system

Abstract

The system according to the embodiment aims to efficiently elicit and record requirements from incoming calls. [Solution] The system according to the embodiment includes a reception unit, a questioning unit, an analysis unit, a recording unit, a storage unit, and a notification unit. The reception unit receives incoming calls. The questioning unit asks the caller for their requirements when a call is received by the reception unit. The analysis unit analyzes the caller's response obtained by the questioning unit. The recording unit records the requirements analyzed by the analysis unit. The storage unit stores the requirements recorded by the recording unit in a database. The notification unit notifies the person in charge of the requirements stored by the storage unit.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to efficiently elicit and record requirements from incoming calls.

[0005] The system according to the embodiment aims to efficiently elicit and record requirements from incoming calls. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a questioning unit, an analysis unit, a recording unit, a storage unit, and a notification unit. The reception unit receives incoming calls. The questioning unit asks for the caller's requirements when the call is received by the reception unit. The analysis unit analyzes the caller's response obtained by the questioning unit. The recording unit records the requirements analyzed by the analysis unit. The storage unit stores the requirements recorded by the recording unit in a database. The notification unit notifies the person in charge of the requirements stored by the storage unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently elicit and record requirements from incoming calls. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An automated answering system according to an embodiment of the present invention uses AI to automatically answer calls, elicit the caller's requirements, and record them. When an automated answering system receives a call, the AI ​​automatically answers the call, asks questions to elicit the caller's requirements, and records the caller's answers. The recorded requirements are stored in a database and notified to a responsible party as needed. For example, when an automated answering system receives a call, the AI ​​sends a message to the caller, such as "Hello, this is the automated answering system. How can I help you?" Next, the AI ​​asks questions such as "What is your need?" and "Can you please tell me your name and contact information?" It analyzes the caller's response and understands the caller's requirements. Finally, the AI ​​stores the caller's name, contact information, and details of the request in a database and notifies a responsible party as needed. This allows the automated answering system to improve the efficiency of telephone response and reduce the burden on the responsible party. For example, even if the responsible party is busy, the AI ​​can automatically answer the call and record the request, allowing them to be checked later. This also enables prompt and appropriate responses to callers.

[0029] An automated answering system according to an embodiment includes a reception unit, a questioning unit, an analysis unit, a recording unit, a storage unit, and a notification unit. The reception unit receives incoming telephone calls. For example, it can receive incoming calls from landlines, mobile phones, IP phones, and the like. The questioning unit elicits the caller's requirements from the call received by the reception unit. For example, it asks questions such as, "What is your business?" or "Can you please tell me your name and contact information?" The analysis unit analyzes the caller's answer obtained by the questioning unit. For example, it understands the caller's requirements using text analysis or voice analysis. The recording unit records the requirements analyzed by the analysis unit. For example, it records the caller's name, contact information, and content of the requirements in text format. The storage unit stores the requirements recorded by the recording unit in a database. For example, it stores the requirements in a relational database or a NoSQL database. The notification unit notifies the person in charge of the requirements stored by the storage unit. For example, it sends an email notification or an SMS notification. As a result, the automated answering system according to an embodiment can improve the efficiency of telephone response and reduce the burden on the person in charge.

[0030] The automated answering system according to the embodiment includes a speech recognition unit that uses speech recognition technology. The speech recognition unit recognizes the caller's speech. For example, deep learning-based speech recognition technology is used to convert the caller's speech into text. The speech recognition unit can also use HMM (Hidden Markov Model)-based speech recognition technology. Furthermore, the speech recognition unit can recognize the caller's speech in real time and save it as text data. This makes it possible to accurately grasp the caller's requirements using speech recognition technology.

[0031] The automatic response system according to the embodiment includes a natural language processing unit that uses natural language processing technology. The natural language processing unit analyzes the caller's response. For example, the natural language processing unit uses morphological analysis to break down the caller's response and understand its meaning. The natural language processing unit can also analyze the structure of the caller's response using grammatical analysis. Furthermore, the natural language processing unit can also understand the meaning of the caller's response using semantic analysis. This allows the use of natural language processing technology to more deeply understand the caller's requirements.

[0032] The automatic response system according to the embodiment includes a database management unit that manages the structure of the database. The database management unit manages the structure of the database. For example, it designs tables and determines how data is stored. The database management unit can also set indexes to improve data search speed. Furthermore, the database management unit can back up data to ensure data integrity. In this way, managing the structure of the database enables efficient management of stored requirements.

[0033] The automatic response system according to the embodiment includes a notification management unit that manages notification methods. The notification management unit manages the notification methods. For example, it sets up email notifications and notifies the person in charge by email. The notification management unit can also set up push notifications and send notifications to the person in charge's smartphone. Furthermore, the notification management unit can also set up SMS notifications and notify the person in charge by SMS. By managing the notification methods, notifications to the person in charge can be sent efficiently.

[0034] The reception unit can refer to the caller's past call history and select the optimal response method. For example, if a caller has called with the same request multiple times in the past, the reception unit will select a standard response for that request. In addition, if the caller has spoken to a specific person in the past, the reception unit can respond by having the AI ​​connect the call directly to that person. In addition, if the caller has filed a complaint in the past, the reception unit can select a response method that will allow the AI ​​to respond quickly. This makes it possible to provide the optimal response to the caller by referring to past call history.

[0035] The reception unit can acquire the geographical information of the caller and greet the caller according to the region. For example, if the caller calls from Tokyo, the reception unit greets the caller with "Hello, you're calling from Tokyo." If the caller calls from Osaka, the reception unit can also greet the caller with "Hello, you're calling from Osaka." If the caller calls from overseas, the reception unit can also greet the caller with "Hello, thank you for calling from overseas." This makes it possible to provide a greeting according to the caller's geographical information, allowing for a friendly response to the caller.

[0036] The reception unit can customize the content of the response based on the caller's call time zone. For example, if the caller calls in the morning, the reception unit greets the caller with "Good morning." If the caller calls in the afternoon, the reception unit can also greet the caller with "Hello." If the caller calls in the evening, the reception unit can also greet the caller with "Good evening." This makes it possible to respond according to the call time zone, allowing the caller to be treated appropriately.

[0037] The reception unit can analyze the caller's social media activity and reflect relevant information in the response. For example, if the caller posts about a specific issue on social media, the reception unit can have the AI ​​reflect information about that issue in the response. Also, if the caller is participating in a specific event on social media, the reception unit can have the AI ​​reflect information about that event in the response. Also, if the caller comments about a specific product on social media, the reception unit can have the AI ​​reflect information about that product in the response. This makes it possible to respond based on the caller's social media activity, resulting in more personalized responses.

[0038] The reception unit can customize the response method by reflecting the caller's past feedback. For example, if the caller has preferred a particular response method in the past, the reception unit will have the AI ​​prioritize using that response method. Also, if the caller has been dissatisfied with a particular response method in the past, the reception unit can have the AI ​​avoid that response method. Also, if the caller has preferred a particular agent in the past, the reception unit can respond by having the AI ​​connect the call directly to that agent. This makes it possible to respond based on past feedback, improving caller satisfaction.

[0039] The reception unit can select the optimal response method by taking into account the caller's device information. For example, if the caller is using a smartphone, the AI ​​can prioritize voice responses. If the caller is using a computer, the AI ​​can also prioritize text responses. If the caller is using a tablet, the AI ​​can also prioritize video responses. This makes it possible to respond based on the caller's device information, resulting in more appropriate responses.

[0040] When asking a question, the questioning unit can refer to the caller's past call content to select the most appropriate question. For example, if the caller has inquired about a specific problem in the past, the questioning unit will have the AI ​​ask a question related to that problem. Also, if the caller has inquired about a specific product in the past, the questioning unit can have the AI ​​ask a question related to that product. Also, if the caller has inquired about a specific service in the past, the questioning unit can have the AI ​​ask a question related to that service. This makes it possible to ask questions based on the call content in the past, allowing appropriate questions to be asked of the caller.

[0041] When asking a question, the questioning unit can customize the question content by taking into account the attribute information of the caller. For example, if the caller is a company representative, the AI ​​will ask questions related to the business. Also, if the caller is an individual, the AI ​​can ask questions related to the individual. Also, if the caller belongs to a specific industry, the AI ​​can ask questions related to that industry. This makes it possible to ask questions based on the attribute information of the caller, resulting in more appropriate questions.

[0042] When a question is asked, the questioning unit can dynamically generate the next question based on the caller's answer history. For example, if the caller answers about a specific problem, the questioning unit will generate the next question related to that problem. Also, if the caller answers about a specific product, the questioning unit will be able to generate the next question related to that product. Also, if the caller answers about a specific service, the questioning unit will be able to generate the next question related to that service. This makes it possible to ask questions based on the caller's answer history, resulting in smoother conversations.

[0043] When asking a question, the questioning unit can customize the question content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​will ask questions related to that region. Also, if the caller calls from overseas, the questioning unit can ask questions related to that country. Also, if the caller calls from a specific city, the questioning unit can ask questions related to that city. This makes it possible to ask questions based on the caller's geographical information, resulting in more appropriate questions.

[0044] When a question is asked, the question unit can analyze the caller's social media activity and ask relevant questions. For example, if the caller posts about a specific issue on social media, the AI ​​can ask questions related to that issue. Also, if the caller is participating in a specific event on social media, the AI ​​can ask questions related to that event. Also, if the caller comments on a specific product on social media, the AI ​​can ask questions related to that product. This makes it possible to ask questions based on the caller's social media activity, resulting in more personalized questions.

[0045] When asking a question, the questioning unit can customize the question content by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific question in the past, the AI ​​will prioritize that question. Also, if the sender has been dissatisfied with a specific question in the past, the questioning unit can have the AI ​​avoid that question. Also, if the sender has given neutral feedback to a specific question in the past, the questioning unit can have the AI ​​ask that question in the normal order. This makes it possible to ask questions based on past feedback, improving the sender's satisfaction.

