system

Abstract

The system according to this embodiment aims to provide appropriate content in response to user questions and to suggest improvements to administrators regarding unresolved issues. [Solution] The system according to the embodiment comprises an analysis unit, a provision unit, a proposal unit, and a collection unit. The analysis unit analyzes the user's questions. The provision unit provides optimal content based on the questions analyzed by the analysis unit. The proposal unit makes improvement suggestions to the administrator based on the content provided by the provision unit. The collection unit collects user behavior data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it has not been sufficiently done to provide appropriate content for a user's question and to make an improvement proposal to an administrator about an unsolved problem.

[0005] The system according to the embodiment aims to provide appropriate content for a user's question and to make an improvement proposal to an administrator about an unsolved problem.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a provision unit, a proposal unit, and a collection unit. The analysis unit analyzes the user's questions. The provision unit provides optimal content based on the questions analyzed by the analysis unit. The proposal unit makes improvement suggestions to the administrator based on the content provided by the provision unit. The collection unit collects user behavior data. [Effects of the Invention]

[0007] The system according to this embodiment can provide appropriate content in response to user questions and make improvement suggestions to the administrator regarding unresolved issues. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The content navigation agent system according to an embodiment of the present invention is an AI system that instantly provides visitors with the information they seek and makes improvement suggestions to site administrators for unresolved issues. This system improves the user experience by understanding user questions and presenting appropriate content. Specifically, it analyzes user questions using natural language processing and provides optimal content using machine learning. Furthermore, it improves the quality of service by continuously learning from user behavior data. This system has the effect of reducing the response time to user inquiries by 50% and improving site dwell time and engagement. In addition, it can streamline the content improvement work of administrators. For example, it improves the overall quality of the site by instantly providing the information users seek and making concrete improvement suggestions to administrators. The target is companies that provide digital content, from small and medium-sized enterprises to large corporations, which face the challenge of difficulty in providing appropriate content and resulting in low user satisfaction. To solve this problem, the content navigation agent utilizes natural language processing and machine learning to respond to user questions and provide optimal content. In terms of market size, the online content platform market is estimated to be approximately 10 trillion yen, and the market size of digital content providers that can initially implement the system is estimated to be approximately 2 trillion yen. The acceleration of digitalization and the evolution of AI technology are creating market demand, aiming to improve user engagement and the quality of digital content. This allows content navigation agent systems to enhance the user experience and improve the overall quality of websites.

[0029] The content navigation agent system according to this embodiment comprises an analysis unit, a provision unit, a suggestion unit, and a collection unit. The analysis unit analyzes the user's question. The analysis unit analyzes the user's question using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to break down the user's question into words and grammatical analysis to analyze the sentence structure. The analysis unit can also understand the meaning of the user's question using semantic analysis. The provision unit provides the optimal content based on the question analyzed by the analysis unit. The provision unit provides the optimal content using, for example, machine learning technology. Machine learning technology includes deep learning, support vector machines, etc. For example, the provision unit uses deep learning to select the optimal content for the user's question. The provision unit can also evaluate the relevance of content using a support vector machine. The suggestion unit makes improvement suggestions to the administrator based on the content provided by the provision unit. The suggestion unit makes, for example, specific improvement suggestions to the administrator. Specific improvement suggestions include the type of suggestion and evaluation criteria for the suggestion. For example, the proposal unit can make suggestions such as improving the site design, adding or modifying content, etc. The data collection unit collects user behavior data. For example, the data collection unit collects user click data, browsing history, purchase history, etc. The data collection unit can use this data to perform analysis to improve the quality of the service. As a result, the content navigation agent system according to the embodiment can improve the user experience by analyzing user questions, providing optimal content, and making improvement suggestions to administrators.

[0030] The analysis unit analyzes the user's question. For example, the analysis unit analyzes the user's question using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Specifically, morphological analysis is used to break down the user's question into words and identify the part of speech of each word. Grammatical analysis analyzes the structure of the sentence and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the entire sentence and grasps the user's intent. For example, in response to the question "Tell me about nearby restaurants," the analysis unit breaks it down into the words "nearby," "restaurant," and "tell me," analyzing "nearby" as a modifier indicating location, "restaurant" as a noun, and "tell me" as a verb. Furthermore, semantic analysis helps understand that the user is looking for nearby restaurants. Based on these analysis results, the analysis unit accurately grasps the intent of the user's question and provides information to derive an appropriate answer. The analysis unit can also consider the context of the user's question and past question history to perform more accurate analysis. For example, if a user has previously searched for "Italian restaurants," the analytics unit can take that information into consideration and prioritize suggesting Italian restaurants in response to the current question. This allows the analytics unit to accurately analyze the user's question and provide appropriate information that meets the user's needs.

[0031] The content delivery unit provides optimal content based on the questions analyzed by the analysis unit. For example, the content delivery unit uses machine learning techniques to provide optimal content. These machine learning techniques include deep learning and support vector machines. Specifically, deep learning is used to select the most suitable content for a user's question. Deep learning models have the ability to learn from large amounts of data and generate optimal answers to user questions. For example, if a user asks, "Can you recommend some movies?", the content delivery unit uses a deep learning model to select movies that match the user's preferences based on their past viewing history and rating data. Furthermore, the content delivery unit can use support vector machines to evaluate the relevance of content. Support vector machines learn boundaries for classifying data points and predict which category new data points belong to. This allows the content delivery unit to provide the most relevant content to the user's question. In addition, the content delivery unit can collect user feedback and continuously improve the quality of the content it provides. For example, when a user rates the provided content, the content delivery unit can learn from that rating and incorporate it into future content delivery. This allows the service provider to deliver optimal content tailored to user needs and improve user satisfaction.

[0032] The proposal department makes improvement suggestions to administrators based on the content provided by the service provider. For example, the proposal department makes specific improvement suggestions to administrators. These specific suggestions include the type of suggestion and the criteria for evaluating it. For example, the proposal department can suggest improvements to the site design, or the addition or modification of content. The proposal department analyzes user feedback and behavioral data obtained from the service provider to identify areas for improvement. For example, if a user gives a low rating to a particular piece of content, there may be a problem with the content or how it is displayed. The proposal department can identify these problems and propose specific solutions to administrators. The proposal department also analyzes user behavioral data to determine which content is most popular and which is viewed less frequently. This allows administrators to develop specific strategies to further enhance popular content and improve less viewed content. Furthermore, the proposal department can understand user needs and trends and propose the addition of new content or updates to existing content. This enables the proposal department to provide administrators with specific and actionable improvement suggestions, thereby improving the overall quality of the system.

