System

Abstract

An object of a system according to an embodiment is to propose an appropriate topic on the basis of a flow of conversation.SOLUTION: A system includes a conversion unit, an analysis unit, and a proposal unit. The conversion unit converts the content of the conversation into text. The analysis unit analyzes the text converted by the conversion unit and extracts a topic. The suggestion unit suggests a topic on the basis of the analysis result obtained by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to find appropriate topics to talk about when meeting someone for the first time.

[0005] The system according to the embodiment aims to suggest appropriate topics based on the flow of conversation. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversion unit, an analysis unit, and a suggestion unit. The conversion unit converts the content of a conversation into text. The analysis unit analyzes the text converted by the conversion unit and extracts topics. The suggestion unit suggests topics based on the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can suggest appropriate topics based on the flow of the conversation. [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) A conversation support system according to an embodiment of the present invention analyzes conversation content in real time and suggests appropriate topics. The conversation support system converts the conversation content into text, analyzes it, and suggests appropriate topics, thereby enabling a smooth conversation with someone meeting for the first time. For example, when a user starts a conversation, the conversation support system analyzes the conversation content in real time. For example, the conversation content is converted into text and analyzed using voice recognition technology. Next, the conversation support system suggests appropriate topics based on the analysis results. For example, if a user says, "I went on a trip recently," the conversation support system extracts the keyword "travel" and suggests related topics. This allows the user to continue the conversation in a natural flow. Furthermore, the conversation support system suggests topics that fit the flow of the conversation, making it easier to deepen friendships. For example, if a user says, "I ate some delicious food on my trip," the conversation support system suggests questions such as, "What kind of food did you eat?" or "I'd like to know the recipe for that dish." This makes it easier for the user to find common topics with the other person and deepen friendships. This allows the conversation support system to smoothly advance a conversation with someone meeting for the first time. For example, by having topics suggested that fit the flow of the conversation, users will no longer be at a loss for topics to talk about, making it easier to deepen friendships.

[0029] A conversation support system according to an embodiment includes a conversion unit, an analysis unit, and a suggestion unit. The conversion unit converts the content of a conversation into text. The conversion unit converts the content of a conversation into text using, for example, speech recognition technology. The conversion unit can also use speech recognition technology using deep learning. The conversion unit can also use speech recognition technology using an HMM (hidden Markov model). For example, the conversion unit converts a user's speech into text in real time using speech recognition technology. The conversion unit can also convert the user's speech into text with high accuracy using speech recognition technology. The analysis unit analyzes the text converted by the conversion unit and extracts appropriate topics. The analysis unit analyzes the text using, for example, natural language processing technology. The analysis unit can also analyze the text using a machine learning algorithm. The analysis unit can also analyze the text using deep learning. For example, the analysis unit extracts keywords from the text using natural language processing technology. The analysis unit can also extract important information from the text using a machine learning algorithm. The suggestion unit suggests appropriate topics based on the analysis results obtained by the analysis unit. The suggestion unit, for example, suggests questions to the user based on the analysis results. The suggestion unit can also suggest related topics to the user based on the analysis results. Furthermore, the suggestion unit can also suggest specific topics to the user based on the analysis results. For example, the suggestion unit can suggest questions to the user, such as "Where did you go?" or "What did you do on your trip?" based on the analysis results. The suggestion unit can also suggest questions to the user, such as "What kind of food did you eat?" or "I want to know the recipe for that dish," based on the analysis results. This allows the conversation support system according to the embodiment to analyze the content of a conversation in real time and suggest appropriate topics. This allows a conversation with someone meeting for the first time to proceed smoothly. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can suggest topics using an AI model that receives the analysis results obtained by the analysis unit as input and outputs appropriate topics.

[0030] The conversion unit can convert the content of the conversation into text using speech recognition technology. Examples of speech recognition technology include, but are not limited to, speech recognition technology using deep learning and speech recognition technology using HMM (hidden Markov model). The conversion unit can convert the user's speech into text in real time using speech recognition technology. The conversion unit can also convert the user's speech into text with high accuracy using speech recognition technology using deep learning. Furthermore, the conversion unit can convert the user's speech into text using speech recognition technology using HMM. This allows the use of speech recognition technology to accurately convert the content of the conversation into text. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input speech data to a generation AI and cause the generation AI to convert the speech data into text data.

[0031] The analysis unit can analyze the text converted by the conversion unit and extract appropriate topics. Appropriate topics include, but are not limited to, user interests and conversational contexts. The analysis unit can analyze the text and extract appropriate topics using, for example, natural language processing technology. The analysis unit can also analyze the text and extract appropriate topics using a machine learning algorithm. The analysis unit can also analyze the text and extract appropriate topics using deep learning. For example, the analysis unit can extract keywords from the text using natural language processing technology. The analysis unit can also extract important information from the text using a machine learning algorithm. This allows for the extraction of appropriate topics through text analysis, thereby smoothing the flow of conversation. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to extract appropriate topics.

[0032] The suggestion unit can suggest appropriate topics based on the analysis results obtained by the analysis unit. Appropriate topics include, but are not limited to, the user's interests and the conversation context. For example, the suggestion unit can suggest questions to the user based on the analysis results. The suggestion unit can also suggest related topics to the user based on the analysis results. Furthermore, the suggestion unit can suggest specific topics to the user based on the analysis results. For example, the suggestion unit can suggest questions to the user, such as "Where did you go?" or "What did you do on your trip?" based on the analysis results. The suggestion unit can also suggest questions to the user, such as "What kind of food did you eat?" or "I want to know the recipe for that dish." By suggesting topics based on the analysis results, the conversation can continue uninterrupted. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can suggest topics using an AI model that receives the analysis results obtained by the analysis unit as input and outputs appropriate topics.