[0046] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the analysis unit can have the AI ​​reflect information related to that problem in the analysis. Also, if the caller has inquired about a specific product in the past, the analysis unit can have the AI ​​reflect information related to that product in the analysis. Also, if the caller has inquired about a specific service in the past, the analysis unit can have the AI ​​reflect information related to that service in the analysis. This makes it possible to perform analysis based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0047] During analysis, the analysis unit can select an analysis algorithm taking into account the sender's attribute information. For example, if the sender is a company representative, the analysis unit can have the AI ​​select an analysis algorithm related to the business. Also, if the sender is an individual, the analysis unit can have the AI ​​select an analysis algorithm related to the individual. Also, if the sender belongs to a specific industry, the analysis unit can have the AI ​​select an analysis algorithm related to that industry. This makes it possible to perform analysis based on the sender's attribute information, resulting in more appropriate analysis.

[0048] During analysis, the analysis unit can weight the analysis based on the sender's response history. For example, if the sender has previously provided a detailed response about a specific issue, the analysis unit can weight the response and perform the analysis using the AI. Furthermore, if the sender has previously provided a detailed response about a specific product, the analysis unit can weight the response and perform the analysis using the AI. Furthermore, if the sender has previously provided a detailed response about a specific service, the analysis unit can weight the response and perform the analysis using the AI. This makes it possible to perform analysis based on the sender's response history, resulting in more accurate analysis.

[0049] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the analysis unit allows the AI ​​to reflect information related to that region in the analysis. Also, if the caller calls from overseas, the analysis unit can allow the AI ​​to reflect information related to that country in the analysis. Also, if the caller calls from a specific city, the analysis unit can allow the AI ​​to reflect information related to that city in the analysis. This makes it possible to perform analysis based on the caller's geographical information, resulting in more accurate analysis.

[0050] During analysis, the analysis unit can analyze the sender's social media activity and reflect related information in the analysis. For example, if the sender posts about a specific issue on social media, the analysis unit can reflect information related to that issue in the analysis. Also, if the sender is participating in a specific event on social media, the analysis unit can reflect information related to that event in the analysis. Also, if the sender comments on a specific product on social media, the analysis unit can reflect information related to that product in the analysis. This makes it possible to perform analysis based on the sender's social media activity, resulting in more personalized analysis.

[0051] During analysis, the analysis unit can adjust the analysis algorithm by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to use that algorithm preferentially. Also, if the sender has been dissatisfied with a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to avoid that algorithm. Also, if the sender has given neutral feedback to a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to use that algorithm in the normal order. This makes it possible to perform analysis based on past feedback, improving the sender's satisfaction.

[0052] When recording, the recording unit can improve the accuracy of the recording by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the recording unit can have the AI ​​reflect information related to that problem in the record. Also, if the caller has inquired about a specific product in the past, the recording unit can have the AI ​​reflect information related to that product in the record. Also, if the caller has inquired about a specific service in the past, the recording unit can have the AI ​​reflect information related to that service in the record. This makes it possible to record based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0053] When recording, the recording unit can customize the recording content by taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​will record information related to the business. Also, if the sender is an individual, the AI ​​can record information related to the individual. Also, if the sender belongs to a specific industry, the AI ​​can record information related to that industry. This makes it possible to record based on the sender's attribute information, resulting in more appropriate recording.

[0054] When recording, the recording unit can weight the record based on the caller's response history. For example, if the caller has previously provided a detailed response about a specific issue, the recording unit will weight the response and record it using the AI. Also, if the caller has previously provided a detailed response about a specific product, the recording unit can weight the response and record it using the AI. Also, if the caller has previously provided a detailed response about a specific service, the recording unit can weight the response and record it using the AI. This makes it possible to record based on the caller's response history, resulting in more accurate recording.

[0055] When recording, the recording unit can customize the recording content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​will reflect information related to that region in the recording. Also, if the caller calls from overseas, the AI ​​can reflect information related to that country in the recording. Also, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the recording. This makes it possible to record based on the caller's geographical information, resulting in more appropriate recording.

[0056] When recording, the recording unit can analyze the caller's social media activity and reflect related information in the record. For example, if the caller posts about a specific issue on social media, the recording unit can have the AI ​​reflect information related to that issue in the record. Also, if the caller is participating in a specific event on social media, the recording unit can have the AI ​​reflect information related to that event in the record. Also, if the caller comments on a specific product on social media, the recording unit can have the AI ​​reflect information related to that product in the record. This makes it possible to record based on the caller's social media activity, resulting in more personalized recording.

[0057] The recording unit can customize the recording method by reflecting the caller's past feedback when recording. For example, if the caller has given favorable feedback to a specific recording method in the past, the recording unit can cause the AI ​​to use that method preferentially. Also, if the caller has previously been dissatisfied with a specific recording method, the recording unit can cause the AI ​​to avoid that method. Also, if the caller has previously given neutral feedback to a specific recording method, the recording unit can cause the AI ​​to use that method in the normal order. This makes it possible to record based on past feedback, improving caller satisfaction.

[0058] When saving, the storage unit can improve the accuracy of the saving by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the storage unit can reflect information related to that problem in the saved data. In addition, if the caller has inquired about a specific product in the past, the storage unit can reflect information related to that product in the saved data. In addition, if the caller has inquired about a specific service in the past, the storage unit can reflect information related to that service in the saved data. This makes it possible to save data based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0059] The storage unit can customize the stored content by taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​can store business-related information. Also, if the sender is an individual, the AI ​​can store information related to the individual. Also, if the sender belongs to a specific industry, the AI ​​can store information related to that industry. This makes it possible to store information based on the sender's attribute information, resulting in more appropriate storage.

[0060] When saving, the storage unit can weight the saved responses based on the sender's response history. For example, if the sender has previously provided a detailed response to a specific issue, the storage unit will store the response with the AI ​​weighting it. Also, if the sender has previously provided a detailed response about a specific product, the storage unit can weight the response and store it. Also, if the sender has previously provided a detailed response about a specific service, the storage unit can weight the response and store it. This makes it possible to save responses based on the sender's response history, resulting in more accurate saving.

[0061] The storage unit can customize the stored content by taking into account the caller's geographical information when storing the call. For example, if the caller calls from a specific region, the AI ​​can reflect information related to that region in the stored content. In addition, if the caller calls from overseas, the AI ​​can reflect information related to that country in the stored content. In addition, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the stored content. This makes it possible to store the call based on the caller's geographical information, resulting in more appropriate storage.

[0062] When saving, the storage unit can analyze the sender's social media activity and reflect related information in the saved content. For example, if the sender posts about a specific issue on social media, the storage unit can have the AI ​​reflect information related to that issue in the saved content. Also, if the sender is participating in a specific event on social media, the storage unit can have the AI ​​reflect information related to that event in the saved content. Also, if the sender comments on a specific product on social media, the storage unit can have the AI ​​reflect information related to that product in the saved content. This makes it possible to save content based on the sender's social media activity, resulting in more personalized saving.

[0063] The storage unit can customize the storage method by reflecting the sender's past feedback when saving. For example, if the sender has given favorable feedback about a specific storage method in the past, the storage unit allows the AI ​​to use that method preferentially. Also, if the sender has been dissatisfied with a specific storage method in the past, the storage unit can allow the AI ​​to avoid that method. Also, if the sender has given neutral feedback about a specific storage method in the past, the storage unit can allow the AI ​​to use that method in the normal order. This makes it possible to save based on past feedback, improving the sender's satisfaction.

[0064] When sending a notification, the notification unit can improve the accuracy of the notification by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the notification unit can have the AI ​​reflect information related to that problem in the notification. Also, if the caller has inquired about a specific product in the past, the notification unit can have the AI ​​reflect information related to that product in the notification. Also, if the caller has inquired about a specific service in the past, the notification unit can have the AI ​​reflect information related to that service in the notification. This makes it possible to provide notifications based on the content of past calls, allowing the caller's requirements to be understood more accurately.

[0065] When sending a notification, the notification unit can customize the notification content by taking into account the attribute information of the sender. For example, if the sender is a company representative, the AI ​​can notify the sender of business-related information. Furthermore, if the sender is an individual, the AI ​​can also notify the sender of information related to the individual. Furthermore, if the sender belongs to a specific industry, the AI ​​can also notify the sender of information related to that industry. This makes it possible to send notifications based on the sender's attribute information, resulting in more appropriate notifications.

[0066] When sending a notification, the notification unit can weight the notification based on the caller's response history. For example, if the caller has previously provided a detailed response about a specific problem, the notification unit can weight the response and send the notification using the AI. Also, if the caller has previously provided a detailed response about a specific product, the notification unit can weight the response and send the notification using the AI. Also, if the caller has previously provided a detailed response about a specific service, the notification unit can weight the response and send the notification using the AI. This makes it possible to send notifications based on the caller's response history, resulting in more accurate notifications.

[0067] When making a notification, the notification unit can customize the notification content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the notification unit's AI can reflect information related to that region in the notification. Also, if the caller calls from overseas, the notification unit's AI can reflect information related to that country in the notification. Also, if the caller calls from a specific city, the notification unit's AI can reflect information related to that city in the notification. This makes it possible to provide notifications based on the caller's geographical information, resulting in more appropriate notifications.

[0068] At the time of notification, the notification unit can analyze the sender's social media activity and reflect relevant information in the notification. For example, if the sender posts about a specific issue on social media, the notification unit's AI can reflect information related to that issue in the notification. Also, if the sender is participating in a specific event on social media, the notification unit's AI can reflect information related to that event in the notification. Also, if the sender comments on a specific product on social media, the notification unit's AI can reflect information related to that product in the notification. This makes it possible to provide notifications based on the sender's social media activity, resulting in more personalized notifications.

[0069] The notification unit can customize the notification method by reflecting the caller's past feedback when notifying. For example, if the caller has given favorable feedback about a specific notification method in the past, the notification unit allows the AI ​​to use that method preferentially. Also, if the caller has been dissatisfied with a specific notification method in the past, the notification unit can allow the AI ​​to avoid that method. Also, if the caller has given neutral feedback about a specific notification method in the past, the notification unit can allow the AI ​​to use that method in the normal order. This enables notifications based on past feedback, improving caller satisfaction.

