System

Abstract

An object of the system according to the embodiment is to filter out nuisance calls and unauthorized calls and accept only authorized calls.SOLUTION: A system includes a response unit, a confirmation unit, a determination unit, and a ringing unit. The response unit automatically responds to an incoming call using the AI. The confirmation unit confirms the call content acquired by the response unit. The determination unit determines whether or not the call is a regular call based on the call content confirmed by the confirmation unit. The ringing unit rings the telephone when the determination unit determines that the call is a regular call.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to efficiently filter out nuisance and fraudulent calls, and being unable to accept only legitimate calls.

[0005] The system according to the embodiment aims to filter out nuisance calls and fraudulent calls and to accept only legitimate calls. [Means for solving the problem]

[0006] The system according to the embodiment includes a response unit, a confirmation unit, a determination unit, and a ringing unit. The response unit uses AI to automatically answer an incoming call. The confirmation unit checks the call content acquired by the response unit. The determination unit determines whether the call is legitimate based on the call content confirmed by the confirmation unit. The ringing unit rings the phone when the determination unit determines that the call is legitimate. [Effects of the Invention]

[0007] The system according to the embodiment can filter out nuisance calls and fraudulent calls and accept only legitimate calls. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The telephone answering system according to an embodiment of the present invention is a system that uses AI to function as a primary contact point for all telephone calls. When a call comes in, the AI ​​automatically answers the call, checks the content of the call, and only rings if it is determined to be a legitimate call. This allows the telephone answering system to block out nuisance calls and answer only necessary calls.

[0029] A telephone answering system according to an embodiment includes a response unit, a confirmation unit, a determination unit, and a ringing unit. The response unit automatically responds to an incoming call using an AI. For example, the AI ​​uses voice recognition technology to understand what the caller is saying and ask appropriate questions. For example, the AI ​​responds in the form of, "Hello, this is an automated answering system. Who is calling?" The confirmation unit checks the call content acquired by the response unit. For example, the AI ​​asks questions such as, "Who is calling?", "Who do you need?", and "Please tell us your business." to understand the call content in detail. The determination unit determines whether the call is legitimate based on the call content confirmed by the confirmation unit. For example, if the caller is a family member or acquaintance, or if the call is an important business call, the determination unit determines the call to be legitimate. Conversely, if the call is a nuisance sales call or is likely to be a fraudulent call, the determination unit does not determine the call to be legitimate. The ringing unit rings the phone when the determination unit determines the call to be legitimate. For example, the phone rings only if there is an important call from a family member or an important business call. As a result, the telephone answering system according to the embodiment can block out nuisance calls and answer only necessary calls. For example, it can protect the livelihood of grandparents in rural areas and block out nuisance sales calls to businesses.

[0030] The response unit can analyze the background sounds of the other party, determine the call environment, and adjust the tone of the response accordingly. For example, when the AI ​​answers a call, the response unit analyzes the background sounds of the other party and determines the call environment. For example, if the background sounds are quiet, the response will be in a normal tone. Also, if the AI ​​detects that the call is being made in a noisy place, it will respond in a clearer tone so that the other party can hear it more easily. Also, if it detects that the background sounds are in a specific environment (for example, inside a car or a cafe), it will respond appropriately to that environment. For example, if the call is made in a car, it will respond in a short, concise manner. This makes it possible to analyze the background sounds of the other party, determine the call environment, and change the tone of the response, thereby enabling a more appropriate response.

[0031] The response unit can refer to the other party's past call history and provide an individually customized response. For example, when the AI ​​answers a call, it refers to the other party's past call history and provides a customized response based on the content of the previous conversation. For example, it may revisit topics discussed in previous calls. It can also understand the other party's preferences and interests based on the past call history and provide a response accordingly. For example, if the other party is interested in a particular product, it can provide information about that product. It can also analyze the call history and follow up on any problems or questions the other party had previously. For example, it can check whether the previous problem has been resolved. This makes it possible to provide a more appropriate response by referring to the other party's past call history and providing an individually customized response.

[0032] The verification unit can analyze the characteristics of the other party's voice and perform voiceprint authentication to identify the other party's identity. For example, when verifying the contents of a call, the verification unit analyzes the characteristics of the other party's voice and performs voiceprint authentication. For example, the identity is verified by comparing it with a voiceprint database of the other party. Voiceprint authentication is also used to verify whether the other party is a registered user. For example, voiceprint data of family members and acquaintances is registered in advance. Voiceprint authentication is also performed at the beginning of the call to verify the other party's identity before verifying the contents of the call. For example, in the case of an important business call, the identity of the other party can be reliably verified. In this way, by analyzing the characteristics of the other party's voice and performing voiceprint authentication to verify the other party's identity, it is possible to verify the contents of the call with higher accuracy.

