system

Abstract

The system according to this embodiment aims to efficiently manage incoming call content and automatically reject unwanted solicitations and scams. [Solution] The system according to the embodiment comprises a questioning unit, a text conversion unit, a storage unit, and a rejection unit. The questioning unit extracts the content of the request in response to an incoming call. The text conversion unit converts the content extracted by the questioning unit into text. The storage unit saves the content converted into text by the text conversion unit as text in a messaging app or SMS. The rejection unit automatically rejects solicitations and scams based on the user's persona.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that incoming content could not be efficiently managed and unwanted solicitations and frauds could not be automatically rejected.

[0005] The system according to the embodiment aims to efficiently manage incoming content and automatically reject unwanted solicitations and frauds.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a questioning unit, a text conversion unit, a storage unit, and a rejection unit. The questioning unit extracts the content of the request in response to an incoming call. The text conversion unit converts the content extracted by the questioning unit into text. The storage unit saves the content converted into text by the text conversion unit as text in a messaging app or SMS. The rejection unit automatically rejects solicitations and scams based on the user's persona. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently manage incoming calls and automatically reject unwanted solicitations and scams. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An embodiment of the present invention provides a high-performance answering machine system as an option for voice services such as mobile devices. This high-performance answering machine system asks questions in response to incoming calls, such as the content of the call, further details about the content, whether a callback is expected, and contact information, to elicit the message the caller wants to convey. Next, it provides an automatic memo function by summarizing the content into text and saving it as a text message in a messaging app or SMS, eliminating the need to listen to voicemails. It also provides a function to automatically reject solicitations for products or religions, as well as scams, by allowing the user to set their own persona. For example, when an incoming call is received, the AI ​​automatically answers and asks about the content of the call. For example, it might ask, "What can I help you with?" Next, the AI ​​further details the content to elicit more information. For example, it might ask, "What exactly is the matter?" Furthermore, it asks whether a callback is expected and provides contact information. For example, it might ask, "Do you need a callback?" or "Please provide your contact information." The extracted information is summarized into text by the AI ​​and saved as a text message in a messaging app or SMS. This eliminates the need for the user to listen to voicemails. For example, messages such as "I'm calling about XX. What can I help you with?" or "I'll look into △△ and get back to you. Please call me back at XXX-XXXX-XXXX" are left as text. Users can also set up their own persona, and the system provides a function to automatically reject solicitations for products or religions, as well as scams. For example, in response to a solicitation like "Are you interested in XX?", it will automatically respond with "I'm not interested, so no thank you." Similarly, in response to a scam call like "It's me," it will automatically reject the call with "I don't have a son named Kenji. Goodbye." This system saves users the trouble of listening to voicemails and helps prevent them from becoming victims of solicitations and scams. For example, even if a call comes in while the user is out, the AI ​​will automatically answer, extract the necessary information, and leave it as text for later review. It can also automatically reject solicitation and scam calls, allowing for safe use. In this way, a high-performance voicemail system improves user convenience and helps prevent victims of solicitations and scams.

[0029] The high-performance answering machine system according to this embodiment comprises a questioning unit, a text conversion unit, a storage unit, and a rejection unit. The questioning unit extracts the content of the request in response to an incoming call. For example, when an incoming call is received, the questioning unit asks a question such as, "What can I help you with?" The questioning unit further probes the content to extract more detailed information. For example, it asks a question such as, "What exactly is the matter?" The questioning unit asks whether a callback is necessary and for contact information. For example, it asks a question such as, "Do you need me to call you back?" or "Could you please provide your contact information?" The text conversion unit converts the content extracted by the questioning unit into text. For example, the text conversion unit converts the extracted content into text using speech recognition technology. The text conversion unit can also convert the extracted content into natural-sounding sentences using generation AI. The storage unit saves the content converted into text by the text conversion unit as text for messaging apps or SMS. For example, the storage unit sends the converted text as a message for messaging apps or SMS. The storage unit can also save the converted text to cloud storage. The rejection unit automatically rejects solicitations and scams based on the user's persona. For example, in response to solicitations for products or religion, the rejection unit automatically responds with "I'm not interested, thank you." In response to a phone call from someone attempting a "It's me" scam, the rejection unit automatically rejects it with "I don't have a son named Kenji. Goodbye." As a result, the high-performance answering machine system according to this embodiment can extract the content of the request in response to an incoming call, transcribe it into text, save it, and automatically reject solicitations and scams.

[0030] The questioning unit extracts the details of the caller's request. For example, when a call comes in, the questioning unit will ask, "What can I help you with?" The questioning unit will then delve deeper into the content of the call to extract more detailed information. For example, it might ask, "What exactly is the matter?" The questioning unit will also ask whether a callback is necessary and for contact information. For example, it might ask, "Do you need me to call you back?" or "Could you please provide your contact information?" The questioning unit can use speech recognition technology to analyze the caller's responses in real time and automatically generate appropriate questions. For example, if the caller answers, "I have a product inquiry," the questioning unit will follow up with a more specific question such as, "Which product are you inquiring about?" Furthermore, the questioning unit can use natural language processing technology to accurately understand the caller's intent and ask appropriate follow-up questions. For example, if the caller answers, "I'd like to request a repair," the questioning unit will ask more detailed questions such as, "Which part needs repair?" or "How urgent is the repair?" This allows the questioning unit to efficiently extract necessary information from the caller and proceed smoothly with subsequent processing. Furthermore, the questioning function can prioritize certain questions based on user settings. For example, for business users, the questioning function can prioritize questions such as "Please tell me the company name and the name of the contact person." This allows the questioning function to respond flexibly to user needs, improving the overall usability of the system.

[0031] The text conversion unit converts the content elicited by the question unit into text. For example, the text conversion unit can use speech recognition technology to convert the elicited content into text. The text conversion unit can also use generative AI to convert the elicited content into natural-sounding sentences. Specifically, speech recognition technology analyzes the caller's voice in real time and converts it into text data. In this process, speech recognition technology considers background noise and the speaker's accent to achieve highly accurate text conversion. Furthermore, the generative AI converts the text data generated by speech recognition technology into grammatically correct and natural sentences. For example, if the caller says, "I'd like to confirm something about tomorrow's meeting," the generative AI can convert it into a natural sentence such as, "I'd like to confirm something about tomorrow's meeting; could you please give me the details?" This allows the text conversion unit to generate text data that accurately reflects the caller's intent, enabling smoother subsequent processing. Additionally, the text conversion unit can format the generated text data based on user settings. For example, business users can format the text data into email format and send it immediately. This allows the text conversion unit to respond flexibly to user needs, improving the overall usability of the system.

