system

Abstract

The system according to the embodiment aims to produce utterances that give a sense of familiarity to the user. [Solution] A system according to an embodiment includes a reception unit, a generation unit, an emotion imparting unit, and a speaking unit. The reception unit receives user input. The generation unit generates a sentence based on the information received by the reception unit. The emotion imparting unit describes a specific method for imparting emotion to the sentence generated by the generation unit. The speaking unit describes a specific method for speaking the sentence to which emotion has been imparted by the emotion imparting unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that it is difficult for users to feel familiar with what is being said by smart devices, and they are not sufficiently effective in reducing users' feelings of isolation.

[0005] The system according to the embodiment aims to produce utterances that give a sense of familiarity to the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, an emotion imparting unit, and a speaking unit. The reception unit receives user input. The generation unit generates a sentence based on the information received by the reception unit. The emotion imparting unit describes a specific method for imparting emotion to the sentence generated by the generation unit. The speaking unit describes a specific method for speaking the sentence to which emotion has been imparted by the emotion imparting unit. [Effects of the Invention]

[0007] The system according to the embodiment can produce speech that gives a user a sense of familiarity. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The friendly speech system according to an embodiment of the present invention accepts user input, generates sentences using a generation AI, and then speaks them with emotion. This system achieves friendly speech by accepting user input, generating appropriate sentences based on the user's input, and then imbuing the sentences with emotion. For example, if a user inputs "I'm tired today," the generation AI generates a friendly sentence such as "I see you're tired today. Have a good rest." The generated sentence is then spoken using an artificial voice. By imbuing the voice with emotion, the user feels more at ease. This mechanism allows smart devices to feel friendly toward users and encourage isolated users through their voice. For example, if a user inputs "I'm lonely today," the generation AI generates encouraging words such as "I see you're lonely today. Don't worry, I'm here for you," and speaks them in an emotional voice. This allows the user to feel like their smart device is a friend, reducing their sense of isolation. As a result, the familiar speech system can realize familiar speech by speaking sentences to which emotions are added based on the user's input.

[0029] A speech system that creates a sense of familiarity according to an embodiment includes a reception unit, a generation unit, an emotion imparting unit, and a speech unit. The reception unit receives user input. The user input includes, but is not limited to, text input, voice input, and gesture input. The reception unit provides, for example, an interface through which the user inputs text. The reception unit may also include a microphone for receiving voice input. The reception unit may also include a sensor for receiving gesture input. For example, the reception unit provides an interface through which the user inputs text using a keyboard. The reception unit can receive voice input by the user speaking into the microphone. The reception unit can also receive input by the user making gestures with hand movements. The generation unit generates sentences based on the information received by the reception unit using a generation AI. The generation unit generates sentences using, for example, natural language generation technology. The generation unit can also generate sentences using template-based generation. The generation unit can also generate appropriate sentences based on the user's input using a generation AI. For example, the generation unit generates sentences based on the user's input using natural language generation technology. The generation unit can also use template-based generation to generate sentences based on templates prepared in advance. The emotion imparting unit imparts emotions to the sentences generated by the generation unit. The emotion imparting unit imparts emotions using, for example, an emotion analysis algorithm. The emotion imparting unit can also include an adjustment unit that adjusts the tone, speed, and intonation of the voice. The emotion imparting unit can also include a selection unit that selects an appropriate emotion according to the user's input. For example, the emotion imparting unit imparts emotions to the generated sentences using an emotion analysis algorithm. The emotion imparting unit can also include an adjustment unit that adjusts the tone, speed, and intonation of the voice, and can impart emotions. The emotion imparting unit can also include a selection unit that selects an appropriate emotion according to the user's input, and can impart emotions. The speaking unit speaks the sentences to which emotions have been imparted by the emotion imparting unit. The speaking unit speaks the sentences using, for example, speech synthesis technology.The speech unit can also speak in a voice that has been imparted with emotion. Furthermore, the speech unit can also speak a sentence that has been imparted with emotion using a generation AI. For example, the speech unit uses a voice synthesis technology to speak a sentence that has been imparted with emotion. Furthermore, the speech unit can speak in a voice that has been imparted with emotion. Furthermore, the speech unit can speak a sentence that has been imparted with emotion using a generation AI. As a result, the speech system that creates a sense of familiarity according to the embodiment can realize speech that creates a sense of familiarity by speaking a sentence that has been imparted with emotion based on a user's input.

[0030] The emotion imparting unit may include an adjustment unit that adjusts the tone, speed, and intonation of the voice. The adjustment unit, for example, adjusts the tone of the voice. For example, the adjustment unit can adjust the tone, such as high or low, depending on the emotion. The adjustment unit can also adjust the speed of the voice. For example, the adjustment unit can adjust the speed, such as fast or slow, depending on the emotion. The adjustment unit can also adjust the intonation of the voice. For example, the adjustment unit can adjust the parts to be emphasized or the intonation depending on the emotion. By adjusting the tone, speed, and intonation of the voice, more natural and familiar speech can be achieved. Some or all of the above-described processing in the adjustment unit may be performed using, or without, AI. For example, the adjustment unit may input voice data to a generation AI and cause the generation AI to adjust the tone, speed, and intonation of the voice.

[0031] The emotion assigning unit may include a selection unit that selects an emotion based on the user's input. The selection unit selects an emotion based on the user's input, for example, using an emotion analysis algorithm. For example, if the user inputs "I'm tired today," the selection unit may select an emotion that represents fatigue. Furthermore, if the user inputs "I'm happy today," the selection unit may select an emotion that represents joy. Furthermore, if the user inputs "I'm lonely today," the selection unit may select an emotion that represents loneliness. By selecting an appropriate emotion based on the user's input, it is possible to realize utterances that are assigned a more appropriate emotion. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the user's input data to a generation AI and cause the generation AI to select an emotion.