[0070] During voice recognition, the voice recognition unit can improve the accuracy of recognition by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the voice recognition unit's AI can reflect information related to that problem in the voice recognition. Also, if a caller has previously inquired about a specific product, the voice recognition unit can also reflect information related to that product in the voice recognition. Also, if a caller has previously inquired about a specific service, the voice recognition unit can also reflect information related to that service in the voice recognition. This makes it possible to perform voice recognition based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0071] When recognizing a voice, the voice recognition unit can select a recognition algorithm taking into consideration the caller's attribute information. For example, if the caller is a company representative, the AI ​​in the voice recognition unit can select a recognition algorithm related to the business. Also, if the caller is an individual, the AI ​​in the voice recognition unit can select a recognition algorithm related to the individual. Also, if the caller belongs to a specific industry, the AI ​​in the voice recognition unit can select a recognition algorithm related to that industry. This enables voice recognition based on the caller's attribute information, resulting in more appropriate recognition.

[0072] When performing voice recognition, the voice recognition unit can weight the recognition based on the caller's response history. For example, if a caller has previously provided a detailed response to a specific problem, the voice recognition unit can weight the response and perform voice recognition using the AI. Also, if a caller has previously provided a detailed response about a specific product, the voice recognition unit can weight the response and perform voice recognition using the AI. Also, if a caller has previously provided a detailed response about a specific service, the voice recognition unit can weight the response and perform voice recognition using the AI. This enables voice recognition based on the caller's response history, resulting in more accurate recognition.

[0073] The speech recognition unit can improve the accuracy of speech recognition by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​of the speech recognition unit can reflect information related to that region in the speech recognition. Also, if the caller calls from overseas, the AI ​​can reflect information related to that country in the speech recognition. Also, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the speech recognition. This enables speech recognition based on the caller's geographical information, resulting in more accurate recognition.

[0074] The voice recognition unit can analyze the caller's social media activity during voice recognition and reflect related information in the recognition. For example, if the caller posts about a specific issue on social media, the voice recognition unit's AI can reflect information related to that issue in the voice recognition. Also, if the caller is participating in a specific event on social media, the voice recognition unit's AI can reflect information related to that event in the voice recognition. Also, if the caller comments on a specific product on social media, the voice recognition unit's AI can reflect information related to that product in the voice recognition. This enables voice recognition based on the caller's social media activity, resulting in more personalized recognition.

[0075] During voice recognition, the voice recognition unit can adjust the recognition algorithm by reflecting the caller's past feedback. For example, if the caller has given favorable feedback to a specific recognition algorithm in the past, the voice recognition unit allows the AI ​​to use that algorithm preferentially. Also, if the caller has been dissatisfied with a specific recognition algorithm in the past, the voice recognition unit can allow the AI ​​to avoid that algorithm. Also, if the caller has given neutral feedback to a specific recognition algorithm in the past, the voice recognition unit can allow the AI ​​to use that algorithm in the normal order. This enables voice recognition based on past feedback, improving caller satisfaction.

[0076] During natural language processing, the natural language processing unit can improve the accuracy of processing by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the natural language processing unit's AI can reflect information related to that problem in the natural language processing. Furthermore, if a caller has inquired about a specific product in the past, the natural language processing unit's AI can reflect information related to that product in the natural language processing. Furthermore, if a caller has inquired about a specific service in the past, the natural language processing unit's AI can reflect information related to that service in the natural language processing. This makes it possible to perform natural language processing based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0077] During natural language processing, the natural language processing unit can select a processing algorithm taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​of the natural language processing unit selects a processing algorithm related to the business. Furthermore, if the sender is an individual, the AI ​​of the natural language processing unit can also select a processing algorithm related to the individual. Furthermore, if the sender belongs to a specific industry, the AI ​​of the natural language processing unit can also select a processing algorithm related to that industry. This enables natural language processing based on the sender's attribute information, resulting in more appropriate processing.

[0078] During natural language processing, the natural language processing unit can weight the processing based on the caller's response history. For example, if a caller has previously provided a detailed response to a specific problem, the natural language processing unit can weight the response and perform natural language processing using the AI. Furthermore, if a caller has previously provided a detailed response about a specific product, the natural language processing unit can also weight the response and perform natural language processing using the AI. Furthermore, if a caller has previously provided a detailed response about a specific service, the natural language processing unit can also weight the response and perform natural language processing using the AI. This enables natural language processing based on the caller's response history, resulting in more accurate processing.

[0079] The natural language processing unit can improve the accuracy of natural language processing by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the natural language processing unit's AI can reflect information related to that region in the natural language processing. Furthermore, if the caller calls from overseas, the natural language processing unit's AI can also reflect information related to that country in the natural language processing. Furthermore, if the caller calls from a specific city, the natural language processing unit's AI can also reflect information related to that city in the natural language processing. This enables natural language processing based on the caller's geographical information, resulting in more accurate processing.

[0080] During natural language processing, the natural language processing unit can analyze the sender's social media activity and reflect related information in the processing. For example, if the sender posts about a specific issue on social media, the natural language processing unit's AI can reflect information related to that issue in the natural language processing. Furthermore, if the sender is participating in a specific event on social media, the natural language processing unit's AI can reflect information related to that event in the natural language processing. Furthermore, if the sender comments on a specific product on social media, the natural language processing unit's AI can reflect information related to that product in the natural language processing. This enables natural language processing based on the sender's social media activity, resulting in more personalized processing.

[0081] During natural language processing, the natural language processing unit can adjust the processing algorithm by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific processing algorithm in the past, the natural language processing unit allows the AI ​​to preferentially use that algorithm. Also, if the sender has been dissatisfied with a specific processing algorithm in the past, the natural language processing unit can also allow the AI ​​to avoid that algorithm. Also, if the sender has given neutral feedback to a specific processing algorithm in the past, the natural language processing unit can also allow the AI ​​to use that algorithm in the normal order. This enables natural language processing based on past feedback, improving sender satisfaction.

[0082] When managing the database, the database management unit can optimize the database by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the database management unit will update the database with information related to that problem. Also, if a caller has inquired about a specific product in the past, the database management unit can update the database with information related to that product. Also, if a caller has inquired about a specific service in the past, the database management unit can update the database with information related to that service. This makes it possible to optimize the database based on the call content in the past, allowing for a more accurate understanding of the caller's requirements.

[0083] When managing the database, the database management unit can customize the database structure by taking into account the sender's attribute information. For example, if the sender is a company representative, the database management unit can have the AI ​​create a database structure related to the business. Also, if the sender is an individual, the database management unit can have the AI ​​create a database structure related to the individual. Also, if the sender belongs to a specific industry, the database management unit can have the AI ​​create a database structure related to that industry. This makes it possible to customize the database structure based on the sender's attribute information, resulting in more appropriate database management.

[0084] When managing the database, the database management unit can adjust the structure of the database by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the database management unit causes the AI ​​to update the database with information related to that region. In addition, if the caller calls from overseas, the database management unit can also cause the AI ​​to update the database with information related to that country. In addition, if the caller calls from a specific city, the database management unit can also update the database with information related to that city. This makes it possible to adjust the database structure based on the caller's geographical information, resulting in more appropriate database management.

[0085] During database management, the database management unit can analyze the sender's social media activity and reflect related information in the database. For example, if the sender posts about a specific issue on social media, the database management unit can reflect information related to that issue in the database using the AI. In addition, if the sender is participating in a specific event on social media, the database management unit can also reflect information related to that event in the database using the AI. In addition, if the sender comments on a specific product on social media, the database management unit can also reflect information related to that product in the database using the AI. This enables database management based on the sender's social media activity, resulting in more personalized database management.

[0086] When managing notifications, the notification management unit can optimize the notification method by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the notification management unit will have the AI ​​reflect information related to that problem in the notification. Also, if a caller has inquired about a specific product in the past, the notification management unit can also reflect information related to that product in the notification. Also, if a caller has inquired about a specific service in the past, the AI ​​can also reflect information related to that service in the notification. This makes it possible to optimize the notification method based on the call content in the past, allowing for a more accurate understanding of the caller's requirements.

[0087] When managing notifications, the notification management unit can customize the notification method by taking into account the sender's attribute information. For example, if the sender is a company representative, the notification management unit will have the AI ​​notify the sender of business-related information. Also, if the sender is an individual, the notification management unit can have the AI ​​notify the sender of information related to the individual. Also, if the sender belongs to a specific industry, the notification management unit can have the AI ​​notify the sender of information related to that industry. This makes it possible to customize the notification method based on the sender's attribute information, resulting in more appropriate notifications.

[0088] When managing notifications, the notification management unit can weight notifications based on the caller's response history. For example, if a caller has previously provided a detailed response about a specific issue, the notification management unit can weight that response and send a notification using the AI. Also, if a caller has previously provided a detailed response about a specific product, the notification management unit can weight that response and send a notification using the AI. Also, if a caller has previously provided a detailed response about a specific service, the notification management unit can weight that response and send a notification using the AI. This makes it possible to send notifications based on the caller's response history, resulting in more accurate notifications.

[0089] When managing notifications, the notification management unit can adjust the notification method by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the notification management unit will have the AI ​​reflect information related to that region in the notification. Also, if the caller calls from overseas, the notification management unit can have the AI ​​reflect information related to that country in the notification. Also, if the caller calls from a specific city, the notification management unit can have the AI ​​reflect information related to that city in the notification. This makes it possible to adjust the notification method based on the caller's geographical information, resulting in more appropriate notifications.

[0090] When managing notifications, the notification management unit can analyze the sender's social media activity and reflect relevant information in the notification. For example, if the sender posts about a specific issue on social media, the notification management unit's AI can reflect information related to that issue in the notification. Also, if the sender is participating in a specific event on social media, the notification management unit's AI can reflect information related to that event in the notification. Also, if the sender comments on a specific product on social media, the notification management unit's AI can reflect information related to that product in the notification. This makes it possible to provide notifications based on the sender's social media activity, resulting in more personalized notifications.

[0091] The notification management unit can customize the notification method by reflecting the sender's past feedback when managing notifications. For example, if the sender has given favorable feedback about a specific notification method in the past, the notification management unit can cause the AI ​​to use that method preferentially. Also, if the sender has been dissatisfied with a specific notification method in the past, the notification management unit can cause the AI ​​to avoid that method. Also, if the sender has given neutral feedback about a specific notification method in the past, the notification management unit can cause the AI ​​to use that method in the normal order. This makes it possible to provide notifications based on past feedback, improving the sender's satisfaction.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The questioning section can dynamically generate the next question based on the caller's response. For example, if the caller responds, "Regarding returning a product," the AI ​​can generate a related question such as, "Can you tell me the reason for the return?". If the caller responds, "I need technical support," the AI ​​can also generate a question such as, "What specific problem are you experiencing?". Furthermore, if the caller responds, "I would like to know about a new product," the AI ​​can generate a question such as, "Which product would you like to know about?" This makes it possible to ask questions based on the caller's response, resulting in smoother conversations.

