system

Abstract

To provide a system for quickly determining a country and a language, for performing quick language processing.SOLUTION: A system in an embodiment comprises: a determination part; an identification part; and a speed up part. The determination part determines a country or a language using an IP address. The identification part identifies each language on the basis of the information determined by the determination part. The speed up part performs speed up of language processing using a communication history statistic on the basis of the information identified by the identification part.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not adequately speed up country and language determination and language processing, and there is room for improvement.

[0005] The system according to the embodiment aims to quickly determine the country and language and speed up language processing. [Means for solving the problem]

[0006] The system according to the embodiment includes a determination unit, a specification unit, and a speed-up unit. The determination unit determines a country or language using an IP address. The specification unit specifies an individual language based on the information determined by the determination unit. The speed-up unit speeds up language processing using communication history statistics based on the information specified by the specification unit. Effect of the Invention

[0007] The system according to the embodiment can quickly determine the country and language, and can speed up language processing. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The low-latency multilingual translation natural language processing system according to the embodiment of the present invention is a system that brings new innovation to telephone network services in the 150 years of telephone history in Japan. The system aims to become the de facto standard ahead of other companies and to become a leader in AI big data and to monetize. The low-latency multilingual translation natural language processing system uses IP addresses to determine the country and language early, uses caller numbers to identify individual-level language, and uses communication history statistics to speed up language processing. For example, the country and language of the call origin is determined early using IP addresses. This enables appropriate language translation at the start of the call. For example, if the call is from Japan, translation based on Japanese is immediately started. Next, the caller number is used to identify the language at the individual level. This makes it possible to identify the language used by the caller based on past call history and registered information, and provide a more accurate translation. For example, if a specific caller often uses English, English translation is prioritized based on that information. Furthermore, communication history statistics are used to speed up language processing. Past communication history is analyzed and frequently used phrases and words are learned in advance to speed up real-time translation processing. For example, by having the system learn phrases frequently used in business conversations in advance, translation delays during phone calls can be minimized. In this way, the low-latency multilingual translation natural language processing system utilizes IP addresses, caller numbers, and communication history statistics to achieve low-latency, highly accurate multilingual translation, providing new value in telephone network services. As a result, the low-latency multilingual translation natural language processing system can provide fast and accurate multilingual translation in telephone network services.

[0029] The low-delay multilingual translation natural language processing system according to the embodiment includes a determination unit, a specification unit, and an expediting unit. The determination unit determines a country or a language using an IP address. For example, the determination unit can determine a country from which a call originates based on geographical information of the IP address. The determination unit can also determine a language by referring to a language setting of the IP address. For example, the determination unit analyzes geographical information of the IP address to specify a country from which a call originates. Furthermore, the determination unit can specify a language of the call based on a language setting of the IP address. The specification unit specifies a language at an individual level based on the information determined by the determination unit. For example, the specification unit can specify an individual language using a caller number. The specification unit can specify a language by referring to a regional code of the caller number. Furthermore, the specification unit can specify a language based on a past call history. For example, the specification unit analyzes a regional code of the caller number to specify an individual language. Furthermore, the specification unit can specify a language used by a caller based on a past call history. The expediting unit expedites language processing using communication history statistics based on the information specified by the specification unit. For example, the speed-up unit can analyze past communication data and learn frequently used phrases in advance. The speed-up unit can perform frequency analysis and speed up translation processing in real time. For example, the speed-up unit can learn frequently used phrases based on past communication data and speed up translation processing. Furthermore, the speed-up unit can perform frequency analysis and optimize translation processing in real time. As a result, the low-latency multilingual translation natural language processing system according to the embodiment can realize low-latency, highly accurate multilingual translation by utilizing IP addresses, caller numbers, and communication history statistics, thereby providing new value in telephone network services.

[0030] The determination unit uses the IP address to determine the country and language. Specifically, the determination unit analyzes the geographical information of the IP address to identify the country from which the call originates. For example, the determination unit can determine the country from which the call originates by referring to a database of IP addresses and checking which country a specific IP address is assigned to. The determination unit can also determine the language by referring to the language setting of the IP address. For example, the determination unit obtains language setting information of a device associated with the IP address and identifies the language of the call based on that information. This allows the determination unit to quickly and accurately determine the country and language from which the call originates. Furthermore, the determination unit is designed to be able to handle changes in IP addresses and the use of dynamic IP addresses, and can update information in real time. This allows the determination unit to always determine the country and language based on the latest information, improving the accuracy and reliability of the entire system.

[0031] The identification unit identifies the individual language based on the information determined by the determination unit. Specifically, the identification unit can identify individual languages ​​using the caller number. For example, the identification unit can identify a language commonly used in the area by referring to the area code of the caller number. The identification unit can also identify the language based on past call history. For example, the identification unit can record which language the caller used in the past and identify the language of the current call based on the information. This allows the identification unit to identify the individual language of the caller with high accuracy. Furthermore, the identification unit can perform more detailed language identification by referring to the caller's profile information and user settings. For example, if the caller uses multiple languages, the identification unit can identify the most frequently used language among them. This allows the identification unit to provide the optimal language settings for each user and improve the user experience of the entire system.

[0032] The speeding up unit speeds up language processing using communication history statistics based on the information identified by the identifying unit. Specifically, the speeding up unit can analyze past communication data and learn frequently used phrases in advance. For example, by collecting past call data and performing frequency analysis, frequently used phrases and words in a specific language are identified. As a result, the speeding up unit can learn these phrases in advance and speed up real-time translation processing. Furthermore, the speeding up unit uses AI to optimize the translation algorithm and improve the accuracy and speed of translation. For example, a machine learning model using a neural network can be trained to improve the translation accuracy for a specific language pair. As a result, the speeding up unit can optimize real-time translation processing and realize low-latency, high-precision multilingual translation. Furthermore, the speeding up unit can continuously update the communication history statistics and respond to new phrases and changes in language. As a result, the speeding up unit can always provide fast and accurate translation processing based on the latest information, improving the performance of the entire system.

[0033] The determination unit includes a complementing unit that acquires additional information. The complementing unit can acquire, for example, profile information of the user. For example, the complementing unit acquires profile information such as the user's age, sex, and place of residence. The complementing unit can also acquire device information. For example, the complementing unit acquires the type and setting information of the device used by the user. Furthermore, the complementing unit can acquire network information. For example, the complementing unit acquires the user's network connection status and connection speed. In this way, the complementing unit can improve the accuracy of the judgment by acquiring complementary information. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the user's profile information to AI and cause the AI ​​to analyze the profile information.

[0034] The identification unit includes a protection unit for protecting personal information. The protection unit can protect personal information using, for example, data encryption technology. For example, the protection unit encrypts the user's call data to prevent unauthorized access by a third party. The protection unit can also protect personal information using access control technology. For example, the protection unit restricts access to the user's personal information so that only users with specific authority can access it. Furthermore, the protection unit can protect personal information using data anonymization technology. For example, the protection unit anonymizes the user's personal information so that a specific individual cannot be identified. As a result, the protection unit can protect the user's personal information by including a protection unit for privacy protection. A part or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and have the AI ​​execute data encryption.

[0035] The speed-up unit includes a management unit that manages training data. The management unit can manage, for example, past communication history as training data. For example, the management unit analyzes the contents of the user's past calls, extracts frequent phrases, and uses them as training data. The management unit can also manage the user's behavioral data as training data. For example, the management unit analyzes the user's call frequency and call time, and uses them as training data. Furthermore, the management unit can also manage the user's profile information as training data. For example, the management unit analyzes profile information such as the user's age, gender, and place of residence, and uses them as training data. In this way, the management unit can improve the accuracy of language processing by managing the training data. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the contents of the user's past calls to AI and cause AI to extract frequent phrases.

[0036] The determination unit can determine the country or language of the call originating source using the IP address. The determination unit can determine the country of the call originating source based on, for example, geographical information of the IP address. For example, the determination unit analyzes the geographical information of the IP address to identify the country of the call originating source. The determination unit can also determine the language by referring to the language setting of the IP address. For example, the determination unit identifies the language of the call based on the language setting of the IP address. In this way, the determination unit can use the IP address to perform appropriate language translation at the start of the call. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the geographical information of the IP address to AI and have the AI ​​execute the country identification.

[0037] The identification unit can identify each language using the caller number. The identification unit can identify the language, for example, by referring to the area code of the caller number. For example, the identification unit analyzes the area code of the caller number to identify each language. The identification unit can also identify the language based on past call history. For example, the identification unit analyzes past call history to identify the language used by the caller. In this way, the identification unit can provide a more accurate translation by using the caller number. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the area code of the caller number to AI and have AI execute language identification.

[0038] The speed-up unit can speed up language processing by using communication history statistics. The speed-up unit can, for example, analyze past communication data and learn frequently used phrases in advance. For example, the speed-up unit can learn frequently used phrases based on past communication data and speed up translation processing. The speed-up unit can also perform frequency analysis and optimize real-time translation processing. For example, the speed-up unit can perform frequency analysis and speed up real-time translation processing. As a result, the speed-up unit can speed up real-time translation processing by using communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed by using AI, for example, or may be performed without using AI. For example, the speed-up unit can input past communication data to AI and cause AI to learn frequently used phrases.

[0039] The determination unit can determine the country and language using the device information of the user in addition to the IP address. The determination unit can determine the country and language by, for example, referring to the language setting of the user's device. For example, the determination unit analyzes the language setting of the user's device to identify the country and language. The determination unit can also obtain location information of the user's device to determine the country and language. For example, the determination unit identifies the country and language based on the location information of the user's device. Furthermore, the determination unit can analyze the usage history of the user's device to determine the country and language. For example, the determination unit analyzes the usage history of the user's device to identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the device information of the user in addition to the IP address. Part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the language setting of the user's device to AI and cause AI to execute the identification of the country and language.

