System

Abstract

To provide a system for proposing an appropriate topic by analyzing an opposite party's manner of speaking and a wording.SOLUTION: A system includes an analysis section, a proposal section, and a substitution proposal section. The analysis section analyzes an opposite party's manner of speaking or a wording in real time. The proposal section proposes a topic on the basis of an analysis result obtained by the analysis section. The substitution proposal section proposes another topic when determining that a topic proposed by the proposal section is inappropriate.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it was difficult to find appropriate topics to talk about in conversations with people you meet for the first time or with your boss.

[0005] The system according to the embodiment aims to analyze the speaking style and language of the other person and suggest appropriate topics. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a suggestion unit, and an alternative suggestion unit. The analysis unit analyzes the other person's speaking style or language in real time. The suggestion unit suggests a topic based on the analysis result obtained by the analysis unit. The alternative suggestion unit suggests a different topic when the topic suggested by the suggestion unit is determined to be inappropriate. Effect of the Invention

[0007] The system according to the embodiment can analyze the speaking style and vocabulary of the other person and suggest appropriate topics. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The topic advisor system according to the embodiment of the present invention is a system for people who have trouble with conversations with people they meet for the first time, their superiors, or their seniors. This system analyzes the other person's way of speaking and language in real time and suggests appropriate topics, thereby making it possible to smoothly advance a conversation. For example, data for analyzing the other person's way of speaking and language in real time is collected. This data includes the other person's intonation and language. For example, the other person's way of speaking and language can be collected while the other person is talking. Next, the analysis unit analyzes the collected data in real time. This analysis unit estimates the other person's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For example, the accuracy of the analysis can be adjusted according to the emotions, such as when the other person is excited or calm. In addition, the analysis unit adjusts the analysis algorithm by referring to the other person's past conversation history and geographical background, thereby improving the accuracy of the analysis. Based on the analysis result, the suggestion unit suggests an appropriate topic. Based on the analysis result, the suggestion unit suggests topics for talking to a person meeting for the first time, for talking to a superior, for talking to a subordinate, and the like. For example, the system can propose topics related to common hobbies and interests to a person who is meeting for the first time, and topics related to work to a superior. Furthermore, if the topic proposed by the proposal unit fails, the alternative proposal unit proposes another topic. The alternative proposal unit includes an alternative proposal generation unit for proposing another topic in case the topic proposed by the proposal unit fails. For example, if the other party does not show interest in the proposed topic, the alternative proposal unit can propose a new topic. This system allows the system to delve deeper into topics that interest the other party, making it easier to find another topic. For example, if the other party is interested in sports, a topic related to sports can be proposed and further explored. Furthermore, even if the other party does not show interest, the alternative proposal unit proposes a new topic, so that the conversation can continue without interruption. As a result, the topic advisor system can smoothly advance conversations with people who meet for the first time, superiors, and seniors.

[0029] The topic advisor system according to the embodiment includes an analysis unit, a suggestion unit, and an alternative suggestion unit. The analysis unit analyzes the other party's speech or language in real time. For example, the analysis unit collects voice data and converts it into text data using a voice recognition technology. Next, the analysis unit analyzes the text data and extracts the other party's speech or language pattern. For example, the analysis unit analyzes the other party's intonation and accent to grasp the characteristics of the speech. The analysis unit also estimates the other party's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For example, if the other party is excited, the analysis unit estimates the emotions using an emotion engine and takes into account the emotion data to improve the accuracy of the analysis. The suggestion unit suggests a topic based on the analysis result obtained by the analysis unit. For example, the suggestion unit selects an appropriate topic based on the analysis result to suggest a topic that will interest the other party. For example, the suggestion unit suggests a topic related to the other party's occupation or hobby. The suggestion unit can also suggest a topic according to the other party's emotions. For example, if the other party is relaxed, the suggestion unit suggests a relaxing topic. The alternative suggestion unit proposes another topic when the topic proposed by the suggestion unit fails. The alternative suggestion unit, for example, proposes another topic by referring to the other party's past conversation history. For example, the alternative suggestion unit acquires the other party's past conversation history from a database and proposes a topic that the other party showed interest in in the past. The alternative suggestion unit can also estimate the other party's emotions and propose another topic based on the emotions. For example, if the other party is excited, the alternative suggestion unit proposes an interesting topic. In this way, the topic advisor system according to the embodiment can smoothly advance the conversation by analyzing the other party's way of speaking and language and proposing an appropriate topic. Furthermore, even if the proposed topic fails, the conversation will not be interrupted by proposing another topic.

[0030] The analysis unit analyzes the other party's speech or language in real time. For example, the analysis unit collects voice data and converts it into text data using voice recognition technology. Specifically, the voice data is collected through a microphone and processed into clear voice data using noise reduction technology. After that, a voice recognition engine analyzes the voice data and converts it into text data. This voice recognition engine uses a model using deep learning, and can convert voice into text with high accuracy. Next, the analysis unit analyzes the text data and extracts patterns of the other party's speech and language. For example, natural language processing (NLP) technology is used to extract keywords and phrases from the text data and grasp the characteristics of the other party's speech. Furthermore, speech prosody analysis technology is used to analyze intonation and accent. This allows the rhythm and emphasis of the other party's speech to be grasped, enabling more detailed analysis. The analysis unit also estimates the other party's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For emotion estimation, an emotion analysis algorithm based on the tone and speed of the voice and the content of the text is used. For example, if the other person is excited, the analysis unit uses an emotion engine to estimate the emotion and takes into account the emotion data to improve the accuracy of the analysis. This allows the analysis unit to comprehensively analyze the other person's speaking style and emotions and provide more accurate analysis results.