[0094] The recording unit can improve the accuracy of recording by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can reflect information related to that problem in the record. Also, if a caller has previously inquired about a specific product, the AI ​​can reflect information related to that product in the record. Also, if a caller has previously inquired about a specific service, the AI ​​can reflect information related to that service in the record. This makes it possible to record based on past call content, allowing for a more accurate understanding of the caller's requirements.

[0095] The speech recognition unit can improve the accuracy of recognition by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can incorporate information related to that problem into the speech recognition. Also, if a caller has previously inquired about a specific product, the AI ​​can incorporate information related to that product into the speech recognition. Also, if a caller has previously inquired about a specific service, the AI ​​can incorporate information related to that service into the speech recognition. This makes it possible to recognize speech based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0096] The database management unit can optimize the database by referencing the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can update the database with information related to that problem. Also, if a caller has previously inquired about a specific product, the AI ​​can update the database with information related to that product. Also, if a caller has previously inquired about a specific service, the AI ​​can update the database with information related to that service. This makes it possible to optimize the database based on past call content, allowing for a more accurate understanding of caller requirements.

[0097] The reception unit can acquire the caller's geographical information and provide a greeting appropriate to the region. For example, if the caller calls from Tokyo, the reception unit can greet the caller with "Hello, you're calling from Tokyo." If the caller calls from Osaka, the reception unit can greet the caller with "Hello, you're calling from Osaka." If the caller calls from overseas, the reception unit can greet the caller with "Hello, thank you for calling from overseas." This makes it possible to provide a greeting appropriate to the caller's geographical information, resulting in a friendly response to the caller.

[0098] The processing flow of the first embodiment will be briefly explained below.

[0099] Step 1: The reception unit receives an incoming call. For example, it can receive an incoming call from a landline phone, a mobile phone, an IP phone, etc. Step 2: The inquiry department asks the caller about their needs after the call is received by the reception department. For example, they ask questions such as, "What is your business?" and "Can I have your name and contact information?" Step 3: The analysis unit analyzes the caller's response obtained by the question unit, for example, by using text analysis or voice analysis to understand the caller's requirements. Step 4: The recording unit records the requirements analyzed by the analysis unit, such as the sender's name, contact information, and requirements content in text format. Step 5: The storage unit stores the requirements recorded by the recording unit in a database, such as a relational database or a NoSQL database. Step 6: The notification unit notifies the person in charge of the requirements stored by the storage unit, for example, by email or SMS.

[0100] (Example 2) An automated answering system according to an embodiment of the present invention uses AI to automatically answer calls, elicit the caller's requirements, and record them. When an automated answering system receives a call, the AI ​​automatically answers the call, asks questions to elicit the caller's requirements, and records the caller's answers. The recorded requirements are stored in a database and notified to a responsible party as needed. For example, when an automated answering system receives a call, the AI ​​sends a message to the caller, such as "Hello, this is the automated answering system. How can I help you?" Next, the AI ​​asks questions such as "What is your need?" and "Can you please tell me your name and contact information?" It analyzes the caller's response and understands the caller's requirements. Finally, the AI ​​stores the caller's name, contact information, and details of the request in a database and notifies a responsible party as needed. This allows the automated answering system to improve the efficiency of telephone response and reduce the burden on the responsible party. For example, even if the responsible party is busy, the AI ​​can automatically answer the call and record the request, allowing them to be checked later. This also enables prompt and appropriate responses to callers.

[0101] An automated answering system according to an embodiment includes a reception unit, a questioning unit, an analysis unit, a recording unit, a storage unit, and a notification unit. The reception unit receives incoming telephone calls. For example, it can receive incoming calls from landlines, mobile phones, IP phones, and the like. The questioning unit elicits the caller's requirements from the call received by the reception unit. For example, it asks questions such as, "What is your business?" or "Can you please tell me your name and contact information?" The analysis unit analyzes the caller's answer obtained by the questioning unit. For example, it understands the caller's requirements using text analysis or voice analysis. The recording unit records the requirements analyzed by the analysis unit. For example, it records the caller's name, contact information, and content of the requirements in text format. The storage unit stores the requirements recorded by the recording unit in a database. For example, it stores the requirements in a relational database or a NoSQL database. The notification unit notifies the person in charge of the requirements stored by the storage unit. For example, it sends an email notification or an SMS notification. As a result, the automated answering system according to an embodiment can improve the efficiency of telephone response and reduce the burden on the person in charge.

[0102] The automated answering system according to the embodiment includes a speech recognition unit that uses speech recognition technology. The speech recognition unit recognizes the caller's speech. For example, deep learning-based speech recognition technology is used to convert the caller's speech into text. The speech recognition unit can also use HMM (Hidden Markov Model)-based speech recognition technology. Furthermore, the speech recognition unit can recognize the caller's speech in real time and save it as text data. This makes it possible to accurately grasp the caller's requirements using speech recognition technology.

[0103] The automatic response system according to the embodiment includes a natural language processing unit that uses natural language processing technology. The natural language processing unit analyzes the caller's response. For example, the natural language processing unit uses morphological analysis to break down the caller's response and understand its meaning. The natural language processing unit can also analyze the structure of the caller's response using grammatical analysis. Furthermore, the natural language processing unit can also understand the meaning of the caller's response using semantic analysis. This allows the use of natural language processing technology to more deeply understand the caller's requirements.

[0104] The automatic response system according to the embodiment includes a database management unit that manages the structure of the database. The database management unit manages the structure of the database. For example, it designs tables and determines how data is stored. The database management unit can also set indexes to improve data search speed. Furthermore, the database management unit can back up data to ensure data integrity. In this way, managing the structure of the database enables efficient management of stored requirements.

[0105] The automatic response system according to the embodiment includes a notification management unit that manages notification methods. The notification management unit manages the notification methods. For example, it sets up email notifications and notifies the person in charge by email. The notification management unit can also set up push notifications and send notifications to the person in charge's smartphone. Furthermore, the notification management unit can also set up SMS notifications and notify the person in charge by SMS. By managing the notification methods, notifications to the person in charge can be sent efficiently.

[0106] The reception unit can estimate the caller's emotions and adjust the tone of the response based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the reception unit can respond in a calm tone to calm the caller's emotions. If the caller is nervous, the AI ​​can respond in a gentle tone to relax the caller. If the caller is relaxed, the AI ​​can respond in a friendly tone to smoothly advance the conversation. This enables a response that is appropriate for the caller's emotions, improving the caller's satisfaction. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0107] The reception unit can refer to the caller's past call history and select the optimal response method. For example, if a caller has called with the same request multiple times in the past, the reception unit will select a standard response for that request. In addition, if the caller has spoken to a specific person in the past, the reception unit can respond by having the AI ​​connect the call directly to that person. In addition, if the caller has filed a complaint in the past, the reception unit can select a response method that will allow the AI ​​to respond quickly. This makes it possible to provide the optimal response to the caller by referring to past call history.

[0108] The reception unit can acquire the geographical information of the caller and greet the caller according to the region. For example, if the caller calls from Tokyo, the reception unit greets the caller with "Hello, you're calling from Tokyo." If the caller calls from Osaka, the reception unit can also greet the caller with "Hello, you're calling from Osaka." If the caller calls from overseas, the reception unit can also greet the caller with "Hello, thank you for calling from overseas." This makes it possible to provide a greeting according to the caller's geographical information, allowing for a friendly response to the caller.

[0109] The reception unit can customize the content of the response based on the caller's call time zone. For example, if the caller calls in the morning, the reception unit greets the caller with "Good morning." If the caller calls in the afternoon, the reception unit can also greet the caller with "Hello." If the caller calls in the evening, the reception unit can also greet the caller with "Good evening." This makes it possible to respond according to the call time zone, allowing the caller to be treated appropriately.

[0110] The reception unit can estimate the caller's emotions and determine the priority of responses based on the estimated emotions of the caller. For example, if the caller is very angry, the reception unit has the AI ​​handle the call with the highest priority. The reception unit can also have the AI ​​handle the call with priority if the caller has an urgent request. The reception unit can also have the AI ​​respond with normal priority if the caller is relaxed. This makes it possible to respond with a priority according to the caller's emotions, and important calls can be handled with priority. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The reception unit can analyze the caller's social media activity and reflect relevant information in the response. For example, if the caller posts about a specific issue on social media, the reception unit can have the AI ​​reflect information about that issue in the response. Also, if the caller is participating in a specific event on social media, the reception unit can have the AI ​​reflect information about that event in the response. Also, if the caller comments about a specific product on social media, the reception unit can have the AI ​​reflect information about that product in the response. This makes it possible to respond based on the caller's social media activity, resulting in more personalized responses.

[0112] The reception unit can customize the response method by reflecting the caller's past feedback. For example, if the caller has preferred a particular response method in the past, the reception unit will have the AI ​​prioritize using that response method. Also, if the caller has been dissatisfied with a particular response method in the past, the reception unit can have the AI ​​avoid that response method. Also, if the caller has preferred a particular agent in the past, the reception unit can respond by having the AI ​​connect the call directly to that agent. This makes it possible to respond based on past feedback, improving caller satisfaction.

[0113] The reception unit can select the optimal response method by taking into account the caller's device information. For example, if the caller is using a smartphone, the AI ​​can prioritize voice responses. If the caller is using a computer, the AI ​​can also prioritize text responses. If the caller is using a tablet, the AI ​​can also prioritize video responses. This makes it possible to respond based on the caller's device information, resulting in more appropriate responses.