[0032] The storage unit saves the text converted by the text conversion unit as text in messaging apps or SMS. For example, the storage unit sends the converted text as a message in a messaging app or SMS. The storage unit can also save the converted text to cloud storage. Specifically, the storage unit converts the text data received from the text conversion unit into an appropriate format according to the user's specified contact method and sends it. For example, when using a messaging app, the storage unit converts the text data into the messaging app's message format and sends it to the specified contact. Similarly, when using SMS, it converts the text data into the SMS message format and sends it. The storage unit also saves the text data to cloud storage, making it accessible to the user at any time. Data stored in cloud storage is secure and encrypted to protect user privacy. Furthermore, the storage unit provides a search function for the stored data, allowing users to easily search past messages. For example, by entering specific keywords, users can quickly search and display related messages. This improves user convenience and ensures that important information is securely stored and quickly accessible when needed.

[0033] The rejection function automatically rejects solicitations and scams based on the user's persona. For example, it automatically responds to product or religious solicitations with "I'm not interested, thank you." It also automatically rejects phone calls from people trying to scam others by saying "I don't have a son named Kenji. Goodbye." Specifically, the rejection function analyzes the caller's statements in real time and automatically provides an appropriate response if there is a possibility of solicitation or fraud. For example, if the caller says "I'd like to introduce a new product," the rejection function automatically responds "I'm not interested, thank you." Also, if the caller says "This is my son, Kenji," the rejection function automatically rejects it by saying "I don't have a son named Kenji. Goodbye." The rejection function uses natural language processing technology to accurately understand the caller's statements and generate appropriate responses. Furthermore, the rejection function can provide customized responses to specific statements based on the user's settings. For example, if a user has set a specific response for a particular keyword, the rejection unit will respond based on that setting. This allows the rejection unit to respond flexibly to the user's needs and effectively protect the user from solicitations and scams. The rejection unit also records the response content so that the user can review it later. This allows the user to understand what kind of solicitations or scams they have encountered and take countermeasures as needed.

[0034] The questioning unit can generate additional questions to delve deeper into the requirements. For example, it might generate an additional question such as "What exactly are the requirements?" to explore the requirements further. It can also generate an additional question such as "Could you tell me more about that?" to elicit even more detailed information. The questioning unit can also dynamically generate additional questions based on the user's response. For example, if the user gives a vague answer, the questioning unit might generate an additional question such as "What exactly are the problems?" In this way, the questioning unit can elicit more detailed information by generating additional questions to explore the requirements further. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the user's response into a generating AI and have the generating AI perform the generation of additional questions.

[0035] The text conversion unit can save the extracted content as text for messaging apps or SMS. For example, the text conversion unit can send the extracted content as a message in a messaging app. The text conversion unit can also send the extracted content as an SMS message. The text conversion unit can also save the extracted content to cloud storage and send it later as a message in a messaging app or SMS. For example, the text conversion unit saves the extracted content to cloud storage and sends it as a message in a messaging app or SMS at a time specified by the user. This makes it easier for the user to review the extracted content later by saving it as text in a messaging app or SMS. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the extracted content into a generation AI and have the generation AI perform the generation of text for messaging apps or SMS.

[0036] The rejection unit can automatically reject calls based on a set persona. For example, it can automatically respond to product or religious solicitations with "I'm not interested, thank you." It can also automatically reject phone calls from "ore-ore" scammers with "I don't have a son named Kenji. Goodbye." The rejection unit can also detect specific keywords or phrases based on a user-set persona and automatically reject them. For example, if the rejection unit detects the keyword "ore-ore" scam, it will automatically generate a rejection response. In this way, the rejection unit can automatically reject calls based on a set persona, allowing users to avoid solicitation and fraudulent calls. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not. For example, the rejection unit can input the user's persona information into a generating AI and have the generating AI execute the rejection response.

[0037] The questioning unit can analyze past call history and generate optimal question patterns. For example, the questioning unit can generate optimal question patterns based on questions the user has frequently asked in the past. The questioning unit can also prioritize questions on specific topics based on the user's past call history. The questioning unit can also analyze the user's past call history and determine the most effective order of questions. In this way, the questioning unit can generate optimal question patterns by analyzing past call history. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input past call history data into a generating AI and have the generating AI perform the generation of optimal question patterns.

[0038] The questioning unit can dynamically change the order of questions and apply strategies to elicit more detailed information. For example, the questioning unit can dynamically change the next question in response to the user's response to elicit more detailed information. If the user gives an ambiguous answer, the questioning unit can also add specific questions to clarify the information. If the user provides important information, the questioning unit can also ask additional questions based on that information. In this way, the questioning unit can elicit more detailed information by dynamically changing the order of questions. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user response data into a generating AI and have the generating AI perform the dynamic change of the question order.

[0039] The questioning unit can customize the content of its questions by considering the background information of the person it is calling. For example, if the person it is calling is a business associate, it will ask business-related questions. If the person it is calling is family or a friend, it can also ask personal questions. If the person it is calling is someone it is meeting for the first time, it can ask general questions to build rapport. In this way, the questioning unit can provide more appropriate questions by considering the background information of the person it is calling. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the background information of the person it is calling into a generating AI and have the generating AI customize the content of the questions.

[0040] The questioning unit can adjust the difficulty of questions by referring to the caller's past response patterns. For example, if the caller has given detailed answers in the past, the questioning unit will ask detailed questions. If the caller has given concise answers in the past, the questioning unit can also ask concise questions. If the caller has given vague answers in the past, the questioning unit can also ask specific questions. In this way, the questioning unit can appropriately adjust the difficulty of questions by referring to the caller's past response patterns. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the caller's past response data into a generating AI and have the generating AI adjust the difficulty of the questions.

[0041] The text generation unit can adjust the level of detail in the text based on the importance of the call content. For example, the text generation unit will create detailed text for important call content. For general call content, the text generation unit can also create concise text. For urgent call content, the text generation unit can quickly create text that gets to the point. In this way, the text generation unit can generate text with an appropriate amount of information by adjusting the level of detail in the text based on the importance of the call content. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the text.

[0042] The text conversion unit can apply different text conversion algorithms depending on the category of the call content. For example, the text conversion unit applies a business-oriented text conversion algorithm for business-related call content. The text conversion unit can also apply a personal-oriented text conversion algorithm for personal call content. The text conversion unit can also apply an emergency-oriented text conversion algorithm for urgent call content. This allows the text conversion unit to generate more accurate text by applying the appropriate text conversion algorithm according to the category of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content category data into a generating AI and have the generating AI perform the application of the text conversion algorithm.