[0032] The generation unit can generate sentences based on user input. The generation unit generates sentences using, for example, natural language generation technology. For example, if a user inputs "I'm tired today," the generation unit can generate a sentence such as "You're tired today. Have a good rest." The generation unit can also generate sentences using template-based generation. For example, the generation unit can generate sentences based on the user's input based on a pre-prepared template. Furthermore, the generation unit can use a generation AI to generate appropriate sentences based on the user's input. For example, if a user inputs "I'm lonely today," the generation unit can use a generation AI to generate a sentence such as "You're lonely today. Don't worry, I'm here." This allows the generation of appropriate sentences based on the user's input to provide an appropriate response to the user. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input user input data to a generation AI and have the generation AI generate sentences.

[0033] The speech unit can speak in a voice with an emotion imparted to it. The speech unit can, for example, speak sentences using speech synthesis technology. For example, the speech unit can speak in a voice with an emotion imparted to it, such as "You must be tired today. Have a good rest." The speech unit can also speak in a voice with an emotion imparted to it. For example, the speech unit can speak in a voice with an emotion imparted to it, such as "You must be lonely today. Don't worry, I'm here." The speech unit can also speak sentences with an emotion imparted to it using a generation AI. For example, the speech unit can speak in a voice with an emotion imparted to it using a generation AI. In this way, speaking in a voice with an emotion imparted to it can make the user feel closer to it. Some or all of the above-described processing in the speech unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speech unit can input speech data with an emotion imparted to it into a generation AI and cause the generation AI to execute the speech utterance.

[0034] The reception unit can analyze the user's past input history and select a reception method. The reception unit can analyze the user's past input history using, for example, data mining technology. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. Furthermore, the reception unit can suggest a related input method by referring to content entered by the user in the past. This allows the optimal reception method to be selected by analyzing the user's past input history, improving user convenience. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without AI. For example, the reception unit can input the user's past input data into a generation AI and have the generation AI select the optimal reception method.

[0035] The reception unit can perform filtering based on the user's current situation and areas of interest when receiving input. The reception unit, for example, uses real-time data to identify the user's current situation. For example, the reception unit can filter appropriate input content based on the user's situation, such as whether the user is at work or on a break. The reception unit can also preferentially receive related input content based on the user's areas of interest (hobbies, interests, etc.). Furthermore, the reception unit can filter appropriate input content based on the user's current activity (exercising, reading, etc.). This allows for filtering based on the user's current situation and areas of interest, thereby enabling more appropriate input content to be received. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's real-time data to a generation AI and have the generation AI perform filtering.

[0036] When receiving input, the reception unit can prioritize receiving highly relevant inputs by taking into account the user's geographical location information. The reception unit, for example, uses GPS data to identify the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize receiving information related to that area. Furthermore, when the user is traveling, the reception unit can prioritize receiving information related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving information about the area around the user's home. In this way, by taking the user's geographical location information into account, highly relevant inputs can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location data to the generation AI and cause the generation AI to execute a process of determining the priority of highly relevant inputs.

[0037] The reception unit can analyze the user's social media activities and receive related inputs when receiving inputs. The reception unit can, for example, analyze the content of social media posts. For example, the reception unit can prioritize receiving related inputs based on information shared by the user on social media. The reception unit can also prioritize receiving related inputs based on information about accounts the user follows on social media. Furthermore, the reception unit can prioritize receiving related inputs based on topics in which the user has shown interest on social media. In this way, by analyzing the user's social media activities, related inputs can be prioritized. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's social media data to a generation AI and cause the generation AI to execute a process of determining the priority of related inputs.

[0038] When generating a sentence, the generation unit can adjust the level of detail of the sentence based on the importance of the input content. The generation unit, for example, evaluates the importance of the user's input content. For example, the generation unit can generate a sentence including a detailed explanation if the content is important. The generation unit can also generate a concise sentence if the content is general. Furthermore, the generation unit can generate a short sentence that hits the main points if the content is urgent. In this way, by adjusting the level of detail of the sentence based on the importance of the input content, more appropriate sentences can be generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's input data into the generation AI and cause the generation AI to adjust the level of detail of the sentence.

[0039] When generating sentences, the generation unit can apply different generation algorithms depending on the category of the input content. The generation unit, for example, uses a topic classification algorithm to identify the category of the input content. For example, the generation unit can generate fact-based sentences for news-related content. Furthermore, the generation unit can generate sentences including fun expressions for entertainment-related content. Furthermore, the generation unit can generate sentences including technical expressions for business-related content. In this way, by applying different generation algorithms depending on the category of the input content, more appropriate sentences can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to apply a generation algorithm depending on the category.

[0040] When generating a sentence, the generation unit can determine a generation priority based on the submission time of the input content. The generation unit identifies the submission time of the input content using, for example, a timestamp. For example, the generation unit can generate a sentence with the highest priority for urgent content. The generation unit can also generate a sentence with priority for content with an approaching deadline. Furthermore, the generation unit can generate a sentence with normal priority for general content. In this way, by determining the generation priority based on the submission time of the input content, sentences can be generated at a more appropriate time. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to execute a process of determining a generation priority based on the submission time.

[0041] When generating sentences, the generation unit can adjust the order of generation based on the relevance of the input content. The generation unit evaluates the relevance of the input content using, for example, context analysis. For example, the generation unit can prioritize generating sentences for highly relevant content. Furthermore, the generation unit can postpone generating sentences for content with low relevance. Furthermore, the generation unit can generate sentences in a normal order for content with medium relevance. In this way, by adjusting the order of generation based on the relevance of the input content, sentences can be generated in a more appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to execute a process of adjusting the order of generation based on relevance.