[0114] The questioning unit can estimate the sender's emotions and adjust the way the question is phrased based on the estimated emotions of the sender. For example, if the sender is angry, the AI ​​in the questioning unit can ask the question in a calm tone to calm the sender's emotions. If the sender is nervous, the AI ​​can ask the question in a gentle tone to relax the sender. If the sender is relaxed, the AI ​​can ask the question in a friendly tone to smoothly advance the conversation. This makes it possible to ask questions according to the sender's emotions, thereby improving the sender's satisfaction. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0115] When asking a question, the questioning unit can refer to the caller's past call content to select the most appropriate question. For example, if the caller has inquired about a specific problem in the past, the questioning unit will have the AI ​​ask a question related to that problem. Also, if the caller has inquired about a specific product in the past, the questioning unit can have the AI ​​ask a question related to that product. Also, if the caller has inquired about a specific service in the past, the questioning unit can have the AI ​​ask a question related to that service. This makes it possible to ask questions based on the call content in the past, allowing appropriate questions to be asked of the caller.

[0116] When asking a question, the questioning unit can customize the question content by taking into account the attribute information of the caller. For example, if the caller is a company representative, the AI ​​will ask questions related to the business. Also, if the caller is an individual, the AI ​​can ask questions related to the individual. Also, if the caller belongs to a specific industry, the AI ​​can ask questions related to that industry. This makes it possible to ask questions based on the attribute information of the caller, resulting in more appropriate questions.

[0117] When a question is asked, the questioning unit can dynamically generate the next question based on the caller's answer history. For example, if the caller answers about a specific problem, the questioning unit will generate the next question related to that problem. Also, if the caller answers about a specific product, the questioning unit will be able to generate the next question related to that product. Also, if the caller answers about a specific service, the questioning unit will be able to generate the next question related to that service. This makes it possible to ask questions based on the caller's answer history, resulting in smoother conversations.

[0118] The questioning unit can estimate the caller's emotions and adjust the order of questions based on the estimated caller's emotions. For example, if the caller is angry, the questioning unit can have the AI ​​ask the most important question first to calm the caller's emotions. If the caller is nervous, the questioning unit can also have the AI ​​start with simple questions to relax the caller. If the caller is relaxed, the questioning unit can also have the AI ​​ask questions in the normal order. This enables the order of questions to be based on the caller's emotions, improving the caller's satisfaction. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0119] When asking a question, the questioning unit can customize the question content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​will ask questions related to that region. Also, if the caller calls from overseas, the questioning unit can ask questions related to that country. Also, if the caller calls from a specific city, the questioning unit can ask questions related to that city. This makes it possible to ask questions based on the caller's geographical information, resulting in more appropriate questions.

[0120] When a question is asked, the question unit can analyze the caller's social media activity and ask relevant questions. For example, if the caller posts about a specific issue on social media, the AI ​​can ask questions related to that issue. Also, if the caller is participating in a specific event on social media, the AI ​​can ask questions related to that event. Also, if the caller comments on a specific product on social media, the AI ​​can ask questions related to that product. This makes it possible to ask questions based on the caller's social media activity, resulting in more personalized questions.

[0121] When asking a question, the questioning unit can customize the question content by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific question in the past, the AI ​​will prioritize that question. Also, if the sender has been dissatisfied with a specific question in the past, the questioning unit can have the AI ​​avoid that question. Also, if the sender has given neutral feedback to a specific question in the past, the questioning unit can have the AI ​​ask that question in the normal order. This makes it possible to ask questions based on past feedback, improving the sender's satisfaction.

[0122] The analysis unit can estimate the sender's emotions and adjust the accuracy of the analysis based on the estimated emotions of the sender. For example, if the sender is angry, the analysis unit has the AI ​​perform a detailed analysis to accurately grasp the sender's requirements. If the sender is nervous, the analysis unit can also have the AI ​​perform the analysis in a gentle tone to relax the sender. If the sender is relaxed, the analysis unit can also perform the analysis with normal accuracy. This enables analysis according to the sender's emotions and accurately grasp the sender's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0123] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the analysis unit can have the AI ​​reflect information related to that problem in the analysis. Also, if the caller has inquired about a specific product in the past, the analysis unit can have the AI ​​reflect information related to that product in the analysis. Also, if the caller has inquired about a specific service in the past, the analysis unit can have the AI ​​reflect information related to that service in the analysis. This makes it possible to perform analysis based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0124] During analysis, the analysis unit can select an analysis algorithm taking into account the sender's attribute information. For example, if the sender is a company representative, the analysis unit can have the AI ​​select an analysis algorithm related to the business. Also, if the sender is an individual, the analysis unit can have the AI ​​select an analysis algorithm related to the individual. Also, if the sender belongs to a specific industry, the analysis unit can have the AI ​​select an analysis algorithm related to that industry. This makes it possible to perform analysis based on the sender's attribute information, resulting in more appropriate analysis.

[0125] During analysis, the analysis unit can weight the analysis based on the sender's response history. For example, if the sender has previously provided a detailed response about a specific issue, the analysis unit can weight the response and perform the analysis using the AI. Furthermore, if the sender has previously provided a detailed response about a specific product, the analysis unit can weight the response and perform the analysis using the AI. Furthermore, if the sender has previously provided a detailed response about a specific service, the analysis unit can weight the response and perform the analysis using the AI. This makes it possible to perform analysis based on the sender's response history, resulting in more accurate analysis.

[0126] The analysis unit can estimate the caller's emotions and adjust the display method of the analysis results based on the estimated caller's emotions. For example, if the caller is angry, the analysis unit has the AI ​​display detailed analysis results to accurately grasp the caller's requirements. If the caller is nervous, the analysis unit can also display the analysis results in a gentle tone to relax the caller. If the caller is relaxed, the analysis unit can also display the analysis results in a normal display method. This makes it possible to display analysis results according to the caller's emotions, improving the caller's satisfaction. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0127] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the analysis unit allows the AI ​​to reflect information related to that region in the analysis. Also, if the caller calls from overseas, the analysis unit can allow the AI ​​to reflect information related to that country in the analysis. Also, if the caller calls from a specific city, the analysis unit can allow the AI ​​to reflect information related to that city in the analysis. This makes it possible to perform analysis based on the caller's geographical information, resulting in more accurate analysis.

[0128] During analysis, the analysis unit can analyze the sender's social media activity and reflect related information in the analysis. For example, if the sender posts about a specific issue on social media, the analysis unit can reflect information related to that issue in the analysis. Also, if the sender is participating in a specific event on social media, the analysis unit can reflect information related to that event in the analysis. Also, if the sender comments on a specific product on social media, the analysis unit can reflect information related to that product in the analysis. This makes it possible to perform analysis based on the sender's social media activity, resulting in more personalized analysis.

[0129] During analysis, the analysis unit can adjust the analysis algorithm by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to use that algorithm preferentially. Also, if the sender has been dissatisfied with a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to avoid that algorithm. Also, if the sender has given neutral feedback to a specific analysis algorithm in the past, the analysis unit can cause the AI ​​to use that algorithm in the normal order. This makes it possible to perform analysis based on past feedback, improving the sender's satisfaction.

[0130] The recording unit can estimate the caller's emotions and adjust the recording method based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the recording unit can record in detail to accurately grasp the caller's requirements. If the caller is nervous, the AI ​​can record in a gentle tone to relax the caller. If the caller is relaxed, the AI ​​can record in a normal manner. This makes it possible to record according to the caller's emotions and accurately grasp the caller's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0131] When recording, the recording unit can improve the accuracy of the recording by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the recording unit can have the AI ​​reflect information related to that problem in the record. Also, if the caller has inquired about a specific product in the past, the recording unit can have the AI ​​reflect information related to that product in the record. Also, if the caller has inquired about a specific service in the past, the recording unit can have the AI ​​reflect information related to that service in the record. This makes it possible to record based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0132] When recording, the recording unit can customize the recording content by taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​will record information related to the business. Also, if the sender is an individual, the AI ​​can record information related to the individual. Also, if the sender belongs to a specific industry, the AI ​​can record information related to that industry. This makes it possible to record based on the sender's attribute information, resulting in more appropriate recording.

[0133] When recording, the recording unit can weight the record based on the caller's response history. For example, if the caller has previously provided a detailed response about a specific issue, the recording unit will weight the response and record it using the AI. Also, if the caller has previously provided a detailed response about a specific product, the recording unit can weight the response and record it using the AI. Also, if the caller has previously provided a detailed response about a specific service, the recording unit can weight the response and record it using the AI. This makes it possible to record based on the caller's response history, resulting in more accurate recording.

[0134] The recording unit can estimate the caller's emotions and determine the priority of recording based on the estimated caller's emotions. For example, if the caller is very angry, the recording unit allows the AI ​​to process that record as a top priority. Also, if the caller has an urgent request, the recording unit can also allow the AI ​​to process that record as a priority. Also, if the caller is relaxed, the recording unit can allow the AI ​​to record with normal priority. This makes it possible to record with a priority according to the caller's emotions, and important requests can be recorded with priority. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0135] When recording, the recording unit can customize the recording content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​will reflect information related to that region in the recording. Also, if the caller calls from overseas, the AI ​​can reflect information related to that country in the recording. Also, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the recording. This makes it possible to record based on the caller's geographical information, resulting in more appropriate recording.

[0136] When recording, the recording unit can analyze the caller's social media activity and reflect related information in the record. For example, if the caller posts about a specific issue on social media, the recording unit can have the AI ​​reflect information related to that issue in the record. Also, if the caller is participating in a specific event on social media, the recording unit can have the AI ​​reflect information related to that event in the record. Also, if the caller comments on a specific product on social media, the recording unit can have the AI ​​reflect information related to that product in the record. This makes it possible to record based on the caller's social media activity, resulting in more personalized recording.

[0137] The recording unit can customize the recording method by reflecting the caller's past feedback when recording. For example, if the caller has given favorable feedback to a specific recording method in the past, the recording unit can cause the AI ​​to use that method preferentially. Also, if the caller has previously been dissatisfied with a specific recording method, the recording unit can cause the AI ​​to avoid that method. Also, if the caller has previously given neutral feedback to a specific recording method, the recording unit can cause the AI ​​to use that method in the normal order. This makes it possible to record based on past feedback, improving caller satisfaction.