[0033] The data collection unit collects user behavior data. For example, it collects user click data, browsing history, and purchase history. Specifically, it collects data such as which links users clicked, which pages they viewed, and which products they purchased. This data is important for understanding user interests and preferences. The data collection unit can use this data to perform analysis to improve the quality of services. For example, by analyzing user click data, the unit can identify which content is most popular. By analyzing browsing history, it can understand what kind of content users are interested in. Furthermore, by analyzing purchase history, it can identify what kind of products users prefer to buy. This allows the data collection unit to develop specific strategies for improving service quality based on user behavior data. The data collection unit centrally manages this data and can collaborate with other systems and departments as needed. For example, collected data is stored on a cloud server and made accessible to the analysis and service departments. Adjusting the frequency and accuracy of data collection allows for flexible responses to specific situations and conditions. This enables the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0034] The analysis unit can analyze user questions using natural language processing. For example, the analysis unit can break down user questions into words using morphological analysis. For example, the analysis unit can also analyze sentence structure using grammatical analysis. Furthermore, the analysis unit can understand the meaning of user questions using semantic analysis. In this way, user questions can be accurately analyzed by utilizing natural language processing. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user question into a generative AI, which can then analyze the question.

[0035] The content provider can provide optimal content using machine learning. For example, the provider can use deep learning to select the most suitable content for a user's question. For example, the provider can also use support vector machines to evaluate the relevance of content. Furthermore, the provider can use machine learning algorithms to provide content based on the user's interests and past behavior history. In this way, machine learning can be used to provide the user with the most suitable content. Some or all of the above processes in the content provider may be performed using, for example, generative AI, or not using generative AI. For example, the provider can input the user's question and past behavior history into a generative AI, which can then select the most suitable content.

[0036] The proposal department can make specific improvement suggestions to administrators. For example, the proposal department may suggest improvements to the site design, or add or modify content. For example, the proposal department can analyze user behavior data to identify areas that need improvement. The proposal department can also make specific improvement suggestions based on user feedback. This allows for an improvement in the quality of the site by providing specific improvement suggestions to administrators. Some or all of the above processes in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input user behavior data into a generative AI, which can then generate improvement suggestions.

[0037] The data collection unit can collect user behavior data and use it to improve the quality of the service. For example, the data collection unit collects user click data, browsing history, purchase history, etc. For example, the data collection unit analyzes user behavior data to identify areas for service improvement. The data collection unit can also personalize the service based on user behavior data. This allows for the collection of user behavior data and improvement of service quality. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input user behavior data into a generative AI, which can then analyze the data.

[0038] The analysis unit can improve the accuracy of its analysis by referring to the user's past question history when analyzing a question. For example, the analysis unit can analyze patterns in questions the user has asked in the past and respond quickly to similar questions. For example, the analysis unit can estimate the user's knowledge level on a particular topic from the user's past question history and perform an appropriate analysis. The analysis unit can also prioritize analyzing and re-provide answers to questions the user was unable to resolve in the past. This improves the accuracy of the analysis by referring to the user's past question history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's past question history into a generative AI, which can then perform analysis to improve the accuracy of the analysis.

[0039] The analysis unit can perform analysis while considering the user's current context when analyzing a question. For example, if the user is visiting a specific page, the analysis unit will prioritize analyzing information related to that page. For example, if the user is asking a question at night, the analysis unit will provide information related to nighttime. The analysis unit can also analyze information related to an event if the user is asking a question during a specific event. This allows for the provision of more relevant analysis results by considering the user's current context. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's current context data into a generative AI, which can then perform the analysis.

[0040] The analysis unit can prioritize providing highly relevant analysis results by considering the user's geographical location information when analyzing a question. For example, if the user is in a specific region, the analysis unit will prioritize providing information related to that region. For example, if the user is traveling, the analysis unit will prioritize providing information related to the travel destination. The analysis unit can also prioritize providing information related to a specific city if the user is in that city. This allows for the provision of more relevant analysis results by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's geographical location information into a generative AI, which can then perform the analysis.

[0041] The analysis unit can analyze the user's social media activity when analyzing a question and reflect relevant information in the analysis. For example, the analysis unit can provide relevant analysis results based on information the user has shared on social media. For example, the analysis unit can prioritize providing information related to topics the user follows on social media. The analysis unit can also provide information that the user might be interested in based on their social media activity history. This allows for the provision of more relevant analysis results by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's social media activity data into a generative AI, which can then perform the analysis.

[0042] The content provider can select the most suitable content by referring to the user's past browsing history when providing content. For example, the provider can provide relevant content based on the content the user has previously viewed. For example, the provider can prioritize providing content that the user is likely to be interested in based on the user's past browsing history. The provider can also analyze patterns in the content the user has previously viewed and provide the most suitable content. In this way, the provider can provide the most suitable content by referring to the user's past browsing history. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or without a generative AI. For example, the provider can input the user's past browsing history into a generative AI, which can then select the most suitable content.

[0043] The content provider can customize the content it provides based on the user's current areas of interest. For example, the provider can provide content related to topics the user is currently interested in. For example, if the provider is interested in a particular field, it can prioritize providing content related to that field. The provider can also provide customized content based on the user's current areas of interest. This allows for the provision of more appropriate content by customizing it based on the user's current areas of interest. Some or all of the above processing in the provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the provider can input the user's current areas of interest data into a generative AI, which can then customize the content.

[0044] The content provider can prioritize providing highly relevant content by considering the user's geographical location when delivering content. For example, if the user is in a specific region, the provider will prioritize providing content related to that region. For example, if the user is traveling, the provider will prioritize providing content related to their travel destination. The provider can also prioritize providing content related to a specific city if the user is in that city. This allows for the provision of more relevant content by considering the user's geographical location. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or without a generative AI. For example, the content provider can input the user's geographical location information into a generative AI, which can then select the content.