[0031] The suggestion unit proposes a topic based on the analysis result obtained by the analysis unit. For example, the suggestion unit selects an appropriate topic based on the analysis result in order to propose a topic that will interest the other party. Specifically, the suggestion unit refers to the other party's profile information and past conversation history in order to propose a topic related to the other party's occupation or hobby. For example, if the other party is an engineer, the suggestion unit proposes topics related to the latest technology trends and industry news. Also, if the other party likes sports, the suggestion unit can propose topics related to recent game results and player performance. Furthermore, the suggestion unit can also propose a topic according to the other party's emotions. For example, if the other party is relaxed, the suggestion unit proposes a topic that will relax them. Specifically, if it is estimated that the other party is relaxed, the suggestion unit selects topics related to travel, hobbies, and relaxation. Also, if the other party is feeling stressed, the suggestion unit can propose a topic related to stress relief methods and relaxation techniques. When proposing these topics, the suggestion unit monitors the other party's reaction in real time and evaluates the effectiveness of the proposal. As a result, the suggestion unit can propose optimal topics according to the other party's interests and emotions, and smoothly progress the conversation.

[0032] The alternative suggestion unit proposes another topic when the topic proposed by the suggestion unit fails. The alternative suggestion unit proposes another topic by, for example, referring to the other party's past conversation history. Specifically, the alternative suggestion unit acquires the other party's past conversation history from a database and proposes topics that the other party has shown interest in in the past. For example, if the other party has shown interest in topics related to travel in the past, the alternative suggestion unit proposes topics related to the latest travel information and recommended travel destinations. The alternative suggestion unit can also estimate the other party's emotions and propose another topic based on the emotions. For example, if the other party is excited, the alternative suggestion unit proposes an interesting topic. Specifically, if it is estimated that the other party is excited, the alternative suggestion unit selects a topic related to sports or entertainment. Also, if the other party is calm, the alternative suggestion unit can propose a topic that will relax the other party. The alternative suggestion unit, like the suggestion unit, monitors the other party's reaction in real time and evaluates the effectiveness of the proposal. As a result, even if the topic proposed by the suggestion unit fails, the alternative suggestion unit can quickly propose another topic to prevent the conversation from being interrupted. Furthermore, the alternative suggestion unit accumulates a history of suggestions and uses it for future suggestions, thereby continuously improving the accuracy of the suggestions. This allows the alternative suggestion unit to always suggest optimal topics and smoothly advance the conversation.

[0033] The topic advisor system includes a collection unit that collects data for analyzing the other party's speech or language in real time. The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit, for example, collects voice data and converts it into text data using voice recognition technology. The collection unit collects the other party's intonation and accent in real time. For example, the collection unit collects the other party's speaking speed and rhythm in real time. The collection unit can also collect specific words and phrases used by the other party in real time. For example, the collection unit analyzes voice data and extracts specific words and phrases in order to grasp the characteristics of the other party's speaking style. As a result, the accuracy of the analysis is improved by collecting the other party's speaking style and language in real time. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0034] The suggestion unit includes a proposal generation unit for suggesting an appropriate topic based on the analysis result. The suggestion unit includes a proposal generation unit for suggesting an appropriate topic based on the analysis result. The suggestion unit proposes a topic that will interest the other party based on the analysis result, for example. The suggestion unit can propose a topic related to the other party's occupation or hobby. For example, the suggestion unit can also propose a topic according to the other party's emotions. If the other party is relaxed, the suggestion unit proposes a relaxing topic. If the other party is excited, the suggestion unit can propose an interesting topic. This improves the quality of the conversation by suggesting an appropriate topic based on the analysis result. A part or all of the above-mentioned 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 the analysis result to the generation AI and cause the generation AI to execute the proposal of an appropriate topic.

[0035] The alternative suggestion unit includes an alternative suggestion generation unit for suggesting another topic when the topic proposed by the suggestion unit is determined to be inappropriate. The alternative suggestion unit includes an alternative suggestion generation unit for suggesting another topic when the topic proposed by the suggestion unit is determined to be inappropriate. For example, when the topic proposed by the suggestion unit fails, the alternative suggestion unit suggests another topic by referring to the other party's past conversation history. The alternative suggestion unit can estimate the other party's emotions and suggest another topic based on the emotions. For example, the alternative suggestion unit suggests another topic based on the other party's occupation or hobby. In this way, even if the proposed topic fails, the conversation is not interrupted by proposing another topic. A part or all of the above-mentioned processing in the alternative suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, when the topic proposed by the suggestion unit fails, the alternative suggestion unit can cause the generation AI to execute the proposal of another topic.

[0036] The analysis unit adjusts the analysis algorithm by referring to the other party's past conversation history during analysis. The analysis unit adjusts the analysis algorithm by referring to the other party's past conversation history during analysis. The analysis unit, for example, acquires the other party's past conversation history from a database and adjusts the analysis algorithm. The analysis unit performs analysis by referring to the other party's past conversation history and placing emphasis on specific keywords and phrases. The analysis unit analyzes the other party's past conversation history and adjusts the analysis algorithm based on frequently used words and phrases. As a result, the accuracy of analysis is improved by referring to the past conversation history. A part or all of the above-mentioned 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 past conversation history data to the generation AI and cause the generation AI to adjust the analysis algorithm.

[0037] The analysis unit learns the speech pattern of the other party during analysis, and improves the accuracy of the analysis. The analysis unit learns the speech pattern of the other party during analysis, and improves the accuracy of the analysis. The analysis unit, for example, learns the speech pattern of the other party using a machine learning algorithm, and improves the accuracy of the analysis. The analysis unit learns the speed and rhythm of the other party's speech, and improves the accuracy of the analysis. The analysis unit learns the intonation and accent of the other party's speech, and improves the accuracy of the analysis. In this way, the speech pattern is learned, and the accuracy of the analysis is improved. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input speech pattern data to the generation AI and cause the generation AI to execute learning.

[0038] The analysis unit performs analysis based on the geographical background of the other party during analysis. The analysis unit performs analysis based on the geographical background of the other party during analysis. The analysis unit, for example, acquires the geographical background of the other party from a database and adjusts the analysis algorithm. The analysis unit prioritizes topics related to a specific region based on the geographical background of the other party during analysis. The analysis unit considers the geographical background of the other party and performs analysis with emphasis on words and phrases specific to the region. As a result, analysis based on the geographical background makes it possible to perform analysis taking into account information specific to the region. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input geographical background data to the generation AI and cause the generation AI to execute the analysis.