[0033] The confirmation unit can convert the contents of the call into text in real time, extract important keywords, and automatically classify the requirements. For example, the confirmation unit converts the contents of the call into text in real time and extracts important keywords. For example, it automatically detects keywords such as "urgent," "important," and "family." It also analyzes the converted text of the call and automatically classifies the requirements. For example, it classifies the requirements into business-related, family-related, emergency, etc. It also highlights important keywords based on the converted text of the call in real time, allowing the requirements to be quickly grasped. For example, if an urgent requirement is included, it is notified immediately. This makes it possible to convert the contents of the call into text in real time, extract important keywords, and automatically classify the requirements, thereby enabling more efficient confirmation of the call content.

[0034] The verification unit can automatically translate the contents of calls into multiple languages ​​and can also handle calls in different languages. The verification unit, for example, builds a system that automatically translates the contents of calls into multiple languages ​​in real time. For example, it translates from English to Japanese and from Japanese to English. It also develops a multilingual call verification system that can handle calls in different languages. For example, it translates French, Spanish, Chinese, etc. It also automatically translates the contents of calls to enable smooth communication between users who speak different languages. For example, it removes language barriers in international business calls. This allows the automatic translation of the contents of calls into multiple languages ​​and handles calls in different languages, making it possible to accommodate a wider range of users.

[0035] The confirmation unit may enable the content of a call to be confirmed not only by voice but also by text messages or a chatbot. The confirmation unit, for example, builds a system that enables the content of a call to be confirmed not only by voice but also by text messages. For example, the content of a call is converted into text in real time and confirmed through a chatbot. A system for checking the content of a call using text messages or a chatbot is also developed. For example, the content of a call is sent as a text message and confirmed. A system for checking the content of a call using both voice calls and text messages is also built. For example, the content of a call is saved as a text message and confirmed later. This allows the content of a call to be checked not only by voice but also by text messages or a chatbot, thereby providing more diverse methods of checking.

[0036] The judgment unit can refer to the other party's past call history or behavioral patterns to more accurately determine whether a call is legitimate. For example, when analyzing the content of a call, the judgment unit refers to the other party's past call history to determine whether a call is legitimate. For example, if the other party has been called many times in the past, it is determined to be a legitimate call. In addition, a system is constructed that analyzes behavioral patterns to determine whether a call is legitimate. For example, if the other party calls during a specific time period, the judgment is made based on that pattern. In addition, the past call history and behavioral patterns are analyzed comprehensively to determine whether a call is legitimate with high accuracy. For example, the judgment is made based on the frequency of calls and the content of the calls of the other party. In this way, by referring to the other party's past call history and behavioral patterns to more accurately determine whether a call is legitimate, the accuracy of detecting nuisance calls is improved.

[0037] The judgment unit analyzes the tone of the other party's voice or language to detect the possibility of a fraudulent or nuisance call with high accuracy. For example, when analyzing the content of a call, the judgment unit analyzes the tone of the other party's voice to detect the possibility of a fraudulent or nuisance call. For example, if the other party's voice sounds unnaturally calm, it determines that there is a high possibility of fraud. In addition, a system is constructed that analyzes language to detect the possibility of a fraudulent or nuisance call. For example, if a specific phrase or expression is frequently used, it determines that there is a high possibility of a nuisance call. In addition, both the tone of voice and language are analyzed to detect the possibility of a fraudulent or nuisance call with high accuracy. For example, if the other party uses language that sounds urgent, it determines that there is a high possibility of a fraud. In this way, by analyzing the tone of the other party's voice and language to detect the possibility of a fraudulent or nuisance call with high accuracy, the accuracy of nuisance call detection is improved.

[0038] The determination unit can evaluate the trustworthiness of the other party by referring to their social media or online profile. For example, when determining whether a call is legitimate, the determination unit may evaluate the trustworthiness of the other party by referring to their social media profile. For example, if the other party's social media account has been active for a long period of time, the determination unit may determine that the other party is highly trustworthy. In addition, a system may be constructed that analyzes online profiles and evaluates the trustworthiness of the other party. For example, the reliability may be determined based on the other party's professional background and recommendations. In addition, the information on social media and online profiles may be comprehensively analyzed to determine whether the call is legitimate. For example, the reliability may be evaluated based on the content of the other party's posts and the number of followers. In this way, by evaluating the reliability of the other party by referring to their social media or online profile, it is possible to more accurately determine whether the call is legitimate.