[0042] The emotion imparting unit can adjust the intensity of the emotion based on the content of the text when imparting an emotion. The emotion imparting unit adjusts the intensity of the emotion based on, for example, the content of the text. For example, the emotion imparting unit can impart a strong emotion to important content. Furthermore, the emotion imparting unit can impart a calm emotion to general content. Furthermore, the emotion imparting unit can impart a tense emotion to urgent content. In this way, by adjusting the intensity of the emotion based on the content of the text, it is possible to impart a more appropriate emotion. Some or all of the above-described processing in the emotion imparting unit may be performed using, or without, AI, for example. For example, the emotion imparting unit can input text data to a generation AI and cause the generation AI to execute a process of adjusting the intensity of the emotion.

[0043] When assigning emotions, the emotion assigning unit can apply different emotion assigning algorithms depending on the category of the text. The emotion assigning unit, for example, uses a topic classification algorithm to identify the category of the text. For example, the emotion assigning unit can assign a fact-based emotion to news-related content. The emotion assigning unit can assign a happy emotion to entertainment-related content. The emotion assigning unit can assign a technical emotion to business-related content. In this way, by applying different emotion assigning algorithms depending on the category of the text, more appropriate emotions can be assigned. Some or all of the above-mentioned processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to apply an emotion assigning algorithm depending on the category.

[0044] When assigning emotions, the emotion assigning unit can determine the priority of emotions based on the time of submission of the text. The emotion assigning unit identifies the time of submission of the text using, for example, a timestamp. For example, the emotion assigning unit can assign emotions with the highest priority to urgent content. Furthermore, the emotion assigning unit can assign emotions with the highest priority to content with an approaching deadline. Furthermore, the emotion assigning unit can assign emotions with the normal priority to general content. In this way, by determining the priority of emotions based on the time of submission of the text, emotions can be assigned at a more appropriate time. Some or all of the above-described processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to execute a process of determining the priority of emotions based on the time of submission.

[0045] When assigning an emotion, the emotion assigning unit can select a type of emotion based on the relevance of the text. The emotion assigning unit can evaluate the relevance of the text using, for example, context analysis. For example, the emotion assigning unit can assign a strong emotion to highly relevant content. Furthermore, the emotion assigning unit can assign a mild emotion to low-relevance content. Furthermore, the emotion assigning unit can assign a normal emotion to medium-relevance content. In this way, by selecting a type of emotion based on the relevance of the text, a more appropriate emotion can be assigned. Some or all of the above-described processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to execute a process of selecting a type of emotion based on relevance.

[0046] The speech unit can adjust the speech rate based on the content of the sentence when speaking. The speech unit adjusts the speech rate based on, for example, the content of the sentence. For example, the speech unit can speak at a slower speed if the content is important. Furthermore, the speech unit can speak at a normal speed if the content is general. Furthermore, the speech unit can speak at a faster speed if the content is urgent. In this way, by adjusting the speech rate based on the content of the sentence, speech can be spoken at a more appropriate speed. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input sentence data to a generation AI and cause the generation AI to perform processing to adjust the speech rate.

[0047] The speech unit can apply different speech algorithms depending on the category of the text when speaking. The speech unit, for example, uses a topic classification algorithm to identify the category of the text. For example, the speech unit can provide factual speech for news-related content. The speech unit can also provide a fun tone for entertainment-related content. The speech unit can also provide a professional tone for business-related content. This allows for more appropriate speech by applying different speech algorithms depending on the category of the text. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input text data into a generation AI and cause the generation AI to apply a speech algorithm depending on the category.

[0048] The speech unit can determine the priority of speech based on the time of submission of the text when speaking. The speech unit identifies the time of submission of the text using, for example, a timestamp. For example, the speech unit can give top priority to urgent content when it is urgent. Furthermore, the speech unit can give priority to content when the deadline is approaching. Furthermore, the speech unit can give normal priority to general content when it is general. In this way, by determining the priority of speech based on the time of submission of the text, speech can be spoken at a more appropriate time. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input text data to a generation AI and cause the generation AI to execute a process of determining the priority of speech based on the time of submission.

[0049] When speaking, the speech unit can select a speech tone based on the relevance of the sentence. The speech unit evaluates the relevance of the sentence using, for example, context analysis. For example, the speech unit can use a strong tone when the content is highly relevant. Furthermore, the speech unit can use a gentle tone when the content is lowly relevant. Furthermore, the speech unit can use a normal tone when the content is mediumly relevant. In this way, by selecting a speech tone based on the relevance of the sentence, it is possible to speak in a more appropriate tone. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input sentence data to a generation AI and cause the generation AI to perform a process of selecting a speech tone based on relevance.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The friendly speech system can further analyze the user's past speech history and customize the speech content based on the user's preferences and tendencies. For example, if the user has frequently talked about a particular topic in the past, it can prioritize providing information related to that topic. Also, if the user prefers specific vocabulary or expressions, it can generate speech that incorporates those expressions. Furthermore, if the user has been in a particular emotional state in the past, it can provide speech content that corresponds to that emotional state. In this way, by utilizing the user's past speech history, it is possible to realize more personalized and friendly speech.

[0052] The generation unit can further generate sentences taking into account the user's geographical location information. For example, if the user is in a specific area, it can generate sentences containing information related to that area. If the user is traveling, it can generate sentences containing information and advice related to the travel destination. If the user is at home, it can generate sentences related to information and events around the user's home. In this way, by utilizing the user's geographical location information, it is possible to generate more relevant sentences.

[0053] The speech unit can also learn the user's past speech content and select a speech style that suits the user's preferences. For example, it can analyze the user's preferred language and tone in the past and adjust the speech style based on that. It can also learn how the user reacted to a particular topic and customize the speech content based on that reaction. It can also take into account the user's past emotional state and provide speech that suits that emotional state. In this way, by utilizing the user's past speech content, more personalized speech can be achieved.

[0054] The reception unit can further analyze the user's past input history and suggest input methods based on the user's preferences and tendencies. For example, it can preferentially suggest input methods (voice, text, etc.) that the user has frequently used in the past. It can also predict the input method that the user will use in a specific time period and suggest an input method suitable for that time period. Furthermore, it can suggest related input methods by referring to content that the user has input in the past. In this way, it is possible to provide more convenient input methods by utilizing the user's past input history.