[0033] During speech recognition, the conversion unit can adjust the recognition algorithm according to the user's speaking speed and accent. Examples of speaking speed and accent include, but are not limited to, fast speaking, slow speaking, and specific accents. For example, when the user speaks quickly, the conversion unit can speed up the speech recognition algorithm and accurately convert the speech into text. Furthermore, when the user speaks slowly, the conversion unit can adjust the speech recognition algorithm and convert the speech into text at a natural pace. Furthermore, when the user has a specific accent, the conversion unit can apply a speech recognition algorithm corresponding to that accent. This improves the accuracy of speech recognition by optimizing the recognition algorithm according to the user's speaking speed and accent. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without AI. For example, the conversion unit can input the user's voice data into a generation AI and cause the generation AI to adjust the recognition algorithm according to the speaking speed and accent.

[0034] The conversion unit can apply filtering technology to remove background noise during speech recognition. Examples of background noise include, but are not limited to, environmental sounds and background noise. For example, the conversion unit detects background noise during a conversation in real time and removes it using filtering technology. Furthermore, when a user is speaking in a noisy environment, the conversion unit can also apply noise canceling technology to improve speech recognition accuracy. Furthermore, when a user is speaking in a quiet environment, the conversion unit can minimize filtering technology and convert natural speech into text. This removes background noise, improving speech recognition accuracy. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input speech data to a generation AI and have the generation AI remove background noise.

[0035] During speech recognition, the conversion unit can learn the user's past speech patterns to improve recognition accuracy. Past speech patterns include, but are not limited to, frequently used phrases, words, and speech rhythms. For example, the conversion unit analyzes the user's past speech data to learn specific speech patterns. The conversion unit can also apply an algorithm that prioritizes recognition of phrases and words frequently used by the user. Furthermore, the conversion unit can continuously improve the accuracy of speech recognition based on the user's speech patterns. This improves the accuracy of speech recognition by learning the user's past speech patterns. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the user's past speech data into a generation AI and cause the generation AI to learn the speech patterns and improve recognition accuracy.

[0036] The conversion unit can improve recognition accuracy by taking into account the user's geographical dialect and slang during speech recognition. Geographical dialects and slang include, but are not limited to, regional language models and slang dictionaries. For example, if the user speaks a specific dialect, the conversion unit can apply a speech recognition algorithm corresponding to that dialect. Furthermore, if the user frequently uses slang, the conversion unit can add a dictionary for recognizing that slang. Furthermore, the conversion unit can prioritize recognition of specific dialects and slang based on the user's geographical background. This improves speech recognition accuracy by taking into account the user's geographical dialect and slang. Some or all of the above-described processing in the conversion unit can be performed using, for example, AI, or without AI. For example, the conversion unit can input the user's voice data into a generation AI and cause the generation AI to improve recognition accuracy by taking into account the user's geographical dialect and slang.

[0037] During speech recognition, the conversion unit can analyze the user's social media activity and recognize related speech patterns. Social media activity includes, but is not limited to, the content of posts and the phrases and words used. For example, the conversion unit analyzes the user's social media posts to learn related speech patterns. The conversion unit can also add specific phrases and words used by the user on social media to the speech recognition algorithm. Furthermore, the conversion unit can prioritize the recognition of specific topics based on the user's social media activity. This makes it easier to recognize related speech patterns by analyzing the user's social media activity. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input the user's social media data into a generation AI and have the generation AI learn and recognize speech patterns.

[0038] During speech recognition, the conversion unit can customize the recognition algorithm by reflecting the user's past feedback. Past feedback includes, but is not limited to, user evaluation data and feedback loops. The conversion unit adjusts the speech recognition algorithm, for example, based on feedback provided by the user in the past. The conversion unit can also reflect feedback provided by the user to make it easier for the user to recognize specific speech patterns. Furthermore, the conversion unit can continuously improve the accuracy of speech recognition based on the user's feedback. This improves the accuracy of speech recognition by reflecting the user's past feedback. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input user feedback data into the generation AI and cause the generation AI to customize the recognition algorithm.

[0039] The analysis unit can improve the accuracy of keyword extraction by taking into account the context of the conversation during text analysis. The context of the conversation includes, but is not limited to, the content of previous and following utterances and related topics. For example, the analysis unit analyzes the context before and after the conversation to extract related keywords. The analysis unit can also preferentially extract important keywords based on the flow of the conversation. Furthermore, the analysis unit can extract keywords including synonyms and related words by taking into account the context of the conversation. This improves the accuracy of keyword extraction by taking into account the context of the conversation. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to extract keywords taking into account the context of the conversation.

[0040] When analyzing text, the analysis unit can apply different analysis algorithms depending on the category of the conversation. Conversation categories include, but are not limited to, business, everyday conversation, and technical conversation. For example, if the conversation is about a hobby, the analysis unit can apply an analysis algorithm specialized for hobbies. Furthermore, if the conversation is about work, the analysis unit can also apply an analysis algorithm specialized for work. Furthermore, if the conversation is about travel, the analysis unit can also apply an analysis algorithm specialized for travel. By applying an analysis algorithm depending on the category of the conversation, analysis accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to apply an analysis algorithm depending on the category of the conversation.

[0041] During text analysis, the analysis unit can improve analysis accuracy by referring to the user's past conversation history. Past conversation history includes, but is not limited to, frequently used phrases and words, specific topics, and the like. For example, the analysis unit analyzes the user's past conversation history and prioritizes analysis of specific topics. The analysis unit can also add frequently used phrases and words to the analysis algorithm. Furthermore, the analysis unit can continuously improve the accuracy of text analysis based on the user's past conversation history. This improves analysis accuracy by referring to the user's past conversation history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past conversation data into the generation AI and cause the generation AI to analyze the conversation history and improve analysis accuracy.

[0042] During text analysis, the analysis unit can determine the analysis priority based on the time of submission of the conversation. The submission time includes, but is not limited to, for example, the submission date and time, the submission order, etc. The analysis unit, for example, prioritizes analysis of the most recent conversation and provides the analysis results in real time. The analysis unit can also prioritize analysis of conversations of higher importance based on the time of submission of the conversation. Furthermore, the analysis unit can adjust the order of analysis according to the time of submission of the conversation to perform analysis efficiently. This enables efficient analysis by determining the analysis priority based on the time of submission of the conversation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation data to a generation AI and have the generation AI determine the analysis priority based on the time of submission.