[0039] The suggestion unit suggests topics to talk about when talking with a person who meets for the first time, when talking with a superior, or when talking with a subordinate. The suggestion unit suggests topics to talk about when talking with a person who meets for the first time, when talking with a superior, or when talking with a subordinate. For example, the suggestion unit suggests topics of common hobbies or interests to a person who meets for the first time. The suggestion unit suggests topics related to work to a superior. The suggestion unit suggests topics that are relaxing to a subordinate. In this way, the conversation progresses smoothly by suggesting topics according to the other person's position. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit may input the other person's position data into the generation AI and cause the generation AI to execute the topic suggestion.

[0040] The suggestion unit, at the time of making a proposal, improves the accuracy of the proposal by referring to the other party's past conversation history. The suggestion unit, at the time of making a proposal, improves the accuracy of the proposal by referring to the other party's past conversation history. For example, the suggestion unit acquires the other party's past conversation history from a database and improves the accuracy of the proposal. The suggestion unit makes a proposal by referring to the other party's past conversation history and placing emphasis on specific keywords and phrases. The suggestion unit analyzes the other party's past conversation history and improves the accuracy of the proposal based on frequently used words and phrases. As a result, the accuracy of the proposal is improved by referring to the past conversation history. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit may input past conversation history data to the generation AI and cause the generation AI to execute improvement of the accuracy of the proposal.

[0041] The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit collects, for example, the intonation and accent of the other party's speech in real time. The collection unit collects the other party's speaking speed and rhythm in real time. The collection unit can collect specific words and phrases used by the other party in real time. This improves the accuracy of the analysis by collecting the other party's speech and language in real time. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0042] The collection unit adjusts the collection method by referring to the other party's past conversation history at the time of collection. The collection unit adjusts the collection method by referring to the other party's past conversation history at the time of collection. For example, the collection unit acquires the other party's past conversation history from a database and adjusts the collection method. The collection unit refers to the other party's past conversation history and performs collection with emphasis on specific keywords and phrases. The collection unit analyzes the other party's past conversation history and adjusts the collection method based on frequently used words and phrases. As a result, the collection method is optimized by referring to the past conversation history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit inputs past conversation history data to the generation AI and causes the generation AI to adjust the collection method.

[0043] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0044] The analysis unit can take into account the cultural background of the other party when analyzing the other party's speech style and vocabulary. For example, if the other party is from a particular cultural region, the analysis will prioritize words and expressions specific to that culture. The analysis unit can also learn the characteristics of the other party's speech style and vocabulary according to their age group, improving the accuracy of the analysis. Furthermore, the analysis unit can perform a more accurate analysis by incorporating technical terms and phrases related to the other party's occupation or field of expertise into the analysis. This makes it possible to perform an analysis according to the other party's cultural background, age group, and occupation, and to suggest more appropriate topics.

[0045] The suggestion unit can analyze the other person's real-time body language and suggest appropriate topics. For example, if the other person has their arms crossed, it can suggest relaxing topics. Also, if the other person nods frequently, it can dig deeper into interesting topics. Furthermore, if the other person looks away, it can suggest the right time to change the topic. This makes it possible to suggest topics based on the other person's body language, improving the quality of conversation.

[0046] The alternative suggestion unit can analyze the other person's real-time physiological data (e.g., heart rate and electrodermal activity) and suggest appropriate alternative topics. For example, if the other person's heart rate is increasing, relaxing topics can be suggested. Also, if the other person's electrodermal activity is increasing, interesting topics can be suggested. Furthermore, if the other person's physiological data is stable, topics that can be explored in more depth can be suggested. This makes it possible to suggest alternative topics based on the other person's physiological data, allowing the conversation to continue without interruption.

[0047] The analysis unit can analyze changes in the tone and volume of the other person's voice and suggest appropriate topics. For example, if the other person's voice tone is getting louder, it can suggest topics that will pique their interest. Also, if the other person's volume is dropping, it can suggest topics that will relax them. Furthermore, it can suggest topics to be deepened or changed depending on changes in the other person's voice tone and volume. This makes it possible to suggest topics based on the other person's voice tone and volume, improving the quality of conversation.

[0048] The analysis unit can analyze the other party's past social media posts and suggest appropriate topics. For example, it can suggest topics related to the other party's hobbies and interests that the other party has posted about in the past. It can also suggest topics based on topics that the other party frequently mentions. Furthermore, it can suggest common topics taking into account the other party's friendships and networks on social media. This makes it possible to suggest topics based on the other party's social media data, improving the quality of conversation.

[0049] The suggestion unit can analyze the other person's real-time body language and suggest appropriate topics. For example, if the other person has their arms crossed, it can suggest relaxing topics. Also, if the other person nods frequently, it can dig deeper into interesting topics. Furthermore, if the other person looks away, it can suggest the right time to change the topic. This makes it possible to suggest topics based on the other person's body language, improving the quality of conversation.

[0050] The process flow of the first embodiment will be briefly described below.

[0051] Step 1: The analysis unit analyzes the other party's speech or language in real time. The analysis unit collects voice data and converts it into text data using voice recognition technology. Next, the text data is analyzed to extract patterns in the other party's speech and language. For example, the other party's intonation and accent are analyzed to grasp the characteristics of their speech. In addition, the other party's emotions are estimated and the accuracy of the analysis is adjusted based on the estimated emotions. For example, if the other party is excited, the emotion engine is used to estimate the emotions and the emotion data is taken into account to improve the accuracy of the analysis. Step 2: The suggestion unit suggests topics based on the analysis results obtained by the analysis unit. The suggestion unit selects appropriate topics based on the analysis results in order to suggest topics that will interest the other person. For example, it may suggest topics related to the other person's occupation or hobbies. It may also suggest topics that correspond to the other person's emotions. For example, if the other person is relaxed, it may suggest relaxing topics. Step 3: The alternative suggestion unit suggests a different topic if the topic suggested by the suggestion unit is determined to be inappropriate. The alternative suggestion unit suggests a different topic by referring to the other person's past conversation history. For example, the alternative suggestion unit retrieves the other person's past conversation history from a database and suggests topics that the other person has shown interest in in the past. It can also estimate the other person's emotions and suggest a different topic based on the emotions. For example, if the other person is excited, it suggests a topic that will interest them.

