages during, for example, summer vacations and New Year's holidays. Furthermore, the time schedule setting unit can manage multiple schedules simultaneously, and the user can set multiple auto-response messages according to different conditions. This allows the time schedule setting unit to flexibly set messages according to the time period and situation, and efficiently and effectively manage communication on social media.

[0075] The automatic response unit detects specific keywords or phrases in the received message and responds automatically according to the detected results. For example, AI analyzes the received message and detects specific keywords or phrases. Specifically, it uses natural language processing (NLP) technology to analyze the content of the message and generate an appropriate response based on the pre-set keywords and phrases. For example, if a message is received asking "What are your business hours?", AI detects the keyword "business hours" and automatically replies with a message containing information about the pre-set business hours. AI also has the ability to understand context and can handle complex questions and requests. For example, in response to the message "How do I return an item?", AI can provide detailed information about return policies and procedures. In addition, the automatic response unit learns the user's past response history and is continuously improved to provide more accurate responses. As a result, the automatic response unit can reduce the burden on the user and provide quick and accurate responses, thereby streamlining customer support on social media.

[0076] The sharing unit automatically shares specific information and links. For example, a link set by the user can be automatically shared. Specifically, the user can set information and links to be shared in advance through the system interface, and set them to be automatically shared when specific conditions are met. For example, by automatically sharing new product release information and campaign announcements, timely information can be provided to followers and customers. The sharing unit also has a function of sharing information in response to specific events and actions, and for example, when a user posts using a specific hashtag, related links can be automatically shared. Furthermore, the sharing unit also provides a function of customizing the format and style of the information to be shared, and the user can share information in accordance with the brand image. In this way, the sharing unit allows the user to efficiently and effectively share information and improve engagement on social media.

[0077] The direct message response unit automatically replies to direct messages. For example, AI analyzes direct messages and generates appropriate replies. Specifically, it uses natural language processing (NLP) technology to analyze the contents of direct messages, understands the user's intention, and generates appropriate replies. For example, in response to a message such as "Is the product in stock?", AI checks stock information and automatically replies according to the availability of the product. In addition, the direct message response unit can provide more personalized responses by referring to the user's past message history. For example, for a user who has purchased a specific product in the past, it can suggest related information and recommended products for that product. Furthermore, the direct message response unit has the ability to process multiple messages simultaneously, and can respond quickly even when a large number of messages are sent. As a result, the direct message response unit can reduce the burden on users and provide quick and accurate responses, thereby streamlining customer support on social media.

[0078] The social media automatic response system includes an automatic follow-back unit that automatically follows back new followers. For example, when a new follower is detected, the AI ​​can adjust the timing of the follow-back and follow back at an appropriate timing. This allows for a quick and appropriate follow-back for new followers. A part or all of the above-mentioned processing in the automatic follow-back unit may be performed using AI, or may be performed without using AI. For example, the automatic follow-back unit can select an optimal follow-back method in consideration of attribute information of the new follower. This allows for an optimal follow-back method to be selected based on the attribute information of the new follower.

[0079] The social media auto-response system includes a message classification unit that assigns received messages to different auto-response messages according to topics or categories. The message classification unit analyzes received messages and classifies them according to topics or categories. For example, an AI analyzes received messages, detects specific keywords or phrases, and classifies the messages into topics or categories. This makes it possible to classify received messages according to topics or categories and provide appropriate auto-response messages. Some or all of the above-mentioned processing in the message classification unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the message classification unit can analyze the contents of received messages using a generation AI and detect specific keywords or phrases. This makes it possible to classify received messages according to topics or categories and provide appropriate auto-response messages.

[0080] The social media auto-response system includes a collection unit that collects user information and a generation unit that generates an auto-response message based on the collected information. The collection unit collects user information. For example, it can collect profile information and behavioral history of the user. The generation unit generates an auto-response message based on the collected information. For example, an AI can analyze the collected information and generate an optimal auto-response message for the user. This makes it possible to collect user information and generate an individualized auto-response message. A part or all of the above-mentioned processing in the collection unit and the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can analyze the behavioral history of the user using the generation AI, and the generation unit can generate an individualized auto-response message using the generation AI. This makes it possible to collect user information and generate an individualized auto-response message.