[0040] The judgment unit can analyze the change history of the IP address and improve the accuracy of the judgment based on past data. The judgment unit can, for example, analyze the past change history of the IP address and improve the accuracy of the judgment of the country and the language. For example, the judgment unit analyzes the past change history of the IP address and identifies the country and the language. The judgment unit can also adjust the accuracy of the judgment in consideration of the frequency of the change of the IP address. For example, the judgment unit identifies the country and the language based on the frequency of the change of the IP address. Furthermore, the judgment unit can analyze the change pattern of the IP address to improve the accuracy of the judgment of the country and the language. For example, the judgment unit analyzes the change pattern of the IP address and identifies the country and the language. As a result, the judgment unit can improve the accuracy of the judgment by analyzing the change history of the IP address. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input the past change history of the IP address to AI and cause the AI ​​to execute the identification of the country and the language.

[0041] The determination unit can determine the country and language using the user's browser history in addition to the IP address. The determination unit can, for example, determine the country and language by analyzing the user's browser history. For example, the determination unit analyzes the user's browser history to identify the country and language. The determination unit can also determine the country and language by referring to the language setting of the user's browser. For example, the determination unit identifies the country and language based on the language setting of the user's browser. Furthermore, the determination unit can determine the country and language in consideration of the frequency of use of the user's browser. For example, the determination unit analyzes the frequency of use of the user's browser to identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the user's browser history in addition to the IP address. Part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the user's browser history into AI and cause AI to execute the identification of the country and language.

[0042] The determination unit can make a determination by considering the network connection speed of the user in addition to the IP address. The determination unit can, for example, determine the country and language by analyzing the network connection speed of the user. For example, the determination unit analyzes the network connection speed of the user to identify the country and language. The determination unit can also adjust the accuracy of the determination by considering fluctuations in the network connection speed. For example, the determination unit identifies the country and language based on fluctuations in the network connection speed. Furthermore, the determination unit can also determine the country and language by referring to the history of the network connection speed. For example, the determination unit analyzes the history of the network connection speed to identify the country and language. Thereby, the determination unit can improve the accuracy of the determination by considering the network connection speed of the user in addition to the IP address. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the network connection speed of the user to the AI ​​and cause the AI ​​to identify the country and language.

[0043] The identification unit can analyze the user's voice pattern in addition to the caller number to identify the language. The identification unit can, for example, analyze the user's voice pattern to identify the language. For example, the identification unit analyzes the user's pronunciation characteristics to identify the language. The identification unit can also analyze the rhythm and intonation of the user's voice to identify the language. For example, the identification unit analyzes the rhythm and intonation of the user's voice to identify the language. Thereby, the identification unit can improve the accuracy of language identification by analyzing the user's voice pattern in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI or may be performed without using AI. For example, the identification unit can input the user's voice pattern to AI and cause AI to execute language identification.

[0044] The identification unit can analyze the change history of the caller number and improve the accuracy of identification based on past data. The identification unit can, for example, improve the accuracy of language identification by analyzing the past caller number change history. For example, the identification unit analyzes the past caller number change history and identifies the language. The identification unit can also adjust the accuracy of identification in consideration of the frequency of caller number change. For example, the identification unit identifies the language based on the frequency of caller number change. Furthermore, the identification unit can analyze the change pattern of the caller number to improve the accuracy of language identification. For example, the identification unit analyzes the change pattern of the caller number and identifies the language. In this way, the identification unit can improve the accuracy of identification by analyzing the change history of the caller number. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the past caller number change history to AI and have AI execute language identification.

[0045] The identification unit can identify the language using the user's email address in addition to the caller number. The identification unit can, for example, analyze the user's email address to identify the language. For example, the identification unit identifies the language based on domain information of the user's email address. The identification unit can also analyze the user's email sending history to identify the language. For example, the identification unit can analyze the user's email sending history to identify the language. Furthermore, the identification unit can analyze the content of the user's email to identify the language. For example, the identification unit can analyze the content of the user's email to identify the language. Thereby, the identification unit can improve the accuracy of language identification by using the user's email address in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's email address to AI and cause the AI ​​to perform language identification.

[0046] The identification unit can identify the language using the user's SNS account information in addition to the caller number. The identification unit can, for example, analyze the user's SNS account information to identify the language. For example, the identification unit identifies the language based on the profile information of the user's SNS account. The identification unit can also identify the language by analyzing the user's SNS posting history. For example, the identification unit analyzes the user's SNS posting history to identify the language. Furthermore, the identification unit can also identify the language by referring to the user's SNS follower information. For example, the identification unit identifies the language based on the user's SNS follower information. Thereby, the identification unit can improve the accuracy of language identification by using the user's SNS account information in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's SNS account information into AI and cause AI to execute language identification.

[0047] The speed-up unit can speed up language processing by using real-time communication data of the user in addition to the communication history statistics. The speed-up unit can, for example, analyze the real-time communication data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the current communication content of the user. The speed-up unit can also perform real-time data analysis and select an optimal algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time communication data. Thereby, the speed-up unit can improve the speed of language processing by using the real-time communication data of the user in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI or may be performed without using AI. For example, the speed-up unit can input the real-time communication data of the user to AI and cause the AI ​​to perform data analysis.

[0048] The speed-up unit can analyze the change history of the communication history statistics and improve the accuracy of the speed-up based on past data. The speed-up unit can, for example, analyze the change history of the past communication history statistics to improve the accuracy of the speed-up. For example, the speed-up unit analyzes the change history of the past communication history statistics to improve the accuracy of the language processing. The speed-up unit can also adjust the accuracy of the speed-up in consideration of the change frequency of the communication history statistics. For example, the speed-up unit adjusts the accuracy of the language processing based on the change frequency of the communication history statistics. Furthermore, the speed-up unit can analyze the change pattern of the communication history statistics to improve the accuracy of the speed-up. For example, the speed-up unit analyzes the change pattern of the communication history statistics to improve the accuracy of the language processing. Thereby, the speed-up unit can improve the accuracy of the speed-up by analyzing the change history of the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the speed-up unit can input the change history of the past communication history statistics to AI and cause AI to perform data analysis.

[0049] The speed-up unit can speed up language processing by using the user's app usage history in addition to the communication history statistics. The speed-up unit can speed up language processing, for example, by analyzing the user's app usage history. For example, the speed-up unit pre-learns frequently used phrases based on the user's app usage history. The speed-up unit can also select an optimal algorithm by referring to the app usage history. For example, the speed-up unit selects an optimal translation algorithm based on the app usage history. Thereby, the speed-up unit can improve the speed of language processing by using the user's app usage history in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the speed-up unit can input the user's app usage history into AI and cause AI to perform data analysis.

[0050] The speed-up unit can speed up language processing by using the user's web browsing history in addition to the communication history statistics. The speed-up unit can, for example, analyze the user's web browsing history to speed up language processing. For example, the speed-up unit pre-learns frequently used phrases based on the user's web browsing history. The speed-up unit can also select an optimal algorithm by referring to the web browsing history. For example, the speed-up unit selects an optimal translation algorithm based on the web browsing history. Thereby, the speed-up unit can improve the speed of language processing by using the user's web browsing history in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speed-up unit can input the user's web browsing history into an AI and cause the AI ​​to perform data analysis.

[0051] The complementing unit can analyze and acquire the contents of the user's past calls as additional information. The complementing unit can, for example, analyze the contents of the user's past calls to acquire the complementary information. For example, the complementing unit extracts frequent phrases based on the contents of the user's past calls and uses them as complementary information. The complementing unit can also analyze the context of the call contents to acquire the complementary information. For example, the complementing unit analyzes the context of the call contents to acquire the complementary information. As a result, the complementing unit can improve the accuracy of the complementary information by analyzing the contents of the past calls. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the contents of the user's past calls into AI and have the AI ​​perform data analysis.

[0052] The complementing unit can analyze the change history of the additional information and improve the accuracy of acquisition based on past data. The complementing unit can, for example, analyze the change history of the past complementary information to improve the accuracy of acquisition. For example, the complementing unit analyzes the change history of the past complementary information to improve the accuracy of the complementary information. The complementing unit can also adjust the accuracy of acquisition in consideration of the change frequency of the complementary information. For example, the complementing unit acquires the complementary information based on the change frequency of the complementary information. Furthermore, the complementing unit can analyze the change pattern of the complementary information to improve the accuracy of acquisition. For example, the complementing unit analyzes the change pattern of the complementary information and acquires the complementary information. Thereby, the complementing unit can improve the accuracy of acquisition by analyzing the change history of the complementary information. A part or all of the above-mentioned processing in the complementing unit may be performed using, for example, AI, or may be performed without using AI. For example, the complementing unit can input the change history of the past complementary information to AI and cause AI to perform data analysis.

[0053] The completion unit can analyze and acquire the user's email history as additional information. The completion unit can, for example, analyze the user's email history to acquire the complementary information. For example, the completion unit extracts frequent phrases based on the user's email history and uses them as complementary information. The completion unit can also analyze the context of the email to acquire the complementary information. For example, the completion unit analyzes the context of the email to acquire the complementary information. As a result, the completion unit can improve the accuracy of the complementary information by analyzing the email history. A part or all of the above-mentioned processing in the completion unit may be performed, for example, using AI, or may be performed without using AI. For example, the completion unit can input the user's email history into AI and have the AI ​​perform data analysis.

