system

Abstract

The system according to this embodiment aims to naturally insert advertisements during conversations with users. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a suggestion unit, and an insertion unit. The collection unit collects user hobbies, preferences, and behavioral data. The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation content in real time. The suggestion unit suggests appropriate advertisements based on the conversation content analyzed by the analysis unit. The insertion unit naturally inserts the advertisements suggested by the suggestion unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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, unnatural advertisements may be inserted during a conversation with a user, which may damage the user experience.

[0005] The system according to the embodiment aims to naturally insert advertisements during a conversation with a user.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an analysis unit, a suggestion unit, and an insertion unit. The data collection unit collects user hobbies, preferences, and behavioral data. The analysis unit analyzes the data collected by the data collection unit and analyzes the user's conversation content in real time. The suggestion unit suggests appropriate advertisements based on the conversation content analyzed by the analysis unit. The insertion unit naturally inserts the advertisements suggested by the suggestion unit. [Effects of the Invention]

[0007] The system according to this embodiment can naturally insert advertisements during conversations with users. [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, and the like. 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 receiving 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 receiving 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) An advertising insertion system according to an embodiment of the present invention is a system that naturally inserts advertisements into conversations between a user and a generative AI using generative AI. The advertising insertion system collects user hobbies, preferences, and behavioral data, and the generative AI analyzes the user's conversation in real time and proposes highly relevant advertisements at the appropriate time. Furthermore, it naturally inserts the proposed advertisements to improve the user experience. This system protects user privacy while also providing high effectiveness to advertisers. Because the generative AI analyzes the user's interests and behavior and proposes the most suitable advertisements, the click-through rate and conversion rate of advertisements are improved. For example, the advertising insertion system collects user hobbies, preferences, and behavioral data. For example, the advertising insertion system can collect behavioral data such as the user's website browsing history and purchase history. Next, the advertising insertion system uses generative AI to analyze the user's conversation in real time. The input to the generative AI is the user's conversation itself, and the generative AI performs analysis based on that content. For example, the generative AI receives a prompt such as "Understand the context of this conversation and propose relevant advertisements," analyzes the context of the conversation, and proposes appropriate advertisements. Next, the advertising insertion system naturally inserts the advertisements proposed by the generative AI. Ad insertion is performed in a way that does not disrupt the flow of conversation. For example, a generative AI selects a way to introduce ads naturally within the conversation, inserting them in a way that does not make the user feel uncomfortable. This allows the ad insertion system to maximize the effectiveness of ads while improving the user experience. In this way, the ad insertion system can achieve natural ad insertion based on the user's interests, preferences, and behavioral data, thereby improving ad click-through rates and conversion rates.

[0029] The advertising insertion system according to this embodiment comprises a collection unit, an analysis unit, a suggestion unit, and an insertion unit. The collection unit collects user hobbies, preferences, and behavioral data. For example, the collection unit collects the user's website browsing history. The collection unit can also collect, for example, the user's purchase history. The collection unit can also collect, for example, the user's search history. The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation content in real time. The analysis unit analyzes the user's conversation content using, for example, a generative AI. The generative AI analyzes the conversation content using, for example, a text generation AI (e.g., LLM). The generative AI can also analyze the conversation content using, for example, a multimodal generation AI. The generative AI can also analyze the conversation content using, for example, natural language processing technology. The suggestion unit suggests appropriate advertisements based on the conversation content analyzed by the analysis unit. The suggestion unit suggests advertisements related to the conversation content using, for example, a generative AI. The generative AI suggests advertisements using, for example, a text generation AI. The generating AI can, for example, suggest advertisements using a multimodal generating AI. The generating AI can also, for example, suggest advertisements using a recommendation algorithm. The insertion unit naturally inserts the advertisements suggested by the suggestion unit. The insertion unit inserts advertisements in a way that does not disrupt the flow of conversation, for example. The insertion unit selects a way to introduce advertisements naturally within a conversation, for example. The insertion unit can also insert advertisements in a way that does not cause discomfort to the user, for example. As a result, the advertisement insertion system according to the embodiment can achieve natural advertisement insertion based on the user's tastes, preferences and behavioral data, and can improve the click-through rate and conversion rate of advertisements.