[0052] (Example 2) The topic advisor system according to the embodiment of the present invention is a system for people who have trouble with conversations with people they meet for the first time, their superiors, or their seniors. This system analyzes the other person's way of speaking and language in real time and suggests appropriate topics, thereby making it possible to smoothly advance a conversation. For example, data for analyzing the other person's way of speaking and language in real time is collected. This data includes the other person's intonation and language. For example, the other person's way of speaking and language can be collected while the other person is talking. Next, the analysis unit analyzes the collected data in real time. This analysis unit estimates the other person's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For example, the accuracy of the analysis can be adjusted according to the emotions, such as when the other person is excited or calm. In addition, the analysis unit adjusts the analysis algorithm by referring to the other person's past conversation history and geographical background, thereby improving the accuracy of the analysis. Based on the analysis result, the suggestion unit suggests an appropriate topic. Based on the analysis result, the suggestion unit suggests topics for talking to a person meeting for the first time, for talking to a superior, for talking to a subordinate, and the like. For example, the system can propose topics related to common hobbies and interests to a person who is meeting for the first time, and topics related to work to a superior. Furthermore, if the topic proposed by the proposal unit fails, the alternative proposal unit proposes another topic. The alternative proposal unit includes an alternative proposal generation unit for proposing another topic in case the topic proposed by the proposal unit fails. For example, if the other party does not show interest in the proposed topic, the alternative proposal unit can propose a new topic. This system allows the system to delve deeper into topics that interest the other party, making it easier to find another topic. For example, if the other party is interested in sports, a topic related to sports can be proposed and further explored. Furthermore, even if the other party does not show interest, the alternative proposal unit proposes a new topic, so that the conversation can continue without interruption. As a result, the topic advisor system can smoothly advance conversations with people who meet for the first time, superiors, and seniors.

[0053] The topic advisor system according to the embodiment includes an analysis unit, a suggestion unit, and an alternative suggestion unit. The analysis unit analyzes the other party's speech or language in real time. For example, the analysis unit collects voice data and converts it into text data using a voice recognition technology. Next, the analysis unit analyzes the text data and extracts the other party's speech or language pattern. For example, the analysis unit analyzes the other party's intonation and accent to grasp the characteristics of the speech. The analysis unit also estimates the other party's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For example, if the other party is excited, the analysis unit estimates the emotions using an emotion engine and takes into account the emotion data to improve the accuracy of the analysis. The suggestion unit suggests a topic based on the analysis result obtained by the analysis unit. For example, the suggestion unit selects an appropriate topic based on the analysis result to suggest a topic that will interest the other party. For example, the suggestion unit suggests a topic related to the other party's occupation or hobby. The suggestion unit can also suggest a topic according to the other party's emotions. For example, if the other party is relaxed, the suggestion unit suggests a relaxing topic. The alternative suggestion unit proposes another topic when the topic proposed by the suggestion unit fails. The alternative suggestion unit, for example, proposes another topic by referring to the other party's past conversation history. For example, the alternative suggestion unit acquires the other party's past conversation history from a database and proposes a topic that the other party showed interest in in the past. The alternative suggestion unit can also estimate the other party's emotions and propose another topic based on the emotions. For example, if the other party is excited, the alternative suggestion unit proposes an interesting topic. In this way, the topic advisor system according to the embodiment can smoothly advance the conversation by analyzing the other party's way of speaking and language and proposing an appropriate topic. Furthermore, even if the proposed topic fails, the conversation will not be interrupted by proposing another topic.

[0054] The analysis unit analyzes the other party's speech or language in real time. For example, the analysis unit collects voice data and converts it into text data using voice recognition technology. Specifically, the voice data is collected through a microphone and processed into clear voice data using noise reduction technology. After that, a voice recognition engine analyzes the voice data and converts it into text data. This voice recognition engine uses a model using deep learning, and can convert voice into text with high accuracy. Next, the analysis unit analyzes the text data and extracts patterns of the other party's speech and language. For example, natural language processing (NLP) technology is used to extract keywords and phrases from the text data and grasp the characteristics of the other party's speech. Furthermore, speech prosody analysis technology is used to analyze intonation and accent. This allows the rhythm and emphasis of the other party's speech to be grasped, enabling more detailed analysis. The analysis unit also estimates the other party's emotions and adjusts the accuracy of the analysis based on the estimated emotions. For emotion estimation, an emotion analysis algorithm based on the tone and speed of the voice and the content of the text is used. For example, if the other person is excited, the analysis unit uses an emotion engine to estimate the emotion and takes into account the emotion data to improve the accuracy of the analysis. This allows the analysis unit to comprehensively analyze the other person's speaking style and emotions and provide more accurate analysis results.

[0055] The suggestion unit proposes a topic based on the analysis result obtained by the analysis unit. For example, the suggestion unit selects an appropriate topic based on the analysis result in order to propose a topic that will interest the other party. Specifically, the suggestion unit refers to the other party's profile information and past conversation history in order to propose a topic related to the other party's occupation or hobby. For example, if the other party is an engineer, the suggestion unit proposes topics related to the latest technology trends and industry news. Also, if the other party likes sports, the suggestion unit can propose topics related to recent game results and player performance. Furthermore, the suggestion unit can also propose a topic according to the other party's emotions. For example, if the other party is relaxed, the suggestion unit proposes a topic that will relax them. Specifically, if it is estimated that the other party is relaxed, the suggestion unit selects topics related to travel, hobbies, and relaxation. Also, if the other party is feeling stressed, the suggestion unit can propose a topic related to stress relief methods and relaxation techniques. When proposing these topics, the suggestion unit monitors the other party's reaction in real time and evaluates the effectiveness of the proposal. As a result, the suggestion unit can propose optimal topics according to the other party's interests and emotions, and smoothly progress the conversation.