[0054] The complementing unit can analyze and acquire the user's SNS posting history as additional information. The complementing unit can, for example, analyze the user's SNS posting history to acquire the complementary information. For example, the complementing unit extracts frequent phrases based on the user's SNS posting history and uses them as complementary information. The complementing unit can also analyze the context of the SNS posting to acquire the complementary information. For example, the complementing unit analyzes the context of the SNS posting to acquire the complementary information. As a result, the complementing unit can improve the accuracy of the complementary information by analyzing the SNS posting history. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the user's SNS posting history into AI and have the AI ​​perform data analysis.

[0055] The protection unit can encrypt and protect the user's data in order to protect personal information. The protection unit can protect the user's personal information using, for example, data encryption technology. For example, the protection unit encrypts the user's call data to prevent unauthorized access by a third party. The protection unit can also encrypt and protect the user's communication history. For example, the protection unit encrypts the user's communication history to protect privacy. Furthermore, the protection unit can also encrypt and protect the user's personal information. For example, the protection unit encrypts the user's personal information to protect privacy. As a result, the protection unit can improve the accuracy of privacy protection by encrypting data. Part or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and cause the AI ​​to perform data encryption.

[0056] The protection unit can analyze the change history of the personal information protection and improve the accuracy of the protection based on past data. The protection unit can, for example, analyze the past change history of the privacy protection to improve the accuracy of the protection. For example, the protection unit analyzes the past change history of the privacy protection to improve the accuracy of the protection. The protection unit can also adjust the accuracy of the protection in consideration of the frequency of the change of the privacy protection. For example, the protection unit adjusts the accuracy of the protection based on the frequency of the change of the privacy protection. Furthermore, the protection unit can also analyze the change pattern of the privacy protection to improve the accuracy of the protection. For example, the protection unit analyzes the change pattern of the privacy protection to improve the accuracy of the protection. As a result, the protection unit can improve the accuracy of the protection by analyzing the change history of the privacy protection. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the change history of the past privacy protection to AI and cause the AI ​​to perform data analysis.

[0057] The protection unit can anonymize and protect the user's data in order to protect the personal information. The protection unit can protect the user's personal information by using, for example, a data anonymization technique. For example, the protection unit anonymizes the user's call data to prevent unauthorized access by a third party. The protection unit can also anonymize and protect the user's communication history. For example, the protection unit anonymizes the user's communication history to protect privacy. Furthermore, the protection unit can also anonymize and protect the user's personal information. For example, the protection unit anonymizes the user's personal information to protect privacy. As a result, the protection unit can improve the accuracy of privacy protection by anonymizing data. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and cause the AI ​​to perform data anonymization.

[0058] The protection unit can monitor and protect the data access history of the user in order to protect the personal information. The protection unit can, for example, protect the personal information of the user by monitoring the data access history. For example, the protection unit monitors the data access history of the user and detects abnormal access. The protection unit can also analyze the data access pattern to protect privacy. For example, the protection unit analyzes the data access pattern and detects abnormal access. As a result, the protection unit can improve the accuracy of privacy protection by monitoring the data access history. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the data access history of the user to AI and cause AI to perform data analysis.

[0059] The management unit can analyze and manage the user's past communication history as training data. The management unit can, for example, analyze the user's past communication history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's past communication history and uses them as training data. The management unit can also analyze the context of the communication history to manage the training data. For example, the management unit analyzes the context of the communication history and manages the training data. In this way, the management unit can improve the accuracy of the training data by analyzing the past communication history. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the user's past communication history into AI and have the AI ​​perform data analysis.

[0060] The management unit can analyze the change history of the training data and improve the accuracy of the management based on the past data. The management unit can, for example, analyze the change history of the past training data to improve the accuracy of the management. For example, the management unit analyzes the change history of the past training data to improve the accuracy of the management. The management unit can also adjust the accuracy of the management in consideration of the change frequency of the training data. For example, the management unit adjusts the accuracy of the management based on the change frequency of the training data. Furthermore, the management unit can also analyze the change pattern of the training data to improve the accuracy of the management. For example, the management unit analyzes the change pattern of the training data to improve the accuracy of the management. As a result, the management unit can improve the accuracy of the management by analyzing the change history of the training data. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the change history of the past training data to AI and cause the AI ​​to perform data analysis.

[0061] The management unit can analyze and manage the user's email history as training data. The management unit can, for example, analyze the user's email history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's email history and uses them as training data. The management unit can also analyze the context of emails to manage the training data. For example, the management unit analyzes the context of emails and manages the training data. As a result, the management unit can improve the accuracy of the training data by analyzing the email history. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the user's email history into AI and have the AI ​​perform data analysis.

[0062] The management unit can analyze and manage the user's SNS posting history as training data. The management unit can, for example, analyze the user's SNS posting history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's SNS posting history and uses them as training data. The management unit can also analyze the context of the SNS posting to manage the training data. For example, the management unit analyzes the context of the SNS posting and manages the training data. In this way, the management unit can improve the accuracy of the training data by analyzing the SNS posting history. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the user's SNS posting history into AI and have the AI ​​perform data analysis.

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

[0064] The determination unit can analyze the usage history of the user's device and determine the country and language. For example, the determination unit can analyze the language settings of an application used by the user in the past and identify the country and language. The determination unit can also determine the country and language by referring to the location information history of the user's device. For example, the determination unit can analyze the location information history of the user's device and identify the country and language. Furthermore, the determination unit can analyze the usage pattern of the user's device and determine the country and language. For example, the determination unit can analyze the usage pattern of the user's device and identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the usage history of the user's device.

[0065] The identification unit can analyze the content of the user's social media posts and identify each language. For example, the identification unit can analyze the content of the user's social media posts and identify the language used. The identification unit can also identify the language by referring to the language settings of the user's social media followers. For example, the identification unit can analyze the language settings of the user's followers and identify the language. Furthermore, the identification unit can also identify the language by analyzing the frequency of the user's social media use. For example, the identification unit can analyze the frequency of the user's social media use and identify the language. In this way, the identification unit can improve the accuracy of language identification by using social media information.

[0066] The speed-up unit can analyze real-time voice data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the real-time voice data of the user. The speed-up unit can also analyze the real-time voice data to select an optimal translation algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time voice data. In this way, the speed-up unit can improve the speed of language processing by using real-time voice data.

[0067] The speed-up unit can analyze the real-time communication data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the real-time communication data of the user. The speed-up unit can also analyze the real-time communication data to select an optimal translation algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time communication data. In this way, the speed-up unit can improve the speed of language processing by using the real-time communication data.

[0068] The process flow of the first embodiment will be briefly described below.

[0069] Step 1: The determination unit determines the country and language using the IP address. For example, the determination unit determines the country from which the call originates based on the geographic information of the IP address, and determines the language by referring to the language setting of the IP address. Step 2: The identification unit identifies an individual-level language based on the information determined by the determination unit. For example, the identification unit identifies an individual language by referring to the area code of the caller ID or past call history. Step 3: The speed-up unit speeds up language processing using communication history statistics based on the information identified by the identification unit. For example, the speed-up unit analyzes past communication data, learns frequently used phrases in advance, and performs frequency analysis to speed up real-time translation processing.

[0070] (Example 2) The low-latency multilingual translation natural language processing system according to the embodiment of the present invention is a system that brings new innovation to telephone network services in the 150 years of telephone history in Japan. The system aims to become the de facto standard ahead of other companies and to become a leader in AI big data and to monetize. The low-latency multilingual translation natural language processing system uses IP addresses to determine the country and language early, uses caller numbers to identify individual-level language, and uses communication history statistics to speed up language processing. For example, the country and language of the call origin is determined early using IP addresses. This enables appropriate language translation at the start of the call. For example, if the call is from Japan, translation based on Japanese is immediately started. Next, the caller number is used to identify the language at the individual level. This makes it possible to identify the language used by the caller based on past call history and registered information, and provide a more accurate translation. For example, if a specific caller often uses English, English translation is prioritized based on that information. Furthermore, communication history statistics are used to speed up language processing. Past communication history is analyzed and frequently used phrases and words are learned in advance to speed up real-time translation processing. For example, by having the system learn phrases frequently used in business conversations in advance, translation delays during phone calls can be minimized. In this way, the low-latency multilingual translation natural language processing system utilizes IP addresses, caller numbers, and communication history statistics to achieve low-latency, highly accurate multilingual translation, providing new value in telephone network services. As a result, the low-latency multilingual translation natural language processing system can provide fast and accurate multilingual translation in telephone network services.

[0071] The low-delay multilingual translation natural language processing system according to the embodiment includes a determination unit, a specification unit, and an expediting unit. The determination unit determines a country or a language using an IP address. For example, the determination unit can determine a country from which a call originates based on geographical information of the IP address. The determination unit can also determine a language by referring to a language setting of the IP address. For example, the determination unit analyzes geographical information of the IP address to specify a country from which a call originates. Furthermore, the determination unit can specify a language of the call based on a language setting of the IP address. The specification unit specifies a language at an individual level based on the information determined by the determination unit. For example, the specification unit can specify an individual language using a caller number. The specification unit can specify a language by referring to a regional code of the caller number. Furthermore, the specification unit can specify a language based on a past call history. For example, the specification unit analyzes a regional code of the caller number to specify an individual language. Furthermore, the specification unit can specify a language used by a caller based on a past call history. The expediting unit expedites language processing using communication history statistics based on the information specified by the specification unit. For example, the speed-up unit can analyze past communication data and learn frequently used phrases in advance. The speed-up unit can perform frequency analysis and speed up translation processing in real time. For example, the speed-up unit can learn frequently used phrases based on past communication data and speed up translation processing. Furthermore, the speed-up unit can perform frequency analysis and optimize translation processing in real time. As a result, the low-latency multilingual translation natural language processing system according to the embodiment can realize low-latency, highly accurate multilingual translation by utilizing IP addresses, caller numbers, and communication history statistics, thereby providing new value in telephone network services.