[0055] The reception unit can further monitor the user's current activity status and adjust the input reception method according to the status. For example, if the user is exercising, voice input can be given priority. If the user is reading, text input can be given priority. If the user is in a meeting, gesture input can be given priority. This makes it possible to provide a more appropriate input reception method by taking the user's current activity status into consideration.

[0056] The reception unit can further filter the input contents taking into consideration the geographical location information of the user. For example, if the user is in a specific area, information related to that area can be preferentially received. Also, if the user is traveling, information related to the travel destination can be preferentially received. Furthermore, if the user is at home, information about the area around the user's home can be preferentially received. In this way, by taking into consideration the geographical location information of the user, more relevant input contents can be provided.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The reception unit receives user input. User input includes text input, voice input, gesture input, etc. For example, the reception unit provides an interface for the user to input text, and may include a microphone for receiving voice input and a sensor for receiving gesture input. Step 2: The generation unit generates sentences based on the information received by the reception unit. The generation unit can generate sentences using generative AI, natural language generation technology, or template-based generation. For example, the generation unit generates appropriate sentences based on the user's input. Step 3: The emotion assigning unit assigns emotions to the sentences generated by the generation unit. The emotion assigning unit assigns emotions using an emotion analysis algorithm, and may include an adjustment unit that adjusts the tone, speed, and intonation of the voice, and a selection unit that selects an appropriate emotion based on the user's input content. Step 4: The speech unit speaks the sentences to which emotions have been added by the emotion addition unit. The speech unit can use voice synthesis technology and generation AI to speak sentences to which emotions have been added. This allows for speech that feels familiar to the user.

[0059] (Example 2) The friendly speech system according to an embodiment of the present invention accepts user input, generates sentences using a generation AI, and then speaks them with emotion. This system achieves friendly speech by accepting user input, generating appropriate sentences based on the user's input, and then imbuing the sentences with emotion. For example, if a user inputs "I'm tired today," the generation AI generates a friendly sentence such as "I see you're tired today. Have a good rest." The generated sentence is then spoken using an artificial voice. By imbuing the voice with emotion, the user feels more at ease. This mechanism allows smart devices to feel friendly toward users and encourage isolated users through their voice. For example, if a user inputs "I'm lonely today," the generation AI generates encouraging words such as "I see you're lonely today. Don't worry, I'm here for you," and speaks them in an emotional voice. This allows the user to feel like their smart device is a friend, reducing their sense of isolation. As a result, the familiar speech system can realize familiar speech by speaking sentences to which emotions are added based on the user's input.

[0060] A speech system that creates a sense of familiarity according to an embodiment includes a reception unit, a generation unit, an emotion imparting unit, and a speech unit. The reception unit receives user input. The user input includes, but is not limited to, text input, voice input, and gesture input. The reception unit provides, for example, an interface through which the user inputs text. The reception unit may also include a microphone for receiving voice input. The reception unit may also include a sensor for receiving gesture input. For example, the reception unit provides an interface through which the user inputs text using a keyboard. The reception unit can receive voice input by the user speaking into the microphone. The reception unit can also receive input by the user making gestures with hand movements. The generation unit generates sentences based on the information received by the reception unit using a generation AI. The generation unit generates sentences using, for example, natural language generation technology. The generation unit can also generate sentences using template-based generation. The generation unit can also generate appropriate sentences based on the user's input using a generation AI. For example, the generation unit generates sentences based on the user's input using natural language generation technology. The generation unit can also use template-based generation to generate sentences based on templates prepared in advance. The emotion imparting unit imparts emotions to the sentences generated by the generation unit. The emotion imparting unit imparts emotions using, for example, an emotion analysis algorithm. The emotion imparting unit can also include an adjustment unit that adjusts the tone, speed, and intonation of the voice. The emotion imparting unit can also include a selection unit that selects an appropriate emotion according to the user's input. For example, the emotion imparting unit imparts emotions to the generated sentences using an emotion analysis algorithm. The emotion imparting unit can also include an adjustment unit that adjusts the tone, speed, and intonation of the voice, and can impart emotions. The emotion imparting unit can also include a selection unit that selects an appropriate emotion according to the user's input, and can impart emotions. The speaking unit speaks the sentences to which emotions have been imparted by the emotion imparting unit. The speaking unit speaks the sentences using, for example, speech synthesis technology.The speech unit can also speak in a voice that has been imparted with emotion. Furthermore, the speech unit can also speak a sentence that has been imparted with emotion using a generation AI. For example, the speech unit uses a voice synthesis technology to speak a sentence that has been imparted with emotion. Furthermore, the speech unit can speak in a voice that has been imparted with emotion. Furthermore, the speech unit can speak a sentence that has been imparted with emotion using a generation AI. As a result, the speech system that creates a sense of familiarity according to the embodiment can realize speech that creates a sense of familiarity by speaking a sentence that has been imparted with emotion based on a user's input.

[0061] The emotion imparting unit may include an adjustment unit that adjusts the tone, speed, and intonation of the voice. The adjustment unit, for example, adjusts the tone of the voice. For example, the adjustment unit can adjust the tone, such as high or low, depending on the emotion. The adjustment unit can also adjust the speed of the voice. For example, the adjustment unit can adjust the speed, such as fast or slow, depending on the emotion. The adjustment unit can also adjust the intonation of the voice. For example, the adjustment unit can adjust the parts to be emphasized or the intonation depending on the emotion. By adjusting the tone, speed, and intonation of the voice, more natural and familiar speech can be achieved. Some or all of the above-described processing in the adjustment unit may be performed using, or without, AI. For example, the adjustment unit may input voice data to a generation AI and cause the generation AI to adjust the tone, speed, and intonation of the voice.