[0056] The alternative suggestion unit proposes another topic when the topic proposed by the suggestion unit fails. The alternative suggestion unit proposes another topic by, for example, referring to the other party's past conversation history. Specifically, the alternative suggestion unit acquires the other party's past conversation history from a database and proposes topics that the other party has shown interest in in the past. For example, if the other party has shown interest in topics related to travel in the past, the alternative suggestion unit proposes topics related to the latest travel information and recommended travel destinations. The alternative suggestion unit can also estimate the other party's emotions and propose another topic based on the emotions. For example, if the other party is excited, the alternative suggestion unit proposes an interesting topic. Specifically, if it is estimated that the other party is excited, the alternative suggestion unit selects a topic related to sports or entertainment. Also, if the other party is calm, the alternative suggestion unit can propose a topic that will relax the other party. The alternative suggestion unit, like the suggestion unit, monitors the other party's reaction in real time and evaluates the effectiveness of the proposal. As a result, even if the topic proposed by the suggestion unit fails, the alternative suggestion unit can quickly propose another topic to prevent the conversation from being interrupted. Furthermore, the alternative suggestion unit accumulates a history of suggestions and uses it for future suggestions, thereby continuously improving the accuracy of the suggestions. This allows the alternative suggestion unit to always suggest optimal topics and smoothly advance the conversation.

[0057] The topic advisor system includes a collection unit that collects data for analyzing the other party's speech or language in real time. The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit, for example, collects voice data and converts it into text data using voice recognition technology. The collection unit collects the other party's intonation and accent in real time. For example, the collection unit collects the other party's speaking speed and rhythm in real time. The collection unit can also collect specific words and phrases used by the other party in real time. For example, the collection unit analyzes voice data and extracts specific words and phrases in order to grasp the characteristics of the other party's speaking style. As a result, the accuracy of the analysis is improved by collecting the other party's speaking style and language in real time. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0058] The suggestion unit includes a proposal generation unit for suggesting an appropriate topic based on the analysis result. The suggestion unit includes a proposal generation unit for suggesting an appropriate topic based on the analysis result. The suggestion unit proposes a topic that will interest the other party based on the analysis result, for example. The suggestion unit can propose a topic related to the other party's occupation or hobby. For example, the suggestion unit can also propose a topic according to the other party's emotions. If the other party is relaxed, the suggestion unit proposes a relaxing topic. If the other party is excited, the suggestion unit can propose an interesting topic. This improves the quality of the conversation by suggesting an appropriate topic based on the analysis result. A part or all of the above-mentioned 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 the analysis result to the generation AI and cause the generation AI to execute the proposal of an appropriate topic.

[0059] The alternative suggestion unit includes an alternative suggestion generation unit for suggesting another topic when the topic proposed by the suggestion unit is determined to be inappropriate. The alternative suggestion unit includes an alternative suggestion generation unit for suggesting another topic when the topic proposed by the suggestion unit is determined to be inappropriate. For example, when the topic proposed by the suggestion unit fails, the alternative suggestion unit suggests another topic by referring to the other party's past conversation history. The alternative suggestion unit can estimate the other party's emotions and suggest another topic based on the emotions. For example, the alternative suggestion unit suggests another topic based on the other party's occupation or hobby. In this way, even if the proposed topic fails, the conversation is not interrupted by proposing another topic. A part or all of the above-mentioned processing in the alternative suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, when the topic proposed by the suggestion unit fails, the alternative suggestion unit can cause the generation AI to execute the proposal of another topic.

[0060] The analysis unit estimates the emotion of the other party and adjusts the accuracy of the analysis based on the estimated emotion of the other party. The analysis unit estimates the emotion of the other party and adjusts the accuracy of the analysis based on the estimated emotion of the other party. For example, when the other party is excited, the analysis unit estimates the emotion using an emotion engine and considers the emotion data to improve the accuracy of the analysis. When the other party is calm, the analysis unit estimates the emotion using an emotion engine and adjusts the accuracy of the analysis. When the other party is nervous, the analysis unit estimates the emotion using an emotion engine and adjusts the accuracy of the analysis. This allows for more accurate analysis by adjusting the accuracy of the analysis according to the emotion of the other party. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the emotion data of the other party to the generation AI and cause the generation AI to execute the estimation of the emotion.

[0061] The analysis unit adjusts the analysis algorithm by referring to the other party's past conversation history during analysis. The analysis unit adjusts the analysis algorithm by referring to the other party's past conversation history during analysis. The analysis unit, for example, acquires the other party's past conversation history from a database and adjusts the analysis algorithm. The analysis unit performs analysis by referring to the other party's past conversation history and placing emphasis on specific keywords and phrases. The analysis unit analyzes the other party's past conversation history and adjusts the analysis algorithm based on frequently used words and phrases. As a result, the accuracy of analysis is improved by referring to the past conversation history. A part or all of the above-mentioned 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 past conversation history data to the generation AI and cause the generation AI to adjust the analysis algorithm.

[0062] The analysis unit learns the speech pattern of the other party during analysis, and improves the accuracy of the analysis. The analysis unit learns the speech pattern of the other party during analysis, and improves the accuracy of the analysis. The analysis unit, for example, learns the speech pattern of the other party using a machine learning algorithm, and improves the accuracy of the analysis. The analysis unit learns the speed and rhythm of the other party's speech, and improves the accuracy of the analysis. The analysis unit learns the intonation and accent of the other party's speech, and improves the accuracy of the analysis. In this way, the speech pattern is learned, and the accuracy of the analysis is improved. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input speech pattern data to the generation AI and cause the generation AI to execute learning.

[0063] The analysis unit estimates the emotion of the other party and adjusts the display method of the analysis result based on the estimated emotion of the other party. The analysis unit estimates the emotion of the other party and adjusts the display method of the analysis result based on the estimated emotion of the other party. For example, when the other party is excited, the analysis unit estimates the emotion using an emotion engine and displays the analysis result with visual emphasis. When the other party is calm, the analysis unit estimates the emotion using an emotion engine and displays the analysis result simply. When the other party is nervous, the analysis unit estimates the emotion using an emotion engine and displays the analysis result in a calm color. This allows for a more appropriate display by adjusting the display method of the analysis result according to the emotion of the other party. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input emotion data to the generation AI and cause the generation AI to adjust the display method.