[0072] The determination unit uses the IP address to determine the country and language. Specifically, the determination unit analyzes the geographical information of the IP address to identify the country from which the call originates. For example, the determination unit can determine the country from which the call originates by referring to a database of IP addresses and checking which country a specific IP address is assigned to. The determination unit can also determine the language by referring to the language setting of the IP address. For example, the determination unit obtains language setting information of a device associated with the IP address and identifies the language of the call based on that information. This allows the determination unit to quickly and accurately determine the country and language from which the call originates. Furthermore, the determination unit is designed to be able to handle changes in IP addresses and the use of dynamic IP addresses, and can update information in real time. This allows the determination unit to always determine the country and language based on the latest information, improving the accuracy and reliability of the entire system.

[0073] The identification unit identifies the individual language based on the information determined by the determination unit. Specifically, the identification unit can identify individual languages ​​using the caller number. For example, the identification unit can identify a language commonly used in the area by referring to the area code of the caller number. The identification unit can also identify the language based on past call history. For example, the identification unit can record which language the caller used in the past and identify the language of the current call based on the information. This allows the identification unit to identify the individual language of the caller with high accuracy. Furthermore, the identification unit can perform more detailed language identification by referring to the caller's profile information and user settings. For example, if the caller uses multiple languages, the identification unit can identify the most frequently used language among them. This allows the identification unit to provide the optimal language settings for each user and improve the user experience of the entire system.

[0074] The speeding up unit speeds up language processing using communication history statistics based on the information identified by the identifying unit. Specifically, the speeding up unit can analyze past communication data and learn frequently used phrases in advance. For example, by collecting past call data and performing frequency analysis, frequently used phrases and words in a specific language are identified. As a result, the speeding up unit can learn these phrases in advance and speed up real-time translation processing. Furthermore, the speeding up unit uses AI to optimize the translation algorithm and improve the accuracy and speed of translation. For example, a machine learning model using a neural network can be trained to improve the translation accuracy for a specific language pair. As a result, the speeding up unit can optimize real-time translation processing and realize low-latency, high-precision multilingual translation. Furthermore, the speeding up unit can continuously update the communication history statistics and respond to new phrases and changes in language. As a result, the speeding up unit can always provide fast and accurate translation processing based on the latest information, improving the performance of the entire system.

[0075] The determination unit includes a complementing unit that acquires additional information. The complementing unit can acquire, for example, profile information of the user. For example, the complementing unit acquires profile information such as the user's age, sex, and place of residence. The complementing unit can also acquire device information. For example, the complementing unit acquires the type and setting information of the device used by the user. Furthermore, the complementing unit can acquire network information. For example, the complementing unit acquires the user's network connection status and connection speed. In this way, the complementing unit can improve the accuracy of the judgment by acquiring complementary information. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the user's profile information to AI and cause the AI ​​to analyze the profile information.

[0076] The identification unit includes a protection unit for protecting personal information. The protection unit can protect personal information using, for example, data encryption technology. For example, the protection unit encrypts the user's call data to prevent unauthorized access by a third party. The protection unit can also protect personal information using access control technology. For example, the protection unit restricts access to the user's personal information so that only users with specific authority can access it. Furthermore, the protection unit can protect personal information using data anonymization technology. For example, the protection unit anonymizes the user's personal information so that a specific individual cannot be identified. As a result, the protection unit can protect the user's personal information by including a protection unit for privacy protection. A part or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and have the AI ​​execute data encryption.

[0077] The speed-up unit includes a management unit that manages training data. The management unit can manage, for example, past communication history as training data. For example, the management unit analyzes the contents of the user's past calls, extracts frequent phrases, and uses them as training data. The management unit can also manage the user's behavioral data as training data. For example, the management unit analyzes the user's call frequency and call time, and uses them as training data. Furthermore, the management unit can also manage the user's profile information as training data. For example, the management unit analyzes profile information such as the user's age, gender, and place of residence, and uses them as training data. In this way, the management unit can improve the accuracy of language processing by managing the training data. Part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the contents of the user's past calls to AI and cause AI to extract frequent phrases.

[0078] The determination unit can determine the country or language of the call originating source using the IP address. The determination unit can determine the country of the call originating source based on, for example, geographical information of the IP address. For example, the determination unit analyzes the geographical information of the IP address to identify the country of the call originating source. The determination unit can also determine the language by referring to the language setting of the IP address. For example, the determination unit identifies the language of the call based on the language setting of the IP address. In this way, the determination unit can use the IP address to perform appropriate language translation at the start of the call. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the geographical information of the IP address to AI and have the AI ​​execute the country identification.

[0079] The identification unit can identify each language using the caller number. The identification unit can identify the language, for example, by referring to the area code of the caller number. For example, the identification unit analyzes the area code of the caller number to identify each language. The identification unit can also identify the language based on past call history. For example, the identification unit analyzes past call history to identify the language used by the caller. In this way, the identification unit can provide a more accurate translation by using the caller number. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the area code of the caller number to AI and have AI execute language identification.

[0080] The speed-up unit can speed up language processing by using communication history statistics. The speed-up unit can, for example, analyze past communication data and learn frequently used phrases in advance. For example, the speed-up unit can learn frequently used phrases based on past communication data and speed up translation processing. The speed-up unit can also perform frequency analysis and optimize real-time translation processing. For example, the speed-up unit can perform frequency analysis and speed up real-time translation processing. As a result, the speed-up unit can speed up real-time translation processing by using communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed by using AI, for example, or may be performed without using AI. For example, the speed-up unit can input past communication data to AI and cause AI to learn frequently used phrases.

[0081] The judgment unit can estimate the user's emotion and adjust the accuracy of the judgment based on the estimated user's emotion. The judgment unit can estimate the user's emotion using, for example, voice analysis technology. For example, the judgment unit analyzes the tone and speed of the user's voice and calculates an emotion score. The judgment unit can also estimate the user's emotion using facial expression recognition technology. For example, the judgment unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the judgment unit can estimate the user's emotion using text analysis technology. For example, the judgment unit analyzes the content of the user's remarks and calculates an emotion score. This allows the judgment unit to adjust the accuracy of the judgment according to the user's emotion. For example, if the user is feeling stressed, the judgment unit obtains more detailed information to improve the accuracy of the judgment. Also, if the user is relaxed, the judgment unit adjusts the accuracy of the judgment to prioritize quick processing. Furthermore, if the user is in a hurry, the judgment unit adjusts the accuracy of the judgment to make a judgment in the shortest time. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the judgment unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the judgment unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0082] The determination unit can determine the country and language using the device information of the user in addition to the IP address. The determination unit can determine the country and language by, for example, referring to the language setting of the user's device. For example, the determination unit analyzes the language setting of the user's device to identify the country and language. The determination unit can also obtain location information of the user's device to determine the country and language. For example, the determination unit identifies the country and language based on the location information of the user's device. Furthermore, the determination unit can analyze the usage history of the user's device to determine the country and language. For example, the determination unit analyzes the usage history of the user's device to identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the device information of the user in addition to the IP address. Part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the language setting of the user's device to AI and cause AI to execute the identification of the country and language.

[0083] The judgment unit can analyze the change history of the IP address and improve the accuracy of the judgment based on past data. The judgment unit can, for example, analyze the past change history of the IP address and improve the accuracy of the judgment of the country and the language. For example, the judgment unit analyzes the past change history of the IP address and identifies the country and the language. The judgment unit can also adjust the accuracy of the judgment in consideration of the frequency of the change of the IP address. For example, the judgment unit identifies the country and the language based on the frequency of the change of the IP address. Furthermore, the judgment unit can analyze the change pattern of the IP address to improve the accuracy of the judgment of the country and the language. For example, the judgment unit analyzes the change pattern of the IP address and identifies the country and the language. As a result, the judgment unit can improve the accuracy of the judgment by analyzing the change history of the IP address. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input the past change history of the IP address to AI and cause the AI ​​to execute the identification of the country and the language.

[0084] The judgment unit can estimate the user's emotion and adjust the display format of the judgment result based on the estimated user's emotion. The judgment unit can estimate the user's emotion using, for example, voice analysis technology. For example, the judgment unit analyzes the tone and speed of the user's voice and calculates an emotion score. The judgment unit can also estimate the user's emotion using facial expression recognition technology. For example, the judgment unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the judgment unit can estimate the user's emotion using text analysis technology. For example, the judgment unit analyzes the content of the user's remarks and calculates an emotion score. This allows the judgment unit to adjust the display method according to the user's emotion. For example, if the user is nervous, the judgment unit provides a simple and highly visible display method. Furthermore, if the user is relaxed, the judgment unit provides a display method including detailed information. Furthermore, if the user is in a hurry, the judgment unit provides a display method that focuses on the main points. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the judgment unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the judgment unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0085] The determination unit can determine the country and language using the user's browser history in addition to the IP address. The determination unit can, for example, determine the country and language by analyzing the user's browser history. For example, the determination unit analyzes the user's browser history to identify the country and language. The determination unit can also determine the country and language by referring to the language setting of the user's browser. For example, the determination unit identifies the country and language based on the language setting of the user's browser. Furthermore, the determination unit can determine the country and language in consideration of the frequency of use of the user's browser. For example, the determination unit analyzes the frequency of use of the user's browser to identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the user's browser history in addition to the IP address. Part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the user's browser history into AI and cause AI to execute the identification of the country and language.