[0081] The social media autoresponder system includes an integration unit that supports integration with a CRM system or a customer database. For example, the integration unit can use AI to analyze data in a CRM system or a customer database and perform integration. This can support integration with a CRM system or a customer database and improve customer engagement. Some or all of the above-mentioned processing in the integration unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the integration unit can use a generation AI to analyze data in a CRM system or a customer database and perform integration. This can support integration with a CRM system or a customer database and improve customer engagement.

[0082] The social media automatic response system includes an evaluation unit that evaluates the effect of the automatic response, and a provision unit that provides the evaluation result. The evaluation unit evaluates the effect of the automatic response. For example, an AI can analyze the effect of the automatic response and generate an evaluation result. The provision unit provides the evaluation result. For example, an AI can analyze the evaluation result and provide it to a user. This makes it possible to evaluate the effect of the automatic response and provide the result. A part or all of the above-mentioned processing in the evaluation unit and the provision unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the evaluation unit can analyze the effect of the automatic response using a generation AI, and the provision unit can provide the evaluation result using a generation AI. This makes it possible to evaluate the effect of the automatic response and provide the result.

[0083] The generation unit can acquire the geographical location information of the user and customize the auto-response message based on the acquired geographical location information of the user. For example, an AI can analyze the geographical location information of the user and generate an auto-response message including information related to the area. This allows the auto-response message to be customized based on the geographical location information of the user. A part or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the geographical location information of the user using the generation AI and customize the auto-response message. This allows the auto-response message to be customized based on the geographical location information of the user.

[0084] The automatic response unit can include advertising or promotional information in the automatic response message. For example, when the AI ​​generates the automatic response message, the advertising or promotional information can be inserted. This allows the advertising or promotional information to be included in the automatic response message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze advertising or promotional information using the generation AI and appropriately insert it into the automatic response message. This allows the advertising or promotional information to be included in the automatic response message.

[0085] The automatic response unit can predict the optimal response time based on the user's time zone or activity pattern. For example, the AI ​​can analyze the user's past activity pattern and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's activity pattern using the generation AI and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern.

[0086] The automatic response unit can select a response message for a specific keyword from multiple templates set by the user. For example, the AI ​​can detect a specific keyword and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific keyword using the generation AI and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user.

[0087] The automatic response unit can generate an automatic response message related to a message including a specific hashtag. For example, an AI can detect a specific hashtag and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific hashtag using the generation AI and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag.

[0088] The custom message setting unit can estimate the user's emotions and adjust the content of the custom message based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and suggest a relaxing message, a congratulatory message, or an encouraging message. This allows the content of the custom message to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the custom message setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the custom message setting unit can analyze the user's emotions using the generation AI and adjust the content of the custom message. This allows the content of the custom message to be adjusted based on the user's emotions.

[0089] The custom message setting unit can analyze the user's past message history and propose an optimal custom message. For example, an AI can analyze the user's past message history and propose similar or related messages. This makes it possible to analyze the user's past message history and propose an optimal custom message. A part or all of the above-mentioned processing in the custom message setting unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the custom message setting unit can analyze the user's past message history using a generation AI and propose an optimal custom message. This makes it possible to analyze the user's past message history and propose an optimal custom message.

[0090] The custom message setting unit can customize the message based on the user's current activity status when setting the custom message. For example, the AI ​​can analyze the user's current activity status and suggest a business-oriented message, a relaxing message, or a message related to an event. This allows the message to be customized based on the user's current activity status. A part or all of the above-mentioned processing in the custom message setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the custom message setting unit can analyze the user's current activity status using the generation AI and customize the message. This allows the message to be customized based on the user's current activity status.

[0091] The time schedule setting unit can estimate the user's emotions and adjust the setting of the time schedule based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and set an automatic response to a time period when the user can relax, or set a time period when a proactive message is sent. This allows the setting of the time schedule to be adjusted based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's emotions using the generation AI and adjust the setting of the time schedule. This allows the setting of the time schedule to be adjusted based on the user's emotions.

[0092] The time schedule setting unit can analyze the user's past activity patterns and propose an optimal time schedule. For example, the AI ​​can analyze the user's past activity patterns and set an automatic response to the time period when the user was most active or the time period when the user received the most messages. This makes it possible to analyze the user's past activity patterns and propose an optimal time schedule. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's past activity patterns using the generation AI and propose an optimal time schedule. This makes it possible to analyze the user's past activity patterns and propose an optimal time schedule.