[0043] The text conversion unit can determine the priority of text based on the submission timing of the call content. For example, the text conversion unit prioritizes the conversion of urgent call content. It can also prioritize the conversion of important call content. It can also finalize the conversion of general call content. In this way, the text conversion unit can prioritize the conversion of important information by determining the priority of text based on the submission timing of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content submission timing data into a generating AI and have the generating AI perform the determination of text priority.

[0044] The text conversion unit can adjust the order of the text based on the relevance of the call content. For example, the text conversion unit may place important information first, followed by detailed information. It can also place urgent information first, followed by general information. It can also group highly relevant information together, followed by less relevant information. In this way, the text conversion unit can generate more understandable text by adjusting the order of the text based on the relevance of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input relevance data of the call content into a generating AI and have the generating AI perform the adjustment of the text order.

[0045] The storage unit can adjust the level of detail in saving based on the importance of the call content. For example, in the case of important call content, the storage unit will save detailed information. In the case of general call content, the storage unit can also save concise information. In the case of urgent call content, the storage unit can quickly save the main points. In this way, the storage unit can save an appropriate amount of information by adjusting the level of detail in saving based on the importance of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in saving.

[0046] The storage unit can apply different storage algorithms depending on the category of the call content. For example, the storage unit applies a business-oriented storage algorithm for business-related call content. The storage unit can also apply a personal-oriented storage algorithm for personal call content. The storage unit can also apply an emergency-oriented storage algorithm for urgent call content. This allows the storage unit to achieve more accurate storage by applying the appropriate storage algorithm according to the category of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input call content category data into a generating AI and have the generating AI perform the application of the storage algorithm.

[0047] The storage unit can determine the priority of saving based on when the call content was submitted. For example, the storage unit will prioritize saving urgent call content. The storage unit may also prioritize saving important call content. The storage unit may also save general call content last. In this way, the storage unit can prioritize saving important information by determining the priority of saving based on when the call content was submitted. Some or all of the above processing in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit can input call content submission time data into a generating AI and have the generating AI perform the determination of the saving priority.

[0048] The storage unit can adjust the order of saving based on the relevance of the call content. For example, the storage unit may save important information first, followed by detailed information. It may also save urgent information first, followed by general information. It may also save highly relevant information together, followed by less relevant information. This allows the storage unit to save data in a more understandable way by adjusting the order of saving based on the relevance of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit may input call content relevance data into a generating AI and have the generating AI perform the adjustment of the saving order.

[0049] The rejection unit can customize the rejection message by considering the caller's background information. For example, if the caller is a business associate, the rejection unit will provide a business-related rejection message. If the caller is family or a friend, the rejection unit can also provide a personal rejection message. If the caller is someone the user is speaking to for the first time, the rejection unit can provide a general rejection message. This allows the rejection unit to provide a more appropriate rejection message by considering the caller's background information. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not. For example, the rejection unit can input the caller's background information into a generating AI and have the generating AI customize the rejection message.

[0050] The rejection unit can adjust the difficulty of rejection by referring to the caller's past response patterns. For example, if the caller has given a detailed answer in the past, the rejection unit will provide a detailed rejection. If the caller has given a concise answer in the past, the rejection unit can also provide a concise rejection. If the caller has given an ambiguous answer in the past, the rejection unit can also provide a specific rejection. In this way, the rejection unit can appropriately adjust the difficulty of rejection by referring to the caller's past response patterns. Some or all of the above processing in the rejection unit may be performed using AI, for example, or without AI. For example, the rejection unit can input the caller's past response data into a generating AI and have the generating AI perform the adjustment of the difficulty of rejection.

[0051] The rejection unit can customize the rejection message by considering the caller's geographical location. For example, if the caller is nearby, the rejection unit can provide a region-specific rejection message. If the caller is far away, the rejection unit can also provide a general rejection message. If the caller is in a specific region, the rejection unit can also provide a region-specific rejection message. This allows the rejection unit to provide a more appropriate rejection message by considering the caller's geographical location. Some or all of the above processing in the rejection unit may be performed using AI, for example, or without AI. For example, the rejection unit can input the caller's geographical location information into a generating AI and have the generating AI customize the rejection message.

[0052] The rejection unit can improve the accuracy of its rejections by referring to relevant literature related to the caller. For example, if the caller is a business contact, the rejection unit can refer to business-related literature to provide rejection content. If the caller is a family member or friend, the rejection unit can also refer to personal literature to provide rejection content. If the caller is someone the user is meeting for the first time, the rejection unit can also refer to general literature to provide rejection content. In this way, the rejection unit can improve the accuracy of its rejections by referring to relevant literature related to the caller. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not using AI. For example, the rejection unit can input the caller's relevant literature data into a generating AI and have the generating AI perform the task of improving the accuracy of the rejection content.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The questioning unit can analyze past call history and generate optimal question patterns. For example, it can generate optimal question patterns based on questions the user has frequently asked in the past. It can also prioritize questions on specific topics based on the user's past call history. It can also analyze the user's past call history and determine the most effective order of questions. In this way, the questioning unit can generate optimal question patterns by analyzing past call history. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input past call history data into a generating AI and have the generating AI perform the generation of optimal question patterns.

[0055] The questioning unit can dynamically change the order of questions and apply strategies to elicit more detailed information. For example, it can dynamically change the next question based on the user's response to elicit more detailed information. If the user gives an ambiguous answer, it can also add specific questions to clarify the information. If the user provides important information, it can also ask additional questions based on that information. In this way, the questioning unit can elicit more detailed information by dynamically changing the order of questions. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user response data into a generating AI and have the generating AI perform the dynamic change of the question order.

[0056] The questioning unit can customize the questions by considering the background information of the person being called. For example, if the person being called is a business associate, it will ask business-related questions. If the person being called is family or a friend, it can also ask personal questions. If the person being called is someone you are meeting for the first time, it can ask general questions to build rapport. In this way, the questioning unit can provide more appropriate questions by considering the background information of the person being called. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the background information of the person being called into a generating AI and have the generating AI perform the customization of the questions.

[0057] The text generation unit can adjust the level of detail in the text based on the importance of the call content. For example, it can create detailed text for important call content, concise text for general call content, and quick, concise text for urgent call content. This allows the text generation unit to generate text with an appropriate amount of information by adjusting the level of detail based on the importance of the call content. Some or all of the above-described processes in the text generation unit may be performed using AI, for example, or without AI. For example, the text generation unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the text detail.