[0086] The determination unit can make a determination by considering the network connection speed of the user in addition to the IP address. The determination unit can, for example, determine the country and language by analyzing the network connection speed of the user. For example, the determination unit analyzes the network connection speed of the user to identify the country and language. The determination unit can also adjust the accuracy of the determination by considering fluctuations in the network connection speed. For example, the determination unit identifies the country and language based on fluctuations in the network connection speed. Furthermore, the determination unit can also determine the country and language by referring to the history of the network connection speed. For example, the determination unit analyzes the history of the network connection speed to identify the country and language. Thereby, the determination unit can improve the accuracy of the determination by considering the network connection speed of the user in addition to the IP address. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the network connection speed of the user to the AI ​​and cause the AI ​​to identify the country and language.

[0087] The identification unit can estimate the user's emotion and adjust the accuracy of identification based on the estimated user's emotion. The identification unit can estimate the user's emotion using, for example, voice analysis technology. For example, the identification unit analyzes the tone and speed of the user's voice and calculates an emotion score. The identification unit can also estimate the user's emotion using facial expression recognition technology. For example, the identification unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the identification unit can estimate the user's emotion using text analysis technology. For example, the identification unit analyzes the content of the user's remarks and calculates an emotion score. This allows the identification unit to adjust the accuracy of identification according to the user's emotion. For example, if the user is feeling stressed, the identification unit obtains more detailed information to increase the accuracy of identification. Also, if the user is relaxed, the identification unit adjusts the accuracy of identification to prioritize rapid processing. Furthermore, if the user is in a hurry, the identification unit adjusts the accuracy of identification to perform identification in the shortest time. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the identification unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0088] The identification unit can analyze the user's voice pattern in addition to the caller number to identify the language. The identification unit can, for example, analyze the user's voice pattern to identify the language. For example, the identification unit analyzes the user's pronunciation characteristics to identify the language. The identification unit can also analyze the rhythm and intonation of the user's voice to identify the language. For example, the identification unit analyzes the rhythm and intonation of the user's voice to identify the language. Thereby, the identification unit can improve the accuracy of language identification by analyzing the user's voice pattern in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI or may be performed without using AI. For example, the identification unit can input the user's voice pattern to AI and cause AI to execute language identification.

[0089] The identification unit can analyze the change history of the caller number and improve the accuracy of identification based on past data. The identification unit can, for example, improve the accuracy of language identification by analyzing the past caller number change history. For example, the identification unit analyzes the past caller number change history and identifies the language. The identification unit can also adjust the accuracy of identification in consideration of the frequency of caller number change. For example, the identification unit identifies the language based on the frequency of caller number change. Furthermore, the identification unit can analyze the change pattern of the caller number to improve the accuracy of language identification. For example, the identification unit analyzes the change pattern of the caller number and identifies the language. In this way, the identification unit can improve the accuracy of identification by analyzing the change history of the caller number. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can input the past caller number change history to AI and have AI execute language identification.

[0090] The identification unit can estimate the user's emotion and adjust the display format of the identification result based on the estimated user's emotion. The identification unit can estimate the user's emotion using, for example, voice analysis technology. For example, the identification unit analyzes the tone and speed of the user's voice and calculates an emotion score. The identification unit can also estimate the user's emotion using facial expression recognition technology. For example, the identification unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the identification unit can estimate the user's emotion using text analysis technology. For example, the identification unit analyzes the content of the user's remarks and calculates an emotion score. This allows the identification unit to adjust the display method according to the user's emotion. For example, when the user is nervous, the identification unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the identification unit provides a display method including detailed information. Furthermore, when the user is in a hurry, the identification unit provides a display method that focuses on the main points. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the identification unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the identification unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0091] The identification unit can identify the language using the user's email address in addition to the caller number. The identification unit can, for example, analyze the user's email address to identify the language. For example, the identification unit identifies the language based on domain information of the user's email address. The identification unit can also analyze the user's email sending history to identify the language. For example, the identification unit can analyze the user's email sending history to identify the language. Furthermore, the identification unit can analyze the content of the user's email to identify the language. For example, the identification unit can analyze the content of the user's email to identify the language. Thereby, the identification unit can improve the accuracy of language identification by using the user's email address in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's email address to AI and cause the AI ​​to perform language identification.

[0092] The identification unit can identify the language using the user's SNS account information in addition to the caller number. The identification unit can, for example, analyze the user's SNS account information to identify the language. For example, the identification unit identifies the language based on the profile information of the user's SNS account. The identification unit can also identify the language by analyzing the user's SNS posting history. For example, the identification unit analyzes the user's SNS posting history to identify the language. Furthermore, the identification unit can also identify the language by referring to the user's SNS follower information. For example, the identification unit identifies the language based on the user's SNS follower information. Thereby, the identification unit can improve the accuracy of language identification by using the user's SNS account information in addition to the caller number. Part or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the user's SNS account information into AI and cause AI to execute language identification.

[0093] The speed-up unit can estimate the user's emotion and adjust the speed-up algorithm based on the estimated user's emotion. The speed-up unit can estimate the user's emotion using, for example, a voice analysis technology. For example, the speed-up unit analyzes the tone and speed of the user's voice and calculates an emotion score. The speed-up unit can also estimate the user's emotion using facial expression recognition technology. For example, the speed-up unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the speed-up unit can estimate the user's emotion using a text analysis technology. For example, the speed-up unit analyzes the content of the user's remarks and calculates an emotion score. This allows the speed-up unit to adjust the algorithm according to the user's emotion. For example, if the user is stressed, the speed-up unit adjusts the algorithm to prioritize quick processing. Also, if the user is relaxed, the speed-up unit adjusts the algorithm to prioritize accuracy. Furthermore, if the user is in a hurry, the speed-up unit adjusts the algorithm to perform processing in the shortest time. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the speed-up unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the speed-up unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate the emotion score.

[0094] The speed-up unit can speed up language processing by using real-time communication data of the user in addition to the communication history statistics. The speed-up unit can, for example, analyze the real-time communication data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the current communication content of the user. The speed-up unit can also perform real-time data analysis and select an optimal algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time communication data. Thereby, the speed-up unit can improve the speed of language processing by using the real-time communication data of the user in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI or may be performed without using AI. For example, the speed-up unit can input the real-time communication data of the user to AI and cause the AI ​​to perform data analysis.

[0095] The speed-up unit can analyze the change history of the communication history statistics and improve the accuracy of the speed-up based on past data. The speed-up unit can, for example, analyze the change history of the past communication history statistics to improve the accuracy of the speed-up. For example, the speed-up unit analyzes the change history of the past communication history statistics to improve the accuracy of the language processing. The speed-up unit can also adjust the accuracy of the speed-up in consideration of the change frequency of the communication history statistics. For example, the speed-up unit adjusts the accuracy of the language processing based on the change frequency of the communication history statistics. Furthermore, the speed-up unit can analyze the change pattern of the communication history statistics to improve the accuracy of the speed-up. For example, the speed-up unit analyzes the change pattern of the communication history statistics to improve the accuracy of the language processing. Thereby, the speed-up unit can improve the accuracy of the speed-up by analyzing the change history of the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the speed-up unit can input the change history of the past communication history statistics to AI and cause AI to perform data analysis.

[0096] The speedup unit can estimate the user's emotion and adjust the display format of the speedup result based on the estimated user's emotion. The speedup unit can estimate the user's emotion using, for example, a voice analysis technology. For example, the speedup unit analyzes the tone and speed of the user's voice and calculates an emotion score. The speedup unit can also estimate the user's emotion using facial expression recognition technology. For example, the speedup unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the speedup unit can estimate the user's emotion using a text analysis technology. For example, the speedup unit analyzes the content of the user's remarks and calculates an emotion score. This allows the speedup unit to adjust the display method according to the user's emotion. For example, if the user is nervous, the speedup unit provides a simple and highly visible display method. Also, if the user is relaxed, the speedup unit provides a display method including detailed information. Furthermore, if the user is in a hurry, the speedup unit provides a display method that focuses on the main points. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the speed-up unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the speed-up unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate the emotion score.

[0097] The speed-up unit can speed up language processing by using the user's app usage history in addition to the communication history statistics. The speed-up unit can speed up language processing, for example, by analyzing the user's app usage history. For example, the speed-up unit pre-learns frequently used phrases based on the user's app usage history. The speed-up unit can also select an optimal algorithm by referring to the app usage history. For example, the speed-up unit selects an optimal translation algorithm based on the app usage history. Thereby, the speed-up unit can improve the speed of language processing by using the user's app usage history in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed, for example, using AI, or may be performed without using AI. For example, the speed-up unit can input the user's app usage history into AI and cause AI to perform data analysis.

[0098] The speed-up unit can speed up language processing by using the user's web browsing history in addition to the communication history statistics. The speed-up unit can, for example, analyze the user's web browsing history to speed up language processing. For example, the speed-up unit pre-learns frequently used phrases based on the user's web browsing history. The speed-up unit can also select an optimal algorithm by referring to the web browsing history. For example, the speed-up unit selects an optimal translation algorithm based on the web browsing history. Thereby, the speed-up unit can improve the speed of language processing by using the user's web browsing history in addition to the communication history statistics. A part or all of the above-mentioned processing in the speed-up unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speed-up unit can input the user's web browsing history into an AI and cause the AI ​​to perform data analysis.