[0043] During text analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. Examples of the relevance of the conversations include, but are not limited to, commonality of topics and relevance scores. For example, the analysis unit analyzes the relevance of the conversations and prioritizes analysis of highly relevant conversations. The analysis unit can also analyze related conversations consecutively based on the flow of the conversation. Furthermore, the analysis unit can adjust the order of analysis according to the relevance of the conversations and perform analysis efficiently. This enables efficient analysis by adjusting the order of analysis based on the relevance of the conversations. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation data to a generation AI and cause the generation AI to adjust the order of analysis based on the relevance.

[0044] During text analysis, the analysis unit can adjust the use of technical terms in the analysis based on the user's level of expertise. Examples of technical terms include, but are not limited to, the user's occupation and past comments. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Alternatively, if the user does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. Furthermore, the analysis unit can adjust the way the analysis results are presented based on the user's level of expertise. This allows for more appropriate analysis results to be obtained by adjusting the use of technical terms in the analysis based on the user's level of expertise. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's technical expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the analysis based on the user's level of expertise.

[0045] When proposing a topic, the suggestion unit can adjust the level of detail of the suggestion based on the importance of the conversation. The importance of the conversation includes, but is not limited to, the purpose of the conversation and the roles of the participants. For example, the suggestion unit can suggest detailed topics in the case of an important conversation. The suggestion unit can also suggest concise topics in the case of a casual conversation. Furthermore, the suggestion unit can adjust the level of detail of the suggested topic according to the importance of the conversation. This allows for more appropriate topic suggestions by adjusting the level of detail of the suggestion based on the importance of the conversation. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input conversation data into a generation AI and cause the generation AI to adjust the level of detail of the suggestion based on the importance.

[0046] When suggesting a topic, the suggestion unit can apply different suggestion algorithms depending on the category of the conversation. Conversation categories include, but are not limited to, business, everyday conversation, and technical conversation. For example, if the conversation is about hobbies, the suggestion unit can apply a suggestion algorithm specialized for hobbies. Furthermore, if the conversation is about work, the suggestion unit can also apply a suggestion algorithm specialized for work. Furthermore, if the conversation is about travel, the suggestion unit can also apply a suggestion algorithm specialized for travel. By applying a suggestion algorithm depending on the category of the conversation, more appropriate topic suggestions can be made. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input conversation data into a generation AI and cause the generation AI to apply a suggestion algorithm depending on the category.

[0047] When suggesting a topic, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. Past suggestion results include, but are not limited to, the success rate of the suggestion and user feedback. For example, the suggestion unit analyzes the user's past suggestion results and prioritizes suggesting successful topics. The suggestion unit can also make new suggestions based on topics that the user has previously preferred. Furthermore, the suggestion unit can continuously improve the suggestion algorithm based on the user's past suggestion results. This improves the accuracy of the suggestions by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's past suggestion data into the generation AI and cause the generation AI to improve the accuracy of the suggestions.

[0048] When proposing a topic, the suggestion unit can determine the priority of the suggestions based on the time of submission of the conversation. The submission time includes, but is not limited to, for example, the submission date and time, the submission order, etc. The suggestion unit can, for example, prioritize the most recent conversation and provide topics in real time. The suggestion unit can also prioritize the suggestions of higher importance based on the time of submission of the conversation. Furthermore, the suggestion unit can adjust the order of suggestions according to the time of submission of the conversation to efficiently provide topics. This enables more appropriate topic suggestions by determining the priority of suggestions based on the time of submission of the conversation. Some or all of the above-described processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input conversation data to a generation AI and cause the generation AI to determine the priority of suggestions based on the time of submission.

[0049] When suggesting topics, the suggestion unit can adjust the order of suggestions based on the relevance of the conversation. Conversational relevance includes, but is not limited to, for example, topic commonality and relevance scores. For example, the suggestion unit can analyze the relevance of the conversation and prioritize suggesting highly relevant topics. The suggestion unit can also consecutively suggest related topics based on the flow of the conversation. Furthermore, the suggestion unit can adjust the order of suggestions according to the relevance of the conversation to efficiently provide topics. This enables more appropriate topic suggestions by adjusting the order of suggestions based on the relevance of the conversation. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input conversation data to a generation AI and cause the generation AI to adjust the order of suggestions based on relevance.

[0050] When proposing a topic, the suggestion unit can adjust the use of technical terms in the proposal depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation and past comments. For example, if the user has technical expertise, the suggestion unit may make a proposal that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the suggestion unit may make a proposal using easy-to-understand language. Furthermore, the suggestion unit can adjust the way the proposal is expressed depending on the user's level of expertise. This allows for more appropriate topic suggestions by adjusting the use of technical terms in the proposal depending on the user's level of expertise. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit may input the user's technical expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the proposal based on the user's level of expertise.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The conversation support system can also learn from the user's past conversation history to improve the accuracy of the topics it suggests. For example, it can analyze what the user has said in the past and prioritize recognizing frequently used phrases and words. It can also make new suggestions based on topics the user has shown interest in in the past. Furthermore, it can continuously improve the suggestion algorithm based on the user's past conversation history. This improves the accuracy of suggestions by referring to the user's past conversation history.

[0053] The conversation support system can further analyze the user's social media activity to recognize related speech patterns. For example, it can analyze the user's social media posts to learn related speech patterns. It can also add specific phrases and words used by the user on social media to the speech recognition algorithm. It can also prioritize recognition of specific topics based on the user's social media activity. This makes it easier to recognize related speech patterns by analyzing the user's social media activity.

[0054] The conversation support system can further improve recognition accuracy by taking into account the user's geographical dialect and slang. For example, if the user speaks a specific dialect, a speech recognition algorithm corresponding to that dialect can be applied. Also, if the user frequently uses slang, a dictionary for recognizing that slang can be added. Furthermore, specific dialects and slang can be prioritized for recognition based on the user's geographical background. In this way, the accuracy of speech recognition can be improved by taking into account the user's geographical dialect and slang.