[0039] The determination unit can compare the contents of the other party's call with other databases and with a blacklist or whitelist. For example, when determining whether a call is legitimate, the determination unit compares the contents of the other party's call with a blacklist. For example, if the number has been registered as a nuisance call in the past, it is determined to be an illegitimate call. The determination unit also compares the contents of the other party's call with a whitelist to determine whether the other party is trustworthy. For example, if the number of a family member or acquaintance is registered on the whitelist, it is determined to be a legitimate call. The determination unit also refers to both the blacklist and the whitelist to comprehensively determine the contents of the other party's call. For example, if the number is not registered on the blacklist but also on the whitelist, additional checks are performed. In this way, by comparing the contents of the other party's call with other databases and with the blacklist or whitelist, it is possible to more accurately determine whether the call is legitimate.

[0040] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0041] The response unit can analyze the background sounds of the other party, determine the call environment, and adjust the tone of the response accordingly. For example, if the background sounds are quiet, it will respond in a normal tone. If it detects that the call is being made in a noisy place, the AI ​​will respond in a clearer tone to make it easier for the other party to hear. If it detects that the background sounds are from a specific environment (such as the inside of a car or a cafe), it will respond in a way that is appropriate for that environment. For example, if the call is being made in a car, it will respond in a short, concise manner. This allows the system to analyze the background sounds of the other party, determine the call environment, and change the tone of the response, enabling a more appropriate response.

[0042] The response unit can refer to the other party's past call history and provide an individually customized response. For example, when the AI ​​answers a call, it refers to the other party's past call history and provides a customized response based on the content of the previous conversation. For example, it may revisit topics discussed in previous calls. It can also understand the other party's preferences and interests based on the past call history and provide a response accordingly. For example, if the other party is interested in a particular product, it can provide information about that product. It can also analyze the call history and follow up on any problems or questions the other party had previously. For example, it can check whether the previous problem has been resolved. This makes it possible to provide a more appropriate response by referring to the other party's past call history and providing an individually customized response.

[0043] The verification unit can analyze the characteristics of the other party's voice and perform voiceprint authentication to identify the other party's identity. For example, when verifying the contents of a call, the characteristics of the other party's voice are analyzed and voiceprint authentication is performed. For example, the identity is verified by comparing it with a voiceprint database of the other party. Voiceprint authentication is also used to verify whether the other party is a registered user. For example, voiceprint data of family members and acquaintances is registered in advance. Voiceprint authentication is also performed at the beginning of the call to verify the other party's identity before verifying the contents of the call. For example, in the case of an important business call, the identity of the other party can be reliably verified. In this way, by analyzing the characteristics of the other party's voice and performing voiceprint authentication to verify the other party's identity, it is possible to verify the contents of the call with greater accuracy.

[0044] The confirmation unit can convert call content into text in real time, extract important keywords, and automatically classify requirements. For example, it converts call content into text in real time and extracts important keywords. For example, it automatically detects keywords such as "urgent," "important," and "family." It also analyzes the converted call content and automatically classifies requirements. For example, it classifies them into business-related, family-related, emergency, etc. It also highlights important keywords based on the call content converted into text in real time, allowing the system to quickly grasp requirements. For example, it immediately notifies the user if an urgent requirement is included. This makes it possible to more efficiently confirm call content by converting call content into text in real time, extracting important keywords, and automatically classifying requirements.

[0045] The verification unit can automatically translate the contents of calls into multiple languages ​​and can also handle calls in different languages. For example, a system can be built that automatically translates the contents of calls into multiple languages ​​in real time. For example, it can translate from English to Japanese and from Japanese to English. A multilingual call verification system can also be developed to handle calls in different languages. For example, it can translate French, Spanish, Chinese, etc. The contents of calls can also be automatically translated to enable smooth communication between users who speak different languages. For example, it can remove language barriers in international business calls. This allows the contents of calls to be automatically translated into multiple languages ​​and handle calls in different languages, making it possible to accommodate a wider range of users.

[0046] The processing flow of the first embodiment will be briefly explained below.

[0047] Step 1: In the response section, when a call comes in, the AI ​​automatically answers the call. For example, the AI ​​uses voice recognition technology to understand what the other person is saying and ask appropriate questions. For example, it might respond in the form of, "Hello, this is an automated response system. Who is calling?" Step 2: The confirmation unit checks the call content obtained by the response unit. For example, the AI ​​asks questions such as "Who is calling?", "Who do you need?", and "Please tell us your business" to understand the details of the call. Step 3: The judgment unit determines whether the call is legitimate based on the content of the call confirmed by the confirmation unit. For example, if the call is from a family member or acquaintance, or if it is an important business call, it is determined to be legitimate. Conversely, if there is a possibility of a nuisance sales call or fraud, it is not determined to be legitimate. Step 4: The ringing unit rings the phone if the judgment unit judges that the call is legitimate. For example, the phone rings only when there is an important message from a family member or an important business call.