[0045] The content provider can analyze a user's social media activity and provide relevant content when delivering content. For example, the provider can provide relevant content based on information shared by the user on social media. For example, the provider can prioritize providing content related to topics the user follows on social media. The provider can also provide content that is likely to be of interest to the user based on their social media activity history. This allows for the provision of more relevant content by analyzing the user's social media activity. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the provider can input the user's social media activity data into a generative AI, which can then select the content.

[0046] The proposal department can select the optimal proposal by referring to past proposal history when making improvement proposals. For example, the proposal department can analyze the effectiveness of past proposals and select the optimal proposal. For example, the proposal department can select the optimal proposal for similar problems from past proposal history. The proposal department can also select proposals with high improvement effectiveness based on past proposal history. In this way, the optimal improvement proposal can be made by referring to past proposal history. Some or all of the above processing in the proposal department may be performed using, for example, a generation AI, or without a generation AI. For example, the proposal department can input past proposal history data into a generation AI, and the generation AI can select the optimal proposal.

[0047] The proposal department can make improvement suggestions while considering the current status and trends of the site. For example, the proposal department can make optimal improvement suggestions by considering the current traffic situation of the site. For example, the proposal department can make optimal improvement suggestions by considering the current content trends of the site. Furthermore, the proposal department can also make optimal improvement suggestions by considering the current user engagement situation of the site. This allows for more appropriate improvement suggestions to be made by considering the current status and trends of the site. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input current site status data into a generative AI, and the generative AI can generate optimal suggestions.

[0048] The proposal unit can make suggestions for improvement while considering the geographical usage of the site. For example, the proposal unit can make optimal improvement suggestions by considering the usage of the site in a specific region. For example, the proposal unit can make optimal improvement suggestions by considering the usage of the site in a specific city. Furthermore, the proposal unit can also make optimal improvement suggestions by considering the usage of the site in a specific country. This allows for more appropriate improvement suggestions to be made by considering the geographical usage of the site. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input geographical usage data of the site into a generative AI, and the generative AI can generate optimal suggestions.

[0049] The proposal department can improve the accuracy of its proposals by referring to trends in the relevant industry when making improvement suggestions. For example, the proposal department can make optimal improvement suggestions by referring to the latest trends in the relevant industry. For example, the proposal department can make optimal improvement suggestions by referring to best practices in the relevant industry. The proposal department can also make optimal improvement suggestions by referring to the trends of competitors in the relevant industry. In this way, by referring to trends in the relevant industry, it is possible to make more accurate improvement suggestions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input data on trends in the relevant industry into a generative AI, and the generative AI can generate the optimal suggestion.

[0050] The data collection unit can improve the accuracy of data collection by referring to the user's past behavioral history when collecting behavioral data. For example, the data collection unit prioritizes collecting relevant behavioral data based on the user's past behavioral history. For example, the data collection unit analyzes the user's past behavioral patterns and optimizes the scope of data to be collected. The data collection unit can also collect behavioral data from the user's past behavioral history for specific time periods or situations. This allows for improved data collection accuracy by referring to the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's past behavioral history data into a generative AI, which can then collect the data.

[0051] The data collection unit can collect behavioral data while considering the user's current context. For example, if the user is visiting a specific page, the data collection unit can collect behavioral data related to that page. For example, if the user is active during a specific time period, the data collection unit can collect behavioral data related to that time period. The data collection unit can also collect behavioral data related to an event if the user is active during that event. This allows for the collection of more relevant behavioral data by considering the user's current context. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's current context data into a generative AI, which can then collect the data.

[0052] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting behavioral data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of behavioral data related to that region. For example, if the user is traveling, the data collection unit will prioritize the collection of behavioral data related to the travel destination. The data collection unit can also prioritize the collection of behavioral data related to a specific city if the user is in that city. This allows for the collection of more relevant behavioral data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's geographical location information into a generative AI, which can then collect the data.

[0053] The data collection unit can analyze a user's social media activity and collect relevant data when collecting behavioral data. For example, the data collection unit can collect relevant behavioral data based on information shared by the user on social media. For example, the data collection unit can prioritize collecting behavioral data related to topics the user follows on social media. The data collection unit can also collect behavioral data that the user might be interested in based on their social media activity history. This allows for the collection of more relevant behavioral data by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI, which can then collect the data.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The analysis unit can improve the accuracy of its analysis of user questions by utilizing the user's voice data. For example, the analysis unit converts the user's voice data into text using speech recognition technology and analyzes the question based on that text. The analysis unit can also analyze voice characteristics such as the user's voice tone and speaking speed to estimate the user's emotions and intentions. This allows for a more accurate analysis of user questions by utilizing voice data. Furthermore, the analysis unit can input the user's voice data into a generating AI, which then analyzes the voice data.

[0056] The content delivery system can customize content based on the user's visual preferences when providing the most suitable content in response to a user's question. For example, it can analyze the design and layout of content the user has previously viewed and provide content with a design that matches the user's preferences. It can also adjust the color scheme and font size of the content based on the user's visual preferences. This allows for the delivery of more satisfying content by customizing it according to the user's visual preferences. Furthermore, the content delivery system can input the user's visual preference data into a generating AI, which can then customize the content.

[0057] The suggestion department can collect user feedback in real time and immediately incorporate it when making improvement suggestions to administrators. For example, the suggestion department can collect user ratings and comments on content in real time and make improvement suggestions based on that feedback. The suggestion department can also analyze user feedback and determine the priority of improvements. This allows for faster and more appropriate improvement suggestions by collecting user feedback in real time and immediately incorporating it. Furthermore, the suggestion department can input user feedback data into a generation AI, which can then generate improvement suggestions.

[0058] The data collection unit can improve the accuracy of user behavior data by utilizing the user's biometric information. For example, the data collection unit can collect biometric information such as the user's heart rate and skin electrical response to estimate the user's stress level and level of agitation. The data collection unit can also evaluate the reliability of user behavior data based on the user's biometric information. In this way, the accuracy of user behavior data can be improved by utilizing biometric information. Furthermore, the data collection unit can input the user's biometric information data into a generating AI, which can then analyze the data.