[0138] The storage unit can estimate the sender's emotions and adjust the storage method based on the estimated sender's emotions. For example, if the sender is angry, the AI ​​in the storage unit can perform detailed storage to accurately grasp the sender's requirements. If the sender is nervous, the AI ​​can perform storage in a gentle tone to relax the sender. If the sender is relaxed, the AI ​​can perform storage in a normal manner. This enables storage according to the sender's emotions and accurately grasp the sender's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0139] When saving, the storage unit can improve the accuracy of the saving by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the storage unit can reflect information related to that problem in the saved data. In addition, if the caller has inquired about a specific product in the past, the storage unit can reflect information related to that product in the saved data. In addition, if the caller has inquired about a specific service in the past, the storage unit can reflect information related to that service in the saved data. This makes it possible to save data based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0140] The storage unit can customize the stored content by taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​can store business-related information. Also, if the sender is an individual, the AI ​​can store information related to the individual. Also, if the sender belongs to a specific industry, the AI ​​can store information related to that industry. This makes it possible to store information based on the sender's attribute information, resulting in more appropriate storage.

[0141] When saving, the storage unit can weight the saved responses based on the sender's response history. For example, if the sender has previously provided a detailed response to a specific issue, the storage unit will store the response with the AI ​​weighting it. Also, if the sender has previously provided a detailed response about a specific product, the storage unit can weight the response and store it. Also, if the sender has previously provided a detailed response about a specific service, the storage unit can weight the response and store it. This makes it possible to save responses based on the sender's response history, resulting in more accurate saving.

[0142] The storage unit can estimate the sender's emotions and determine the priority of saving based on the estimated emotions of the sender. For example, if the sender is very angry, the storage unit allows the AI ​​to prioritize saving that message. Also, if the sender has an urgent request, the storage unit can also allow the AI ​​to prioritize saving that request. Also, if the sender is relaxed, the storage unit can allow the AI ​​to save messages with normal priority. This makes it possible to save messages with priority according to the sender's emotions, allowing important requests to be saved with priority. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0143] The storage unit can customize the stored content by taking into account the caller's geographical information when storing the call. For example, if the caller calls from a specific region, the AI ​​can reflect information related to that region in the stored content. In addition, if the caller calls from overseas, the AI ​​can reflect information related to that country in the stored content. In addition, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the stored content. This makes it possible to store the call based on the caller's geographical information, resulting in more appropriate storage.

[0144] When saving, the storage unit can analyze the sender's social media activity and reflect related information in the saved content. For example, if the sender posts about a specific issue on social media, the storage unit can have the AI ​​reflect information related to that issue in the saved content. Also, if the sender is participating in a specific event on social media, the storage unit can have the AI ​​reflect information related to that event in the saved content. Also, if the sender comments on a specific product on social media, the storage unit can have the AI ​​reflect information related to that product in the saved content. This makes it possible to save content based on the sender's social media activity, resulting in more personalized saving.

[0145] The storage unit can customize the storage method by reflecting the sender's past feedback when saving. For example, if the sender has given favorable feedback about a specific storage method in the past, the storage unit allows the AI ​​to use that method preferentially. Also, if the sender has been dissatisfied with a specific storage method in the past, the storage unit can allow the AI ​​to avoid that method. Also, if the sender has given neutral feedback about a specific storage method in the past, the storage unit can allow the AI ​​to use that method in the normal order. This makes it possible to save based on past feedback, improving the sender's satisfaction.

[0146] The notification unit can estimate the caller's emotions and adjust the notification method based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the notification unit can quickly notify the person in charge. If the caller is nervous, the AI ​​can also notify in a gentle tone. If the caller is relaxed, the AI ​​can also notify in a normal manner. This makes it possible to provide a notification according to the caller's emotions and accurately grasp the caller's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0147] When sending a notification, the notification unit can improve the accuracy of the notification by referring to the caller's past call content. For example, if the caller has inquired about a specific problem in the past, the notification unit can have the AI ​​reflect information related to that problem in the notification. Also, if the caller has inquired about a specific product in the past, the notification unit can have the AI ​​reflect information related to that product in the notification. Also, if the caller has inquired about a specific service in the past, the notification unit can have the AI ​​reflect information related to that service in the notification. This makes it possible to provide notifications based on the content of past calls, allowing the caller's requirements to be understood more accurately.

[0148] When sending a notification, the notification unit can customize the notification content by taking into account the attribute information of the sender. For example, if the sender is a company representative, the AI ​​can notify the sender of business-related information. Furthermore, if the sender is an individual, the AI ​​can also notify the sender of information related to the individual. Furthermore, if the sender belongs to a specific industry, the AI ​​can also notify the sender of information related to that industry. This makes it possible to send notifications based on the sender's attribute information, resulting in more appropriate notifications.

[0149] When sending a notification, the notification unit can weight the notification based on the caller's response history. For example, if the caller has previously provided a detailed response about a specific problem, the notification unit can weight the response and send the notification using the AI. Also, if the caller has previously provided a detailed response about a specific product, the notification unit can weight the response and send the notification using the AI. Also, if the caller has previously provided a detailed response about a specific service, the notification unit can weight the response and send the notification using the AI. This makes it possible to send notifications based on the caller's response history, resulting in more accurate notifications.

[0150] The notification unit can estimate the caller's emotions and determine the priority of notifications based on the estimated emotions of the caller. For example, if the caller is very angry, the notification unit has the AI ​​process that notification as the highest priority. Also, if the caller has an urgent request, the notification unit can also have the AI ​​process that notification as a priority. Also, if the caller is relaxed, the notification unit can have the AI ​​notify with normal priority. This makes it possible to prioritize notifications according to the caller's emotions, allowing important requests to be notified first. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0151] When making a notification, the notification unit can customize the notification content by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the notification unit's AI can reflect information related to that region in the notification. Also, if the caller calls from overseas, the notification unit's AI can reflect information related to that country in the notification. Also, if the caller calls from a specific city, the notification unit's AI can reflect information related to that city in the notification. This makes it possible to provide notifications based on the caller's geographical information, resulting in more appropriate notifications.

[0152] At the time of notification, the notification unit can analyze the sender's social media activity and reflect relevant information in the notification. For example, if the sender posts about a specific issue on social media, the notification unit's AI can reflect information related to that issue in the notification. Also, if the sender is participating in a specific event on social media, the notification unit's AI can reflect information related to that event in the notification. Also, if the sender comments on a specific product on social media, the notification unit's AI can reflect information related to that product in the notification. This makes it possible to provide notifications based on the sender's social media activity, resulting in more personalized notifications.

[0153] The notification unit can customize the notification method by reflecting the caller's past feedback when notifying. For example, if the caller has given favorable feedback about a specific notification method in the past, the notification unit allows the AI ​​to use that method preferentially. Also, if the caller has been dissatisfied with a specific notification method in the past, the notification unit can allow the AI ​​to avoid that method. Also, if the caller has given neutral feedback about a specific notification method in the past, the notification unit can allow the AI ​​to use that method in the normal order. This enables notifications based on past feedback, improving caller satisfaction.

[0154] The speech recognition unit can estimate the caller's emotions and adjust the accuracy of speech recognition based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the speech recognition unit can perform detailed speech recognition to accurately grasp the caller's requirements. If the caller is nervous, the AI ​​can perform speech recognition in a gentler tone to relax the caller. If the caller is relaxed, the AI ​​can perform speech recognition with normal accuracy. This enables speech recognition according to the caller's emotions and accurately grasp the caller's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0155] During voice recognition, the voice recognition unit can improve the accuracy of recognition by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the voice recognition unit's AI can reflect information related to that problem in the voice recognition. Also, if a caller has previously inquired about a specific product, the voice recognition unit can also reflect information related to that product in the voice recognition. Also, if a caller has previously inquired about a specific service, the voice recognition unit can also reflect information related to that service in the voice recognition. This makes it possible to perform voice recognition based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0156] When recognizing a voice, the voice recognition unit can select a recognition algorithm taking into consideration the caller's attribute information. For example, if the caller is a company representative, the AI ​​in the voice recognition unit can select a recognition algorithm related to the business. Also, if the caller is an individual, the AI ​​in the voice recognition unit can select a recognition algorithm related to the individual. Also, if the caller belongs to a specific industry, the AI ​​in the voice recognition unit can select a recognition algorithm related to that industry. This enables voice recognition based on the caller's attribute information, resulting in more appropriate recognition.

[0157] When performing voice recognition, the voice recognition unit can weight the recognition based on the caller's response history. For example, if a caller has previously provided a detailed response to a specific problem, the voice recognition unit can weight the response and perform voice recognition using the AI. Also, if a caller has previously provided a detailed response about a specific product, the voice recognition unit can weight the response and perform voice recognition using the AI. Also, if a caller has previously provided a detailed response about a specific service, the voice recognition unit can weight the response and perform voice recognition using the AI. This enables voice recognition based on the caller's response history, resulting in more accurate recognition.

[0158] The speech recognition unit can estimate the caller's emotions and adjust the display method of the speech recognition results based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the speech recognition unit can display detailed speech recognition results to accurately grasp the caller's requirements. If the caller is nervous, the AI ​​can display the speech recognition results in a gentle tone to relax the caller. If the caller is relaxed, the AI ​​can display the speech recognition results in a normal display method. This makes it possible to display speech recognition results according to the caller's emotions, thereby improving the caller's satisfaction. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0159] The speech recognition unit can improve the accuracy of speech recognition by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the AI ​​of the speech recognition unit can reflect information related to that region in the speech recognition. Also, if the caller calls from overseas, the AI ​​can reflect information related to that country in the speech recognition. Also, if the caller calls from a specific city, the AI ​​can reflect information related to that city in the speech recognition. This enables speech recognition based on the caller's geographical information, resulting in more accurate recognition.

[0160] The voice recognition unit can analyze the caller's social media activity during voice recognition and reflect related information in the recognition. For example, if the caller posts about a specific issue on social media, the voice recognition unit's AI can reflect information related to that issue in the voice recognition. Also, if the caller is participating in a specific event on social media, the voice recognition unit's AI can reflect information related to that event in the voice recognition. Also, if the caller comments on a specific product on social media, the voice recognition unit's AI can reflect information related to that product in the voice recognition. This enables voice recognition based on the caller's social media activity, resulting in more personalized recognition.

[0161] During voice recognition, the voice recognition unit can adjust the recognition algorithm by reflecting the caller's past feedback. For example, if the caller has given favorable feedback to a specific recognition algorithm in the past, the voice recognition unit allows the AI ​​to use that algorithm preferentially. Also, if the caller has been dissatisfied with a specific recognition algorithm in the past, the voice recognition unit can allow the AI ​​to avoid that algorithm. Also, if the caller has given neutral feedback to a specific recognition algorithm in the past, the voice recognition unit can allow the AI ​​to use that algorithm in the normal order. This enables voice recognition based on past feedback, improving caller satisfaction.