[0048] (Example 2) The telephone answering system according to an embodiment of the present invention is a system that uses AI to function as a primary contact point for all telephone calls. When a call comes in, the AI ​​automatically answers the call, checks the content of the call, and only rings if it is determined to be a legitimate call. This allows the telephone answering system to block out nuisance calls and answer only necessary calls.

[0049] A telephone answering system according to an embodiment includes a response unit, a confirmation unit, a determination unit, and a ringing unit. The response unit automatically responds to an incoming call using an AI. For example, the AI ​​uses voice recognition technology to understand what the caller is saying and ask appropriate questions. For example, the AI ​​responds in the form of, "Hello, this is an automated answering system. Who is calling?" The confirmation unit checks the call content acquired by the response unit. For example, the AI ​​asks questions such as, "Who is calling?", "Who do you need?", and "Please tell us your business." to understand the call content in detail. The determination unit determines whether the call is legitimate based on the call content confirmed by the confirmation unit. For example, if the caller is a family member or acquaintance, or if the call is an important business call, the determination unit determines the call to be legitimate. Conversely, if the call is a nuisance sales call or is likely to be a fraudulent call, the determination unit does not determine the call to be legitimate. The ringing unit rings the phone when the determination unit determines the call to be legitimate. For example, the phone rings only if there is an important call from a family member or an important business call. As a result, the telephone answering system according to the embodiment can block out nuisance calls and answer only necessary calls. For example, it can protect the livelihood of grandparents in rural areas and block out nuisance sales calls to businesses.

[0050] The response unit can analyze the tone or speed of the other person's voice, determine the urgency or emotional state, and adjust the response accordingly. For example, when the AI ​​responds, the response unit analyzes the tone and speed of the other person's voice in real time to determine the urgency. For example, if the other person sounds urgent, it will respond to respond quickly. It also analyzes the tone of the other person's voice to infer their emotional state. For example, if the other person sounds angry, it will respond to respond calmly. It also analyzes the speed of the voice to determine whether the other person is impatient. For example, if the other person sounds impatient, it will respond to calm them down. This makes it possible to respond more appropriately by analyzing the tone and speed of the other person's voice, determining the urgency or emotional state, and adjusting the response accordingly.

[0051] The response unit can analyze the background sounds of the other party, determine the call environment, and adjust the tone of the response accordingly. For example, when the AI ​​answers a call, the response unit analyzes the background sounds of the other party and determines the call environment. For example, if the background sounds are quiet, the response will be in a normal tone. Also, if the AI ​​detects that the call is being made in a noisy place, it will respond in a clearer tone so that the other party can hear it more easily. Also, if it detects that the background sounds are in a specific environment (for example, inside a car or a cafe), it will respond appropriately to that environment. For example, if the call is made in a car, it will respond in a short, concise manner. This makes it possible to analyze the background sounds of the other party, determine the call environment, and change the tone of the response, thereby enabling a more appropriate response.

[0052] The response unit can use the emotion estimation function to estimate the emotional state of the other party and optimize the response content. For example, when the AI ​​responds, the response unit analyzes the tone and speed of the other party's voice and uses the emotion estimation function to estimate the other party's emotional state. For example, if the other party is impatient, it responds to calm them down. Also, if the other party is angry, it uses the emotion estimation function to respond calmly. For example, it selects words to soothe the other party's anger. Also, if the other party is sad, it uses the emotion estimation function to respond in a comforting way. For example, it selects words that are sympathetic to the other party's feelings. In this way, by using the emotion estimation function to estimate the other party's emotional state and adjusting the response content, it becomes possible to respond more appropriately.

[0053] The response unit can handle video calls and adjust the response by analyzing the other party's facial expressions or gestures. For example, the response unit uses AI to handle video calls and analyze the other party's facial expressions. For example, if the other party is smiling, it will respond in a friendly manner. It also uses gesture analysis to understand the other party's intentions. For example, if the other party is waving, it will respond as a greeting. It also analyzes both facial expressions and gestures to comprehensively judge the other party's emotional state. For example, if the other party looks troubled, it will respond by asking for help. This makes it possible to handle video calls and adjust the response by analyzing the other party's facial expressions and gestures, thereby enabling more appropriate responses.

[0054] The response unit can refer to the other party's past call history and provide an individually customized response. For example, when the AI ​​answers a call, it refers to the other party's past call history and provides a customized response based on the content of the previous conversation. For example, it may revisit topics discussed in previous calls. It can also understand the other party's preferences and interests based on the past call history and provide a response accordingly. For example, if the other party is interested in a particular product, it can provide information about that product. It can also analyze the call history and follow up on any problems or questions the other party had previously. For example, it can check whether the previous problem has been resolved. This makes it possible to provide a more appropriate response by referring to the other party's past call history and providing an individually customized response.