[0055] The conversation support system can further customize the recognition algorithm by reflecting the user's past feedback. For example, the speech recognition algorithm can be adjusted based on feedback provided by the user in the past. The system can also reflect feedback from the user to make it easier to recognize specific speech patterns. Furthermore, the conversation support system can continuously improve the accuracy of speech recognition based on the user's feedback. In this way, the accuracy of speech recognition can be improved by reflecting the user's past feedback.

[0056] The conversation support system can also adjust the use of technical terms in the analysis based on the user's level of expertise. For example, if the user has technical expertise, the system can provide analysis results that use a lot of technical terms. On the other hand, if the user does not have technical expertise, the system can provide analysis results in easy-to-understand language. Furthermore, the system can also adjust the way the analysis results are presented based on the user's level of expertise. This allows for more appropriate analysis results to be obtained by adjusting the use of technical terms in the analysis based on the user's level of expertise.

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

[0058] Step 1: The conversion unit converts the content of the conversation into text. The conversion unit converts the content of the conversation into text using, for example, speech recognition technology. The conversion unit can also use speech recognition technology using deep learning or speech recognition technology using HMM (hidden Markov model). For example, the conversion unit uses speech recognition technology to convert the user's speech into text in real time with high accuracy. Step 2: The analysis unit analyzes the text converted by the conversion unit and extracts appropriate topics. The analysis unit analyzes the text using, for example, natural language processing technology, machine learning algorithms, or deep learning. For example, the analysis unit can extract keywords from the text using natural language processing technology and extract important information using machine learning algorithms. Step 3: The suggestion unit suggests appropriate topics based on the analysis results obtained by the analysis unit. The suggestion unit, for example, suggests questions, related topics, or specific topics to the user based on the analysis results. For example, it can suggest questions such as "Where did you go?", "What did you do on your trip?", "What kind of food did you eat?", or "I want to know the recipe for that dish." The processing in the suggestion unit can also be performed using an AI model.

[0059] (Example 2) A conversation support system according to an embodiment of the present invention analyzes conversation content in real time and suggests appropriate topics. The conversation support system converts the conversation content into text, analyzes it, and suggests appropriate topics, thereby enabling a smooth conversation with someone meeting for the first time. For example, when a user starts a conversation, the conversation support system analyzes the conversation content in real time. For example, the conversation content is converted into text and analyzed using voice recognition technology. Next, the conversation support system suggests appropriate topics based on the analysis results. For example, if a user says, "I went on a trip recently," the conversation support system extracts the keyword "travel" and suggests related topics. This allows the user to continue the conversation in a natural flow. Furthermore, the conversation support system suggests topics that fit the flow of the conversation, making it easier to deepen friendships. For example, if a user says, "I ate some delicious food on my trip," the conversation support system suggests questions such as, "What kind of food did you eat?" or "I'd like to know the recipe for that dish." This makes it easier for the user to find common topics with the other person and deepen friendships. This allows the conversation support system to smoothly advance a conversation with someone meeting for the first time. For example, by having topics suggested that fit the flow of the conversation, users will no longer be at a loss for topics to talk about, making it easier to deepen friendships.

[0060] A conversation support system according to an embodiment includes a conversion unit, an analysis unit, and a suggestion unit. The conversion unit converts the content of a conversation into text. The conversion unit converts the content of a conversation into text using, for example, speech recognition technology. The conversion unit can also use speech recognition technology using deep learning. The conversion unit can also use speech recognition technology using an HMM (hidden Markov model). For example, the conversion unit converts a user's speech into text in real time using speech recognition technology. The conversion unit can also convert the user's speech into text with high accuracy using speech recognition technology. The analysis unit analyzes the text converted by the conversion unit and extracts appropriate topics. The analysis unit analyzes the text using, for example, natural language processing technology. The analysis unit can also analyze the text using a machine learning algorithm. The analysis unit can also analyze the text using deep learning. For example, the analysis unit extracts keywords from the text using natural language processing technology. The analysis unit can also extract important information from the text using a machine learning algorithm. The suggestion unit suggests appropriate topics based on the analysis results obtained by the analysis unit. The suggestion unit, for example, suggests questions to the user based on the analysis results. The suggestion unit can also suggest related topics to the user based on the analysis results. Furthermore, the suggestion unit can also suggest specific topics to the user based on the analysis results. For example, the suggestion unit can suggest questions to the user, such as "Where did you go?" or "What did you do on your trip?" based on the analysis results. The suggestion unit can also suggest questions to the user, such as "What kind of food did you eat?" or "I want to know the recipe for that dish," based on the analysis results. This allows the conversation support system according to the embodiment to analyze the content of a conversation in real time and suggest appropriate topics. This allows a conversation with someone meeting for the first time to proceed smoothly. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can suggest topics using an AI model that receives the analysis results obtained by the analysis unit as input and outputs appropriate topics.

[0061] The conversion unit can convert the content of the conversation into text using speech recognition technology. Examples of speech recognition technology include, but are not limited to, speech recognition technology using deep learning and speech recognition technology using HMM (hidden Markov model). The conversion unit can convert the user's speech into text in real time using speech recognition technology. The conversion unit can also convert the user's speech into text with high accuracy using speech recognition technology using deep learning. Furthermore, the conversion unit can convert the user's speech into text using speech recognition technology using HMM. This allows the use of speech recognition technology to accurately convert the content of the conversation into text. Some or all of the above-mentioned processing in the conversion unit can be performed using, for example, AI, or can be performed without using AI. For example, the conversion unit can input speech data to a generation AI and cause the generation AI to convert the speech data into text data.

[0062] The analysis unit can analyze the text converted by the conversion unit and extract appropriate topics. Appropriate topics include, but are not limited to, user interests and conversational contexts. The analysis unit can analyze the text and extract appropriate topics using, for example, natural language processing technology. The analysis unit can also analyze the text and extract appropriate topics using a machine learning algorithm. The analysis unit can also analyze the text and extract appropriate topics using deep learning. For example, the analysis unit can extract keywords from the text using natural language processing technology. The analysis unit can also extract important information from the text using a machine learning algorithm. This allows for the extraction of appropriate topics through text analysis, thereby smoothing the flow of conversation. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to extract appropriate topics.