[0059] The analysis unit can improve the accuracy of its analysis of user questions by utilizing user gesture data. For example, the analysis unit collects user gesture data using cameras and sensors and estimates the intent of the question based on that data. The analysis unit can also analyze the user's gesture data to estimate the user's emotions and intentions. This allows for a more accurate analysis of user questions by utilizing gesture data. Furthermore, the analysis unit can input the user's gesture data into a generating AI, which then analyzes the gesture data.

[0060] The content delivery system can customize content based on user preferences when providing the most suitable content in response to user inquiries. For example, it can analyze the genres and themes of content previously viewed by the user and provide content that matches their preferences. It can also adjust the order and display method of content based on user preferences. This allows for the delivery of more satisfying content by customizing it according to user preferences. Furthermore, the content delivery system can input user preference data into a content generation AI, which can then customize the content.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the user's question. The analysis unit analyzes the user's question using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down the user's question into words and grammatical analysis to analyze the sentence structure. The analysis unit can also use semantic analysis to understand the meaning of the user's question. Step 2: The delivery unit provides the most suitable content based on the questions analyzed by the analysis unit. The delivery unit uses machine learning techniques to provide the most suitable content. Machine learning techniques include deep learning and support vector machines. For example, the delivery unit uses deep learning to select the most suitable content for the user's question. The delivery unit can also use support vector machines to evaluate the relevance of the content. Step 3: The proposal team makes improvement suggestions to the administrator based on the content provided by the delivery team. The proposal team makes specific improvement suggestions to the administrator. These specific suggestions include the type of suggestion and the criteria for evaluating the suggestion. For example, the proposal team may suggest improvements to the site design, or the addition or modification of content. Step 4: The data collection unit collects user behavior data. The data collection unit collects user click data, browsing history, purchase history, etc. The data collection unit can use this data to perform analysis to improve the quality of the service.

[0063] (Example of form 2) The content navigation agent system according to an embodiment of the present invention is an AI system that instantly provides visitors with the information they seek and makes improvement suggestions to site administrators for unresolved issues. This system improves the user experience by understanding user questions and presenting appropriate content. Specifically, it analyzes user questions using natural language processing and provides optimal content using machine learning. Furthermore, it improves the quality of service by continuously learning from user behavior data. This system has the effect of reducing the response time to user inquiries by 50% and improving site dwell time and engagement. In addition, it can streamline the content improvement work of administrators. For example, it improves the overall quality of the site by instantly providing the information users seek and making concrete improvement suggestions to administrators. The target is companies that provide digital content, from small and medium-sized enterprises to large corporations, which face the challenge of difficulty in providing appropriate content and resulting in low user satisfaction. To solve this problem, the content navigation agent utilizes natural language processing and machine learning to respond to user questions and provide optimal content. In terms of market size, the online content platform market is estimated to be approximately 10 trillion yen, and the market size of digital content providers that can initially implement the system is estimated to be approximately 2 trillion yen. The acceleration of digitalization and the evolution of AI technology are creating market demand, aiming to improve user engagement and the quality of digital content. This allows content navigation agent systems to enhance the user experience and improve the overall quality of websites.

[0064] The content navigation agent system according to this embodiment comprises an analysis unit, a provision unit, a suggestion unit, and a collection unit. The analysis unit analyzes the user's question. The analysis unit analyzes the user's question using, for example, natural language processing technology. Natural language processing technology includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to break down the user's question into words and grammatical analysis to analyze the sentence structure. The analysis unit can also understand the meaning of the user's question using semantic analysis. The provision unit provides the optimal content based on the question analyzed by the analysis unit. The provision unit provides the optimal content using, for example, machine learning technology. Machine learning technology includes deep learning, support vector machines, etc. For example, the provision unit uses deep learning to select the optimal content for the user's question. The provision unit can also evaluate the relevance of content using a support vector machine. The suggestion unit makes improvement suggestions to the administrator based on the content provided by the provision unit. The suggestion unit makes, for example, specific improvement suggestions to the administrator. Specific improvement suggestions include the type of suggestion and evaluation criteria for the suggestion. For example, the proposal unit can make suggestions such as improving the site design, adding or modifying content, etc. The data collection unit collects user behavior data. For example, the data collection unit collects user click data, browsing history, purchase history, etc. The data collection unit can use this data to perform analysis to improve the quality of the service. As a result, the content navigation agent system according to the embodiment can improve the user experience by analyzing user questions, providing optimal content, and making improvement suggestions to administrators.

[0065] The analysis unit analyzes the user's question. For example, the analysis unit analyzes the user's question using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Specifically, morphological analysis is used to break down the user's question into words and identify the part of speech of each word. Grammatical analysis analyzes the structure of the sentence and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the meaning of the entire sentence and grasps the user's intent. For example, in response to the question "Tell me about nearby restaurants," the analysis unit breaks it down into the words "nearby," "restaurant," and "tell me," analyzing "nearby" as a modifier indicating location, "restaurant" as a noun, and "tell me" as a verb. Furthermore, semantic analysis helps understand that the user is looking for nearby restaurants. Based on these analysis results, the analysis unit accurately grasps the intent of the user's question and provides information to derive an appropriate answer. The analysis unit can also consider the context of the user's question and past question history to perform more accurate analysis. For example, if a user has previously searched for "Italian restaurants," the analytics unit can take that information into consideration and prioritize suggesting Italian restaurants in response to the current question. This allows the analytics unit to accurately analyze the user's question and provide appropriate information that meets the user's needs.

[0066] The content delivery unit provides optimal content based on the questions analyzed by the analysis unit. For example, the content delivery unit uses machine learning techniques to provide optimal content. These machine learning techniques include deep learning and support vector machines. Specifically, deep learning is used to select the most suitable content for a user's question. Deep learning models have the ability to learn from large amounts of data and generate optimal answers to user questions. For example, if a user asks, "Can you recommend some movies?", the content delivery unit uses a deep learning model to select movies that match the user's preferences based on their past viewing history and rating data. Furthermore, the content delivery unit can use support vector machines to evaluate the relevance of content. Support vector machines learn boundaries for classifying data points and predict which category new data points belong to. This allows the content delivery unit to provide the most relevant content to the user's question. In addition, the content delivery unit can collect user feedback and continuously improve the quality of the content it provides. For example, when a user rates the provided content, the content delivery unit can learn from that rating and incorporate it into future content delivery. This allows the service provider to deliver optimal content tailored to user needs and improve user satisfaction.