[0062] The emotion assigning unit may include a selection unit that selects an emotion based on the user's input. The selection unit selects an emotion based on the user's input, for example, using an emotion analysis algorithm. For example, if the user inputs "I'm tired today," the selection unit may select an emotion that represents fatigue. Furthermore, if the user inputs "I'm happy today," the selection unit may select an emotion that represents joy. Furthermore, if the user inputs "I'm lonely today," the selection unit may select an emotion that represents loneliness. By selecting an appropriate emotion based on the user's input, it is possible to realize utterances that are assigned a more appropriate emotion. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the user's input data to a generation AI and cause the generation AI to select an emotion.

[0063] The generation unit can generate sentences based on user input. The generation unit generates sentences using, for example, natural language generation technology. For example, if a user inputs "I'm tired today," the generation unit can generate a sentence such as "You're tired today. Have a good rest." The generation unit can also generate sentences using template-based generation. For example, the generation unit can generate sentences based on the user's input based on a pre-prepared template. Furthermore, the generation unit can use a generation AI to generate appropriate sentences based on the user's input. For example, if a user inputs "I'm lonely today," the generation unit can use a generation AI to generate a sentence such as "You're lonely today. Don't worry, I'm here." This allows the generation of appropriate sentences based on the user's input to provide an appropriate response to the user. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input user input data to a generation AI and have the generation AI generate sentences.

[0064] The speech unit can speak in a voice with an emotion imparted to it. The speech unit can, for example, speak sentences using speech synthesis technology. For example, the speech unit can speak in a voice with an emotion imparted to it, such as "You must be tired today. Have a good rest." The speech unit can also speak in a voice with an emotion imparted to it. For example, the speech unit can speak in a voice with an emotion imparted to it, such as "You must be lonely today. Don't worry, I'm here." The speech unit can also speak sentences with an emotion imparted to it using a generation AI. For example, the speech unit can speak in a voice with an emotion imparted to it using a generation AI. In this way, speaking in a voice with an emotion imparted to it can make the user feel closer to it. Some or all of the above-described processing in the speech unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speech unit can input speech data with an emotion imparted to it into a generation AI and cause the generation AI to execute the speech utterance.

[0065] The reception unit can estimate the user's emotion and adjust the timing of input reception based on the estimated user emotion. The reception unit estimates the user's emotion using, for example, an emotion analysis algorithm. For example, if the user is stressed, the reception unit can delay the timing of input reception and wait until the user is relaxed. Furthermore, if the user is relaxed, the reception unit can immediately accept input, promoting smooth dialogue. Furthermore, if the user is in a hurry, the reception unit can accelerate the timing of input reception and respond quickly. This allows input to be accepted at a more appropriate time by adjusting the timing of input reception according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, an AI. For example, the reception unit can input the user's emotion data to the generation AI and have the generation AI perform emotion estimation.

[0066] The reception unit can analyze the user's past input history and select a reception method. The reception unit can analyze the user's past input history using, for example, data mining technology. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. Furthermore, the reception unit can suggest a related input method by referring to content entered by the user in the past. This allows the optimal reception method to be selected by analyzing the user's past input history, improving user convenience. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without AI. For example, the reception unit can input the user's past input data into a generation AI and have the generation AI select the optimal reception method.

[0067] The reception unit can perform filtering based on the user's current situation and areas of interest when receiving input. The reception unit, for example, uses real-time data to identify the user's current situation. For example, the reception unit can filter appropriate input content based on the user's situation, such as whether the user is at work or on a break. The reception unit can also preferentially receive related input content based on the user's areas of interest (hobbies, interests, etc.). Furthermore, the reception unit can filter appropriate input content based on the user's current activity (exercising, reading, etc.). This allows for filtering based on the user's current situation and areas of interest, thereby enabling more appropriate input content to be received. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's real-time data to a generation AI and have the generation AI perform filtering.

[0068] The reception unit can estimate the user's emotions and determine the priority of inputs to be received based on the estimated user emotions. The reception unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the user is nervous, the reception unit can prioritize receiving inputs with relaxing content. Furthermore, if the user is having fun, the reception unit can prioritize receiving inputs with entertainment-related content. Furthermore, if the user is tired, the reception unit can prioritize receiving inputs with relaxing content. This allows for the priority of inputs to be determined based on the user's emotions, thereby enabling more appropriate inputs to be received preferentially. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, 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-described processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data into the generation AI and cause the generation AI to perform emotion estimation.

[0069] When receiving input, the reception unit can prioritize receiving highly relevant inputs by taking into account the user's geographical location information. The reception unit, for example, uses GPS data to identify the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize receiving information related to that area. Furthermore, when the user is traveling, the reception unit can prioritize receiving information related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving information about the area around the user's home. In this way, by taking the user's geographical location information into account, highly relevant inputs can be prioritized. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location data to the generation AI and cause the generation AI to execute a process of determining the priority of highly relevant inputs.

[0070] The reception unit can analyze the user's social media activities and receive related inputs when receiving inputs. The reception unit can, for example, analyze the content of social media posts. For example, the reception unit can prioritize receiving related inputs based on information shared by the user on social media. The reception unit can also prioritize receiving related inputs based on information about accounts the user follows on social media. Furthermore, the reception unit can prioritize receiving related inputs based on topics in which the user has shown interest on social media. In this way, by analyzing the user's social media activities, related inputs can be prioritized. Some or all of the above-described processing in the reception unit can be performed using, for example, AI, or can be performed without using AI. For example, the reception unit can input the user's social media data to a generation AI and cause the generation AI to execute a process of determining the priority of related inputs.

[0071] The generation unit can estimate the user's emotions and adjust the expression style of the generated sentences based on the estimated user emotions. The generation unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the user is sad, the generation unit can generate sentences using gentle language. If the user is happy, the generation unit can generate sentences using cheerful language. If the user is angry, the generation unit can generate sentences using calm language. This allows for adjusting the expression style of the sentences based on the user's emotions, thereby generating more appropriate sentences. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the expression style of the sentences.