[0058] The text conversion unit can apply different text conversion algorithms depending on the category of the call content. For example, for business-related calls, a business text conversion algorithm can be applied. For personal calls, a personal text conversion algorithm can also be applied. For urgent calls, an emergency text conversion algorithm can also be applied. This allows the text conversion unit to generate more accurate text by applying the appropriate text conversion algorithm according to the category of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the category data of the call content into a generating AI and have the generating AI perform the application of the text conversion algorithm.

[0059] The text conversion unit can determine the priority of text based on when the call content was submitted. For example, urgent call content can be prioritized for text conversion. Important call content can be prioritized for text conversion. General call content can be prioritized for text conversion. In this way, the text conversion unit can prioritize the text conversion of important information by determining the priority of text based on when the call content was submitted. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content submission timing data into a generating AI and have the generating AI perform the determination of text priority.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The questioning section extracts details of the caller's request. For example, when a call comes in, ask "What can I help you with?" and then follow up with a more detailed question such as "What exactly is the matter?". They also ask questions to inquire about whether the caller will return the call and to get contact information. Step 2: The text conversion unit converts the content extracted by the question unit into text. For example, it is possible to convert the extracted content into text using speech recognition technology and then convert it into natural-sounding sentences using generative AI. Step 3: The saving unit saves the text converted by the text conversion unit as text in a messaging app or SMS. For example, the converted text can be sent as a message in a messaging app or SMS and saved to cloud storage. Step 4: The rejection unit automatically rejects solicitations and scams based on the user's persona. For example, it automatically responds to product or religious solicitations with "I'm not interested, thank you," and automatically rejects phone calls from "It's me" scammers with "I don't have a son named Kenji. Goodbye."

[0062] (Example of form 2) An embodiment of the present invention provides a high-performance answering machine system as an option for voice services such as mobile devices. This high-performance answering machine system asks questions in response to incoming calls, such as the content of the call, further details about the content, whether a callback is expected, and contact information, to elicit the message the caller wants to convey. Next, it provides an automatic memo function by summarizing the content into text and saving it as a text message in a messaging app or SMS, eliminating the need to listen to voicemails. It also provides a function to automatically reject solicitations for products or religions, as well as scams, by allowing the user to set their own persona. For example, when an incoming call is received, the AI ​​automatically answers and asks about the content of the call. For example, it might ask, "What can I help you with?" Next, the AI ​​further details the content to elicit more information. For example, it might ask, "What exactly is the matter?" Furthermore, it asks whether a callback is expected and provides contact information. For example, it might ask, "Do you need a callback?" or "Please provide your contact information." The extracted information is summarized into text by the AI ​​and saved as a text message in a messaging app or SMS. This eliminates the need for the user to listen to voicemails. For example, messages such as "I'm calling about XX. What can I help you with?" or "I'll look into △△ and get back to you. Please call me back at XXX-XXXX-XXXX" are left as text. Users can also set up their own persona, and the system provides a function to automatically reject solicitations for products or religions, as well as scams. For example, in response to a solicitation like "Are you interested in XX?", it will automatically respond with "I'm not interested, so no thank you." Similarly, in response to a scam call like "It's me," it will automatically reject the call with "I don't have a son named Kenji. Goodbye." This system saves users the trouble of listening to voicemails and helps prevent them from becoming victims of solicitations and scams. For example, even if a call comes in while the user is out, the AI ​​will automatically answer, extract the necessary information, and leave it as text for later review. It can also automatically reject solicitation and scam calls, allowing for safe use. In this way, a high-performance voicemail system improves user convenience and helps prevent victims of solicitations and scams.

[0063] The high-performance answering machine system according to this embodiment comprises a questioning unit, a text conversion unit, a storage unit, and a rejection unit. The questioning unit extracts the content of the request in response to an incoming call. For example, when an incoming call is received, the questioning unit asks a question such as, "What can I help you with?" The questioning unit further probes the content to extract more detailed information. For example, it asks a question such as, "What exactly is the matter?" The questioning unit asks whether a callback is necessary and for contact information. For example, it asks a question such as, "Do you need me to call you back?" or "Could you please provide your contact information?" The text conversion unit converts the content extracted by the questioning unit into text. For example, the text conversion unit converts the extracted content into text using speech recognition technology. The text conversion unit can also convert the extracted content into natural-sounding sentences using generation AI. The storage unit saves the content converted into text by the text conversion unit as text for messaging apps or SMS. For example, the storage unit sends the converted text as a message for messaging apps or SMS. The storage unit can also save the converted text to cloud storage. The rejection unit automatically rejects solicitations and scams based on the user's persona. For example, in response to solicitations for products or religion, the rejection unit automatically responds with "I'm not interested, thank you." In response to a phone call from someone attempting a "It's me" scam, the rejection unit automatically rejects it with "I don't have a son named Kenji. Goodbye." As a result, the high-performance answering machine system according to this embodiment can extract the content of the request in response to an incoming call, transcribe it into text, save it, and automatically reject solicitations and scams.

[0064] The questioning unit extracts the details of the caller's request. For example, when a call comes in, the questioning unit will ask, "What can I help you with?" The questioning unit will then delve deeper into the content of the call to extract more detailed information. For example, it might ask, "What exactly is the matter?" The questioning unit will also ask whether a callback is necessary and for contact information. For example, it might ask, "Do you need me to call you back?" or "Could you please provide your contact information?" The questioning unit can use speech recognition technology to analyze the caller's responses in real time and automatically generate appropriate questions. For example, if the caller answers, "I have a product inquiry," the questioning unit will follow up with a more specific question such as, "Which product are you inquiring about?" Furthermore, the questioning unit can use natural language processing technology to accurately understand the caller's intent and ask appropriate follow-up questions. For example, if the caller answers, "I'd like to request a repair," the questioning unit will ask more detailed questions such as, "Which part needs repair?" or "How urgent is the repair?" This allows the questioning unit to efficiently extract necessary information from the caller and proceed smoothly with subsequent processing. Furthermore, the questioning function can prioritize certain questions based on user settings. For example, for business users, the questioning function can prioritize questions such as "Please tell me the company name and the name of the contact person." This allows the questioning function to respond flexibly to user needs, improving the overall usability of the system.

[0065] The text conversion unit converts the content elicited by the question unit into text. For example, the text conversion unit can use speech recognition technology to convert the elicited content into text. The text conversion unit can also use generative AI to convert the elicited content into natural-sounding sentences. Specifically, speech recognition technology analyzes the caller's voice in real time and converts it into text data. In this process, speech recognition technology considers background noise and the speaker's accent to achieve highly accurate text conversion. Furthermore, the generative AI converts the text data generated by speech recognition technology into grammatically correct and natural sentences. For example, if the caller says, "I'd like to confirm something about tomorrow's meeting," the generative AI can convert it into a natural sentence such as, "I'd like to confirm something about tomorrow's meeting; could you please give me the details?" This allows the text conversion unit to generate text data that accurately reflects the caller's intent, enabling smoother subsequent processing. Additionally, the text conversion unit can format the generated text data based on user settings. For example, business users can format the text data into email format and send it immediately. This allows the text conversion unit to respond flexibly to user needs, improving the overall usability of the system.