[0055] The response unit uses the emotion estimation function to generate a response that makes the other party feel positive emotions, making it possible to build a good relationship from the start of the call. The response unit, for example, uses the emotion estimation function to generate a response that makes the other party feel positive emotions. For example, calling the other party by name makes the other party feel familiar. The response unit also analyzes the other party's emotional state and generates a response that elicits positive emotions. For example, it provides topics related to the other party's hobbies and interests. The response at the start of the call makes the other party feel relaxed. For example, it starts the conversation with a light joke or greeting. In this way, the emotion estimation function can be used to generate a response that makes the other party feel positive emotions, building a good relationship from the start of the call, making it possible to provide a more appropriate response.

[0056] The verification unit can analyze the characteristics of the other party's voice and perform voiceprint authentication to identify the other party's identity. For example, when verifying the contents of a call, the verification unit analyzes the characteristics of the other party's voice and performs voiceprint authentication. For example, the identity is verified by comparing it with a voiceprint database of the other party. Voiceprint authentication is also used to verify whether the other party is a registered user. For example, voiceprint data of family members and acquaintances is registered in advance. Voiceprint authentication is also performed at the beginning of the call to verify the other party's identity before verifying the contents of the call. For example, in the case of an important business call, the identity of the other party can be reliably verified. In this way, by analyzing the characteristics of the other party's voice and performing voiceprint authentication to verify the other party's identity, it is possible to verify the contents of the call with higher accuracy.

[0057] The confirmation unit can convert the contents of the call into text in real time, extract important keywords, and automatically classify the requirements. For example, the confirmation unit converts the contents of the call into text in real time and extracts important keywords. For example, it automatically detects keywords such as "urgent," "important," and "family." It also analyzes the converted text of the call and automatically classifies the requirements. For example, it classifies the requirements into business-related, family-related, emergency, etc. It also highlights important keywords based on the converted text of the call in real time, allowing the requirements to be quickly grasped. For example, if an urgent requirement is included, it is notified immediately. This makes it possible to convert the contents of the call into text in real time, extract important keywords, and automatically classify the requirements, thereby enabling more efficient confirmation of the call content.

[0058] The confirmation unit can use the emotion estimation function to analyze the emotional state of the other party and provide an appropriate response method as a guideline. For example, when checking the contents of a call, the confirmation unit uses the emotion estimation function to analyze the emotional state of the other party. For example, if the other party is angry, guidelines for responding calmly are presented. Also, using the emotion estimation function, guidelines for comforting the other party are presented if the other party is sad. For example, words that are considerate of the other party's feelings are selected. Also, the confirmation unit analyzes the other party's emotional state and provides an appropriate response method as a guideline. For example, if the other party is impatient, a response to calm them down is made. In this way, by using the emotion estimation function to analyze the other party's emotional state and providing an appropriate response method as a guideline, a more appropriate response is possible.

[0059] The verification unit can automatically translate the contents of calls into multiple languages ​​and can also handle calls in different languages. The verification unit, for example, builds a system that automatically translates the contents of calls into multiple languages ​​in real time. For example, it translates from English to Japanese and from Japanese to English. It also develops a multilingual call verification system that can handle calls in different languages. For example, it translates French, Spanish, Chinese, etc. It also automatically translates the contents of calls to enable smooth communication between users who speak different languages. For example, it removes language barriers in international business calls. This allows the automatic translation of the contents of calls into multiple languages ​​and handles calls in different languages, making it possible to accommodate a wider range of users.

[0060] The confirmation unit may enable the content of a call to be confirmed not only by voice but also by text messages or a chatbot. The confirmation unit, for example, builds a system that enables the content of a call to be confirmed not only by voice but also by text messages. For example, the content of a call is converted into text in real time and confirmed through a chatbot. A system for checking the content of a call using text messages or a chatbot is also developed. For example, the content of a call is sent as a text message and confirmed. A system for checking the content of a call using both voice calls and text messages is also built. For example, the content of a call is saved as a text message and confirmed later. This allows the content of a call to be checked not only by voice but also by text messages or a chatbot, thereby providing more diverse methods of checking.

[0061] The confirmation unit uses the emotion estimation function to generate appropriate questions according to the emotional state of the other party, allowing for smooth confirmation of the call content. The confirmation unit, for example, uses the emotion estimation function to generate appropriate questions according to the emotional state of the other party. For example, if the other party is impatient, it asks questions to calm them down. Furthermore, a system is constructed that analyzes the emotional state of the other party and generates appropriate questions. For example, if the other party is angry, it asks questions to respond calmly. Furthermore, it uses the emotion estimation function to generate questions according to the emotional state of the other party in real time, allowing for smooth confirmation of the call content. For example, if the other party is sad, it asks questions to comfort them. In this way, by using the emotion estimation function to generate appropriate questions according to the emotional state of the other party and smoothly confirming the call content, more appropriate responses are possible.