[0072] When generating a sentence, the generation unit can adjust the level of detail of the sentence based on the importance of the input content. The generation unit, for example, evaluates the importance of the user's input content. For example, the generation unit can generate a sentence including a detailed explanation if the content is important. The generation unit can also generate a concise sentence if the content is general. Furthermore, the generation unit can generate a short sentence that hits the main points if the content is urgent. In this way, by adjusting the level of detail of the sentence based on the importance of the input content, more appropriate sentences can be generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's input data into the generation AI and cause the generation AI to adjust the level of detail of the sentence.

[0073] When generating sentences, the generation unit can apply different generation algorithms depending on the category of the input content. The generation unit, for example, uses a topic classification algorithm to identify the category of the input content. For example, the generation unit can generate fact-based sentences for news-related content. Furthermore, the generation unit can generate sentences including fun expressions for entertainment-related content. Furthermore, the generation unit can generate sentences including technical expressions for business-related content. In this way, by applying different generation algorithms depending on the category of the input content, more appropriate sentences can be generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to apply a generation algorithm depending on the category.

[0074] The generation unit can estimate the user's emotions and adjust the length of the generated sentences based on the estimated user emotions. The generation unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the user is in a hurry, the generation unit can generate short, to-the-point sentences. Furthermore, if the user is relaxed, the generation unit can generate longer sentences with detailed explanations. Furthermore, if the user is excited, the generation unit can generate sentences with visually stimulating effects. This allows for more appropriate sentences to be generated by adjusting the length of the sentences based on the user's emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, 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-described processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the sentences.

[0075] When generating a sentence, the generation unit can determine a generation priority based on the submission time of the input content. The generation unit identifies the submission time of the input content using, for example, a timestamp. For example, the generation unit can generate a sentence with the highest priority for urgent content. The generation unit can also generate a sentence with priority for content with an approaching deadline. Furthermore, the generation unit can generate a sentence with normal priority for general content. In this way, by determining the generation priority based on the submission time of the input content, sentences can be generated at a more appropriate time. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to execute a process of determining a generation priority based on the submission time.

[0076] When generating sentences, the generation unit can adjust the order of generation based on the relevance of the input content. The generation unit evaluates the relevance of the input content using, for example, context analysis. For example, the generation unit can prioritize generating sentences for highly relevant content. Furthermore, the generation unit can postpone generating sentences for content with low relevance. Furthermore, the generation unit can generate sentences in a normal order for content with medium relevance. In this way, by adjusting the order of generation based on the relevance of the input content, sentences can be generated in a more appropriate order. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input user input data to the generation AI and cause the generation AI to execute a process of adjusting the order of generation based on relevance.

[0077] The emotion assigning unit can estimate the user's emotion and determine the type of emotion to assign based on the estimated user emotion. The emotion assigning unit estimates the user's emotion using, for example, an emotion analysis algorithm. For example, if the user is sad, the emotion assigning unit can assign a comforting emotion. Furthermore, if the user is happy, the emotion assigning unit can assign an empathetic emotion. Furthermore, if the user is angry, the emotion assigning unit can assign an emotion encouraging the user to stay calm. This allows a more appropriate emotion to be assigned by determining the type of emotion to assign based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, 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-described processing in the emotion assigning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the emotion assigning unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process of determining the type of emotion.

[0078] The emotion imparting unit can adjust the intensity of the emotion based on the content of the text when imparting an emotion. The emotion imparting unit adjusts the intensity of the emotion based on, for example, the content of the text. For example, the emotion imparting unit can impart a strong emotion to important content. Furthermore, the emotion imparting unit can impart a calm emotion to general content. Furthermore, the emotion imparting unit can impart a tense emotion to urgent content. In this way, by adjusting the intensity of the emotion based on the content of the text, it is possible to impart a more appropriate emotion. Some or all of the above-described processing in the emotion imparting unit may be performed using, or without, AI, for example. For example, the emotion imparting unit can input text data to a generation AI and cause the generation AI to execute a process of adjusting the intensity of the emotion.

[0079] When assigning emotions, the emotion assigning unit can apply different emotion assigning algorithms depending on the category of the text. The emotion assigning unit, for example, uses a topic classification algorithm to identify the category of the text. For example, the emotion assigning unit can assign a fact-based emotion to news-related content. The emotion assigning unit can assign a happy emotion to entertainment-related content. The emotion assigning unit can assign a technical emotion to business-related content. In this way, by applying different emotion assigning algorithms depending on the category of the text, more appropriate emotions can be assigned. Some or all of the above-mentioned processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to apply an emotion assigning algorithm depending on the category.

[0080] The emotion assigning unit can estimate the user's emotion and adjust the order of emotion assignment based on the estimated user's emotion. The emotion assigning unit estimates the user's emotion using, for example, an emotion analysis algorithm. For example, if the user is nervous, the emotion assigning unit can prioritize an emotion that makes them feel relaxed. Furthermore, if the user is having fun, the emotion assigning unit can prioritize an emotion related to entertainment. Furthermore, if the user is tired, the emotion assigning unit can prioritize an emotion that makes them feel relaxed. By adjusting the order of emotion assignment based on the user's emotion, emotions can be assigned in a more appropriate order. The emotion estimation is realized using an emotion estimation function, 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-described processing in the emotion assigning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the emotion assigning unit can input the user's emotion data to the generation AI and cause the generation AI to execute a process of adjusting the order of emotion assignment.

[0081] When assigning emotions, the emotion assigning unit can determine the priority of emotions based on the time of submission of the text. The emotion assigning unit identifies the time of submission of the text using, for example, a timestamp. For example, the emotion assigning unit can assign emotions with the highest priority to urgent content. Furthermore, the emotion assigning unit can assign emotions with the highest priority to content with an approaching deadline. Furthermore, the emotion assigning unit can assign emotions with the normal priority to general content. In this way, by determining the priority of emotions based on the time of submission of the text, emotions can be assigned at a more appropriate time. Some or all of the above-described processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to execute a process of determining the priority of emotions based on the time of submission.