[0099] The completion unit can estimate the user's emotion and adjust the acquisition method of the additional information based on the estimated user's emotion. The completion unit can estimate the user's emotion using, for example, a voice analysis technology. For example, the completion unit analyzes the tone and speed of the user's voice and calculates an emotion score. The completion unit can also estimate the user's emotion using facial expression recognition technology. For example, the completion unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the completion unit can estimate the user's emotion using a text analysis technology. For example, the completion unit analyzes the content of the user's remarks and calculates an emotion score. This allows the completion unit to adjust the acquisition method according to the user's emotion. For example, if the user is stressed, the completion unit adjusts the acquisition method to prioritize quick processing. Also, if the user is relaxed, the completion unit adjusts the acquisition method to prioritize accuracy. Furthermore, if the user is in a hurry, the completion unit adjusts the acquisition method to perform acquisition in the shortest time. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the complementing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the complementing unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0100] The complementing unit can analyze and acquire the contents of the user's past calls as additional information. The complementing unit can, for example, analyze the contents of the user's past calls to acquire the complementary information. For example, the complementing unit extracts frequent phrases based on the contents of the user's past calls and uses them as complementary information. The complementing unit can also analyze the context of the call contents to acquire the complementary information. For example, the complementing unit analyzes the context of the call contents to acquire the complementary information. As a result, the complementing unit can improve the accuracy of the complementary information by analyzing the contents of the past calls. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the contents of the user's past calls into AI and have the AI ​​perform data analysis.

[0101] The complementing unit can analyze the change history of the additional information and improve the accuracy of acquisition based on past data. The complementing unit can, for example, analyze the change history of the past complementary information to improve the accuracy of acquisition. For example, the complementing unit analyzes the change history of the past complementary information to improve the accuracy of the complementary information. The complementing unit can also adjust the accuracy of acquisition in consideration of the change frequency of the complementary information. For example, the complementing unit acquires the complementary information based on the change frequency of the complementary information. Furthermore, the complementing unit can analyze the change pattern of the complementary information to improve the accuracy of acquisition. For example, the complementing unit analyzes the change pattern of the complementary information and acquires the complementary information. Thereby, the complementing unit can improve the accuracy of acquisition by analyzing the change history of the complementary information. A part or all of the above-mentioned processing in the complementing unit may be performed using, for example, AI, or may be performed without using AI. For example, the complementing unit can input the change history of the past complementary information to AI and cause AI to perform data analysis.

[0102] The completion unit can estimate the user's emotion and adjust the display method of the additional information based on the estimated user's emotion. The completion unit can estimate the user's emotion using, for example, voice analysis technology. For example, the completion unit analyzes the tone and speed of the user's voice and calculates an emotion score. The completion unit can also estimate the user's emotion using facial expression recognition technology. For example, the completion unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the completion unit can estimate the user's emotion using text analysis technology. For example, the completion unit analyzes the content of the user's remarks and calculates an emotion score. This allows the completion unit to adjust the display method according to the user's emotion. For example, if the user is nervous, the completion unit provides a simple and highly visible display method. Furthermore, if the user is relaxed, the completion unit provides a display method including detailed information. Furthermore, if the user is in a hurry, the completion unit provides a display method that focuses on the main points. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the complementing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the complementing unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0103] The completion unit can analyze and acquire the user's email history as additional information. The completion unit can, for example, analyze the user's email history to acquire the complementary information. For example, the completion unit extracts frequent phrases based on the user's email history and uses them as complementary information. The completion unit can also analyze the context of the email to acquire the complementary information. For example, the completion unit analyzes the context of the email to acquire the complementary information. As a result, the completion unit can improve the accuracy of the complementary information by analyzing the email history. A part or all of the above-mentioned processing in the completion unit may be performed, for example, using AI, or may be performed without using AI. For example, the completion unit can input the user's email history into AI and have the AI ​​perform data analysis.

[0104] The complementing unit can analyze and acquire the user's SNS posting history as additional information. The complementing unit can, for example, analyze the user's SNS posting history to acquire the complementary information. For example, the complementing unit extracts frequent phrases based on the user's SNS posting history and uses them as complementary information. The complementing unit can also analyze the context of the SNS posting to acquire the complementary information. For example, the complementing unit analyzes the context of the SNS posting to acquire the complementary information. As a result, the complementing unit can improve the accuracy of the complementary information by analyzing the SNS posting history. A part or all of the above-mentioned processing in the complementing unit may be performed, for example, using AI, or may be performed without using AI. For example, the complementing unit can input the user's SNS posting history into AI and have the AI ​​perform data analysis.

[0105] The protection unit can estimate the user's emotion and adjust the level of personal information protection based on the estimated user's emotion. The protection unit can estimate the user's emotion using, for example, voice analysis technology. For example, the protection unit analyzes the tone and speed of the user's voice and calculates an emotion score. The protection unit can also estimate the user's emotion using facial expression recognition technology. For example, the protection unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the protection unit can estimate the user's emotion using text analysis technology. For example, the protection unit analyzes the content of the user's speech and calculates an emotion score. This allows the protection unit to adjust the level of privacy protection according to the user's emotion. For example, if the user is stressed, the protection unit increases the level of privacy protection. Also, if the user is relaxed, the protection unit adjusts the level of privacy protection to prioritize convenience. Furthermore, if the user is in a hurry, the protection unit adjusts the level of privacy protection to prioritize rapid processing. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the protection unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0106] The protection unit can encrypt and protect the user's data in order to protect personal information. The protection unit can protect the user's personal information using, for example, data encryption technology. For example, the protection unit encrypts the user's call data to prevent unauthorized access by a third party. The protection unit can also encrypt and protect the user's communication history. For example, the protection unit encrypts the user's communication history to protect privacy. Furthermore, the protection unit can also encrypt and protect the user's personal information. For example, the protection unit encrypts the user's personal information to protect privacy. As a result, the protection unit can improve the accuracy of privacy protection by encrypting data. Part or all of the above-mentioned processing in the protection unit may be performed using, for example, AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and cause the AI ​​to perform data encryption.

[0107] The protection unit can analyze the change history of the personal information protection and improve the accuracy of the protection based on past data. The protection unit can, for example, analyze the past change history of the privacy protection to improve the accuracy of the protection. For example, the protection unit analyzes the past change history of the privacy protection to improve the accuracy of the protection. The protection unit can also adjust the accuracy of the protection in consideration of the frequency of the change of the privacy protection. For example, the protection unit adjusts the accuracy of the protection based on the frequency of the change of the privacy protection. Furthermore, the protection unit can also analyze the change pattern of the privacy protection to improve the accuracy of the protection. For example, the protection unit analyzes the change pattern of the privacy protection to improve the accuracy of the protection. As a result, the protection unit can improve the accuracy of the protection by analyzing the change history of the privacy protection. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the change history of the past privacy protection to AI and cause the AI ​​to perform data analysis.

[0108] The protection unit can estimate the user's emotion and adjust the notification method of personal information protection based on the estimated user's emotion. The protection unit can estimate the user's emotion using, for example, voice analysis technology. For example, the protection unit analyzes the tone and speed of the user's voice and calculates an emotion score. The protection unit can also estimate the user's emotion using facial expression recognition technology. For example, the protection unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the protection unit can estimate the user's emotion using text analysis technology. For example, the protection unit analyzes the content of the user's remarks and calculates an emotion score. This allows the protection unit to adjust the notification method according to the user's emotion. For example, if the user is nervous, the protection unit provides a notification method that is simple and highly visible. Also, if the user is relaxed, the protection unit provides a notification method that includes detailed information. Furthermore, if the user is in a hurry, the protection unit provides a notification method that focuses on the main points. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the protection unit may input the tone and speed of the user's voice to the AI ​​and cause the AI ​​to calculate an emotion score.

[0109] The protection unit can anonymize and protect the user's data in order to protect the personal information. The protection unit can protect the user's personal information by using, for example, a data anonymization technique. For example, the protection unit anonymizes the user's call data to prevent unauthorized access by a third party. The protection unit can also anonymize and protect the user's communication history. For example, the protection unit anonymizes the user's communication history to protect privacy. Furthermore, the protection unit can also anonymize and protect the user's personal information. For example, the protection unit anonymizes the user's personal information to protect privacy. As a result, the protection unit can improve the accuracy of privacy protection by anonymizing data. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the user's call data to AI and cause the AI ​​to perform data anonymization.

[0110] The protection unit can monitor and protect the data access history of the user in order to protect the personal information. The protection unit can, for example, protect the personal information of the user by monitoring the data access history. For example, the protection unit monitors the data access history of the user and detects abnormal access. The protection unit can also analyze the data access pattern to protect privacy. For example, the protection unit analyzes the data access pattern and detects abnormal access. As a result, the protection unit can improve the accuracy of privacy protection by monitoring the data access history. A part or all of the above-mentioned processing in the protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the protection unit can input the data access history of the user to AI and cause AI to perform data analysis.

[0111] The management unit can estimate the user's emotion and adjust the management method of the training data based on the estimated user's emotion. The management unit can estimate the user's emotion using, for example, voice analysis technology. For example, the management unit analyzes the tone and speed of the user's voice and calculates an emotion score. The management unit can also estimate the user's emotion using facial expression recognition technology. For example, the management unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the management unit can estimate the user's emotion using text analysis technology. For example, the management unit analyzes the content of the user's remarks and calculates an emotion score. This allows the management unit to adjust the management method according to the user's emotion. For example, if the user is stressed, the management unit adjusts the management method to prioritize quick processing. Also, if the user is relaxed, the management unit adjusts the management method to prioritize accuracy. Furthermore, if the user is in a hurry, the management unit adjusts the management method to perform management in the shortest time. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the management unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the management unit may input the tone and speed of the user's voice into the AI ​​and cause the AI ​​to calculate an emotion score.