[0062] The judgment unit can refer to the other party's past call history or behavioral patterns to more accurately determine whether a call is legitimate. For example, when analyzing the content of a call, the judgment unit refers to the other party's past call history to determine whether a call is legitimate. For example, if the other party has been called many times in the past, it is determined to be a legitimate call. In addition, a system is constructed that analyzes behavioral patterns to determine whether a call is legitimate. For example, if the other party calls during a specific time period, the judgment is made based on that pattern. In addition, the past call history and behavioral patterns are analyzed comprehensively to determine whether a call is legitimate with high accuracy. For example, the judgment is made based on the frequency of calls and the content of the calls of the other party. In this way, by referring to the other party's past call history and behavioral patterns to more accurately determine whether a call is legitimate, the accuracy of detecting nuisance calls is improved.

[0063] The judgment unit analyzes the tone of the other party's voice or language to detect the possibility of a fraudulent or nuisance call with high accuracy. For example, when analyzing the content of a call, the judgment unit analyzes the tone of the other party's voice to detect the possibility of a fraudulent or nuisance call. For example, if the other party's voice sounds unnaturally calm, it determines that there is a high possibility of fraud. In addition, a system is constructed that analyzes language to detect the possibility of a fraudulent or nuisance call. For example, if a specific phrase or expression is frequently used, it determines that there is a high possibility of a nuisance call. In addition, both the tone of voice and language are analyzed to detect the possibility of a fraudulent or nuisance call with high accuracy. For example, if the other party uses language that sounds urgent, it determines that there is a high possibility of a fraud. In this way, by analyzing the tone of the other party's voice and language to detect the possibility of a fraudulent or nuisance call with high accuracy, the accuracy of nuisance call detection is improved.

[0064] The judgment unit can use the emotion estimation function to analyze the emotional state of the other party and evaluate the possibility of fraud. The judgment unit, for example, uses the emotion estimation function to analyze the emotional state of the other party and determine the possibility of fraud. For example, if the other party appears unnaturally calm, it determines that there is a high possibility of fraud. Furthermore, a system is constructed that analyzes the emotional state of the other party and detects the possibility of fraud with high accuracy. For example, if the other party appears impatient, it determines that there is a low possibility of fraud. Furthermore, the emotion estimation function is used to analyze the emotional state of the other party in real time and determine the possibility of fraud. For example, if the other party behaves in an overly friendly manner, it determines that there is a high possibility of fraud. In this way, by using the emotion estimation function to analyze the emotional state of the other party and determine the possibility of fraud, the accuracy of detecting nuisance calls is improved.

[0065] The determination unit can evaluate the trustworthiness of the other party by referring to their social media or online profile. For example, when determining whether a call is legitimate, the determination unit may evaluate the trustworthiness of the other party by referring to their social media profile. For example, if the other party's social media account has been active for a long period of time, the determination unit may determine that the other party is highly trustworthy. In addition, a system may be constructed that analyzes online profiles and evaluates the trustworthiness of the other party. For example, the reliability may be determined based on the other party's professional background and recommendations. In addition, the information on social media and online profiles may be comprehensively analyzed to determine whether the call is legitimate. For example, the reliability may be evaluated based on the content of the other party's posts and the number of followers. In this way, by evaluating the reliability of the other party by referring to their social media or online profile, it is possible to more accurately determine whether the call is legitimate.

[0066] The determination unit can compare the contents of the other party's call with other databases and with a blacklist or whitelist. For example, when determining whether a call is legitimate, the determination unit compares the contents of the other party's call with a blacklist. For example, if the number has been registered as a nuisance call in the past, it is determined to be an illegitimate call. The determination unit also compares the contents of the other party's call with a whitelist to determine whether the other party is trustworthy. For example, if the number of a family member or acquaintance is registered on the whitelist, it is determined to be a legitimate call. The determination unit also refers to both the blacklist and the whitelist to comprehensively determine the contents of the other party's call. For example, if the number is not registered on the blacklist but also on the whitelist, additional checks are performed. In this way, by comparing the contents of the other party's call with other databases and with the blacklist or whitelist, it is possible to more accurately determine whether the call is legitimate.