[0066] The storage unit saves the text converted by the text conversion unit as text in messaging apps or SMS. For example, the storage unit sends the converted text as a message in a messaging app or SMS. The storage unit can also save the converted text to cloud storage. Specifically, the storage unit converts the text data received from the text conversion unit into an appropriate format according to the user's specified contact method and sends it. For example, when using a messaging app, the storage unit converts the text data into the messaging app's message format and sends it to the specified contact. Similarly, when using SMS, it converts the text data into the SMS message format and sends it. The storage unit also saves the text data to cloud storage, making it accessible to the user at any time. Data stored in cloud storage is secure and encrypted to protect user privacy. Furthermore, the storage unit provides a search function for the stored data, allowing users to easily search past messages. For example, by entering specific keywords, users can quickly search and display related messages. This improves user convenience and ensures that important information is securely stored and quickly accessible when needed.

[0067] The rejection function automatically rejects solicitations and scams based on the user's persona. For example, it automatically responds to product or religious solicitations with "I'm not interested, thank you." It also automatically rejects phone calls from people trying to scam others by saying "I don't have a son named Kenji. Goodbye." Specifically, the rejection function analyzes the caller's statements in real time and automatically provides an appropriate response if there is a possibility of solicitation or fraud. For example, if the caller says "I'd like to introduce a new product," the rejection function automatically responds "I'm not interested, thank you." Also, if the caller says "This is my son, Kenji," the rejection function automatically rejects it by saying "I don't have a son named Kenji. Goodbye." The rejection function uses natural language processing technology to accurately understand the caller's statements and generate appropriate responses. Furthermore, the rejection function can provide customized responses to specific statements based on the user's settings. For example, if a user has set a specific response for a particular keyword, the rejection unit will respond based on that setting. This allows the rejection unit to respond flexibly to the user's needs and effectively protect the user from solicitations and scams. The rejection unit also records the response content so that the user can review it later. This allows the user to understand what kind of solicitations or scams they have encountered and take countermeasures as needed.

[0068] The questioning unit can generate additional questions to delve deeper into the requirements. For example, it might generate an additional question such as "What exactly are the requirements?" to explore the requirements further. It can also generate an additional question such as "Could you tell me more about that?" to elicit even more detailed information. The questioning unit can also dynamically generate additional questions based on the user's response. For example, if the user gives a vague answer, the questioning unit might generate an additional question such as "What exactly are the problems?" In this way, the questioning unit can elicit more detailed information by generating additional questions to explore the requirements further. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the user's response into a generating AI and have the generating AI perform the generation of additional questions.

[0069] The text conversion unit can save the extracted content as text for messaging apps or SMS. For example, the text conversion unit can send the extracted content as a message in a messaging app. The text conversion unit can also send the extracted content as an SMS message. The text conversion unit can also save the extracted content to cloud storage and send it later as a message in a messaging app or SMS. For example, the text conversion unit saves the extracted content to cloud storage and sends it as a message in a messaging app or SMS at a time specified by the user. This makes it easier for the user to review the extracted content later by saving it as text in a messaging app or SMS. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the extracted content into a generation AI and have the generation AI perform the generation of text for messaging apps or SMS.

[0070] The rejection unit can automatically reject calls based on a set persona. For example, it can automatically respond to product or religious solicitations with "I'm not interested, thank you." It can also automatically reject phone calls from "ore-ore" scammers with "I don't have a son named Kenji. Goodbye." The rejection unit can also detect specific keywords or phrases based on a user-set persona and automatically reject them. For example, if the rejection unit detects the keyword "ore-ore" scam, it will automatically generate a rejection response. In this way, the rejection unit can automatically reject calls based on a set persona, allowing users to avoid solicitation and fraudulent calls. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not. For example, the rejection unit can input the user's persona information into a generating AI and have the generating AI execute the rejection response.

[0071] The questioning unit can estimate the user's emotions and adjust the tone and content of the questions based on the estimated emotions. For example, if the user is nervous, the questioning unit can ask questions in a gentle tone to help them relax. If the user is in a hurry, the questioning unit can ask concise and quick questions to save time. If the user is relaxed, the questioning unit can ask detailed questions to elicit more information. In this way, the questioning unit can ask more appropriate questions by adjusting the tone and content of the questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the questioning unit may be performed using AI, or not using AI. For example, the questioning unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0072] The questioning unit can analyze past call history and generate optimal question patterns. For example, the questioning unit can generate optimal question patterns based on questions the user has frequently asked in the past. The questioning unit can also prioritize questions on specific topics based on the user's past call history. The questioning unit can also analyze the user's past call history and determine the most effective order of questions. In this way, the questioning unit can generate optimal question patterns by analyzing past call history. Some or all of the above processing in the questioning unit may be performed using AI, for example, or without AI. For example, the questioning unit can input past call history data into a generating AI and have the generating AI perform the generation of optimal question patterns.

[0073] The questioning unit can dynamically change the order of questions and apply strategies to elicit more detailed information. For example, the questioning unit can dynamically change the next question in response to the user's response to elicit more detailed information. If the user gives an ambiguous answer, the questioning unit can also add specific questions to clarify the information. If the user provides important information, the questioning unit can also ask additional questions based on that information. In this way, the questioning unit can elicit more detailed information by dynamically changing the order of questions. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user response data into a generating AI and have the generating AI perform the dynamic change of the question order.

[0074] The questioning unit can estimate the user's emotions and prioritize questions based on those emotions. For example, if the user is nervous, the questioning unit can start with simple questions to help them relax. If the user is in a hurry, the questioning unit can also prioritize important questions. If the user is relaxed, the questioning unit can also prioritize detailed questions. This allows the questioning unit to ask more effective questions by prioritizing questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the questioning unit may be performed using AI or not. For example, the questioning unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0075] The questioning unit can customize the content of its questions by considering the background information of the person it is calling. For example, if the person it is calling is a business associate, it will ask business-related questions. If the person it is calling is family or a friend, it can also ask personal questions. If the person it is calling is someone it is meeting for the first time, it can ask general questions to build rapport. In this way, the questioning unit can provide more appropriate questions by considering the background information of the person it is calling. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the background information of the person it is calling into a generating AI and have the generating AI customize the content of the questions.