[0067] The proposal department makes improvement suggestions to administrators based on the content provided by the service provider. For example, the proposal department makes specific improvement suggestions to administrators. These specific suggestions include the type of suggestion and the criteria for evaluating it. For example, the proposal department can suggest improvements to the site design, or the addition or modification of content. The proposal department analyzes user feedback and behavioral data obtained from the service provider to identify areas for improvement. For example, if a user gives a low rating to a particular piece of content, there may be a problem with the content or how it is displayed. The proposal department can identify these problems and propose specific solutions to administrators. The proposal department also analyzes user behavioral data to determine which content is most popular and which is viewed less frequently. This allows administrators to develop specific strategies to further enhance popular content and improve less viewed content. Furthermore, the proposal department can understand user needs and trends and propose the addition of new content or updates to existing content. This enables the proposal department to provide administrators with specific and actionable improvement suggestions, thereby improving the overall quality of the system.

[0068] The data collection unit collects user behavior data. For example, it collects user click data, browsing history, and purchase history. Specifically, it collects data such as which links users clicked, which pages they viewed, and which products they purchased. This data is important for understanding user interests and preferences. The data collection unit can use this data to perform analysis to improve the quality of services. For example, by analyzing user click data, the unit can identify which content is most popular. By analyzing browsing history, it can understand what kind of content users are interested in. Furthermore, by analyzing purchase history, it can identify what kind of products users prefer to buy. This allows the data collection unit to develop specific strategies for improving service quality based on user behavior data. The data collection unit centrally manages this data and can collaborate with other systems and departments as needed. For example, collected data is stored on a cloud server and made accessible to the analysis and service departments. Adjusting the frequency and accuracy of data collection allows for flexible responses to specific situations and conditions. This enables the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0069] The analysis unit can analyze user questions using natural language processing. For example, the analysis unit can break down user questions into words using morphological analysis. For example, the analysis unit can also analyze sentence structure using grammatical analysis. Furthermore, the analysis unit can understand the meaning of user questions using semantic analysis. In this way, user questions can be accurately analyzed by utilizing natural language processing. Some or all of the above-described processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user question into a generative AI, which can then analyze the question.

[0070] The content provider can provide optimal content using machine learning. For example, the provider can use deep learning to select the most suitable content for a user's question. For example, the provider can also use support vector machines to evaluate the relevance of content. Furthermore, the provider can use machine learning algorithms to provide content based on the user's interests and past behavior history. In this way, machine learning can be used to provide the user with the most suitable content. Some or all of the above processes in the content provider may be performed using, for example, generative AI, or not using generative AI. For example, the provider can input the user's question and past behavior history into a generative AI, which can then select the most suitable content.

[0071] The proposal department can make specific improvement suggestions to administrators. For example, the proposal department may suggest improvements to the site design, or add or modify content. For example, the proposal department can analyze user behavior data to identify areas that need improvement. The proposal department can also make specific improvement suggestions based on user feedback. This allows for an improvement in the quality of the site by providing specific improvement suggestions to administrators. Some or all of the above processes in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input user behavior data into a generative AI, which can then generate improvement suggestions.

[0072] The data collection unit can collect user behavior data and use it to improve the quality of the service. For example, the data collection unit collects user click data, browsing history, purchase history, etc. For example, the data collection unit analyzes user behavior data to identify areas for service improvement. The data collection unit can also personalize the service based on user behavior data. This allows for the collection of user behavior data and improvement of service quality. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input user behavior data into a generative AI, which can then analyze the data.

[0073] The analysis unit can estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. For example, if the user is dissatisfied, the analysis unit can quickly analyze the question and immediately provide appropriate content. For example, if the user is interested, the analysis unit can perform a detailed analysis and provide additional relevant information. The analysis unit can also provide a concise and easy-to-understand analysis result if the user is confused. In this way, by adjusting the question analysis method according to the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0074] The analysis unit can improve the accuracy of its analysis by referring to the user's past question history when analyzing a question. For example, the analysis unit can analyze patterns in questions the user has asked in the past and respond quickly to similar questions. For example, the analysis unit can estimate the user's knowledge level on a particular topic from the user's past question history and perform an appropriate analysis. The analysis unit can also prioritize analyzing and re-provide answers to questions the user was unable to resolve in the past. This improves the accuracy of the analysis by referring to the user's past question history. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's past question history into a generative AI, which can then perform analysis to improve the accuracy of the analysis.

[0075] The analysis unit can perform analysis while considering the user's current context when analyzing a question. For example, if the user is visiting a specific page, the analysis unit will prioritize analyzing information related to that page. For example, if the user is asking a question at night, the analysis unit will provide information related to nighttime. The analysis unit can also analyze information related to an event if the user is asking a question during a specific event. This allows for the provision of more relevant analysis results by considering the user's current context. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's current context data into a generative AI, which can then perform the analysis.

[0076] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated emotions. For example, if the user is dissatisfied, the analysis unit will prioritize providing urgent analysis results. For example, if the user is interested, the analysis unit will prioritize providing relevant additional information. The analysis unit can also prioritize providing concise and easy-to-understand analysis results if the user is confused. In this way, more appropriate analysis results can be provided by prioritizing the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0077] The analysis unit can prioritize providing highly relevant analysis results by considering the user's geographical location information when analyzing a question. For example, if the user is in a specific region, the analysis unit will prioritize providing information related to that region. For example, if the user is traveling, the analysis unit will prioritize providing information related to the travel destination. The analysis unit can also prioritize providing information related to a specific city if the user is in that city. This allows for the provision of more relevant analysis results by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's geographical location information into a generative AI, which can then perform the analysis.