[0082] When assigning an emotion, the emotion assigning unit can select a type of emotion based on the relevance of the text. The emotion assigning unit can evaluate the relevance of the text using, for example, context analysis. For example, the emotion assigning unit can assign a strong emotion to highly relevant content. Furthermore, the emotion assigning unit can assign a mild emotion to low-relevance content. Furthermore, the emotion assigning unit can assign a normal emotion to medium-relevance content. In this way, by selecting a type of emotion based on the relevance of the text, a more appropriate emotion can be assigned. Some or all of the above-described processing in the emotion assigning unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion assigning unit can input text data to a generation AI and cause the generation AI to execute a process of selecting a type of emotion based on relevance.

[0083] The speech unit can estimate the user's emotions and adjust the tone of speech based on the estimated user's emotions. The speech unit can estimate the user's emotions using, for example, an emotion analysis algorithm. For example, if the user is sad, the speech unit can speak in a gentle tone. If the user is happy, the speech unit can speak in a bright tone. If the user is angry, the speech unit can speak in a calm tone. By adjusting the tone of speech based on the user's emotions, the speech unit can speak in a more appropriate tone. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 speech unit can be performed using, for example, AI, or without AI. For example, the speech unit can input the user's emotion data into the generation AI and cause the generation AI to perform a process of adjusting the tone of speech.

[0084] The speech unit can adjust the speech rate based on the content of the sentence when speaking. The speech unit adjusts the speech rate based on, for example, the content of the sentence. For example, the speech unit can speak at a slower speed if the content is important. Furthermore, the speech unit can speak at a normal speed if the content is general. Furthermore, the speech unit can speak at a faster speed if the content is urgent. In this way, by adjusting the speech rate based on the content of the sentence, speech can be spoken at a more appropriate speed. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input sentence data to a generation AI and cause the generation AI to perform processing to adjust the speech rate.

[0085] The speech unit can apply different speech algorithms depending on the category of the text when speaking. The speech unit, for example, uses a topic classification algorithm to identify the category of the text. For example, the speech unit can provide factual speech for news-related content. The speech unit can also provide a fun tone for entertainment-related content. The speech unit can also provide a professional tone for business-related content. This allows for more appropriate speech by applying different speech algorithms depending on the category of the text. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input text data into a generation AI and cause the generation AI to apply a speech algorithm depending on the category.

[0086] The speech unit can estimate the user's emotions and adjust the order of speech based on the estimated user emotions. The speech unit estimates the user's emotions using, for example, an emotion analysis algorithm. For example, if the user is nervous, the speech unit can prioritize speech that will help the user relax. Furthermore, if the user is having fun, the speech unit can prioritize speech that will help the user relax. By adjusting the order of speech based on the user's emotions, speech can be delivered in a more appropriate order. The emotion estimation is achieved using, for example, an emotion engine or a generation AI, using an emotion estimation function. The generation AI can be, for example, 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-described processing in the speech unit can be performed using, for example, AI, or without AI. For example, the speech unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process of adjusting the order of speech.

[0087] The speech unit can determine the priority of speech based on the time of submission of the text when speaking. The speech unit identifies the time of submission of the text using, for example, a timestamp. For example, the speech unit can give top priority to urgent content when it is urgent. Furthermore, the speech unit can give priority to content when the deadline is approaching. Furthermore, the speech unit can give normal priority to general content when it is general. In this way, by determining the priority of speech based on the time of submission of the text, speech can be spoken at a more appropriate time. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input text data to a generation AI and cause the generation AI to execute a process of determining the priority of speech based on the time of submission.

[0088] When speaking, the speech unit can select a speech tone based on the relevance of the sentence. The speech unit evaluates the relevance of the sentence using, for example, context analysis. For example, the speech unit can use a strong tone when the content is highly relevant. Furthermore, the speech unit can use a gentle tone when the content is lowly relevant. Furthermore, the speech unit can use a normal tone when the content is mediumly relevant. In this way, by selecting a speech tone based on the relevance of the sentence, it is possible to speak in a more appropriate tone. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input sentence data to a generation AI and cause the generation AI to perform a process of selecting a speech tone based on relevance. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, generation unit, emotion imparting unit, and speaking unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives user input using a touch panel 38A or a microphone 38B of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences using a generation AI. The emotion imparting unit is realized by the specific processing unit 290 of the data processing device 12 and imparts emotions to the generated sentences. The speaking unit speaks the sentences to which emotions have been imparted using a speaker 40B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, generation unit, emotion imparting unit, and speaking unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives user input using the microphone 238 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences using a generation AI. The emotion imparting unit is realized by the specific processing unit 290 of the data processing device 12 and imparts emotions to the generated sentences. The speaking unit speaks the sentences imparted with emotions using the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, generation unit, emotion imparting unit, and speaking unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives user input using the microphone 238 of the headset-type terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences using a generation AI. The emotion imparting unit is realized by the specific processing unit 290 of the data processing device 12 and imparts emotions to the generated sentences. The speaking unit speaks the sentences to which emotions have been imparted using the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, emotion imparting unit, and speaking unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives user input using the microphone 238 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences using a generation AI. The emotion imparting unit is realized by the specific processing unit 290 of the data processing device 12 and imparts emotions to the generated sentences. The speaking unit speaks the sentences imparted with emotions using the speaker 240 of the robot 414.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The friendly speech system can further analyze the user's past speech history and customize the speech content based on the user's preferences and tendencies. For example, if the user has frequently talked about a particular topic in the past, it can prioritize providing information related to that topic. Also, if the user prefers specific vocabulary or expressions, it can generate speech that incorporates those expressions. Furthermore, if the user has been in a particular emotional state in the past, it can provide speech content that corresponds to that emotional state. In this way, by utilizing the user's past speech history, it is possible to realize more personalized and friendly speech.