[0093] The time schedule setting unit can customize the schedule based on the user's current living situation when setting the time schedule. For example, the AI ​​can analyze the user's current living situation and set an automatic response for business, an automatic response with a relaxed content, or an automatic response related to an event. This makes it possible to customize the schedule based on the user's current living situation. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's current living situation using the generation AI and customize the schedule. This makes it possible to customize the schedule based on the user's current living situation.

[0094] The automatic response unit can estimate the user's emotions and adjust the content of the automatic response based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and provide a relaxing response, a congratulatory response, or an encouraging response. This allows the content of the automatic response to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's emotions using the generation AI and adjust the content of the automatic response. This allows the content of the automatic response to be adjusted based on the user's emotions.

[0095] The automatic response unit can adjust the level of detail of the response based on the importance of the received message when automatically responding. For example, the AI ​​can analyze the importance of the received message and provide a detailed response to an important message and a concise response to a general message. This makes it possible to adjust the level of detail of the response based on the importance of the received message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the importance of the received message using the generation AI and adjust the level of detail of the response. This makes it possible to adjust the level of detail of the response based on the importance of the received message.

[0096] The automatic response unit can apply different response algorithms depending on the category of the message when automatically responding. For example, the AI ​​can analyze the category of the message and provide a business-oriented response to a business-related message and a personal response to a personal message. This makes it possible to apply the optimal response algorithm depending on the category of the message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the category of the message using the generation AI and apply different response algorithms. This makes it possible to apply the optimal response algorithm depending on the category of the message.

[0097] The sharing unit can estimate the user's emotions and adjust the content of the information to be shared based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and share relaxing information, congratulatory information, or encouraging information. This makes it possible to adjust the content of the information to be shared based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the user's emotions using the generation AI and adjust the content of the information to be shared. This makes it possible to adjust the content of the information to be shared based on the user's emotions.

[0098] The sharing unit can adjust the level of detail of the sharing based on the importance of the information to be shared at the time of sharing. For example, the AI ​​can analyze the importance of the information to be shared, and important information can be shared in detail, and general information can be shared briefly. This makes it possible to adjust the level of detail of the sharing based on the importance of the information. Some or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the importance of the information to be shared using the generation AI, and adjust the level of detail of the sharing. This makes it possible to adjust the level of detail of the sharing based on the importance of the information.

[0099] The sharing unit can apply different sharing algorithms depending on the category of information when sharing. For example, an AI can analyze the category of information, and perform business-oriented sharing for business-related information and personal sharing for personal information. This makes it possible to apply the optimal sharing algorithm depending on the category of information. Some or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the category of information using the generation AI, and apply different sharing algorithms. This makes it possible to apply the optimal sharing algorithm depending on the category of information.

[0100] The direct message response unit can estimate the user's emotions and adjust the content of the direct message based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and provide a relaxing response, a congratulatory response, or an encouraging response. This allows the content of the direct message to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the direct message response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the direct message response unit can analyze the user's emotions using the generation AI and adjust the content of the direct message. This allows the content of the direct message to be adjusted based on the user's emotions.

[0101] When responding to a direct message, the direct message response unit can adjust the level of detail of the response based on the importance of the message. For example, an AI can analyze the importance of the message and provide a detailed response to an important message and a concise response to a general message. This makes it possible to adjust the level of detail of the response based on the importance of the message. Some or all of the above-mentioned processing in the direct message response unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the direct message response unit can analyze the importance of the message using a generation AI and adjust the level of detail of the response. This makes it possible to adjust the level of detail of the response based on the importance of the message.

[0102] The direct message response unit can apply different response algorithms depending on the category of the message when responding to the direct message. For example, the AI ​​can analyze the category of the message and provide a business-oriented response to a business-related message and a personal response to a personal message. This allows the optimal response algorithm to be applied depending on the category of the message. Some or all of the above-mentioned processing in the direct message response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the direct message response unit can analyze the category of the message using the generation AI and apply different response algorithms. This allows the optimal response algorithm to be applied depending on the category of the message.

[0103] The automatic follow-back unit can estimate the user's emotions and adjust the timing of the follow-back based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and perform a follow-back during a time period when the user can relax, or perform a follow-back at a proactive timing. This allows the timing of the follow-back to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the automatic follow-back unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic follow-back unit can analyze the user's emotions using the generation AI and adjust the timing of the follow-back. This allows the timing of the follow-back to be adjusted based on the user's emotions.