[0078] The analysis unit can analyze the user's social media activity when analyzing a question and reflect relevant information in the analysis. For example, the analysis unit can provide relevant analysis results based on information the user has shared on social media. For example, the analysis unit can prioritize providing information related to topics the user follows on social media. The analysis unit can also provide information that the user might be interested in based on their social media activity history. This allows for the provision of more relevant analysis results by analyzing the user's social media activity. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's social media activity data into a generative AI, which can then perform the analysis.

[0079] The content delivery unit can estimate the user's emotions and adjust the content delivery method based on the estimated emotions. For example, if the user is dissatisfied, the delivery unit can deliver content quickly. For example, if the user is interested, the delivery unit can deliver detailed content. Also, if the user is confused, the delivery unit can deliver concise and easy-to-understand content. In this way, by adjusting the content delivery method according to the user's emotions, more appropriate content can be delivered. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using a generative AI, or not using a generative AI. For example, the delivery unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0080] The content provider can select the most suitable content by referring to the user's past browsing history when providing content. For example, the provider can provide relevant content based on the content the user has previously viewed. For example, the provider can prioritize providing content that the user is likely to be interested in based on the user's past browsing history. The provider can also analyze patterns in the content the user has previously viewed and provide the most suitable content. In this way, the provider can provide the most suitable content by referring to the user's past browsing history. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or without a generative AI. For example, the provider can input the user's past browsing history into a generative AI, which can then select the most suitable content.

[0081] The content provider can customize the content it provides based on the user's current areas of interest. For example, the provider can provide content related to topics the user is currently interested in. For example, if the provider is interested in a particular field, it can prioritize providing content related to that field. The provider can also provide customized content based on the user's current areas of interest. This allows for the provision of more appropriate content by customizing it based on the user's current areas of interest. Some or all of the above processing in the provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the provider can input the user's current areas of interest data into a generative AI, which can then customize the content.

[0082] The service provider can estimate the user's emotions and prioritize the content to be delivered based on those estimated emotions. For example, if the user is dissatisfied, the service provider will prioritize providing urgent content. For example, if the user is interested, the service provider will prioritize providing relevant additional information. The service provider can also prioritize providing concise and easy-to-understand content if the user is confused. This allows for the delivery of more appropriate content by prioritizing content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using a generative AI, or not. For example, the service provider can input user emotion data into a generative AI, which can then estimate the emotion.

[0083] The content provider can prioritize providing highly relevant content by considering the user's geographical location when delivering content. For example, if the user is in a specific region, the provider will prioritize providing content related to that region. For example, if the user is traveling, the provider will prioritize providing content related to their travel destination. The provider can also prioritize providing content related to a specific city if the user is in that city. This allows for the provision of more relevant content by considering the user's geographical location. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or without a generative AI. For example, the content provider can input the user's geographical location information into a generative AI, which can then select the content.

[0084] The content provider can analyze a user's social media activity and provide relevant content when delivering content. For example, the provider can provide relevant content based on information shared by the user on social media. For example, the provider can prioritize providing content related to topics the user follows on social media. The provider can also provide content that is likely to be of interest to the user based on their social media activity history. This allows for the provision of more relevant content by analyzing the user's social media activity. Some or all of the above processing in the content provider may be performed using, for example, a generative AI, or not using a generative AI. For example, the provider can input the user's social media activity data into a generative AI, which can then select the content.

[0085] The suggestion unit can estimate the user's emotions and adjust the content of improvement suggestions based on the estimated emotions. For example, if the user is dissatisfied, the suggestion unit can quickly provide improvement suggestions. For example, if the user is interested, the suggestion unit can provide detailed improvement suggestions. Also, if the user is confused, the suggestion unit can provide concise and easy-to-understand improvement suggestions. In this way, by adjusting the content of improvement suggestions according to the user's emotions, more appropriate improvement suggestions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not using a generative AI. For example, the suggestion unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0086] The proposal department can select the optimal proposal by referring to past proposal history when making improvement proposals. For example, the proposal department can analyze the effectiveness of past proposals and select the optimal proposal. For example, the proposal department can select the optimal proposal for similar problems from past proposal history. The proposal department can also select proposals with high improvement effectiveness based on past proposal history. In this way, the optimal improvement proposal can be made by referring to past proposal history. Some or all of the above processing in the proposal department may be performed using, for example, a generation AI, or without a generation AI. For example, the proposal department can input past proposal history data into a generation AI, and the generation AI can select the optimal proposal.

[0087] The proposal department can make improvement suggestions while considering the current status and trends of the site. For example, the proposal department can make optimal improvement suggestions by considering the current traffic situation of the site. For example, the proposal department can make optimal improvement suggestions by considering the current content trends of the site. Furthermore, the proposal department can also make optimal improvement suggestions by considering the current user engagement situation of the site. This allows for more appropriate improvement suggestions to be made by considering the current status and trends of the site. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input current site status data into a generative AI, and the generative AI can generate optimal suggestions.

[0088] The suggestion unit can estimate the user's emotions and prioritize improvement suggestions based on those emotions. For example, if the user is dissatisfied, the suggestion unit will prioritize urgent improvement suggestions. For example, if the user is interested, the suggestion unit will prioritize providing relevant additional information. Also, if the user is confused, the suggestion unit can prioritize concise and easy-to-understand improvement suggestions. This allows for more appropriate improvement suggestions to be made by prioritizing suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using a generative AI or not. For example, the suggestion unit can input user emotion data into a generative AI, which can then estimate the emotion.

[0089] The proposal unit can make suggestions for improvement while considering the geographical usage of the site. For example, the proposal unit can make optimal improvement suggestions by considering the usage of the site in a specific region. For example, the proposal unit can make optimal improvement suggestions by considering the usage of the site in a specific city. Furthermore, the proposal unit can also make optimal improvement suggestions by considering the usage of the site in a specific country. This allows for more appropriate improvement suggestions to be made by considering the geographical usage of the site. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input geographical usage data of the site into a generative AI, and the generative AI can generate optimal suggestions.

[0090] The proposal department can improve the accuracy of its proposals by referring to trends in the relevant industry when making improvement suggestions. For example, the proposal department can make optimal improvement suggestions by referring to the latest trends in the relevant industry. For example, the proposal department can make optimal improvement suggestions by referring to best practices in the relevant industry. The proposal department can also make optimal improvement suggestions by referring to the trends of competitors in the relevant industry. In this way, by referring to trends in the relevant industry, it is possible to make more accurate improvement suggestions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input data on trends in the relevant industry into a generative AI, and the generative AI can generate the optimal suggestion.