[0091] The emotion assigning unit can also acquire biometric information of the user and assign emotions based on that information. For example, it can monitor the user's heart rate and electrical skin response to detect stress or relaxation. It can also estimate emotions from facial expressions using facial expression recognition technology. It can also detect changes in emotions by analyzing changes in the user's voice tone and speaking style. This makes it possible to assign emotions more accurately by utilizing the user's biometric information.

[0092] The emotion assigning unit can further analyze the user's social media activity and assign emotions based on that information. For example, it can analyze the posts and comments the user has shared on social media to estimate the user's current emotional state. It can also assign related emotions based on the accounts the user follows and topics the user is interested in. It can also detect changes in emotions by taking into account the frequency and time of the user's social media activity. This makes it possible to assign more appropriate emotions by utilizing the user's social media activity.

[0093] The generation unit can further generate sentences taking into account the user's geographical location information. For example, if the user is in a specific area, it can generate sentences containing information related to that area. If the user is traveling, it can generate sentences containing information and advice related to the travel destination. If the user is at home, it can generate sentences related to information and events around the user's home. In this way, by utilizing the user's geographical location information, it is possible to generate more relevant sentences.

[0094] The speech unit can also learn the user's past speech content and select a speech style that suits the user's preferences. For example, it can analyze the user's preferred language and tone in the past and adjust the speech style based on that. It can also learn how the user reacted to a particular topic and customize the speech content based on that reaction. It can also take into account the user's past emotional state and provide speech that suits that emotional state. In this way, by utilizing the user's past speech content, more personalized speech can be achieved.

[0095] The receiving unit can also acquire biometric information of the user and adjust the timing of input reception based on that information. For example, it can monitor the user's heart rate and galvanic skin response to detect stress or relaxation. It can also use facial expression recognition technology to estimate emotions from facial expressions. It can also analyze changes in the user's voice tone and speaking style to detect changes in emotions. This makes it possible to receive input at a more appropriate time by utilizing the user's biometric information.

[0096] The reception unit can further analyze the user's past input history and suggest input methods based on the user's preferences and tendencies. For example, it can preferentially suggest input methods (voice, text, etc.) that the user has frequently used in the past. It can also predict the input method that the user will use in a specific time period and suggest an input method suitable for that time period. Furthermore, it can suggest related input methods by referring to content that the user has input in the past. In this way, it is possible to provide more convenient input methods by utilizing the user's past input history.

[0097] The reception unit can further monitor the user's current activity status and adjust the input reception method according to the status. For example, if the user is exercising, voice input can be given priority. If the user is reading, text input can be given priority. If the user is in a meeting, gesture input can be given priority. This makes it possible to provide a more appropriate input reception method by taking the user's current activity status into consideration.

[0098] The receiving unit can further estimate the user's emotions and determine the priority of input contents based on the emotions. For example, if the user is nervous, inputs with relaxing content can be preferentially received. If the user is having fun, inputs with entertainment-related content can be preferentially received. If the user is tired, inputs with relaxing content can be preferentially received. Thus, by determining the priority of input contents based on the user's emotions, more appropriate input contents can be provided.

[0099] The reception unit can further filter the input contents taking into consideration the geographical location information of the user. For example, if the user is in a specific area, information related to that area can be preferentially received. Also, if the user is traveling, information related to the travel destination can be preferentially received. Furthermore, if the user is at home, information about the area around the user's home can be preferentially received. In this way, by taking into consideration the geographical location information of the user, more relevant input contents can be provided.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The reception unit receives user input. User input includes text input, voice input, gesture input, etc. For example, the reception unit provides an interface for the user to input text, and may include a microphone for receiving voice input and a sensor for receiving gesture input. Step 2: The generation unit generates sentences based on the information received by the reception unit. The generation unit can generate sentences using generative AI, natural language generation technology, or template-based generation. For example, the generation unit generates appropriate sentences based on the user's input. Step 3: The emotion assigning unit assigns emotions to the sentences generated by the generation unit. The emotion assigning unit assigns emotions using an emotion analysis algorithm, and may include an adjustment unit that adjusts the tone, speed, and intonation of the voice, and a selection unit that selects an appropriate emotion based on the user's input content. Step 4: The speech unit speaks the sentences to which emotions have been added by the emotion addition unit. The speech unit can use voice synthesis technology and generation AI to speak sentences to which emotions have been added. This allows for speech that feels familiar to the user.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, etc., and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] 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.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] 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.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] 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.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] 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.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] 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.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0165] 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.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0173] [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives input from a user; a generation unit that generates a sentence based on the information received by the reception unit; an emotion imparting unit that describes a specific method for imparting emotion to the sentence generated by the generation unit; and a speech unit that describes a specific method for speaking the sentence to which the emotion has been added by the emotion adding unit. A system characterized by:

2. The emotion imparting unit Includes an adjustment section that describes specific ways to adjust the tone, speed, and intonation of the voice. The system of claim 1 .

3. The emotion imparting unit A selection section is provided that describes a specific method for selecting an emotion according to the user's input. The system of claim 1 .

4. The generation unit Describe how to generate sentences based on user input. The system of claim 1 .

5. The speech unit is Describe the specific method for speaking with emotion-added voice. The system of claim 1 .

6. The reception unit Describe a specific method for estimating a user's emotions and adjusting the timing of input acceptance based on the estimated user emotions. The system of claim 1 .

7. The reception unit Analyze the user's past input history and describe the specific method for selecting the reception method. The system of claim 1 .

8. The reception unit Describe how to filter input based on the user's current situation and interests. The system of claim 1 .

9. The reception unit Describe a specific method for estimating a user's emotions and determining the priority of inputs to be accepted based on the estimated user emotions. The system of claim 1 .

Images