[0104] The automatic follow-back unit can select the optimal follow-back method in consideration of the attribute information of the new follower when following back. For example, AI can analyze the attribute information of the new follower, perform business-related follow-back for business-related followers, and perform personal follow-back for personal followers. This allows the optimal follow-back method to be selected based on the attribute information of the new follower. A part or all of the above-mentioned processing in the automatic follow-back unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic follow-back unit can analyze the attribute information of the new follower using the generation AI, and select the optimal follow-back method. This allows the optimal follow-back method to be selected based on the attribute information of the new follower.

[0105] The message classification unit can estimate the user's emotion and adjust the classification criteria of the message based on the estimated user's emotion. The message classification unit can estimate the user's emotion and adjust the classification criteria of the message based on the estimated emotion. For example, an emotion engine or a generation AI can analyze the user's emotion and adjust the classification criteria of the message to provide a relaxing response, a congratulatory response, or an encouraging response. This allows the classification criteria of the message to be adjusted based on the user's emotion. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the message classification unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the message classification unit can analyze the user's emotion using the generation AI and adjust the classification criteria of the message. This allows the classification criteria of the message to be adjusted based on the user's emotion.

[0106] The message classification unit can improve the accuracy of classification by taking into account the interrelationships between messages when classifying messages. For example, the AI ​​can analyze the interrelationships between messages, provide a detailed response to an important message, and provide a concise response to a general message. This can improve the accuracy of classification by taking into account the interrelationships between messages. Some or all of the above-mentioned processing in the message classification unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the message classification unit can analyze the interrelationships between messages using the generation AI, and improve the accuracy of classification. This can improve the accuracy of classification by taking into account the interrelationships between messages.

[0107] The collection unit can estimate the user's emotions and adjust the content of the information to be collected based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and collect relaxing information, congratulatory information, and encouraging information. This makes it possible to adjust the content of the information to be collected based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can analyze the user's emotions using the generation AI and adjust the content of the information to be collected. This makes it possible to adjust the content of the information to be collected based on the user's emotions.

[0108] The collection unit can adjust the level of detail of the collection based on the importance of the information to be collected at the time of collection. For example, the AI ​​can analyze the importance of the information to be collected, and important information can be collected in detail, and general information can be collected briefly. This makes it possible to adjust the level of detail of the collection based on the importance of the information. Some or all of the above-mentioned processing in the collection unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collection unit can analyze the importance of the information to be collected using the generation AI, and adjust the level of detail of the collection. This makes it possible to adjust the level of detail of the collection based on the importance of the information.

[0109] The generation unit can estimate the user's emotions and adjust the content of the automatic response to be generated based on the estimated user's emotions. For example, the emotion engine or the generation AI can analyze the user's emotions and generate a relaxing response, a congratulatory response, or an encouraging response. This makes it possible to adjust the content of the automatic response to be generated based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the user's emotions using the generation AI and adjust the content of the automatic response to be generated. This makes it possible to adjust the content of the automatic response to be generated based on the user's emotions.

[0110] The generation unit can adjust the level of detail of the generation based on the importance of the automatic response to be generated at the time of generation. For example, the importance of the automatic response to be generated by the AI ​​can be analyzed, and detailed generation can be performed for important responses and concise generation can be performed for general responses. This makes it possible to adjust the level of detail of the generation based on the importance of the automatic response. A part or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can analyze the importance of the automatic response to be generated using the generation AI, and adjust the level of detail of the generation. This makes it possible to adjust the level of detail of the generation based on the importance of the automatic response.

[0111] The integration unit can estimate the user's emotions and adjust the content of the integration based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and adjust the content of the integration to provide a relaxing response, a congratulatory response, or an encouraging response. This allows the content of the integration to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the integration unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the integration unit can analyze the user's emotions using the generation AI and adjust the content of the integration. This allows the content of the integration to be adjusted based on the user's emotions.

[0112] During integration, the integration unit can adjust the level of detail of the integration based on the importance of the system to be integrated. For example, the AI ​​can analyze the importance of the system to be integrated, and perform detailed integration for important systems and simple integration for general systems. This makes it possible to adjust the level of detail of the integration based on the importance of the systems. Some or all of the above-mentioned processing in the integration unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the integration unit can analyze the importance of the system to be integrated using the generation AI, and adjust the level of detail of the integration. This makes it possible to adjust the level of detail of the integration based on the importance of the systems.