[0091] The data collection unit can estimate the user's emotions and adjust the method of collecting behavioral data based on the estimated user emotions. For example, if the user is feeling dissatisfied, the data collection unit will quickly collect behavioral data. For example, if the user is interested, the data collection unit will collect detailed behavioral data. The data collection unit can also collect concise and easy-to-understand behavioral data if the user is confused. This allows for the collection of more appropriate data by adjusting the method of collecting behavioral data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the data collection unit may be performed using a generative AI, or not using a generative AI. For example, the data collection unit can input user emotion data into a generative AI, which can then estimate the emotion.

[0092] The data collection unit can improve the accuracy of data collection by referring to the user's past behavioral history when collecting behavioral data. For example, the data collection unit prioritizes collecting relevant behavioral data based on the user's past behavioral history. For example, the data collection unit analyzes the user's past behavioral patterns and optimizes the scope of data to be collected. The data collection unit can also collect behavioral data from the user's past behavioral history for specific time periods or situations. This allows for improved data collection accuracy by referring to the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's past behavioral history data into a generative AI, which can then collect the data.

[0093] The data collection unit can collect behavioral data while considering the user's current context. For example, if the user is visiting a specific page, the data collection unit can collect behavioral data related to that page. For example, if the user is active during a specific time period, the data collection unit can collect behavioral data related to that time period. The data collection unit can also collect behavioral data related to an event if the user is active during that event. This allows for the collection of more relevant behavioral data by considering the user's current context. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's current context data into a generative AI, which can then collect the data.

[0094] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated emotions. For example, if the user is feeling dissatisfied, the data collection unit will prioritize collecting urgent behavioral data. For example, if the user is interested, the data collection unit will prioritize collecting relevant additional data. Also, if the user is confused, the data collection unit can prioritize collecting concise and easy-to-understand behavioral data. This allows for the collection of more appropriate data by prioritizing the data to be collected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using a generative AI, or not using a generative AI. For example, the data collection unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0095] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting behavioral data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of behavioral data related to that region. For example, if the user is traveling, the data collection unit will prioritize the collection of behavioral data related to the travel destination. The data collection unit can also prioritize the collection of behavioral data related to a specific city if the user is in that city. This allows for the collection of more relevant behavioral data by considering the user's geographical location. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's geographical location information into a generative AI, which can then collect the data.

[0096] The data collection unit can analyze a user's social media activity and collect relevant data when collecting behavioral data. For example, the data collection unit can collect relevant behavioral data based on information shared by the user on social media. For example, the data collection unit can prioritize collecting behavioral data related to topics the user follows on social media. The data collection unit can also collect behavioral data that the user might be interested in based on their social media activity history. This allows for the collection of more relevant behavioral data by analyzing the user's social media activity. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI, which can then collect the data.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The analysis unit can improve the accuracy of its analysis of user questions by utilizing the user's voice data. For example, the analysis unit converts the user's voice data into text using speech recognition technology and analyzes the question based on that text. The analysis unit can also analyze voice characteristics such as the user's voice tone and speaking speed to estimate the user's emotions and intentions. This allows for a more accurate analysis of user questions by utilizing voice data. Furthermore, the analysis unit can input the user's voice data into a generating AI, which then analyzes the voice data.

[0099] The content delivery system can customize content based on the user's visual preferences when providing the most suitable content in response to a user's question. For example, it can analyze the design and layout of content the user has previously viewed and provide content with a design that matches the user's preferences. It can also adjust the color scheme and font size of the content based on the user's visual preferences. This allows for the delivery of more satisfying content by customizing it according to the user's visual preferences. Furthermore, the content delivery system can input the user's visual preference data into a generating AI, which can then customize the content.

[0100] The suggestion department can collect user feedback in real time and immediately incorporate it when making improvement suggestions to administrators. For example, the suggestion department can collect user ratings and comments on content in real time and make improvement suggestions based on that feedback. The suggestion department can also analyze user feedback and determine the priority of improvements. This allows for faster and more appropriate improvement suggestions by collecting user feedback in real time and immediately incorporating it. Furthermore, the suggestion department can input user feedback data into a generation AI, which can then generate improvement suggestions.

[0101] The data collection unit can improve the accuracy of user behavior data by utilizing the user's biometric information. For example, the data collection unit can collect biometric information such as the user's heart rate and skin electrical response to estimate the user's stress level and level of agitation. The data collection unit can also evaluate the reliability of user behavior data based on the user's biometric information. In this way, the accuracy of user behavior data can be improved by utilizing biometric information. Furthermore, the data collection unit can input the user's biometric information data into a generating AI, which can then analyze the data.

[0102] The analysis unit can estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. For example, if the user is dissatisfied, the analysis unit can quickly analyze the question and immediately provide appropriate content. For example, if the user is interested, the analysis unit can perform a detailed analysis and provide additional relevant information. The analysis unit can also provide a concise and easy-to-understand analysis result if the user is confused. In this way, by adjusting the question analysis method according to the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI, which can then estimate the emotions.

[0103] The content delivery unit can estimate the user's emotions and adjust the content delivery method based on the estimated emotions. For example, if the user is dissatisfied, the delivery unit can deliver content quickly. For example, if the user is interested, the delivery unit can deliver detailed content. Also, if the user is confused, the delivery unit can deliver concise and easy-to-understand content. In this way, by adjusting the content delivery method according to the user's emotions, more appropriate content can be delivered. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using a generative AI, or not using a generative AI. For example, the delivery unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0104] The suggestion unit can estimate the user's emotions and adjust the content of improvement suggestions based on the estimated emotions. For example, if the user is dissatisfied, the suggestion unit can quickly provide improvement suggestions. For example, if the user is interested, the suggestion unit can provide detailed improvement suggestions. Also, if the user is confused, the suggestion unit can provide concise and easy-to-understand improvement suggestions. In this way, by adjusting the content of improvement suggestions according to the user's emotions, more appropriate improvement suggestions can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not using a generative AI. For example, the suggestion unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0105] The data collection unit can estimate the user's emotions and adjust the method of collecting behavioral data based on the estimated user emotions. For example, if the user is feeling dissatisfied, the data collection unit can quickly collect behavioral data. For example, if the user is interested, the data collection unit can collect detailed behavioral data. Also, if the user is confused, the data collection unit can collect concise and easy-to-understand behavioral data. In this way, by adjusting the method of collecting behavioral data according to the user's emotions, more appropriate data can be collected. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using a generative AI, or not using a generative AI. For example, the data collection unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0106] The analysis unit can improve the accuracy of its analysis of user questions by utilizing user gesture data. For example, the analysis unit collects user gesture data using cameras and sensors and estimates the intent of the question based on that data. The analysis unit can also analyze the user's gesture data to estimate the user's emotions and intentions. This allows for a more accurate analysis of user questions by utilizing gesture data. Furthermore, the analysis unit can input the user's gesture data into a generating AI, which then analyzes the gesture data.