[0076] The questioning unit can adjust the difficulty of questions by referring to the caller's past response patterns. For example, if the caller has given detailed answers in the past, the questioning unit will ask detailed questions. If the caller has given concise answers in the past, the questioning unit can also ask concise questions. If the caller has given vague answers in the past, the questioning unit can also ask specific questions. In this way, the questioning unit can appropriately adjust the difficulty of questions by referring to the caller's past response patterns. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the caller's past response data into a generating AI and have the generating AI adjust the difficulty of the questions.

[0077] The text generation unit can estimate the user's emotions and adjust the text's expression based on the estimated emotions. For example, if the user is nervous, the text generation unit will create text using gentle language. If the user is in a hurry, the text generation unit can also create text using concise and quick language. If the user is relaxed, the text generation unit can also create text using detailed language. In this way, the text generation unit can generate more appropriate text by adjusting the text's expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generative AI. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0078] The text generation unit can adjust the level of detail in the text based on the importance of the call content. For example, the text generation unit will create detailed text for important call content. For general call content, the text generation unit can also create concise text. For urgent call content, the text generation unit can quickly create text that gets to the point. In this way, the text generation unit can generate text with an appropriate amount of information by adjusting the level of detail in the text based on the importance of the call content. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in the text.

[0079] The text conversion unit can apply different text conversion algorithms depending on the category of the call content. For example, the text conversion unit applies a business-oriented text conversion algorithm for business-related call content. The text conversion unit can also apply a personal-oriented text conversion algorithm for personal call content. The text conversion unit can also apply an emergency-oriented text conversion algorithm for urgent call content. This allows the text conversion unit to generate more accurate text by applying the appropriate text conversion algorithm according to the category of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content category data into a generating AI and have the generating AI perform the application of the text conversion algorithm.

[0080] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, the text generation unit can create a short, concise text. If the user is relaxed, the text generation unit can also create a longer text with detailed explanations. If the user is excited, the text generation unit can also create text with visually stimulating effects. In this way, the text generation unit can generate more appropriate text by adjusting the length of the text according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generative AI. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0081] The text conversion unit can determine the priority of text based on the submission timing of the call content. For example, the text conversion unit prioritizes the conversion of urgent call content. It can also prioritize the conversion of important call content. It can also finalize the conversion of general call content. In this way, the text conversion unit can prioritize the conversion of important information by determining the priority of text based on the submission timing of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content submission timing data into a generating AI and have the generating AI perform the determination of text priority.

[0082] The text conversion unit can adjust the order of the text based on the relevance of the call content. For example, the text conversion unit may place important information first, followed by detailed information. It can also place urgent information first, followed by general information. It can also group highly relevant information together, followed by less relevant information. In this way, the text conversion unit can generate more understandable text by adjusting the order of the text based on the relevance of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input relevance data of the call content into a generating AI and have the generating AI perform the adjustment of the text order.

[0083] The storage unit can estimate the user's emotions and adjust the format of the saved text based on the estimated emotions. For example, if the user is nervous, the storage unit may use a simple and highly legible format. If the user is relaxed, the storage unit may also use a format that includes detailed information. If the user is in a hurry, the storage unit may also use a concise and quickly understandable format. This allows the storage unit to save text in a more appropriate format by adjusting the format according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not using AI. For example, the storage unit may input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0084] The storage unit can adjust the level of detail in saving based on the importance of the call content. For example, in the case of important call content, the storage unit will save detailed information. In the case of general call content, the storage unit can also save concise information. In the case of urgent call content, the storage unit can quickly save the main points. In this way, the storage unit can save an appropriate amount of information by adjusting the level of detail in saving based on the importance of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the level of detail in saving.

[0085] The storage unit can apply different storage algorithms depending on the category of the call content. For example, the storage unit applies a business-oriented storage algorithm for business-related call content. The storage unit can also apply a personal-oriented storage algorithm for personal call content. The storage unit can also apply an emergency-oriented storage algorithm for urgent call content. This allows the storage unit to achieve more accurate storage by applying the appropriate storage algorithm according to the category of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit can input call content category data into a generating AI and have the generating AI perform the application of the storage algorithm.

[0086] The storage unit can estimate the user's emotions and determine the priority of text to save based on the estimated emotions. For example, if the user is nervous, the storage unit may prioritize saving important information. If the user is relaxed, the storage unit may also prioritize saving detailed information. If the user is in a hurry, the storage unit may also prioritize saving concise information. In this way, the storage unit can prioritize saving important information by determining the priority of text to save according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not using AI. For example, the storage unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0087] The storage unit can determine the priority of saving based on when the call content was submitted. For example, the storage unit will prioritize saving urgent call content. The storage unit may also prioritize saving important call content. The storage unit may also save general call content last. In this way, the storage unit can prioritize saving important information by determining the priority of saving based on when the call content was submitted. Some or all of the above processing in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit can input call content submission time data into a generating AI and have the generating AI perform the determination of the saving priority.

[0088] The storage unit can adjust the order of saving based on the relevance of the call content. For example, the storage unit may save important information first, followed by detailed information. It may also save urgent information first, followed by general information. It may also save highly relevant information together, followed by less relevant information. This allows the storage unit to save data in a more understandable way by adjusting the order of saving based on the relevance of the call content. Some or all of the above processing in the storage unit may be performed using AI, for example, or not using AI. For example, the storage unit may input call content relevance data into a generating AI and have the generating AI perform the adjustment of the saving order.

[0089] The rejection unit can estimate the user's emotions and adjust the way it expresses the rejection based on the estimated emotions. For example, if the user is nervous, the rejection unit may use gentle language to reject the request. If the user is relaxed, the rejection unit may use clear language to reject the request. If the user is in a hurry, the rejection unit may use concise language to reject the request. In this way, the rejection unit can make more appropriate rejections by adjusting the way it expresses the rejection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not using AI. For example, the rejection unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0090] The rejection unit can customize the rejection message by considering the caller's background information. For example, if the caller is a business associate, the rejection unit will provide a business-related rejection message. If the caller is family or a friend, the rejection unit can also provide a personal rejection message. If the caller is someone the user is speaking to for the first time, the rejection unit can provide a general rejection message. This allows the rejection unit to provide a more appropriate rejection message by considering the caller's background information. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not. For example, the rejection unit can input the caller's background information into a generating AI and have the generating AI customize the rejection message.