[0113] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and perform evaluation at a timing when the user can relax or at a timing when the user is proactive. This allows the evaluation criteria to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the user's emotions using the generation AI and adjust the evaluation criteria. This allows the evaluation criteria to be adjusted based on the user's emotions.

[0114] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the data to be evaluated during the evaluation. For example, the importance of the data to be evaluated by the AI ​​can be analyzed, and a detailed evaluation can be performed on important data and a brief evaluation can be performed on general data. This makes it possible to adjust the level of detail of the evaluation based on the importance of the data. Some or all of the above-mentioned processing in the evaluation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can analyze the importance of the data to be evaluated using the generation AI, and adjust the level of detail of the evaluation. This makes it possible to adjust the level of detail of the evaluation based on the importance of the data.

[0115] The providing unit can estimate the user's emotions and adjust the content of the information to be provided based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and provide relaxing information, congratulatory information, or encouraging information. This makes it possible to adjust the content of the information to be provided based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the user's emotions using the generation AI and adjust the content of the information to be provided. This makes it possible to adjust the content of the information to be provided based on the user's emotions.

[0116] The providing unit can adjust the level of detail of the information provided based on the importance of the information to be provided at the time of providing. For example, the AI ​​can analyze the importance of the information to be provided, and provide important information in detail and general information in a concise manner. This makes it possible to adjust the level of detail of the information provided based on the importance of the information. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the importance of the information to be provided using the generation AI, and adjust the level of detail of the information provided. This makes it possible to adjust the level of detail of the information provided based on the importance of the information.

[0117] The providing unit can estimate the user's emotion and adjust the display order of the information to be provided based on the estimated user's emotion. For example, the emotion engine or the generation AI can analyze the user's emotion and preferentially display relaxing information, congratulatory information, and encouraging information. This makes it possible to adjust the display order of the information to be provided based on the user's emotion. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the user's emotion using the generation AI and adjust the display order of the information to be provided. This makes it possible to adjust the display order of the information to be provided based on the user's emotion.

[0118] The providing unit can determine the priority of provision based on the time of information submission at the time of information provision. For example, an AI can analyze the time of information submission and provide the latest information preferentially. This makes it possible to determine the priority of provision based on the time of information submission. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the time of information submission using the generation AI and determine the priority of provision. This makes it possible to determine the priority of provision based on the time of information submission.

[0119] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0120] The custom message setting unit can analyze the user's past message history and propose an optimal custom message. For example, an AI can analyze the user's past message history and propose similar or related messages. This makes it possible to analyze the user's past message history and propose an optimal custom message. A part or all of the above-mentioned processing in the custom message setting unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the custom message setting unit can analyze the user's past message history using a generation AI and propose an optimal custom message. This makes it possible to analyze the user's past message history and propose an optimal custom message.

[0121] The automatic response unit can predict the optimal response time based on the user's time zone or activity pattern. For example, the AI ​​can analyze the user's past activity pattern and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's activity pattern using the generation AI and predict the optimal response time. This makes it possible to predict the optimal response time based on the user's time zone or activity pattern.

[0122] The automatic response unit can select a response message for a specific keyword from multiple templates set by the user. For example, the AI ​​can detect a specific keyword and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific keyword using the generation AI and select an optimal response message from the templates set by the user. This allows a response message for a specific keyword to be selected from multiple templates set by the user.

[0123] The automatic response unit can generate an automatic response message related to a message including a specific hashtag. For example, an AI can detect a specific hashtag and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze a specific hashtag using the generation AI and generate an automatic response message related to the specific hashtag. This makes it possible to generate an automatic response message related to a message including a specific hashtag.

[0124] The automatic response unit can include advertising or promotional information in the automatic response message. For example, when the AI ​​generates the automatic response message, the advertising or promotional information can be inserted. This allows the advertising or promotional information to be included in the automatic response message. Some or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze advertising or promotional information using the generation AI and appropriately insert it into the automatic response message. This allows the advertising or promotional information to be included in the automatic response message.