[0063] The suggestion unit can suggest appropriate topics based on the analysis results obtained by the analysis unit. Appropriate topics include, but are not limited to, the user's interests and the conversation context. For example, the suggestion unit can suggest questions to the user based on the analysis results. The suggestion unit can also suggest related topics to the user based on the analysis results. Furthermore, the suggestion unit can suggest specific topics to the user based on the analysis results. For example, the suggestion unit can suggest questions to the user, such as "Where did you go?" or "What did you do on your trip?" based on the analysis results. The suggestion unit can also suggest questions to the user, such as "What kind of food did you eat?" or "I want to know the recipe for that dish." By suggesting topics based on the analysis results, the conversation can continue uninterrupted. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can suggest topics using an AI model that receives the analysis results obtained by the analysis unit as input and outputs appropriate topics.

[0064] The conversion unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user emotions. Examples of user emotions include, but are not limited to, nervousness, relaxation, and hurrying. For example, if the user is nervous, the conversion unit can increase the sensitivity of speech recognition to convert the speech into text more accurately. Alternatively, if the user is relaxed, the conversion unit can maintain normal sensitivity of speech recognition and convert natural conversation into text. Furthermore, if the user is hurrying, the conversion unit can increase the speed of speech recognition to quickly convert the speech into text. This enables more accurate text conversion by adjusting the accuracy of speech recognition according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation and speech recognition accuracy adjustment.

[0065] During speech recognition, the conversion unit can adjust the recognition algorithm according to the user's speaking speed and accent. Examples of speaking speed and accent include, but are not limited to, fast speaking, slow speaking, and specific accents. For example, when the user speaks quickly, the conversion unit can speed up the speech recognition algorithm and accurately convert the speech into text. Furthermore, when the user speaks slowly, the conversion unit can adjust the speech recognition algorithm and convert the speech into text at a natural pace. Furthermore, when the user has a specific accent, the conversion unit can apply a speech recognition algorithm corresponding to that accent. This improves the accuracy of speech recognition by optimizing the recognition algorithm according to the user's speaking speed and accent. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without AI. For example, the conversion unit can input the user's voice data into a generation AI and cause the generation AI to adjust the recognition algorithm according to the speaking speed and accent.

[0066] The conversion unit can apply filtering technology to remove background noise during speech recognition. Examples of background noise include, but are not limited to, environmental sounds and background noise. For example, the conversion unit detects background noise during a conversation in real time and removes it using filtering technology. Furthermore, when a user is speaking in a noisy environment, the conversion unit can also apply noise canceling technology to improve speech recognition accuracy. Furthermore, when a user is speaking in a quiet environment, the conversion unit can minimize filtering technology and convert natural speech into text. This removes background noise, improving speech recognition accuracy. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input speech data to a generation AI and have the generation AI remove background noise.

[0067] During speech recognition, the conversion unit can learn the user's past speech patterns to improve recognition accuracy. Past speech patterns include, but are not limited to, frequently used phrases, words, and speech rhythms. For example, the conversion unit analyzes the user's past speech data to learn specific speech patterns. The conversion unit can also apply an algorithm that prioritizes recognition of phrases and words frequently used by the user. Furthermore, the conversion unit can continuously improve the accuracy of speech recognition based on the user's speech patterns. This improves the accuracy of speech recognition by learning the user's past speech patterns. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the user's past speech data into a generation AI and cause the generation AI to learn the speech patterns and improve recognition accuracy.

[0068] The conversion unit can estimate the user's emotion and adjust the timing of speech recognition based on the estimated user's emotion. Examples of the timing of speech recognition include, but are not limited to, the start and end of speech. For example, if the user is nervous, the conversion unit can delay the timing of speech recognition to allow the user time to speak more slowly. Furthermore, if the user is relaxed, the conversion unit can maintain the normal timing of speech recognition and convert natural conversation into text. Furthermore, if the user is in a hurry, the conversion unit can accelerate the timing of speech recognition to quickly convert the speech into text. This allows speech to be converted into text at a more appropriate timing by adjusting the timing of speech recognition according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as 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 conversion unit may be performed using, for example, AI, or without AI. For example, the conversion unit can input the user's voice data into the generation AI and have the generation AI estimate emotions and adjust the timing of voice recognition.

[0069] The conversion unit can improve recognition accuracy by taking into account the user's geographical dialect and slang during speech recognition. Geographical dialects and slang include, but are not limited to, regional language models and slang dictionaries. For example, if the user speaks a specific dialect, the conversion unit can apply a speech recognition algorithm corresponding to that dialect. Furthermore, if the user frequently uses slang, the conversion unit can add a dictionary for recognizing that slang. Furthermore, the conversion unit can prioritize recognition of specific dialects and slang based on the user's geographical background. This improves speech recognition accuracy by taking into account the user's geographical dialect and slang. Some or all of the above-described processing in the conversion unit can be performed using, for example, AI, or without AI. For example, the conversion unit can input the user's voice data into a generation AI and cause the generation AI to improve recognition accuracy by taking into account the user's geographical dialect and slang.

[0070] During speech recognition, the conversion unit can analyze the user's social media activity and recognize related speech patterns. Social media activity includes, but is not limited to, the content of posts and the phrases and words used. For example, the conversion unit analyzes the user's social media posts to learn related speech patterns. The conversion unit can also add specific phrases and words used by the user on social media to the speech recognition algorithm. Furthermore, the conversion unit can prioritize the recognition of specific topics based on the user's social media activity. This makes it easier to recognize related speech patterns by analyzing the user's social media activity. Some or all of the above-described processing in the conversion unit may be performed using, or without, AI. For example, the conversion unit can input the user's social media data into a generation AI and have the generation AI learn and recognize speech patterns.