[0091] The rejection unit can adjust the difficulty of rejection by referring to the caller's past response patterns. For example, if the caller has given a detailed answer in the past, the rejection unit will provide a detailed rejection. If the caller has given a concise answer in the past, the rejection unit can also provide a concise rejection. If the caller has given an ambiguous answer in the past, the rejection unit can also provide a specific rejection. In this way, the rejection unit can appropriately adjust the difficulty of rejection by referring to the caller's past response patterns. Some or all of the above processing in the rejection unit may be performed using AI, for example, or without AI. For example, the rejection unit can input the caller's past response data into a generating AI and have the generating AI perform the adjustment of the difficulty of rejection.

[0092] The rejection unit can estimate the user's emotions and determine the priority of rejections based on the estimated emotions. For example, if the user is nervous, the rejection unit may prioritize important rejections. If the user is relaxed, the rejection unit may also prioritize detailed rejections. If the user is in a hurry, the rejection unit may also prioritize concise rejections. In this way, the rejection unit can prioritize important rejections by determining the priority of rejections according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the rejection unit may be performed using AI or not using AI. For example, the rejection unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0093] The rejection unit can customize the rejection message by considering the caller's geographical location. For example, if the caller is nearby, the rejection unit can provide a region-specific rejection message. If the caller is far away, the rejection unit can also provide a general rejection message. If the caller is in a specific region, the rejection unit can also provide a region-specific rejection message. This allows the rejection unit to provide a more appropriate rejection message by considering the caller's geographical location. Some or all of the above processing in the rejection unit may be performed using AI, for example, or without AI. For example, the rejection unit can input the caller's geographical location information into a generating AI and have the generating AI customize the rejection message.

[0094] The rejection unit can improve the accuracy of its rejections by referring to relevant literature related to the caller. For example, if the caller is a business contact, the rejection unit can refer to business-related literature to provide rejection content. If the caller is a family member or friend, the rejection unit can also refer to personal literature to provide rejection content. If the caller is someone the user is meeting for the first time, the rejection unit can also refer to general literature to provide rejection content. In this way, the rejection unit can improve the accuracy of its rejections by referring to relevant literature related to the caller. Some or all of the above processing in the rejection unit may be performed using AI, for example, or not using AI. For example, the rejection unit can input the caller's relevant literature data into a generating AI and have the generating AI perform the task of improving the accuracy of the rejection content.

[0095] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0096] The questioning unit can estimate the user's emotions and adjust the tone and content of the questions based on the estimated emotions. For example, if the user is nervous, the questions can be asked in a gentle tone to help them relax. If the user is in a hurry, the questions can be concise and quick to save time. If the user is relaxed, the questions can be asked in detail to elicit more information. In this way, the questioning unit can ask more appropriate questions by adjusting the tone and content of the questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0097] The questioning unit can analyze past call history and generate optimal question patterns. For example, it can generate optimal question patterns based on questions the user has frequently asked in the past. It can also prioritize questions on specific topics based on the user's past call history. It can also analyze the user's past call history and determine the most effective order of questions. In this way, the questioning unit can generate optimal question patterns by analyzing past call history. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input past call history data into a generating AI and have the generating AI perform the generation of optimal question patterns.

[0098] The questioning unit can dynamically change the order of questions and apply strategies to elicit more detailed information. For example, it can dynamically change the next question based on the user's response to elicit more detailed information. If the user gives an ambiguous answer, it can also add specific questions to clarify the information. If the user provides important information, it can also ask additional questions based on that information. In this way, the questioning unit can elicit more detailed information by dynamically changing the order of questions. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input user response data into a generating AI and have the generating AI perform the dynamic change of the question order.

[0099] The questioning unit can estimate the user's emotions and prioritize questions based on those emotions. For example, if the user is nervous, it can start with simple questions to help them relax. If the user is in a hurry, it can prioritize important questions. If the user is relaxed, it can prioritize detailed questions. This allows the questioning unit to ask more effective questions by prioritizing questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the questioning unit may be performed using AI or not. For example, the questioning unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0100] The questioning unit can customize the questions by considering the background information of the person being called. For example, if the person being called is a business associate, it will ask business-related questions. If the person being called is family or a friend, it can also ask personal questions. If the person being called is someone you are meeting for the first time, it can ask general questions to build rapport. In this way, the questioning unit can provide more appropriate questions by considering the background information of the person being called. Some or all of the above processing in the questioning unit may be performed using AI, for example, or not using AI. For example, the questioning unit can input the background information of the person being called into a generating AI and have the generating AI perform the customization of the questions.

[0101] The text generation unit can estimate the user's emotions and adjust the text's expression based on the estimated emotions. For example, if the user is nervous, it can create text using gentle language. If the user is in a hurry, it can also create text using concise and quick language. If the user is relaxed, it can also create text using detailed language. In this way, the text generation unit can generate more appropriate text by adjusting the text's expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generative AI. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0102] The text generation unit can adjust the level of detail in the text based on the importance of the call content. For example, it can create detailed text for important call content, concise text for general call content, and quick, concise text for urgent call content. This allows the text generation unit to generate text with an appropriate amount of information by adjusting the level of detail based on the importance of the call content. Some or all of the above-described processes in the text generation unit may be performed using AI, for example, or without AI. For example, the text generation unit can input call content importance data into a generating AI and have the generating AI perform the adjustment of the text detail.

[0103] The text conversion unit can apply different text conversion algorithms depending on the category of the call content. For example, for business-related calls, a business text conversion algorithm can be applied. For personal calls, a personal text conversion algorithm can also be applied. For urgent calls, an emergency text conversion algorithm can also be applied. This allows the text conversion unit to generate more accurate text by applying the appropriate text conversion algorithm according to the category of the call content. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input the category data of the call content into a generating AI and have the generating AI perform the application of the text conversion algorithm.

[0104] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, it can create a short, concise text. If the user is relaxed, it can create a longer text with detailed explanations. If the user is excited, it can create text with visually stimulating effects. In this way, the text generation unit can generate more appropriate text by adjusting the length of the text according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to these examples. Some or all of the above processing in the text generation unit may be performed using AI, for example, or not using AI. For example, the text generation unit can input the user's voice data into the generative AI and have the generative AI perform emotion estimation.

[0105] The text conversion unit can determine the priority of text based on when the call content was submitted. For example, urgent call content can be prioritized for text conversion. Important call content can be prioritized for text conversion. General call content can be prioritized for text conversion. In this way, the text conversion unit can prioritize the text conversion of important information by determining the priority of text based on when the call content was submitted. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without AI. For example, the text conversion unit can input call content submission timing data into a generating AI and have the generating AI perform the determination of text priority.

[0106] The following briefly describes the processing flow for example form 2.