[0162] The natural language processing unit can estimate the sender's emotions and adjust the accuracy of the natural language processing based on the estimated emotions of the sender. For example, if the sender is angry, the AI ​​in the natural language processing unit can perform detailed natural language processing to accurately grasp the sender's requirements. Furthermore, if the sender is nervous, the AI ​​can perform natural language processing in a gentle tone to relax the sender. Furthermore, if the sender is relaxed, the AI ​​can perform natural language processing with normal accuracy. This enables natural language processing according to the sender's emotions and accurately grasp the sender's requirements. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0163] During natural language processing, the natural language processing unit can improve the accuracy of processing by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the natural language processing unit's AI can reflect information related to that problem in the natural language processing. Furthermore, if a caller has inquired about a specific product in the past, the natural language processing unit's AI can reflect information related to that product in the natural language processing. Furthermore, if a caller has inquired about a specific service in the past, the natural language processing unit's AI can reflect information related to that service in the natural language processing. This makes it possible to perform natural language processing based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0164] During natural language processing, the natural language processing unit can select a processing algorithm taking into account the sender's attribute information. For example, if the sender is a company representative, the AI ​​of the natural language processing unit selects a processing algorithm related to the business. Furthermore, if the sender is an individual, the AI ​​of the natural language processing unit can also select a processing algorithm related to the individual. Furthermore, if the sender belongs to a specific industry, the AI ​​of the natural language processing unit can also select a processing algorithm related to that industry. This enables natural language processing based on the sender's attribute information, resulting in more appropriate processing.

[0165] During natural language processing, the natural language processing unit can weight the processing based on the caller's response history. For example, if a caller has previously provided a detailed response to a specific problem, the natural language processing unit can weight the response and perform natural language processing using the AI. Furthermore, if a caller has previously provided a detailed response about a specific product, the natural language processing unit can also weight the response and perform natural language processing using the AI. Furthermore, if a caller has previously provided a detailed response about a specific service, the natural language processing unit can also weight the response and perform natural language processing using the AI. This enables natural language processing based on the caller's response history, resulting in more accurate processing.

[0166] The natural language processing unit can estimate the caller's emotions and adjust the display method of the natural language processing results based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​of the natural language processing unit can display detailed natural language processing results to accurately grasp the caller's requirements. If the caller is nervous, the AI ​​can display the natural language processing results in a gentle tone to relax the caller. If the caller is relaxed, the AI ​​can display the natural language processing results in a normal display method. This makes it possible to display natural language processing results according to the caller's emotions, thereby improving the caller's satisfaction. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0167] The natural language processing unit can improve the accuracy of natural language processing by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the natural language processing unit's AI can reflect information related to that region in the natural language processing. Furthermore, if the caller calls from overseas, the natural language processing unit's AI can also reflect information related to that country in the natural language processing. Furthermore, if the caller calls from a specific city, the natural language processing unit's AI can also reflect information related to that city in the natural language processing. This enables natural language processing based on the caller's geographical information, resulting in more accurate processing.

[0168] During natural language processing, the natural language processing unit can analyze the sender's social media activity and reflect related information in the processing. For example, if the sender posts about a specific issue on social media, the natural language processing unit's AI can reflect information related to that issue in the natural language processing. Furthermore, if the sender is participating in a specific event on social media, the natural language processing unit's AI can reflect information related to that event in the natural language processing. Furthermore, if the sender comments on a specific product on social media, the natural language processing unit's AI can reflect information related to that product in the natural language processing. This enables natural language processing based on the sender's social media activity, resulting in more personalized processing.

[0169] During natural language processing, the natural language processing unit can adjust the processing algorithm by reflecting the sender's past feedback. For example, if the sender has given favorable feedback to a specific processing algorithm in the past, the natural language processing unit allows the AI ​​to preferentially use that algorithm. Also, if the sender has been dissatisfied with a specific processing algorithm in the past, the natural language processing unit can also allow the AI ​​to avoid that algorithm. Also, if the sender has given neutral feedback to a specific processing algorithm in the past, the natural language processing unit can also allow the AI ​​to use that algorithm in the normal order. This enables natural language processing based on past feedback, improving sender satisfaction.

[0170] The database management unit can estimate the sender's emotions and adjust the database structure based on the estimated sender's emotions. For example, if the sender is angry, the AI ​​in the database management unit can create a detailed database structure to accurately grasp the sender's requirements. If the sender is nervous, the AI ​​can create a database structure in a gentle tone to relax the sender. If the sender is relaxed, the AI ​​can create a database structure in a normal manner. This makes it possible to adjust the database structure according to the sender's emotions and accurately grasp the sender's requirements. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0171] When managing the database, the database management unit can optimize the database by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the database management unit will update the database with information related to that problem. Also, if a caller has inquired about a specific product in the past, the database management unit can update the database with information related to that product. Also, if a caller has inquired about a specific service in the past, the database management unit can update the database with information related to that service. This makes it possible to optimize the database based on the call content in the past, allowing for a more accurate understanding of the caller's requirements.

[0172] When managing the database, the database management unit can customize the database structure by taking into account the sender's attribute information. For example, if the sender is a company representative, the database management unit can have the AI ​​create a database structure related to the business. Also, if the sender is an individual, the database management unit can have the AI ​​create a database structure related to the individual. Also, if the sender belongs to a specific industry, the database management unit can have the AI ​​create a database structure related to that industry. This makes it possible to customize the database structure based on the sender's attribute information, resulting in more appropriate database management.

[0173] The database management unit can estimate the sender's emotions and determine the priority of databases based on the estimated sender's emotions. For example, if the sender is very angry, the database management unit allows the AI ​​to process that database as a top priority. Also, if the sender has an urgent requirement, the database management unit can also allow the AI ​​to process that database as a priority. Also, if the sender is relaxed, the database management unit can allow the AI ​​to process the database with normal priority. This enables database management based on the priority according to the sender's emotions, allowing important requirements to be processed preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0174] When managing the database, the database management unit can adjust the structure of the database by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the database management unit causes the AI ​​to update the database with information related to that region. In addition, if the caller calls from overseas, the database management unit can also cause the AI ​​to update the database with information related to that country. In addition, if the caller calls from a specific city, the database management unit can also update the database with information related to that city. This makes it possible to adjust the database structure based on the caller's geographical information, resulting in more appropriate database management.

[0175] During database management, the database management unit can analyze the sender's social media activity and reflect related information in the database. For example, if the sender posts about a specific issue on social media, the database management unit can reflect information related to that issue in the database using the AI. In addition, if the sender is participating in a specific event on social media, the database management unit can also reflect information related to that event in the database using the AI. In addition, if the sender comments on a specific product on social media, the database management unit can also reflect information related to that product in the database using the AI. This enables database management based on the sender's social media activity, resulting in more personalized database management.

[0176] The notification management unit can estimate the caller's emotions and adjust the notification method based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​in the notification management unit can quickly notify the person in charge. If the caller is nervous, the AI ​​can also notify the caller in a gentle tone. If the caller is relaxed, the AI ​​can also notify the caller in a normal manner. This makes it possible to adjust the notification method according to the caller's emotions and accurately grasp the caller's requirements. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0177] When managing notifications, the notification management unit can optimize the notification method by referring to the caller's past call content. For example, if a caller has inquired about a specific problem in the past, the notification management unit will have the AI ​​reflect information related to that problem in the notification. Also, if a caller has inquired about a specific product in the past, the notification management unit can also reflect information related to that product in the notification. Also, if a caller has inquired about a specific service in the past, the AI ​​can also reflect information related to that service in the notification. This makes it possible to optimize the notification method based on the call content in the past, allowing for a more accurate understanding of the caller's requirements.

[0178] When managing notifications, the notification management unit can customize the notification method by taking into account the sender's attribute information. For example, if the sender is a company representative, the notification management unit will have the AI ​​notify the sender of business-related information. Also, if the sender is an individual, the notification management unit can have the AI ​​notify the sender of information related to the individual. Also, if the sender belongs to a specific industry, the notification management unit can have the AI ​​notify the sender of information related to that industry. This makes it possible to customize the notification method based on the sender's attribute information, resulting in more appropriate notifications.

[0179] When managing notifications, the notification management unit can weight notifications based on the caller's response history. For example, if a caller has previously provided a detailed response about a specific issue, the notification management unit can weight that response and send a notification using the AI. Also, if a caller has previously provided a detailed response about a specific product, the notification management unit can weight that response and send a notification using the AI. Also, if a caller has previously provided a detailed response about a specific service, the notification management unit can weight that response and send a notification using the AI. This makes it possible to send notifications based on the caller's response history, resulting in more accurate notifications.

[0180] The notification management unit can estimate the sender's emotions and determine the priority of notifications based on the estimated emotions of the sender. For example, if the sender is very angry, the notification management unit allows the AI ​​to process that notification as a top priority. Also, if the sender has an urgent request, the notification management unit can also allow the AI ​​to process that notification as a priority. Also, if the sender is relaxed, the notification management unit can allow the AI ​​to send notifications with normal priority. This makes it possible to prioritize notifications according to the sender's emotions, allowing important requests to be notified first. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0181] When managing notifications, the notification management unit can adjust the notification method by taking into account the caller's geographical information. For example, if the caller calls from a specific region, the notification management unit will have the AI ​​reflect information related to that region in the notification. Also, if the caller calls from overseas, the notification management unit can have the AI ​​reflect information related to that country in the notification. Also, if the caller calls from a specific city, the notification management unit can have the AI ​​reflect information related to that city in the notification. This makes it possible to adjust the notification method based on the caller's geographical information, resulting in more appropriate notifications.

[0182] When managing notifications, the notification management unit can analyze the sender's social media activity and reflect relevant information in the notification. For example, if the sender posts about a specific issue on social media, the notification management unit's AI can reflect information related to that issue in the notification. Also, if the sender is participating in a specific event on social media, the notification management unit's AI can reflect information related to that event in the notification. Also, if the sender comments on a specific product on social media, the notification management unit's AI can reflect information related to that product in the notification. This makes it possible to provide notifications based on the sender's social media activity, resulting in more personalized notifications.