[0071] During speech recognition, the conversion unit can customize the recognition algorithm by reflecting the user's past feedback. Past feedback includes, but is not limited to, user evaluation data and feedback loops. The conversion unit adjusts the speech recognition algorithm, for example, based on feedback provided by the user in the past. The conversion unit can also reflect feedback provided by the user to make it easier for the user to recognize specific speech patterns. Furthermore, the conversion unit can continuously improve the accuracy of speech recognition based on the user's feedback. This improves the accuracy of speech recognition by reflecting the user's past feedback. Some or all of the above-described processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input user feedback data into the generation AI and cause the generation AI to customize the recognition algorithm.

[0072] The analysis unit can estimate the user's emotions and adjust the text analysis method based on the estimated user emotions. Examples of user emotions include, but are not limited to, nervousness, relaxation, and hurrying. For example, if the user is nervous, the analysis unit can perform concise and easy-to-understand text analysis. Furthermore, if the user is relaxed, the analysis unit can perform detailed text analysis to extract more information. Furthermore, if the user is hurrying, the analysis unit can quickly perform text analysis to prioritize the extraction of important information. This enables more appropriate analysis by adjusting the text analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's text data into the generation AI and cause the generation AI to estimate emotions and adjust the text analysis method.

[0073] The analysis unit can improve the accuracy of keyword extraction by taking into account the context of the conversation during text analysis. The context of the conversation includes, but is not limited to, the content of previous and following utterances and related topics. For example, the analysis unit analyzes the context before and after the conversation to extract related keywords. The analysis unit can also preferentially extract important keywords based on the flow of the conversation. Furthermore, the analysis unit can extract keywords including synonyms and related words by taking into account the context of the conversation. This improves the accuracy of keyword extraction by taking into account the context of the conversation. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to extract keywords taking into account the context of the conversation.

[0074] When analyzing text, the analysis unit can apply different analysis algorithms depending on the category of the conversation. Conversation categories include, but are not limited to, business, everyday conversation, and technical conversation. For example, if the conversation is about a hobby, the analysis unit can apply an analysis algorithm specialized for hobbies. Furthermore, if the conversation is about work, the analysis unit can also apply an analysis algorithm specialized for work. Furthermore, if the conversation is about travel, the analysis unit can also apply an analysis algorithm specialized for travel. By applying an analysis algorithm depending on the category of the conversation, analysis accuracy is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data to a generation AI and cause the generation AI to apply an analysis algorithm depending on the category of the conversation.

[0075] During text analysis, the analysis unit can improve analysis accuracy by referring to the user's past conversation history. Past conversation history includes, but is not limited to, frequently used phrases and words, specific topics, and the like. For example, the analysis unit analyzes the user's past conversation history and prioritizes analysis of specific topics. The analysis unit can also add frequently used phrases and words to the analysis algorithm. Furthermore, the analysis unit can continuously improve the accuracy of text analysis based on the user's past conversation history. This improves analysis accuracy by referring to the user's past conversation history. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past conversation data into the generation AI and cause the generation AI to analyze the conversation history and improve analysis accuracy.

[0076] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. Examples of display methods for the analysis results include, but are not limited to, graph display, text display, and user interface design. For example, if the user is nervous, the analysis unit can display concise and easy-to-understand analysis results. Furthermore, if the user is relaxed, the analysis unit can also display detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can prioritize displaying important information. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI estimate the emotion and adjust the display method of the analysis results.

[0077] During text analysis, the analysis unit can determine the analysis priority based on the time of submission of the conversation. The submission time includes, but is not limited to, for example, the submission date and time, the submission order, etc. The analysis unit, for example, prioritizes analysis of the most recent conversation and provides the analysis results in real time. The analysis unit can also prioritize analysis of conversations of higher importance based on the time of submission of the conversation. Furthermore, the analysis unit can adjust the order of analysis according to the time of submission of the conversation to perform analysis efficiently. This enables efficient analysis by determining the analysis priority based on the time of submission of the conversation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation data to a generation AI and have the generation AI determine the analysis priority based on the time of submission.

[0078] During text analysis, the analysis unit can adjust the order of analysis based on the relevance of the conversations. Examples of the relevance of the conversations include, but are not limited to, commonality of topics and relevance scores. For example, the analysis unit analyzes the relevance of the conversations and prioritizes analysis of highly relevant conversations. The analysis unit can also analyze related conversations consecutively based on the flow of the conversation. Furthermore, the analysis unit can adjust the order of analysis according to the relevance of the conversations and perform analysis efficiently. This enables efficient analysis by adjusting the order of analysis based on the relevance of the conversations. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation data to a generation AI and cause the generation AI to adjust the order of analysis based on the relevance.

[0079] During text analysis, the analysis unit can adjust the use of technical terms in the analysis based on the user's level of expertise. Examples of technical terms include, but are not limited to, the user's occupation and past comments. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terms. Alternatively, if the user does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. Furthermore, the analysis unit can adjust the way the analysis results are presented based on the user's level of expertise. This allows for more appropriate analysis results to be obtained by adjusting the use of technical terms in the analysis based on the user's level of expertise. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's technical expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the analysis based on the user's level of expertise.

[0080] The suggestion unit can estimate the user's emotions and adjust the presentation style of topic suggestions based on the estimated user emotions. Examples of topic suggestion presentation styles include, but are not limited to, text tone and suggestion format. For example, if the user is nervous, the suggestion unit can propose topics in a gentle tone. If the user is relaxed, the suggestion unit can also propose topics in a friendly tone. If the user is in a hurry, the suggestion unit can also propose topics that are concise and to the point. This enables more appropriate topic suggestions by adjusting the presentation style of topic suggestions according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the suggestion unit may be performed using, for example, an AI. For example, the suggestion unit can input the user's emotion data into the generation AI and cause the generation AI to estimate emotions and adjust the presentation style of topic suggestions.

[0081] When proposing a topic, the suggestion unit can adjust the level of detail of the suggestion based on the importance of the conversation. The importance of the conversation includes, but is not limited to, the purpose of the conversation and the roles of the participants. For example, the suggestion unit can suggest detailed topics in the case of an important conversation. The suggestion unit can also suggest concise topics in the case of a casual conversation. Furthermore, the suggestion unit can adjust the level of detail of the suggested topic according to the importance of the conversation. This allows for more appropriate topic suggestions by adjusting the level of detail of the suggestion based on the importance of the conversation. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input conversation data into a generation AI and cause the generation AI to adjust the level of detail of the suggestion based on the importance.