[0064] The analysis unit performs analysis based on the geographical background of the other party during analysis. The analysis unit performs analysis based on the geographical background of the other party during analysis. The analysis unit, for example, acquires the geographical background of the other party from a database and adjusts the analysis algorithm. The analysis unit prioritizes topics related to a specific region based on the geographical background of the other party during analysis. The analysis unit considers the geographical background of the other party and performs analysis with emphasis on words and phrases specific to the region. As a result, analysis based on the geographical background makes it possible to perform analysis taking into account information specific to the region. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input geographical background data to the generation AI and cause the generation AI to execute the analysis.

[0065] The suggestion unit suggests topics to talk about when talking with a person who meets for the first time, when talking with a superior, or when talking with a subordinate. The suggestion unit suggests topics to talk about when talking with a person who meets for the first time, when talking with a superior, or when talking with a subordinate. For example, the suggestion unit suggests topics of common hobbies or interests to a person who meets for the first time. The suggestion unit suggests topics related to work to a superior. The suggestion unit suggests topics that are relaxing to a subordinate. In this way, the conversation progresses smoothly by suggesting topics according to the other person's position. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit may input the other person's position data into the generation AI and cause the generation AI to execute the topic suggestion.

[0066] The suggestion unit, at the time of making a proposal, improves the accuracy of the proposal by referring to the other party's past conversation history. The suggestion unit, at the time of making a proposal, improves the accuracy of the proposal by referring to the other party's past conversation history. For example, the suggestion unit acquires the other party's past conversation history from a database and improves the accuracy of the proposal. The suggestion unit makes a proposal by referring to the other party's past conversation history and placing emphasis on specific keywords and phrases. The suggestion unit analyzes the other party's past conversation history and improves the accuracy of the proposal based on frequently used words and phrases. As a result, the accuracy of the proposal is improved by referring to the past conversation history. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit may input past conversation history data to the generation AI and cause the generation AI to execute improvement of the accuracy of the proposal.

[0067] The suggestion unit estimates the emotion of the other party and determines the priority of the proposal based on the estimated emotion of the other party. The suggestion unit estimates the emotion of the other party and determines the priority of the proposal based on the estimated emotion of the other party. For example, when the other party is excited, the suggestion unit estimates the emotion using the emotion engine and preferentially suggests an interesting topic. When the other party is calm, the suggestion unit estimates the emotion using the emotion engine and preferentially suggests a topic that can relax the other party. When the other party is nervous, the suggestion unit estimates the emotion using the emotion engine and preferentially suggests a topic that can relieve the tension. In this way, by determining the priority of the proposal according to the emotion of the other party, a more appropriate topic can be proposed. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input emotion data to the generation AI and have the generation AI determine the prioritization of suggestions.

[0068] The alternative suggestion unit estimates the other party's emotion and determines the priority of alternative proposals based on the estimated emotion of the other party. The alternative suggestion unit estimates the other party's emotion and determines the priority of alternative proposals based on the estimated emotion of the other party. For example, when the other party is excited, the alternative suggestion unit estimates the emotion using an emotion engine and preferentially suggests topics that attract the other party. When the other party is calm, the alternative suggestion unit estimates the emotion using an emotion engine and preferentially suggests topics that can relax the other party. When the other party is nervous, the alternative suggestion unit estimates the emotion using an emotion engine and preferentially suggests topics that can relieve the tension. In this way, by determining the priority of alternative proposals according to the other party's emotion, more appropriate topics can be proposed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the alternative suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the alternative suggestion unit can input emotion data to the generation AI and cause the generation AI to determine the prioritization of alternative suggestions.

[0069] The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit collects data for analyzing the other party's speech or language in real time. The collection unit collects, for example, the intonation and accent of the other party's speech in real time. The collection unit collects the other party's speaking speed and rhythm in real time. The collection unit can collect specific words and phrases used by the other party in real time. This improves the accuracy of the analysis by collecting the other party's speech and language in real time. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data to a generation AI and cause the generation AI to convert the voice data into text data.

[0070] The collection unit adjusts the collection method by referring to the other party's past conversation history at the time of collection. The collection unit adjusts the collection method by referring to the other party's past conversation history at the time of collection. For example, the collection unit acquires the other party's past conversation history from a database and adjusts the collection method. The collection unit refers to the other party's past conversation history and performs collection with emphasis on specific keywords and phrases. The collection unit analyzes the other party's past conversation history and adjusts the collection method based on frequently used words and phrases. As a result, the collection method is optimized by referring to the past conversation history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit inputs past conversation history data to the generation AI and causes the generation AI to adjust the collection method.

[0071] The collection unit estimates the emotion of the other party and adjusts the timing of data collection based on the estimated emotion of the other party. The collection unit estimates the emotion of the other party and adjusts the timing of data collection based on the estimated emotion of the other party. For example, when the other party is excited, the collection unit estimates the emotion using the emotion engine and advances the timing of data collection. When the other party is calm, the collection unit estimates the emotion using the emotion engine and sets the timing of data collection to normal. When the other party is nervous, the collection unit estimates the emotion using the emotion engine and delays the timing of data collection. This allows more appropriate data collection by adjusting the timing of data collection according to the emotion of the other party. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input emotion data to the generation AI and cause the generation AI to adjust the timing of data collection.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The analysis unit can take into account the cultural background of the other party when analyzing the other party's speech style and vocabulary. For example, if the other party is from a particular cultural region, the analysis will prioritize words and expressions specific to that culture. The analysis unit can also learn the characteristics of the other party's speech style and vocabulary according to their age group, improving the accuracy of the analysis. Furthermore, the analysis unit can perform a more accurate analysis by incorporating technical terms and phrases related to the other party's occupation or field of expertise into the analysis. This makes it possible to perform an analysis according to the other party's cultural background, age group, and occupation, and to suggest more appropriate topics.