[0112] The management unit can analyze and manage the user's past communication history as training data. The management unit can, for example, analyze the user's past communication history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's past communication history and uses them as training data. The management unit can also analyze the context of the communication history to manage the training data. For example, the management unit analyzes the context of the communication history and manages the training data. In this way, the management unit can improve the accuracy of the training data by analyzing the past communication history. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the user's past communication history into AI and have the AI ​​perform data analysis.

[0113] The management unit can analyze the change history of the training data and improve the accuracy of the management based on the past data. The management unit can, for example, analyze the change history of the past training data to improve the accuracy of the management. For example, the management unit analyzes the change history of the past training data to improve the accuracy of the management. The management unit can also adjust the accuracy of the management in consideration of the change frequency of the training data. For example, the management unit adjusts the accuracy of the management based on the change frequency of the training data. Furthermore, the management unit can also analyze the change pattern of the training data to improve the accuracy of the management. For example, the management unit analyzes the change pattern of the training data to improve the accuracy of the management. As a result, the management unit can improve the accuracy of the management by analyzing the change history of the training data. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the change history of the past training data to AI and cause the AI ​​to perform data analysis.

[0114] The management unit can estimate the user's emotion and adjust the display method of the training data based on the estimated user's emotion. The management unit can estimate the user's emotion using, for example, voice analysis technology. For example, the management unit analyzes the tone and speed of the user's voice and calculates an emotion score. The management unit can also estimate the user's emotion using facial expression recognition technology. For example, the management unit analyzes changes in the user's facial expression and calculates an emotion score. Furthermore, the management unit can estimate the user's emotion using text analysis technology. For example, the management unit analyzes the content of the user's remarks and calculates an emotion score. This allows the management unit to adjust the display method according to the user's emotion. For example, if the user is nervous, the management unit provides a simple and highly visible display method. Furthermore, if the user is relaxed, the management unit provides a display method including detailed information. Furthermore, if the user is in a hurry, the management unit provides a display method that focuses on the main points. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the management unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the management unit may input the tone and speed of the user's voice into the AI ​​and cause the AI ​​to calculate an emotion score.

[0115] The management unit can analyze and manage the user's email history as training data. The management unit can, for example, analyze the user's email history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's email history and uses them as training data. The management unit can also analyze the context of emails to manage the training data. For example, the management unit analyzes the context of emails and manages the training data. As a result, the management unit can improve the accuracy of the training data by analyzing the email history. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can input the user's email history into AI and have the AI ​​perform data analysis.

[0116] The management unit can analyze and manage the user's SNS posting history as training data. The management unit can, for example, analyze the user's SNS posting history and manage it as training data. For example, the management unit extracts frequent phrases based on the user's SNS posting history and uses them as training data. The management unit can also analyze the context of the SNS posting to manage the training data. For example, the management unit analyzes the context of the SNS posting and manages the training data. In this way, the management unit can improve the accuracy of the training data by analyzing the SNS posting history. A part or all of the above-mentioned processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can input the user's SNS posting history into AI and have the AI ​​perform data analysis.

[0117] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0118] The determination unit can analyze the usage history of the user's device and determine the country and language. For example, the determination unit can analyze the language settings of an application used by the user in the past and identify the country and language. The determination unit can also determine the country and language by referring to the location information history of the user's device. For example, the determination unit can analyze the location information history of the user's device and identify the country and language. Furthermore, the determination unit can analyze the usage pattern of the user's device and determine the country and language. For example, the determination unit can analyze the usage pattern of the user's device and identify the country and language. As a result, the determination unit can improve the accuracy of determining the country and language by using the usage history of the user's device.

[0119] The identification unit can analyze the content of the user's social media posts and identify each language. For example, the identification unit can analyze the content of the user's social media posts and identify the language used. The identification unit can also identify the language by referring to the language settings of the user's social media followers. For example, the identification unit can analyze the language settings of the user's followers and identify the language. Furthermore, the identification unit can also identify the language by analyzing the frequency of the user's social media use. For example, the identification unit can analyze the frequency of the user's social media use and identify the language. In this way, the identification unit can improve the accuracy of language identification by using social media information.

[0120] The speed-up unit can analyze real-time voice data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the real-time voice data of the user. The speed-up unit can also analyze the real-time voice data to select an optimal translation algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time voice data. In this way, the speed-up unit can improve the speed of language processing by using real-time voice data.

[0121] The judgment unit can estimate the user's emotion and adjust the priority of judgment based on the estimated user's emotion. For example, the judgment unit can estimate the user's emotion using a voice analysis technique. For example, the judgment unit can analyze the tone and speed of the user's voice and calculate an emotion score. The judgment unit can also estimate the user's emotion using a facial expression recognition technique. For example, the judgment unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the judgment unit to adjust the priority of judgment according to the user's emotion. For example, when the user is stressed, the judgment unit adjusts the priority of judgment to prioritize quick processing. Also, when the user is relaxed, the judgment unit adjusts the priority of judgment to prioritize accuracy. Furthermore, when the user is in a hurry, the judgment unit adjusts the priority of judgment to make a judgment in the shortest time.

[0122] The identification unit can estimate the user's emotion and adjust the specific method based on the estimated user's emotion. For example, the identification unit can estimate the user's emotion using a voice analysis technique. For example, the identification unit can analyze the tone and speed of the user's voice and calculate an emotion score. The identification unit can also estimate the user's emotion using a facial expression recognition technique. For example, the identification unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the identification unit to adjust the specific method according to the user's emotion. For example, if the user is stressed, the identification unit adjusts the specific method to prioritize quick processing. Also, if the user is relaxed, the identification unit adjusts the specific method to prioritize accuracy. Furthermore, if the user is in a hurry, the identification unit adjusts the specific method to perform identification in the shortest time.

[0123] The speed-up unit can estimate the user's emotion and adjust the speed-up algorithm based on the estimated user's emotion. For example, the speed-up unit can estimate the user's emotion using a voice analysis technique. For example, the speed-up unit can analyze the tone and speed of the user's voice and calculate an emotion score. The speed-up unit can also estimate the user's emotion using a facial expression recognition technique. For example, the speed-up unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the speed-up unit to adjust the algorithm according to the user's emotion. For example, if the user is stressed, the speed-up unit adjusts the algorithm to prioritize quick processing. Also, if the user is relaxed, the speed-up unit adjusts the algorithm to prioritize accuracy. Furthermore, if the user is in a hurry, the speed-up unit adjusts the algorithm to perform processing in the shortest time.

[0124] The completion unit can estimate the user's emotion and adjust the acquisition method of the additional information based on the estimated user's emotion. For example, the completion unit can estimate the user's emotion using a voice analysis technique. For example, the completion unit can analyze the tone and speed of the user's voice and calculate an emotion score. The completion unit can also estimate the user's emotion using a facial expression recognition technique. For example, the completion unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the completion unit to adjust the acquisition method according to the user's emotion. For example, if the user is stressed, the completion unit adjusts the acquisition method to prioritize quick processing. Also, if the user is relaxed, the completion unit adjusts the acquisition method to prioritize accuracy. Furthermore, if the user is in a hurry, the completion unit adjusts the acquisition method to perform acquisition in the shortest time.

[0125] The protection unit can estimate the user's emotion and adjust the level of personal information protection based on the estimated user's emotion. For example, the protection unit can estimate the user's emotion using a voice analysis technique. For example, the protection unit can analyze the tone and speed of the user's voice and calculate an emotion score. The protection unit can also estimate the user's emotion using a facial expression recognition technique. For example, the protection unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the protection unit to adjust the level of privacy protection according to the user's emotion. For example, if the user is stressed, the protection unit increases the level of privacy protection. Also, if the user is relaxed, the protection unit adjusts the level of privacy protection to prioritize convenience. Furthermore, if the user is in a hurry, the protection unit adjusts the level of privacy protection to prioritize quick processing.

[0126] The management unit can estimate the user's emotion and adjust the management method of the training data based on the estimated user's emotion. For example, the management unit can estimate the user's emotion using a voice analysis technology. For example, the management unit can analyze the tone and speed of the user's voice and calculate an emotion score. The management unit can also estimate the user's emotion using a facial expression recognition technology. For example, the management unit can analyze changes in the user's facial expression and calculate an emotion score. This allows the management unit to adjust the management method according to the user's emotion. For example, if the user is stressed, the management unit adjusts the management method to prioritize quick processing. Also, if the user is relaxed, the management unit adjusts the management method to prioritize accuracy. Furthermore, if the user is in a hurry, the management unit adjusts the management method to perform management in the shortest time.

[0127] The speed-up unit can analyze the real-time communication data of the user to speed up language processing. For example, the speed-up unit learns frequently used phrases in advance based on the real-time communication data of the user. The speed-up unit can also analyze the real-time communication data to select an optimal translation algorithm. For example, the speed-up unit selects an optimal translation algorithm based on the real-time communication data. In this way, the speed-up unit can improve the speed of language processing by using the real-time communication data.

[0128] The process flow of the second embodiment will be briefly described below.

[0129] Step 1: The determination unit determines the country and language using the IP address. For example, the determination unit determines the country from which the call originates based on the geographic information of the IP address, and determines the language by referring to the language setting of the IP address. Step 2: The identification unit identifies an individual-level language based on the information determined by the determination unit. For example, the identification unit identifies an individual language by referring to the area code of the caller ID or past call history. Step 3: The speed-up unit speeds up language processing using communication history statistics based on the information identified by the identification unit. For example, the speed-up unit analyzes past communication data, learns frequently used phrases in advance, and performs frequency analysis to speed up real-time translation processing.