[0082] When suggesting a topic, the suggestion unit can apply different suggestion algorithms depending on the category of the conversation. Conversation categories include, but are not limited to, business, everyday conversation, and technical conversation. For example, if the conversation is about hobbies, the suggestion unit can apply a suggestion algorithm specialized for hobbies. Furthermore, if the conversation is about work, the suggestion unit can also apply a suggestion algorithm specialized for work. Furthermore, if the conversation is about travel, the suggestion unit can also apply a suggestion algorithm specialized for travel. By applying a suggestion algorithm depending on the category of the conversation, more appropriate topic suggestions can be made. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input conversation data into a generation AI and cause the generation AI to apply a suggestion algorithm depending on the category.

[0083] When suggesting a topic, the suggestion unit can improve the accuracy of the suggestion by referring to the user's past suggestion results. Past suggestion results include, but are not limited to, the success rate of the suggestion and user feedback. For example, the suggestion unit analyzes the user's past suggestion results and prioritizes suggesting successful topics. The suggestion unit can also make new suggestions based on topics that the user has previously preferred. Furthermore, the suggestion unit can continuously improve the suggestion algorithm based on the user's past suggestion results. This improves the accuracy of the suggestions by referring to the user's past suggestion results. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's past suggestion data into the generation AI and cause the generation AI to improve the accuracy of the suggestions.

[0084] The suggestion unit can estimate the user's emotions and adjust the length of the suggestions based on the estimated user emotions. Examples of the length of the suggestions include, but are not limited to, the number of characters in the suggestions and the level of detail in the suggestions. For example, if the user is nervous, the suggestion unit can provide short and concise suggestions. If the user is relaxed, the suggestion unit can also provide detailed suggestions. If the user is in a hurry, the suggestion unit can also provide quick and concise suggestions. This enables more appropriate topic suggestions by adjusting the length of the suggestions according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI. For example, the suggestion unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion and adjust the length of the suggestions.

[0085] When proposing a topic, the suggestion unit can determine the priority of the suggestions based on the time of submission of the conversation. The submission time includes, but is not limited to, for example, the submission date and time, the submission order, etc. The suggestion unit can, for example, prioritize the most recent conversation and provide topics in real time. The suggestion unit can also prioritize the suggestions of higher importance based on the time of submission of the conversation. Furthermore, the suggestion unit can adjust the order of suggestions according to the time of submission of the conversation to efficiently provide topics. This enables more appropriate topic suggestions by determining the priority of suggestions based on the time of submission of the conversation. Some or all of the above-described processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input conversation data to a generation AI and cause the generation AI to determine the priority of suggestions based on the time of submission.

[0086] When suggesting topics, the suggestion unit can adjust the order of suggestions based on the relevance of the conversation. Conversational relevance includes, but is not limited to, for example, topic commonality and relevance scores. For example, the suggestion unit can analyze the relevance of the conversation and prioritize suggesting highly relevant topics. The suggestion unit can also consecutively suggest related topics based on the flow of the conversation. Furthermore, the suggestion unit can adjust the order of suggestions according to the relevance of the conversation to efficiently provide topics. This enables more appropriate topic suggestions by adjusting the order of suggestions based on the relevance of the conversation. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input conversation data to a generation AI and cause the generation AI to adjust the order of suggestions based on relevance.

[0087] When proposing a topic, the suggestion unit can adjust the use of technical terms in the proposal depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation and past comments. For example, if the user has technical expertise, the suggestion unit may make a proposal that uses a lot of technical terms. Furthermore, if the user does not have technical expertise, the suggestion unit may make a proposal using easy-to-understand language. Furthermore, the suggestion unit can adjust the way the proposal is expressed depending on the user's level of expertise. This allows for more appropriate topic suggestions by adjusting the use of technical terms in the proposal depending on the user's level of expertise. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit may input the user's technical expertise data into a generation AI and cause the generation AI to adjust the use of technical terms in the proposal based on the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements including the conversion unit, analysis unit, and suggestion unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversion unit can acquire a user's speech as voice data using the microphone 38B of the smart device 14 and convert the speech data into text using voice recognition technology by the processor 46. The analysis unit can be realized, for example, by the specific processing unit 290 of the data processing device 12, and analyze the text converted by the conversion unit to extract appropriate topics. The suggestion unit can be realized, for example, by the specific processing unit 290 of the data processing device 12, and suggest appropriate topics to the user based on the analysis results. The suggestion unit can also be realized, for example, by the control unit 46A of the smart device 14, and can suggest specific topics to the user. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversion unit can acquire the user's speech as voice data using the microphone 238 of the smart glasses 214 and convert the speech into text using voice recognition technology by the processor 46. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text converted by the conversion unit and extracts appropriate topics. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests appropriate topics to the user based on the analysis results. The suggestion unit can also be realized, for example, by the control unit 46A of the smart glasses 214, and can suggest specific topics to the user. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned conversion unit, analysis unit, and suggestion unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the conversion unit can acquire the user's speech as voice data using the microphone 238 of the headset-type terminal 314 and convert the speech into text using voice recognition technology by the processor 46. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text converted by the conversion unit to extract appropriate topics. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests appropriate topics to the user based on the analysis results. The suggestion unit can also be realized, for example, by the control unit 46A of the headset-type terminal 314, and can suggest specific topics to the user. === Hard Collateral 1-4 === Each of the multiple elements including the conversion unit, analysis unit, and suggestion unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversion unit can acquire the user's speech as voice data using the microphone 238 of the robot 414 and convert the speech into text using voice recognition technology by the processor 46. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the text converted by the conversion unit to extract appropriate topics. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests appropriate topics to the user based on the analysis results. The suggestion unit can also be realized, for example, by the control unit 46A of the robot 414, and can suggest specific topics to the user.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The conversation support system can also learn from the user's past conversation history to improve the accuracy of the topics it suggests. For example, it can analyze what the user has said in the past and prioritize recognizing frequently used phrases and words. It can also make new suggestions based on topics the user has shown interest in in the past. Furthermore, it can continuously improve the suggestion algorithm based on the user's past conversation history. This improves the accuracy of suggestions by referring to the user's past conversation history.