[0067] The determination unit can use the emotion estimation function to analyze the emotional state of the other party and evaluate whether the call is legitimate from an emotional perspective. The determination unit, for example, uses the emotion estimation function to analyze the emotional state of the other party and determine whether the call is legitimate. For example, if the other party is calm, it determines that the call is likely to be legitimate. Furthermore, a system is constructed that analyzes the emotional state of the other party and evaluates whether the call is legitimate from an emotional perspective. For example, if the other party is impatient, it determines that the call is unlikely to be legitimate. Furthermore, the emotion estimation function is used to analyze the emotional state of the other party in real time and evaluate whether the call is legitimate. For example, if the other party is acting overly friendly, it determines that the call is unlikely to be legitimate. In this way, by using the emotion estimation function to analyze the emotional state of the other party and evaluating whether the call is legitimate from an emotional perspective, it is possible to more accurately determine whether the call is legitimate.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The response unit can analyze the tone or speed of the other party's voice, determine the urgency or emotional state, and adjust the response accordingly. For example, if the other party sounds urgent, a response that allows for a quick response is made. The response unit can also analyze the tone of the other party's voice to estimate the other party's emotional state. For example, if the other party sounds angry, a response that allows for a calm response is made. The response unit can also analyze the speed of the voice to determine whether the other party is impatient. For example, if the other party is impatient, a response that allows for a calm response is made. In this way, by analyzing the tone and speed of the other party's voice, determining the urgency or emotional state, and adjusting the response accordingly, a more appropriate response is possible.

[0070] The response unit can analyze the background sounds of the other party, determine the call environment, and adjust the tone of the response accordingly. For example, if the background sounds are quiet, it will respond in a normal tone. If it detects that the call is being made in a noisy place, the AI ​​will respond in a clearer tone to make it easier for the other party to hear. If it detects that the background sounds are from a specific environment (such as the inside of a car or a cafe), it will respond in a way that is appropriate for that environment. For example, if the call is being made in a car, it will respond in a short, concise manner. This allows the system to analyze the background sounds of the other party, determine the call environment, and change the tone of the response, enabling a more appropriate response.

[0071] The response unit can handle video calls and adjust the response by analyzing the facial expressions or gestures of the other party. For example, if the other party is smiling, a friendly response is made. Gesture analysis is also used to understand the other party's intentions. For example, if the other party is waving, a response can be made as a greeting. Both facial expressions and gestures are analyzed to comprehensively determine the other party's emotional state. For example, if the other party looks troubled, a response can be made asking for help. This makes it possible to handle video calls and adjust the response by analyzing the other party's facial expressions and gestures.

[0072] The response unit can refer to the other party's past call history and provide an individually customized response. For example, when the AI ​​answers a call, it refers to the other party's past call history and provides a customized response based on the content of the previous conversation. For example, it may revisit topics discussed in previous calls. It can also understand the other party's preferences and interests based on the past call history and provide a response accordingly. For example, if the other party is interested in a particular product, it can provide information about that product. It can also analyze the call history and follow up on any problems or questions the other party had previously. For example, it can check whether the previous problem has been resolved. This makes it possible to provide a more appropriate response by referring to the other party's past call history and providing an individually customized response.

[0073] The response unit uses the emotion estimation function to generate a response that makes the other party feel positive emotions, making it possible to build a good relationship from the start of the call. For example, the emotion estimation function is used to generate a response that makes the other party feel positive emotions. For example, calling the other party by name makes them feel familiar. The response also analyzes the other party's emotional state and generates a response that draws out positive emotions. For example, it provides topics related to the other party's hobbies and interests. The response also makes the other party feel relaxed at the start of the call. For example, it starts the conversation with a light joke or greeting. In this way, the emotion estimation function can be used to generate a response that makes the other party feel positive emotions, building a good relationship from the start of the call, making it possible to respond more appropriately.

[0074] The verification unit can analyze the characteristics of the other party's voice and perform voiceprint authentication to identify the other party's identity. For example, when verifying the contents of a call, the characteristics of the other party's voice are analyzed and voiceprint authentication is performed. For example, the identity is verified by comparing it with a voiceprint database of the other party. Voiceprint authentication is also used to verify whether the other party is a registered user. For example, voiceprint data of family members and acquaintances is registered in advance. Voiceprint authentication is also performed at the beginning of the call to verify the other party's identity before verifying the contents of the call. For example, in the case of an important business call, the identity of the other party can be reliably verified. In this way, by analyzing the characteristics of the other party's voice and performing voiceprint authentication to verify the other party's identity, it is possible to verify the contents of the call with greater accuracy.

[0075] The confirmation unit can convert call content into text in real time, extract important keywords, and automatically classify requirements. For example, it converts call content into text in real time and extracts important keywords. For example, it automatically detects keywords such as "urgent," "important," and "family." It also analyzes the converted call content and automatically classifies requirements. For example, it classifies them into business-related, family-related, emergency, etc. It also highlights important keywords based on the call content converted into text in real time, allowing the system to quickly grasp requirements. For example, it immediately notifies the user if an urgent requirement is included. This makes it possible to more efficiently confirm call content by converting call content into text in real time, extracting important keywords, and automatically classifying requirements.