[0074] The suggestion unit can analyze the other person's real-time body language and suggest appropriate topics. For example, if the other person has their arms crossed, it can suggest relaxing topics. Also, if the other person nods frequently, it can dig deeper into interesting topics. Furthermore, if the other person looks away, it can suggest the right time to change the topic. This makes it possible to suggest topics based on the other person's body language, improving the quality of conversation.

[0075] The alternative suggestion unit can analyze the other person's real-time physiological data (e.g., heart rate and electrodermal activity) and suggest appropriate alternative topics. For example, if the other person's heart rate is increasing, relaxing topics can be suggested. Also, if the other person's electrodermal activity is increasing, interesting topics can be suggested. Furthermore, if the other person's physiological data is stable, topics that can be explored in more depth can be suggested. This makes it possible to suggest alternative topics based on the other person's physiological data, allowing the conversation to continue without interruption.

[0076] The analysis unit can analyze changes in the tone and volume of the other person's voice and suggest appropriate topics. For example, if the other person's voice tone is getting louder, it can suggest topics that will pique their interest. Also, if the other person's volume is dropping, it can suggest topics that will relax them. Furthermore, it can suggest topics to be deepened or changed depending on changes in the other person's voice tone and volume. This makes it possible to suggest topics based on the other person's voice tone and volume, improving the quality of conversation.

[0077] The suggestion unit can analyze the other person's real-time facial expressions and suggest appropriate topics. For example, if the other person is smiling, it can suggest fun topics. If the other person is frowning, it can suggest relaxing topics. Furthermore, if the other person has a surprised expression, it can suggest interesting topics. This makes it possible to suggest topics based on the other person's facial expressions, improving the quality of conversation.

[0078] The analysis unit can analyze the other party's past social media posts and suggest appropriate topics. For example, it can suggest topics related to the other party's hobbies and interests that the other party has posted about in the past. It can also suggest topics based on topics that the other party frequently mentions. Furthermore, it can suggest common topics taking into account the other party's friendships and networks on social media. This makes it possible to suggest topics based on the other party's social media data, improving the quality of conversation.

[0079] The suggestion unit can estimate the other party's real-time emotions and adjust the order of topic suggestions based on the estimated emotions. For example, if the other party is excited, topics that pique the other party's interest can be suggested with priority. If the other party is relaxed, topics that will relax the other party can be suggested with priority. Furthermore, if the other party is nervous, topics that will ease the tension can be suggested with priority. This makes it possible to suggest topics according to the other party's emotions, improving the quality of conversation.

[0080] The alternative suggestion unit can estimate the other party's real-time emotions and adjust the order of alternative topic suggestions based on the estimated emotions. For example, if the other party is excited, alternative topics that interest the other party can be suggested with priority. Also, if the other party is relaxed, alternative topics that relax the other party can be suggested with priority. Furthermore, if the other party is nervous, alternative topics that relieve the tension can be suggested with priority. This makes it possible to suggest alternative topics according to the other party's emotions, allowing the conversation to continue without interruption.

[0081] The analysis unit can analyze the other person's real-time physiological data (e.g., heart rate and electrodermal activity) and suggest appropriate topics. For example, if the other person's heart rate is increasing, relaxing topics can be suggested. Also, if the other person's electrodermal activity is increasing, interesting topics can be suggested. Furthermore, if the other person's physiological data is stable, topics that can be explored in more depth can be suggested. This makes it possible to suggest topics based on the other person's physiological data, improving the quality of conversation.

[0082] The suggestion unit can analyze the other person's real-time body language and suggest appropriate topics. For example, if the other person has their arms crossed, it can suggest relaxing topics. Also, if the other person nods frequently, it can dig deeper into interesting topics. Furthermore, if the other person looks away, it can suggest the right time to change the topic. This makes it possible to suggest topics based on the other person's body language, improving the quality of conversation.

[0083] The process flow of the second embodiment will be briefly described below.

[0084] Step 1: The analysis unit analyzes the other party's speech or language in real time. The analysis unit collects voice data and converts it into text data using voice recognition technology. Next, the text data is analyzed to extract patterns in the other party's speech and language. For example, the other party's intonation and accent are analyzed to grasp the characteristics of their speech. In addition, the other party's emotions are estimated and the accuracy of the analysis is adjusted based on the estimated emotions. For example, if the other party is excited, the emotion engine is used to estimate the emotions and the emotion data is taken into account to improve the accuracy of the analysis. Step 2: The suggestion unit suggests topics based on the analysis results obtained by the analysis unit. The suggestion unit selects appropriate topics based on the analysis results in order to suggest topics that will interest the other person. For example, it may suggest topics related to the other person's occupation or hobbies. It may also suggest topics that correspond to the other person's emotions. For example, if the other person is relaxed, it may suggest relaxing topics. Step 3: The alternative suggestion unit suggests a different topic if the topic suggested by the suggestion unit is determined to be inappropriate. The alternative suggestion unit suggests a different topic by referring to the other person's past conversation history. For example, the alternative suggestion unit retrieves the other person's past conversation history from a database and suggests topics that the other person has shown interest in in the past. It can also estimate the other person's emotions and suggest a different topic based on the emotions. For example, if the other person is excited, it suggests a topic that will interest them.

[0085] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0086] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0087] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0088] For example, the collection unit collects the other person's speaking style and language in real time using the camera 42 and microphone 38B of the smart device 14. For example, the collection unit analyzes the voice data by the specific processing unit 290 of the data processing device 12 and converts it into text data. For example, the analysis unit extracts the other person's speaking style and language patterns by the specific processing unit 290 of the data processing device 12 and estimates emotions. For example, the suggestion unit suggests an appropriate topic based on the analysis result by the control unit 46A of the smart device 14. For example, the alternative suggestion unit suggests another topic by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0089] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0090] 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.

[0091] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0092] 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.

[0093] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0094] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0095] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0096] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0097] 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.