[0125] The custom message setting unit can estimate the user's emotions and adjust the content of the custom message based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and suggest a relaxing message, a congratulatory message, or an encouraging message. This allows the content of the custom message to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the custom message setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the custom message setting unit can analyze the user's emotions using the generation AI and adjust the content of the custom message. This allows the content of the custom message to be adjusted based on the user's emotions.

[0126] The time schedule setting unit can estimate the user's emotions and adjust the setting of the time schedule based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and set an automatic response to a time period when the user can relax, or set a time period when a proactive message is sent. This allows the setting of the time schedule to be adjusted based on the user's emotions. The estimation of emotions is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the time schedule setting unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the time schedule setting unit can analyze the user's emotions using the generation AI and adjust the setting of the time schedule. This allows the setting of the time schedule to be adjusted based on the user's emotions.

[0127] The automatic response unit can estimate the user's emotions and adjust the content of the automatic response based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and provide a relaxing response, a congratulatory response, or an encouraging response. This allows the content of the automatic response to be adjusted based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the automatic response unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the automatic response unit can analyze the user's emotions using the generation AI and adjust the content of the automatic response. This allows the content of the automatic response to be adjusted based on the user's emotions.

[0128] The sharing unit can estimate the user's emotions and adjust the content of the information to be shared based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and share relaxing information, congratulatory information, or encouraging information. This makes it possible to adjust the content of the information to be shared based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sharing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the sharing unit can analyze the user's emotions using the generation AI and adjust the content of the information to be shared. This makes it possible to adjust the content of the information to be shared based on the user's emotions.

[0129] The providing unit can estimate the user's emotions and adjust the content of the information to be provided based on the estimated user's emotions. For example, an emotion engine or a generation AI can analyze the user's emotions and provide relaxing information, congratulatory information, or encouraging information. This makes it possible to adjust the content of the information to be provided based on the user's emotions. The emotion estimation is realized using an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit can analyze the user's emotions using the generation AI and adjust the content of the information to be provided. This makes it possible to adjust the content of the information to be provided based on the user's emotions.

[0130] The process flow of the second embodiment will be briefly described below.

[0131] Step 1: The custom message setting section allows users to set their own greetings and messages. For example, users can set messages tailored to specific events or anniversaries. Step 2: The time schedule setting section can set different auto-reply messages according to the day of the week and the time of day. For example, the auto-reply can be enabled during non-business hours. Step 3: The automatic response unit detects specific keywords or phrases in the received message and performs an automatic response based on the detected results. For example, AI analyzes the received message and detects specific keywords or phrases. Step 4: The sharing section automatically shares certain information and links. For example, a link set by the user can be automatically shared. Step 5: The direct message response unit automatically responds to direct messages. For example, AI analyzes direct messages and generates appropriate replies.

[0132] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0133] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0134] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0135] For example, the custom message setting unit and the time schedule setting unit are realized by either the smart device 14 or the data processing device 12. For example, the custom message setting unit is realized by the control unit 46A of the smart device 14, and the user can set his / her own greeting or message. The time schedule setting unit is realized by the specific processing unit 290 of the data processing device 12, and can set different automatic response messages depending on the day of the week or the time period. The automatic response unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and detects specific keywords or phrases and performs an automatic response. The sharing unit and the direct message response unit are also realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or the control unit is not limited to the above-mentioned example, and various changes are possible.

[0136] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0137] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0139] 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.

[0140] 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 the voice according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0142] 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 performed in a secure state.

[0143] Fig. 4 shows an example of 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.

[0144] 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.

[0145] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0146] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0147] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0148] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0149] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0150] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0151] For example, the custom message setting unit and the time schedule setting unit are realized by either the smart glasses 214 or the data processing device 12. For example, the custom message setting unit is realized by the control unit 46A of the smart glasses 214, and the user can set his / her own greeting or message. The time schedule setting unit is realized by the specific processing unit 290 of the data processing device 12, and can set different automatic response messages depending on the day of the week or the time period. The automatic response unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and detects specific keywords or phrases and performs an automatic response. The sharing unit and the direct message response unit are also realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or the control unit is not limited to the above-mentioned example, and various changes are possible.

[0152] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0153] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0154] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0155] 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.

[0156] 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 the voice according to instructions from the processor 46.

[0157] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0158] 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 performed in a secure state.

[0159] 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.

[0160] 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.

[0161] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0162] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0163] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0164] 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 voice indicating a user input for 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.