[0076] The confirmation unit can use the emotion estimation function to analyze the emotional state of the other party and provide an appropriate response method as a guideline. For example, when checking the contents of a call, the emotion estimation function is used to analyze the emotional state of the other party. For example, if the other party is angry, guidelines for responding calmly are presented. Also, if the other party is sad, the emotion estimation function is used to present guidelines for comforting the other party. For example, words that are considerate of the other party's feelings are selected. Also, the confirmation unit analyzes the other party's emotional state and presents an appropriate response method as a guideline. For example, if the other party is impatient, a response to calm them down is made. In this way, by using the emotion estimation function to analyze the other party's emotional state and presenting an appropriate response method as a guideline, a more appropriate response is possible.

[0077] The verification unit can automatically translate the contents of calls into multiple languages ​​and can also handle calls in different languages. For example, a system can be built that automatically translates the contents of calls into multiple languages ​​in real time. For example, it can translate from English to Japanese and from Japanese to English. A multilingual call verification system can also be developed to handle calls in different languages. For example, it can translate French, Spanish, Chinese, etc. The contents of calls can also be automatically translated to enable smooth communication between users who speak different languages. For example, it can remove language barriers in international business calls. This allows the contents of calls to be automatically translated into multiple languages ​​and handle calls in different languages, making it possible to accommodate a wider range of users.

[0078] The confirmation unit uses the emotion estimation function to generate appropriate questions according to the emotional state of the other party, thereby enabling smooth confirmation of the call content. For example, the emotion estimation function is used to generate appropriate questions according to the emotional state of the other party. For example, if the other party is impatient, questions are asked to calm them down. Furthermore, a system is constructed that analyzes the emotional state of the other party and generates appropriate questions. For example, if the other party is angry, questions are asked to respond calmly. Furthermore, the emotion estimation function is used to generate questions according to the emotional state of the other party in real time, allowing smooth confirmation of the call content. For example, if the other party is sad, questions are asked to comfort them. In this way, the emotion estimation function is used to generate appropriate questions according to the emotional state of the other party, allowing smooth confirmation of the call content, thereby enabling a more appropriate response.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: In the response section, when a call comes in, the AI ​​automatically answers the call. For example, the AI ​​uses voice recognition technology to understand what the other person is saying and ask appropriate questions. For example, it might respond in the form of, "Hello, this is an automated response system. Who is calling?" Step 2: The confirmation unit checks the call content obtained by the response unit. For example, the AI ​​asks questions such as "Who is calling?", "Who do you need?", and "Please tell us your business" to understand the details of the call. Step 3: The judgment unit determines whether the call is legitimate based on the content of the call confirmed by the confirmation unit. For example, if the call is from a family member or acquaintance, or if it is an important business call, it is determined to be legitimate. Conversely, if there is a possibility of a nuisance sales call or fraud, it is not determined to be legitimate. Step 4: The ringing unit rings the phone if the judgment unit judges that the call is legitimate. For example, the phone rings only when there is an important message from a family member or an important business call.

[0081] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0082] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0083] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0086] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0087] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0088] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0089] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0090] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0091] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0092] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0093] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0094] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0095] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0096] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0097] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0098] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0102] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0103] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0105] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0106] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0107] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0109] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0110] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0111] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0122] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0131] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0132] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0133] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0134] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0135] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0136] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0137] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0138] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0139] 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.

[0140] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0141] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0142] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0143] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0144] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0145] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0146] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0147] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0148] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system that uses AI to function as a primary contact point for telephone calls, When a call comes in, the AI ​​automatically answers the call, and a confirmation unit that confirms the call content acquired by the response unit; a determination unit that determines whether the call is legitimate based on the call content confirmed by the confirmation unit; a ringing unit that rings the telephone when the determination unit determines that the call is legitimate. A system characterized by:

2. The response unit Analyze the tone or rate of the other person's voice to gauge urgency or emotional state and tailor your response accordingly 2. The system of claim 1.

3. The response unit Respond to video calls and adjust responses based on facial expressions or gestures 2. The system of claim 1.

4. The confirmation unit Analyze the characteristics of the other person's voice and perform voiceprint authentication to identify the other person's identity 2. The system of claim 1.

5. The determination unit By looking at the other party's past call history or behavioral patterns, it is possible to determine with greater accuracy whether the call is legitimate.

2. The system of claim 1.

6. The response unit Estimate the other person's emotional state and optimize the response 2. The system of claim 1.

7. The confirmation unit Analyze the other person's emotional state and provide guidelines on how to respond appropriately 2. The system of claim 1.

8. The determination unit Analyze the other person's emotional state and assess the likelihood of fraud 2. The system of claim 1.

Images