[0098] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0099] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0100] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0102] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0103] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0104] For example, the collection unit collects the other person's speaking style and language in real time using the camera 42 and microphone 238 of the smart glasses 214. For example, the collection unit analyzes the voice data by the specific processing unit 290 of the data processing device 12 and converts it into text data. For example, the analysis unit extracts the other person's speaking style and language patterns by the specific processing unit 290 of the data processing device 12 and estimates emotions. For example, the suggestion unit suggests an appropriate topic based on the analysis result by the control unit 46A of the smart glasses 214. For example, the alternative suggestion unit suggests another topic by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0105] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0106] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] 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.

[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 the voice according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[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 performed in a secure state.

[0112] 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0115] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0119] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0120] For example, the collection unit collects the other person's speaking style and language in real time using the camera 42 and microphone 238 of the headset type terminal 314. For example, the collection unit analyzes the voice data by the specific processing unit 290 of the data processing device 12 and converts it into text data. For example, the analysis unit extracts the other person's speaking style and language patterns by the specific processing unit 290 of the data processing device 12 and estimates emotions. For example, the suggestion unit suggests an appropriate topic based on the analysis result by the control unit 46A of the headset type terminal 314. For example, the alternative suggestion unit suggests another topic by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0121] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0122] 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.

[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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] 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.

[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 the voice according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[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 performed in a secure state.

[0128] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0129] 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.

[0130] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0132] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0134] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0136] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] For example, the collection unit collects the other person's speech and language in real time using the camera 42 and microphone 238 of the robot 414. For example, the collection unit analyzes voice data by the specific processing unit 290 of the data processing device 12 and converts it into text data. For example, the analysis unit extracts the other person's speech and language patterns by the specific processing unit 290 of the data processing device 12 and estimates emotions. For example, the suggestion unit suggests an appropriate topic based on the analysis result by the control unit 46A of the robot 414. For example, the alternative suggestion unit suggests another topic by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0138] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0139] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0140] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0141] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0142] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0143] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0144] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0145] 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.

[0146] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0147] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0148] 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.

[0149] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0150] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0151] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0152] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0153] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0154] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0155] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0156] (Appendix 1) An analysis unit that analyzes the other person's speaking style or language in real time; a suggestion unit that suggests a topic based on the analysis result obtained by the analysis unit; and an alternative suggestion unit that suggests a different topic when the topic suggested by the suggestion unit is determined to be inappropriate. A system characterized by: (Appendix 2) Equipped with a collection unit that collects data for analyzing the other person's speaking style or language in real time 2. The system of claim 1, (Appendix 3) The suggestion unit, Equipped with a suggestion generator to suggest appropriate topics based on the analysis results 2. The system of claim 1, (Appendix 4) The alternative suggestion unit, An alternative suggestion generating unit is provided for suggesting a different topic when the topic suggested by the suggesting unit is determined to be inappropriate. 2. The system of claim 1, (Appendix 5) The analysis unit is Estimate the other person's emotions and adjust the accuracy of the analysis based on the estimated emotions. 2. The system of claim 1, (Appendix 6) The analysis unit is When analyzing, the analysis algorithm is adjusted by referring to the other party's past conversation history. 2. The system of claim 1, (Appendix 7) The analysis unit is During analysis, the system learns the other person's speaking patterns to improve the accuracy of the analysis. 2. The system of claim 1, (Appendix 8) The analysis unit is Estimate the other person's emotions and adjust the way the analysis results are displayed based on the estimated emotions of the other person 2. The system of claim 1, (Appendix 9) The analysis unit is When analyzing, the analysis is based on the geographical background of the other party. 2. The system of claim 1, (Appendix 10) The suggestion unit, Suggest topics to talk about when meeting someone for the first time, when speaking with your boss, or when speaking with your subordinates 2. The system of claim 1, (Appendix 11) The suggestion unit, When making suggestions, the system will refer to the other person's past conversation history to improve the accuracy of the suggestions. 2. The system of claim 1, (Appendix 12) The suggestion unit, Inferring the other person's emotions and prioritizing proposals based on the inferred emotions 2. The system of claim 1, (Appendix 13) The alternative suggestion unit, Inferring the other party's emotions and prioritizing alternative proposals based on the inferred emotions 2. The system of claim 1, (Appendix 14) The collecting unit includes: Collect data to analyze the speech or language used by other people in real time 2. The system of claim 1, (Appendix 15) The collecting unit includes: When collecting information, refer to the other person's past conversation history and adjust the collection method. 2. The system of claim 1, (Appendix 16) The collecting unit includes: Inferring the other person's emotions and adjusting the timing of data collection based on the inferred emotions 2. The system of claim 1, [Explanation of symbols]

[0157] 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. An analysis unit that analyzes the other person's speaking style or language in real time; a suggestion unit that suggests a topic based on the analysis result obtained by the analysis unit; and an alternative suggestion unit that suggests a different topic when the topic suggested by the suggestion unit is determined to be inappropriate. A system characterized by:

2. Equipped with a collection unit that collects data for analyzing the other person's speaking style or language in real time 2. The system of claim 1 .

3. The alternative suggestion unit is An alternative suggestion generating unit is provided for suggesting a different topic when the topic suggested by the suggesting unit is determined to be inappropriate.

2. The system of claim 1 .

4. The analysis unit is Estimate the other person's emotions and adjust the accuracy of the analysis based on the estimated emotions.

2. The system of claim 1 .

5. The analysis unit is When analyzing, the analysis algorithm is adjusted by referring to the other party's past conversation history.

2. The system of claim 1 .

6. The analysis unit is During analysis, the system learns the other person's speaking patterns to improve the accuracy of the analysis.

2. The system of claim 1 .

7. The analysis unit is Estimate the other person's emotions and adjust the way the analysis results are displayed based on the estimated emotions of the other person 2. The system of claim 1 .

8. The analysis unit is When analyzing, the analysis is based on the geographical background of the other party.

2. The system of claim 1 .

9. The suggestion unit, Suggest topics to talk about when meeting someone for the first time, when speaking with your boss, or when speaking with your subordinates 2. The system of claim 1 .

Images