[0165] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0166] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0167] For example, the custom message setting unit and the time schedule setting unit are realized by either the headset terminal 314 or the data processing device 12. For example, the custom message setting unit is realized by the control unit 46A of the headset terminal 314, and the user can set his / her own greeting or message. The time schedule setting unit is realized by the specific processing unit 290 of the data processing device 12, and can set different automatic response messages depending on the day of the week or the time period. The automatic response unit is realized by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and detects specific keywords or phrases to perform an automatic response. The sharing unit and the direct message response unit are also realized by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0171] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0172] 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 the voice according to instructions from the processor 46.

[0173] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0174] 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 performed in a secure state.

[0175] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0176] 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0179] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0181] 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 a voice indicating a user input for 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0183] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0184] For example, the custom message setting unit and the time schedule setting unit are realized by either the robot 414 or the data processing device 12. For example, the custom message setting unit is realized by the control unit 46A of the robot 414, and the user can set his / her own greeting or message. The time schedule setting unit is realized by the specific processing unit 290 of the data processing device 12, and can set different automatic response messages depending on the day of the week or the time period. The automatic response unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and detects specific keywords or phrases and performs an automatic response. The sharing unit and the direct message response unit are also realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0185] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0186] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0187] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0188] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0189] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0190] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0191] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0192] 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.

[0193] 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 Universal Serial Bus (USB) 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.

[0194] In addition, 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 upon request from the data processing device 12.

[0195] 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.