[0090] The conversation support system can further analyze the user's social media activity to recognize related speech patterns. For example, it can analyze the user's social media posts to learn related speech patterns. It can also add specific phrases and words used by the user on social media to the speech recognition algorithm. It can also prioritize recognition of specific topics based on the user's social media activity. This makes it easier to recognize related speech patterns by analyzing the user's social media activity.

[0091] The conversation support system can further improve recognition accuracy by taking into account the user's geographical dialect and slang. For example, if the user speaks a specific dialect, a speech recognition algorithm corresponding to that dialect can be applied. Also, if the user frequently uses slang, a dictionary for recognizing that slang can be added. Furthermore, specific dialects and slang can be prioritized for recognition based on the user's geographical background. In this way, the accuracy of speech recognition can be improved by taking into account the user's geographical dialect and slang.

[0092] The conversation support system can further customize the recognition algorithm by reflecting the user's past feedback. For example, the speech recognition algorithm can be adjusted based on feedback provided by the user in the past. The system can also reflect feedback from the user to make it easier to recognize specific speech patterns. Furthermore, the conversation support system can continuously improve the accuracy of speech recognition based on the user's feedback. In this way, the accuracy of speech recognition can be improved by reflecting the user's past feedback.

[0093] The conversation support system can also adjust the use of technical terms in the analysis based on the user's level of expertise. For example, if the user has technical expertise, the system can provide analysis results that use a lot of technical terms. On the other hand, if the user does not have technical expertise, the system can provide analysis results in easy-to-understand language. Furthermore, the system can also adjust the way the analysis results are presented based on the user's level of expertise. This allows for more appropriate analysis results to be obtained by adjusting the use of technical terms in the analysis based on the user's level of expertise.

[0094] The conversation support system can estimate the user's emotions and adjust the length of suggestions based on the estimated user emotions. For example, if the user is nervous, it can make short and concise suggestions. If the user is relaxed, it can make detailed suggestions. Furthermore, if the user is in a hurry, it can make quick and to the point suggestions. This allows for more appropriate topic suggestions by adjusting the length of suggestions according to the user's emotions.

[0095] The conversation support system can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, it can display simple and easy-to-understand analysis results. If the user is relaxed, it can also display detailed analysis results. Furthermore, if the user is in a hurry, it can prioritize the display of important information. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions.

[0096] The conversation support system can estimate the user's emotions and adjust the way topic suggestions are expressed based on the estimated user's emotions. For example, if the user is nervous, the system can suggest topics in a gentle tone. If the user is relaxed, the system can also suggest topics in a friendly tone. Furthermore, if the user is in a hurry, the system can suggest topics that are concise and to the point. This allows the system to make more appropriate topic suggestions by adjusting the way topic suggestions are expressed based on the user's emotions.

[0097] The conversation support system can estimate the user's emotions and adjust the timing of speech recognition based on the estimated user's emotions. For example, if the user is nervous, the timing of speech recognition can be delayed to provide time for the user to speak slowly. Alternatively, if the user is relaxed, the timing of speech recognition can be kept normal to convert natural conversation into text. Furthermore, if the user is in a hurry, the timing of speech recognition can be accelerated to convert into text quickly. In this way, by adjusting the timing of speech recognition according to the user's emotions, speech can be converted into text at a more appropriate timing.

[0098] The conversation support system can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user's emotions. For example, if the user is nervous, the sensitivity of speech recognition can be increased to convert the speech into text more accurately. Alternatively, if the user is relaxed, the sensitivity of speech recognition can be kept normal to convert natural conversation into text. Furthermore, if the user is in a hurry, the speed of speech recognition can be increased to convert the speech into text quickly. In this way, adjusting the accuracy of speech recognition according to the user's emotions enables more accurate text conversion.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The conversion unit converts the content of the conversation into text. The conversion unit converts the content of the conversation into text using, for example, speech recognition technology. The conversion unit can also use speech recognition technology using deep learning or speech recognition technology using HMM (hidden Markov model). For example, the conversion unit uses speech recognition technology to convert the user's speech into text in real time with high accuracy. Step 2: The analysis unit analyzes the text converted by the conversion unit and extracts appropriate topics. The analysis unit analyzes the text using, for example, natural language processing technology, machine learning algorithms, or deep learning. For example, the analysis unit can extract keywords from the text using natural language processing technology and extract important information using machine learning algorithms. Step 3: The suggestion unit suggests appropriate topics based on the analysis results obtained by the analysis unit. The suggestion unit, for example, suggests questions, related topics, or specific topics to the user based on the analysis results. For example, it can suggest questions such as "Where did you go?", "What did you do on your trip?", "What kind of food did you eat?", or "I want to know the recipe for that dish." The processing in the suggestion unit can also be performed using an AI model.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] [Explanation of symbols]

[0173] 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 conversion unit that converts the content of the conversation into text; an analysis unit that analyzes the text converted by the conversion unit and extracts topics; a suggestion unit that suggests a topic based on the analysis result obtained by the analysis unit. A system characterized by:

2. The conversion unit Converts conversations into text using voice recognition technology 2. The system of claim 1.

3. The analysis unit Analyzing the text converted by the conversion unit and extracting appropriate topics 2. The system of claim 1.

4. The proposal unit Based on the analysis results obtained by the analysis unit, an appropriate topic is suggested.

2. The system of claim 1.

5. The conversion unit Estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user emotions.

2. The system of claim 1.

6. The conversion unit During speech recognition, the recognition algorithm adjusts according to the user's speaking speed and accent.

2. The system of claim 1.

7. The conversion unit Apply filtering techniques to remove background noise during speech recognition 2. The system of claim 1.

8. The conversion unit During voice recognition, the system learns the user's past speech patterns to improve recognition accuracy.

2. The system of claim 1.

Images