[0107] Step 1: The questioning section extracts details of the caller's request. For example, when a call comes in, ask "What can I help you with?" and then follow up with a more detailed question such as "What exactly is the matter?". They also ask questions to inquire about whether the caller will return the call and to get contact information. Step 2: The text conversion unit converts the content extracted by the question unit into text. For example, it is possible to convert the extracted content into text using speech recognition technology and then convert it into natural-sounding sentences using generative AI. Step 3: The saving unit saves the text converted by the text conversion unit as text in a messaging app or SMS. For example, the converted text can be sent as a message in a messaging app or SMS and saved to cloud storage. Step 4: The rejection unit automatically rejects solicitations and scams based on the user's persona. For example, it automatically responds to product or religious solicitations with "I'm not interested, thank you," and automatically rejects phone calls from "It's me" scammers with "I don't have a son named Kenji. Goodbye."

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0110] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0111] Each of the multiple elements described above, including the questioning unit, text conversion unit, storage unit, and rejection unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the questioning unit is implemented by the control unit 46A of the smart device 14 and extracts the content of the request in response to an incoming call. The text conversion unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the extracted content into text. The storage unit is implemented by the control unit 46A of the smart device 14 and saves the textened content as text in a messaging app or SMS. The rejection unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically rejects solicitations and scams based on the user's persona. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0112] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0113] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0114] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0115] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0116] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0118] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0119] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0120] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0121] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0122] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0123] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0126] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the questioning unit, text conversion unit, storage unit, and rejection unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the questioning unit is implemented by the control unit 46A of the smart glasses 214 and extracts the content of the request in response to an incoming call. The text conversion unit is implemented by the identification processing unit 290 of the data processing device 12 and converts the extracted content into text. The storage unit is implemented by the control unit 46A of the smart glasses 214 and saves the textened content as text in a messaging app or SMS. The rejection unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically rejects solicitations and scams based on the user's persona. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0128] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0129] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the questioning unit, text conversion unit, storage unit, and rejection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the questioning unit is implemented by the control unit 46A of the headset terminal 314 and extracts the content of the request in response to an incoming call. The text conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the extracted content into text. The storage unit is implemented by the control unit 46A of the headset terminal 314 and saves the textened content as text in a messaging app or SMS. The rejection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically rejects solicitations and scams based on the user's persona. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0144] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0145] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0152] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the questioning unit, text conversion unit, storage unit, and rejection unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the questioning unit is implemented by the control unit 46A of the robot 414 and extracts the content of the request in response to an incoming call. The text conversion unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and converts the extracted content into text. The storage unit is implemented, for example, by the control unit 46A of the robot 414 and saves the textened content as text in a messaging app or SMS. The rejection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and automatically rejects solicitations and scams based on the user's persona. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0162] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0163] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0164] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0165] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0166] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0167] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0168] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0169] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0170] 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.

[0171] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0172] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0173] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0174] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0175] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0176] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0177] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0178] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0179] (Note 1) A questioning section to extract the content of the request in response to an incoming call, A text conversion unit that converts the content elicited by the aforementioned questioning unit into text, A storage unit that saves the content converted into text by the text conversion unit as text for messaging apps or SMS, It includes a rejection unit that automatically rejects solicitations and scams based on the user's persona. A system characterized by the following features. (Note 2) The aforementioned question section is, Generate additional questions to delve deeper into the requirements. The system described in Appendix 1, characterized by the features described herein. (Note 3) The text conversion unit, The extracted information is saved as text in a messaging app or SMS. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned rejection section is, Automatically rejects based on the configured persona. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned question section is, It estimates the user's emotions and adjusts the tone and content of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned question section is, Analyze past call history to generate optimal question patterns. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned question section is, Dynamically change the order of questions and apply strategies to elicit more detailed information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned question section is, The system estimates the user's emotions and prioritizes questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned question section is, Customize the questions based on the background information of the person you are talking to. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned question section is, Adjust the difficulty of the questions by referring to the caller's past response patterns. The system described in Appendix 1, characterized by the features described herein. (Note 11) The text conversion unit, It estimates the user's emotions and adjusts the way text is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The text conversion unit, Adjust the level of detail in the text based on the importance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The text conversion unit, Apply different text transcription algorithms depending on the category of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 14) The text conversion unit, It estimates the user's emotions and adjusts the length of the text based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The text conversion unit, Prioritize texts based on when the call transcripts were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The text conversion unit, Adjust the order of text based on the relevance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned storage unit is It estimates the user's sentiment and adjusts the format of the saved text based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned storage unit is Adjust the level of detail saved based on the importance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned storage unit is Apply different saving algorithms depending on the category of call content. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned storage unit is It estimates the user's emotions and determines the priority of text to save based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned storage unit is Prioritize saving call content based on when it was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned storage unit is Adjust the save order based on the relevance of the call content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned rejection section is, The system estimates the user's emotions and adjusts the way it rejects the user based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned rejection section is, Customize the rejection message by taking into account the background information of the person you are calling. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned rejection section is, The difficulty of rejecting a call is adjusted by referencing the caller's past response patterns. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned rejection section is, It estimates the user's emotions and determines the priority of rejections based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned rejection section is, Customize the rejection message based on the caller's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned rejection section is, Improve the accuracy of refusals by referring to relevant literature related to the person you are calling. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A questioning section to extract the content of the request in response to an incoming call, A text conversion unit that converts the content elicited by the aforementioned questioning unit into text, A storage unit that saves the content converted into text by the text conversion unit as text for messaging apps or SMS, It includes a rejection unit that automatically rejects solicitations and scams based on the user's persona. A system characterized by the following features.

2. The aforementioned question section is, Generate additional questions to delve deeper into the requirements. The system according to feature 1.

3. The text conversion unit, The extracted information is saved as text in a messaging app or SMS. The system according to feature 1.

4. The aforementioned rejection section is, Automatically rejects based on the configured persona. The system according to feature 1.

5. The aforementioned question section is, It estimates the user's emotions and adjusts the tone and content of questions based on those estimated emotions. The system according to feature 1.

6. The aforementioned question section is, Analyze past call history to generate optimal question patterns. The system according to feature 1.

7. The aforementioned question section is, Dynamically change the order of questions and apply strategies to elicit more detailed information. The system according to feature 1.

8. The aforementioned question section is, The system estimates the user's emotions and prioritizes questions based on those estimated emotions. The system according to feature 1.

9. The aforementioned question section is, Customize the questions based on the background information of the person you are talking to. The system according to feature 1.

10. The aforementioned question section is, Adjust the difficulty of the questions by referring to the caller's past response patterns. The system according to feature 1.

Images