[0196] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0197] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0198] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0199] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0200] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0201] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0202] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0203] (Appendix 1) A custom message setting section for setting a user-specific message; A time schedule setting section for setting different auto-reply messages according to the day of the week and the time of day; an automatic response unit that detects specific keywords or phrases in received messages and performs an automatic response in accordance with the detected results; A sharing section for sharing certain information and links; A direct message response unit that responds to a direct message. A system characterized by: (Appendix 2) Equipped with an automatic follow-back function that automatically follows back new followers 2. The system of claim 1, (Appendix 3) A message classification unit that assigns incoming messages to different auto-response messages according to topic or category. 2. The system of claim 1, (Appendix 4) A collection unit that collects user information; A generating unit generates an automatic response message based on the information collected by the collecting unit. 2. The system of claim 1, (Appendix 5) Includes an integration department to support integration with CRM systems or customer databases 2. The system of claim 1, (Appendix 6) An evaluation unit for evaluating the effectiveness of the automatic response; a providing unit that outputs the evaluation result by the evaluation unit 2. The system of claim 1, (Appendix 7) The generation unit is Customize auto-response messages based on the user's geographic location 5. The system of claim 4. (Appendix 8) The automatic response unit is Include advertising or promotional information in your autoresponder messages 2. The system of claim 1, (Appendix 9) The automatic response unit is Predicting optimal response times based on the user's time of day or activity patterns 2. The system of claim 1, (Appendix 10) The automatic response unit is A response message for a specific keyword is selected from a plurality of templates set by the user. 2. The system of claim 1, (Appendix 11) The automatic response unit is Generate relevant auto-response messages for messages containing specific hashtags 2. The system of claim 1, (Appendix 12) The custom message setting unit includes: Infer user sentiment and tailor custom message content based on the inferred user sentiment 2. The system of claim 1, (Appendix 13) The custom message setting unit includes: Analyze the user's past message history and suggest the best custom message 2. The system of claim 1, (Appendix 14) The custom message setting unit includes: When setting custom messages, customize messages based on the user's current activity 2. The system of claim 1, (Appendix 15) The time schedule setting unit, To estimate a user's emotion and adjust a time schedule setting based on the estimated user's emotion. 2. The system of claim 1, (Appendix 16) The time schedule setting unit, Analyze the user's past activity patterns and suggest optimal time schedules 2. The system of claim 1, (Appendix 17) The time schedule setting unit, Customize schedule based on user's current life situation while setting time schedule 2. The system of claim 1, (Appendix 18) The automatic response unit is Inferring user emotions and adjusting the content of the automated response based on the estimated user emotions 2. The system of claim 1, (Appendix 19) The automatic response unit is During auto-reply, adjust the detail of the response based on the importance of the incoming message 2. The system of claim 1, (Appendix 20) The automatic response unit is When auto-replying, apply different response algorithms depending on the message category 2. The system of claim 1, (Appendix 21) The common part is Estimate the user's emotions and adjust the content of the information to be shared based on the estimated user's emotions 2. The system of claim 1, (Appendix 22) The common part is When sharing, adjust the level of detail you share based on the importance of the information you share 2. The system of claim 1, (Appendix 23) The common part is When sharing, apply different sharing algorithms depending on the category of information 2. The system of claim 1, (Appendix 24) The direct message response unit, Inferring user sentiment and tailoring direct message content based on the estimated user sentiment 2. The system of claim 1, (Appendix 25) The direct message response unit, When responding to direct messages, adjust the detail of your response based on the importance of the message 2. The system of claim 1, (Appendix 26) The direct message response unit, When responding to direct messages, apply different response algorithms depending on the message category. 2. The system of claim 1, (Appendix 27) The automatic follow-back unit is Estimate the user's emotions and adjust the timing of follow-back based on the estimated user's emotions 3. The system of claim 2, (Appendix 28) The automatic follow-back unit is When following back, select the optimal follow-back method taking into account the attribute information of the new follower. 3. The system of claim 2, (Appendix 29) The message classification unit Inferring a user's sentiment and adjusting message classification criteria based on the inferred user's sentiment 4. The system of claim 3. (Appendix 30) The message classification unit When classifying messages, the correlation between messages is taken into account to improve classification accuracy. 4. The system of claim 3. (Appendix 31) The collecting unit includes: To estimate a user's emotion and adjust the content of information to be collected based on the estimated user's emotion. 5. The system of claim 4. (Appendix 32) The collecting unit includes: At the time of collection, adjust the granularity of collection based on the importance of the information being collected 5. The system of claim 4. (Appendix 33) The generation unit is Inferring user emotions and adjusting the content of the generated automatic response based on the estimated user emotions 5. The system of claim 4. (Appendix 34) The generation unit is At generation time, adjust the verbosity of the generated autoresponder based on its importance 5. The system of claim 4. (Appendix 35) The integration unit includes: Infer user sentiment and tailor integration content based on inferred user sentiment 6. The system of claim 5, (Appendix 36) The integration unit includes: At integration time, adjust the granularity of your integration based on the importance of the system you are integrating with. 6. The system of claim 5, (Appendix 37) The evaluation unit is Inferring user emotions and adjusting evaluation criteria based on the estimated user emotions 7. The system of claim 6, (Appendix 38) The evaluation unit is During evaluation, adjust the granularity of the evaluation based on the importance of the data being evaluated 7. The system of claim 6, (Appendix 39) The providing unit is To estimate a user's emotion and adjust the content of information to be provided based on the estimated user's emotion. 7. The system of claim 6, (Appendix 40) The providing unit is When providing, adjust the level of detail provided based on the importance of the information provided 7. The system of claim 6, (Appendix 41) The providing unit is The system estimates the user's emotions and adjusts the display order of information to be provided based on the estimated user's emotions. 7. The system of claim 6, (Appendix 42) The providing unit is At the time of submission, the information will be prioritized based on when it was submitted. 7. The system of claim 6, [Explanation of symbols]

[0204] 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 custom message setting section for setting a user-specific message; A time schedule setting section for setting different auto-reply messages according to the day of the week and the time of day; an automatic response unit that detects specific keywords or phrases in received messages and performs an automatic response in accordance with the detected results; A sharing section for sharing certain information and links; A direct message response unit that responds to a direct message. A system characterized by:

2. Equipped with an automatic follow-back function that automatically follows back new followers 2. The system of claim 1 .

3. A message classification unit that assigns incoming messages to different auto-response messages according to topic or category.

2. The system of claim 1 .

4. A collection unit that collects user information; A generating unit generates an automatic response message based on the information collected by the collecting unit.

2. The system of claim 1 .

5. Includes an integration department to support integration with CRM systems or customer databases 2. The system of claim 1 .

6. An evaluation unit for evaluating the effectiveness of the automatic response; a providing unit that outputs the evaluation result by the evaluation unit 2. The system of claim 1 .

7. The generation unit is Customize auto-response messages based on the user's geographic location 5. The system of claim 4.

8. The automatic response unit is Include advertising or promotional information in your autoresponder messages 2. The system of claim 1 .

9. The automatic response unit is Predicting optimal response times based on the user's time of day or activity patterns 2. The system of claim 1 .

Images