[0130] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0131] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0132] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0133] Each of the above-mentioned elements including the determination unit, the identification unit, the expediting unit, the complementing unit, the protection unit, the management unit, and the emotion estimation function is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the determination unit is realized by the processor 46 of the smart device 14, and determines the country and language using an IP address. The identification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies the language at the individual level using the caller number. The expediting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and expedites language processing using communication history statistics. The complementing unit is realized, for example, by the control unit 46A of the smart device 14, and acquires user profile information. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects personal information using data encryption technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and manages past communication history as training data. The emotion estimation function is realized, for example, by the control unit 46A of the smart device 14, and estimates the user's emotion using a voice analysis technique. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0134] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0135] 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.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] 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.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0141] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] 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.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0144] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0148] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0149] Each of the above-mentioned elements including the determination unit, the identification unit, the expediting unit, the complementing unit, the protection unit, the management unit, and the emotion estimation function is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the determination unit is realized by the processor 46 of the smart glasses 214 and determines the country and language using an IP address. The identification unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and identifies the language at the individual level using the caller number. The expediting unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and expedites language processing using communication history statistics. The complementing unit is realized, for example, by the control unit 46A of the smart glasses 214 and acquires user profile information. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and protects personal information using data encryption technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages past communication history as training data. The emotion estimation function is realized, for example, by the control unit 46A of the smart glasses 214, and estimates the user's emotion using voice analysis technology. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0150] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0151] 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.

[0152] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] 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.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0157] 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.

[0158] 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.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0160] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0164] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0165] Each of the plurality of elements including the above-mentioned determination unit, identification unit, expediting unit, complement unit, protection unit, management unit, and emotion estimation function is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the determination unit is realized by the processor 46 of the headset type terminal 314, and determines a country and a language using an IP address. The identification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies a language at an individual level using a caller number. The expediting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and expedites language processing using communication history statistics. The complement unit is realized, for example, by the control unit 46A of the headset type terminal 314, and acquires user profile information. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects personal information using data encryption technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and manages past communication history as training data. The emotion estimation function is realized, for example, by the control unit 46A of the headset type terminal 314, and estimates the emotion of the user using a voice analysis technique. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0166] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0167] 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.

[0168] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0169] 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.

[0170] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0172] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0173] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0174] 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.

[0175] 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.

[0176] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0177] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0178] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0179] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0180] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0181] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0182] Each of the plurality of elements including the above-mentioned determination unit, identification unit, expediting unit, complement unit, protection unit, management unit, and emotion estimation function is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the determination unit is realized by the processor 46 of the robot 414, and determines a country and a language using an IP address. The identification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and identifies a language at an individual level using a caller number. The expediting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and expedites language processing using communication history statistics. The complement unit is realized, for example, by the control unit 46A of the robot 414, and acquires user profile information. The protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects personal information using data encryption technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and manages past communication history as training data. The emotion estimation function is realized, for example, by the control unit 46A of the robot 414, and estimates the emotion of the user using a voice analysis technique. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0183] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0184] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0185] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0186] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0187] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0188] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0189] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0190] 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.

[0191] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0192] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0193] 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.

[0194] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0195] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0196] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0197] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0198] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0199] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0200] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0201] (Appendix 1) A determination unit for determining a country or language using an IP address; an identification unit that identifies an individual language based on the information determined by the determination unit; a speeding up unit that speeds up language processing using communication history statistics based on the information identified by the identifying unit; Equipped A system characterized by: (Appendix 2) The determination unit is Equipped with a supplementary section to obtain additional information 2. The system of claim 1, (Appendix 3) The identification unit is Equipping a protection department for personal information protection 2. The system of claim 1, (Appendix 4) The speedup unit includes: Equipped with a management section for managing training data 2. The system of claim 1, (Appendix 5) The determination unit is Using IP addresses to determine the country or language a call is coming from 2. The system of claim 1, (Appendix 6) The identification unit is Using caller ID to identify individual languages 2. The system of claim 1, (Appendix 7) The speedup unit includes: Accelerating language processing using communication history statistics 2. The system of claim 1, (Appendix 8) The determination unit is Estimate the user's emotions and adjust the accuracy of the judgment based on the estimated user's emotions. 2. The system of claim 1, (Appendix 9) The determination unit is In addition to IP address, information about the user's device may be used to determine country or language 2. The system of claim 1, (Appendix 10) The determination unit is Analyze IP address change history and improve accuracy of judgment based on past data 2. The system of claim 1, (Appendix 11) The determination unit is The method estimates the user's emotions and adjusts the display format of the judgment result based on the estimated user's emotions. 2. The system of claim 1, (Appendix 12) The determination unit is In addition to IP addresses, users' browser history is used to determine country or language 2. The system of claim 1, (Appendix 13) The determination unit is Make decisions based on the user's network connection speed in addition to their IP address 2. The system of claim 1, (Appendix 14) The identification unit is Inferring a user's emotion and adjusting the specific accuracy based on the estimated user's emotion 2. The system of claim 1, (Appendix 15) The identification unit is In addition to caller ID, it analyzes the user's speech patterns to identify the language 2. The system of claim 1, (Appendix 16) The identification unit is Analyze caller number change history and improve identification accuracy based on past data 2. The system of claim 1, (Appendix 17) The identification unit is Inferring a user's emotion and adjusting the display format of a particular result based on the estimated user's emotion 2. The system of claim 1, (Appendix 18) The identification unit is In addition to the caller ID, the user's email address is used to identify the language 2. The system of claim 1, (Appendix 19) The identification unit is In addition to the caller ID, the language is identified using the user's social media account information. 2. The system of claim 1, (Appendix 20) The speedup unit includes: Inferring user sentiment and adjusting the acceleration algorithm based on the inferred user sentiment 2. The system of claim 1, (Appendix 21) The speedup unit includes: Accelerate language processing by using real-time user communication data in addition to communication history statistics 2. The system of claim 1, (Appendix 22) The speedup unit includes: Analyze the change history of communication history statistics and improve the accuracy of speedup based on past data 2. The system of claim 1, (Appendix 23) The speedup unit includes: Inferring a user's emotion and adjusting a display format of the accelerated result based on the estimated user's emotion 2. The system of claim 1, (Appendix 24) The speedup unit includes: In addition to communication statistics, the app usage history of users is used to speed up language processing. 2. The system of claim 1, (Appendix 25) The speedup unit includes: In addition to communication statistics, users' web browsing history is used to speed up language processing. 2. The system of claim 1, (Appendix 26) The complementing unit is Inferring a user's emotion and adjusting how additional information is obtained based on the estimated user's emotion 3. The system of claim 2, (Appendix 27) The complementing unit is Additional information is obtained by analyzing the user's past calls. 3. The system of claim 2, (Appendix 28) The complementing unit is Analyze the change history of additional information and improve the accuracy of retrieval based on past data 3. The system of claim 2, (Appendix 29) The complementing unit is Inferring a user's emotion and adjusting how additional information is displayed based on the estimated user's emotion 3. The system of claim 2, (Appendix 30) The complementing unit is Analyze and obtain additional information from the user's email history 3. The system of claim 2, (Appendix 31) The complementing unit is Additional information is obtained by analyzing the user's social media posting history. 3. The system of claim 2, (Appendix 32) The protective part is Inferring user emotions and adjusting the level of personal information protection based on the estimated user emotions 4. The system of claim 3. (Appendix 33) The protective part is Encode and protect user data for privacy reasons 4. The system of claim 3. (Appendix 34) The protective part is Analyze the change history of personal information protection and improve the accuracy of protection based on past data 4. The system of claim 3. (Appendix 35) The protective part is Inferring user emotions and adjusting the method of notifying users of personal information protection based on the estimated user emotions 4. The system of claim 3. (Appendix 36) The protective part is To protect personal information, we de-identify and protect your data. 4. The system of claim 3. (Appendix 37) The protective part is Monitor and protect users' data access history to protect personal information 4. The system of claim 3. (Appendix 38) The management unit Inferring user emotions and adjusting the management of training data based on the inferred user emotions 5. The system of claim 4. (Appendix 39) The management unit Analyze and manage users' past communication history as training data 5. The system of claim 4. (Appendix 40) The management unit Analyze the change history of training data and improve the accuracy of management based on past data 5. The system of claim 4. (Appendix 41) The management unit Inferring user emotion and adjusting the way training data is presented based on the inferred user emotion 5. The system of claim 4. (Appendix 42) The management unit Analyze and manage users' email history as training data 5. The system of claim 4. (Appendix 43) The management unit Analyze and manage users' SNS posting history as training data 5. The system of claim 4. [Explanation of symbols]

[0202] 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 determination unit for determining a country or language using an IP address; an identification unit that identifies an individual language based on the information determined by the determination unit; a speeding up unit that speeds up language processing using communication history statistics based on the information identified by the identifying unit; Equipped A system characterized by:

2. The determination unit is Equipped with a supplementary section to obtain additional information 2. The system of claim 1 .

3. The identification unit is Equipping a protection department for personal information protection 2. The system of claim 1 .

4. The speedup unit includes: Equipped with a management section for managing training data 2. The system of claim 1 .

5. The determination unit is Using IP addresses to determine the country or language a call is coming from 2. The system of claim 1 .

6. The identification unit is Using caller ID to identify individual languages 2. The system of claim 1 .

7. The speedup unit includes: Accelerating language processing using communication history statistics 2. The system of claim 1 .

8. The determination unit is Estimate the user's emotions and adjust the accuracy of the judgment based on the estimated user's emotions.

2. The system of claim 1 .

Images