[0107] The content delivery system can customize content based on user preferences when providing the most suitable content in response to user inquiries. For example, it can analyze the genres and themes of content previously viewed by the user and provide content that matches their preferences. It can also adjust the order and display method of content based on user preferences. This allows for the delivery of more satisfying content by customizing it according to user preferences. Furthermore, the content delivery system can input user preference data into a content generation AI, which can then customize the content.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The analysis unit analyzes the user's question. The analysis unit analyzes the user's question using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down the user's question into words and grammatical analysis to analyze the sentence structure. The analysis unit can also use semantic analysis to understand the meaning of the user's question. Step 2: The delivery unit provides the most suitable content based on the questions analyzed by the analysis unit. The delivery unit uses machine learning techniques to provide the most suitable content. Machine learning techniques include deep learning and support vector machines. For example, the delivery unit uses deep learning to select the most suitable content for the user's question. The delivery unit can also use support vector machines to evaluate the relevance of the content. Step 3: The proposal team makes improvement suggestions to the administrator based on the content provided by the delivery team. The proposal team makes specific improvement suggestions to the administrator. These specific suggestions include the type of suggestion and the criteria for evaluating the suggestion. For example, the proposal team may suggest improvements to the site design, or the addition or modification of content. Step 4: The data collection unit collects user behavior data. The data collection unit collects user click data, browsing history, purchase history, etc. The data collection unit can use this data to perform analysis to improve the quality of the service.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the analysis unit, provision unit, proposal unit, and collection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the user's question using natural language processing technology. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides optimal content using machine learning technology. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes specific improvement suggestions to the administrator. The collection unit is implemented by the control unit 46A of the smart device 14 and collects user behavior data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the analysis unit, provision unit, proposal unit, and collection unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the user's questions using natural language processing technology. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides optimal content using machine learning technology. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes specific improvement suggestions to the administrator. The collection unit is implemented by the control unit 46A of the smart glasses 214 and collects user behavior data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the analysis unit, provision unit, proposal unit, and collection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the user's questions using natural language processing technology. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides optimal content using machine learning technology. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes specific improvement suggestions to the administrator. The collection unit is implemented by the control unit 46A of the headset terminal 314 and collects user behavior data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the 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.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the analysis unit, provision unit, proposal unit, and collection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the user's question using natural language processing technology. The provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides optimal content using machine learning technology. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes specific improvement suggestions to the administrator. The collection unit is implemented by the control unit 46A of the robot 414 and collects user behavior data. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0173] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) An analysis unit that analyzes user questions, A provisioning unit that provides optimal content based on the questions analyzed by the aforementioned analysis unit, A proposal unit that makes improvement suggestions to the administrator based on the content provided by the aforementioned provision unit, It comprises a collection unit that collects user behavior data. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze user questions using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned supply unit is, We use machine learning to provide optimal content. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, Make specific improvement suggestions to the administrator. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is We collect user behavior data and use it to improve the quality of our services. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, We estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing questions, we improve the accuracy of the analysis by referring to the user's past question history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing a question, the analysis takes into account the user's current context. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing questions, the system prioritizes providing highly relevant analysis results by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing questions, the system analyzes users' social media activity and incorporates relevant information into the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned supply unit is, We estimate user sentiment and adjust how content is delivered based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned supply unit is, When providing content, the system selects the most suitable content by referring to the user's past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned supply unit is, When providing content, customize the content offered based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the content to be delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned supply unit is, When providing content, we prioritize delivering highly relevant content by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned supply unit is, When providing content, we analyze users' social media activity and provide relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, The system estimates the user's emotions and adjusts the content of improvement suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, When submitting improvement proposals, the most suitable proposal is selected by referring to past proposal history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, When proposing improvements, consider the current state and trends of the site. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, It estimates user emotions and prioritizes improvement suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, When proposing improvements, consider the geographical usage of the site. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, When making improvement proposals, refer to trends in the relevant industry to improve the accuracy of the proposals. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned collection unit is We estimate the user's emotions and adjust the method of collecting behavioral data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned collection unit is When collecting behavioral data, we improve the accuracy of the data collection by referring to the user's past behavioral history. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned collection unit is When collecting behavioral data, the current context of the user is taken into consideration during the collection process. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned collection unit is When collecting behavioral data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned collection unit is When collecting behavioral data, analyze users' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes user questions, A provisioning unit that provides optimal content based on the questions analyzed by the aforementioned analysis unit, A proposal unit that makes improvement suggestions to the administrator based on the content provided by the aforementioned provision unit, It comprises a collection unit that collects user behavior data. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze user questions using natural language processing. The system according to feature 1.

3. The aforementioned supply unit is, We use machine learning to provide optimal content. The system according to feature 1.

4. The aforementioned proposal section is, Make specific improvement suggestions to the administrator. The system according to feature 1.

5. The aforementioned collection unit is We collect user behavior data and use it to improve the quality of our services. The system according to feature 1.

6. The aforementioned analysis unit, We estimate the user's emotions and adjust the question analysis method based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing questions, we improve the accuracy of the analysis by referring to the user's past question history. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing a question, the analysis takes into account the user's current context. The system according to feature 1.

Images