[0183] The notification management unit can customize the notification method by reflecting the sender's past feedback when managing notifications. For example, if the sender has given favorable feedback about a specific notification method in the past, the notification management unit can cause the AI ​​to use that method preferentially. Also, if the sender has been dissatisfied with a specific notification method in the past, the notification management unit can cause the AI ​​to avoid that method. Also, if the sender has given neutral feedback about a specific notification method in the past, the notification management unit can cause the AI ​​to use that method in the normal order. This makes it possible to provide notifications based on past feedback, improving the sender's satisfaction. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, question unit, analysis unit, recording unit, storage unit, notification unit, voice recognition unit, natural language processing unit, database management unit, and notification management unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives an incoming call. The question unit is realized by the control unit 46A of the smart device 14 and elicits the caller's requirements. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The recording unit is realized by the specific processing unit 290 of the data processing device 12 and records the analyzed requirements. The storage unit saves the requirements in the database 24 of the data processing device 12. The notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies the person in charge of the saved requirements. The voice recognition unit is realized by the control unit 46A of the smart device 14 and recognizes the caller's voice. The natural language processing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The database management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the structure of the database. The notification management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the notification method. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, question unit, analysis unit, recording unit, storage unit, notification unit, voice recognition unit, natural language processing unit, database management unit, and notification management unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives an incoming call. The question unit is realized by the control unit 46A of the smart glasses 214 and elicits the caller's requirements. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The recording unit is realized by the specific processing unit 290 of the data processing device 12 and records the analyzed requirements. The storage unit saves the requirements in the database 24 of the data processing device 12. The notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies the person in charge of the saved requirements. The voice recognition unit is realized by the control unit 46A of the smart glasses 214 and recognizes the caller's voice. The natural language processing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The database management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the structure of the database. The notification management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the notification method. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, question unit, analysis unit, recording unit, storage unit, notification unit, voice recognition unit, natural language processing unit, database management unit, and notification management unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives an incoming call. The question unit is realized by the control unit 46A of the headset type terminal 314 and elicits the caller's requirements. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The recording unit is realized by the specific processing unit 290 of the data processing device 12 and records the analyzed requirements. The storage unit saves the requirements in the database 24 of the data processing device 12. The notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies the person in charge of the saved requirements. The voice recognition unit is realized by the control unit 46A of the headset type terminal 314 and recognizes the caller's voice. The natural language processing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The database management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the structure of the database. The notification management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the notification method. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, question unit, analysis unit, recording unit, storage unit, notification unit, voice recognition unit, natural language processing unit, database management unit, and notification management unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives an incoming call. The question unit is realized by the control unit 46A of the robot 414 and elicits the caller's requirements. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The recording unit is realized by the specific processing unit 290 of the data processing device 12 and records the analyzed requirements. The storage unit saves the requirements in the database 24 of the data processing device 12. The notification unit is realized by the specific processing unit 290 of the data processing device 12 and notifies the person in charge of the saved requirements. The voice recognition unit is realized by the control unit 46A of the robot 414 and recognizes the caller's voice. The natural language processing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the caller's response. The database management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the structure of the database. The notification management unit is realized by the specific processing unit 290 of the data processing device 12 and manages the notification method.

[0184] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0185] The reception unit can estimate the caller's stress level by analyzing the caller's tone of voice and speaking style. For example, if the caller's voice is trembling, the AI ​​will determine that the caller is nervous and respond in a gentle tone. Alternatively, if the caller's voice is getting higher, the AI ​​can determine that the caller is excited and respond in a calm tone. Furthermore, if the caller's voice is getting lower, the AI ​​can determine that the caller is calm and respond in a normal tone. This makes it possible to respond according to the caller's stress level, improving caller satisfaction.

[0186] The questioning section can dynamically generate the next question based on the caller's response. For example, if the caller responds, "Regarding returning a product," the AI ​​can generate a related question such as, "Can you tell me the reason for the return?". If the caller responds, "I need technical support," the AI ​​can also generate a question such as, "What specific problem are you experiencing?". Furthermore, if the caller responds, "I would like to know about a new product," the AI ​​can generate a question such as, "Which product would you like to know about?" This makes it possible to ask questions based on the caller's response, resulting in smoother conversations.

[0187] The analysis unit can estimate the caller's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the caller is angry, the AI ​​will perform a detailed analysis to accurately grasp the caller's requirements. If the caller is nervous, the AI ​​can analyze using a gentler tone to relax the caller. If the caller is relaxed, the AI ​​can perform the analysis with normal accuracy. This makes it possible to perform an analysis according to the caller's emotions and accurately grasp the caller's requirements.

[0188] The recording unit can improve the accuracy of recording by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can reflect information related to that problem in the record. Also, if a caller has previously inquired about a specific product, the AI ​​can reflect information related to that product in the record. Also, if a caller has previously inquired about a specific service, the AI ​​can reflect information related to that service in the record. This makes it possible to record based on past call content, allowing for a more accurate understanding of the caller's requirements.

[0189] The notification unit can estimate the caller's emotions and adjust the notification method based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​will quickly notify the person in charge. If the caller is nervous, the AI ​​can notify in a gentle tone. If the caller is relaxed, the AI ​​can notify in a normal manner. This makes it possible to notify according to the caller's emotions and accurately grasp the caller's requirements.

[0190] The speech recognition unit can improve the accuracy of recognition by referring to the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can incorporate information related to that problem into the speech recognition. Also, if a caller has previously inquired about a specific product, the AI ​​can incorporate information related to that product into the speech recognition. Also, if a caller has previously inquired about a specific service, the AI ​​can incorporate information related to that service into the speech recognition. This makes it possible to recognize speech based on the content of past calls, allowing for a more accurate understanding of the caller's requirements.

[0191] The natural language processing unit can estimate the caller's emotions and adjust the accuracy of natural language processing based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​will perform detailed natural language processing to accurately grasp the caller's requirements. Alternatively, if the caller is nervous, the AI ​​can perform natural language processing in a gentle tone to relax the caller. Alternatively, if the caller is relaxed, the AI ​​can perform natural language processing with normal accuracy. This makes it possible to perform natural language processing according to the caller's emotions and accurately grasp the caller's requirements.

[0192] The database management unit can optimize the database by referencing the caller's past call content. For example, if a caller has previously inquired about a specific problem, the AI ​​can update the database with information related to that problem. Also, if a caller has previously inquired about a specific product, the AI ​​can update the database with information related to that product. Also, if a caller has previously inquired about a specific service, the AI ​​can update the database with information related to that service. This makes it possible to optimize the database based on past call content, allowing for a more accurate understanding of caller requirements.

[0193] The notification management unit can estimate the caller's emotions and adjust the notification method based on the estimated caller's emotions. For example, if the caller is angry, the AI ​​will quickly notify the person in charge. If the caller is nervous, the AI ​​can notify in a gentle tone. If the caller is relaxed, the AI ​​can notify in a normal manner. This makes it possible to adjust the notification method according to the caller's emotions, allowing the caller's requirements to be accurately understood.

[0194] The reception unit can acquire the caller's geographical information and provide a greeting appropriate to the region. For example, if the caller calls from Tokyo, the reception unit can greet the caller with "Hello, you're calling from Tokyo." If the caller calls from Osaka, the reception unit can greet the caller with "Hello, you're calling from Osaka." If the caller calls from overseas, the reception unit can greet the caller with "Hello, thank you for calling from overseas." This makes it possible to provide a greeting appropriate to the caller's geographical information, resulting in a friendly response to the caller.

[0195] The processing flow of the second embodiment will be briefly explained below.

[0196] Step 1: The reception unit receives an incoming call. For example, it can receive an incoming call from a landline phone, a mobile phone, an IP phone, etc. Step 2: The inquiry department asks the caller about their needs after the call is received by the reception department. For example, they ask questions such as, "What is your business?" and "Can I have your name and contact information?" Step 3: The analysis unit analyzes the caller's response obtained by the question unit, for example, by using text analysis or voice analysis to understand the caller's requirements. Step 4: The recording unit records the requirements analyzed by the analysis unit, such as the sender's name, contact information, and requirements content in text format. Step 5: The storage unit stores the requirements recorded by the recording unit in a database, such as a relational database or a NoSQL database. Step 6: The notification unit notifies the person in charge of the requirements stored by the storage unit, for example, by email or SMS.

[0197] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0198] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0199] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0200] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0201] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0202] 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.

[0203] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0204] 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.

[0205] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0207] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0208] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0209] 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.

[0210] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0211] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0212] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0213] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0214] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0215] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0216] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0217] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0218] 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.

[0219] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0220] 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.

[0221] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0223] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0224] 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.

[0225] 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.

[0226] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0227] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0228] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0229] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0230] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0231] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0232] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0233] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0234] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0235] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0236] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0237] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0239] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0240] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0241] 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.

[0242] 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.

[0243] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0244] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0245] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0246] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0247] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0248] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0249] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0250] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0251] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0252] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0253] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0254] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0255] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0256] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0257] 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.

[0258] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0259] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0260] 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.

[0261] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0262] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0263] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0264] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0265] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0266] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0267] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0268] [Explanation of symbols]

[0269] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives incoming calls; a questioning unit that asks for requirements of a caller from a call accepted by the accepting unit; an analysis unit that analyzes the answer of the sender obtained by the question unit; a recording unit that records the requirements analyzed by the analysis unit; a storage unit that stores the requirements recorded by the recording unit in a database; a notification unit that notifies a person in charge of the requirements stored by the storage unit. A system characterized by:

2. Equipped with a voice recognition unit that uses voice recognition technology 2. The system of claim 1.

3. Equipped with a natural language processing unit that uses natural language processing technology 2. The system of claim 1.

4. Equipped with a database management section that manages the database structure 2. The system of claim 1.

5. Equipped with a notification management unit that manages notification methods 2. The system of claim 1.

6. The reception unit Estimate the caller's sentiment and adjust the tone of the response based on the estimated sentiment 2. The system of claim 1.

7. The reception unit Refer to the caller's past call history to determine the best way to respond 2. The system of claim 1.

8. The reception unit Get the caller's geographical information and greet them locally 2. The system of claim 1.

9. The reception unit Customize your response based on the time of day the caller is calling 2. The system of claim 1.

Images