[0030] The data collection unit collects user preferences, tastes, and behavioral data. Specifically, it collects users' website browsing history. For example, it can collect detailed data such as the URLs of web pages visited, browsing time, and links clicked. This allows for an understanding of what kind of content users are interested in. The data collection unit can also collect users' purchase history. For example, by collecting data such as purchase history on online shopping sites, categories of purchased products, price range, and purchase frequency, it is possible to analyze users' purchasing trends. Furthermore, the data collection unit can also collect users' search history. For example, by collecting data such as search keywords on search engines, click history of search results, and search date and time, it is possible to understand the topics and information that users are currently interested in. This data is centrally managed by the data collection unit and made accessible to the analysis and proposal units. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. For example, by strengthening data collection during specific time periods or event periods, more detailed user profiles can be created. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation in real time. Specifically, it analyzes the user's conversation using a generative AI. The generative AI analyzes the conversation using, for example, a text generation AI (e.g., LLM). The text generation AI receives the user's conversation text as input and analyzes its content to identify the user's intentions and interests. For example, if a user says, "I'm looking for a new smartphone," the generative AI analyzes this statement and recognizes that the user is interested in smartphones. The generative AI can also analyze the conversation using a multimodal generative AI. A multimodal generative AI can integrate and analyze multiple data formats, such as images and audio, in addition to text. For example, if a user is sharing photos from their smartphone while talking, the generative AI can also analyze the image data to gain a more detailed understanding of the user's interests. Furthermore, the generative AI can also analyze the conversation using natural language processing technology. Natural language processing technology can perform advanced analyses such as contextual understanding and sentiment analysis, allowing for an accurate grasp of the intentions and emotions behind the user's statements. This allows the analysis unit to quickly and accurately analyze the collected data and understand users' interests and intentions in real time.

[0032] The proposal department proposes appropriate advertisements based on the conversation content analyzed by the analysis department. Specifically, it uses generative AI to propose advertisements related to the conversation content. For example, the generative AI can propose advertisements using text generation AI. Text generation AI can generate relevant advertisement text based on the user's conversation content. For example, if a user says, "I'm looking for a new smartphone," the generative AI can generate advertisement text such as, "The latest smartphone is available now at a special price." The generative AI can also propose advertisements using multimodal generative AI. Multimodal generative AI can generate not only text but also advertisement content such as images and videos. For example, if a user is sharing photos from their smartphone while talking, the generative AI can generate advertisement images and videos for smartphones based on that image data. Furthermore, the generative AI can also propose advertisements using recommendation algorithms. Recommendation algorithms can select the most suitable advertisements based on the user's past behavior data and data on similar users. This allows the proposal department to quickly propose appropriate advertisements based on the user's interests and intentions.

[0033] The insertion unit seamlessly inserts advertisements proposed by the suggestion unit. Specifically, it inserts advertisements in a way that does not disrupt the flow of conversation. For example, immediately after a user says, "I'm looking for a new smartphone," it can naturally insert an advertisement such as, "The latest smartphone is available now at a special price." The insertion unit selects the most natural way to introduce advertisements within a conversation. For example, if a user is sharing photos from their smartphone while talking, it can naturally insert advertisement images or videos related to those photos. Furthermore, the insertion unit can also insert advertisements in a way that does not make the user feel uncomfortable. For example, it can adjust the content and expression of the advertisement to match the tone and context of the user's conversation, making the advertisement feel natural. This allows the insertion unit to effectively insert advertisements without disrupting the flow of the user's conversation. In addition, the insertion unit can collect user feedback and continuously improve the accuracy and effectiveness of ad insertion. For example, it can monitor user reactions and click-through rates after ad insertion and optimize the content and timing of the advertisement. The insertion unit can also test multiple ad formats and select the most effective one. This allows the insertion section to achieve a natural and seamless ad insertion for the user, thereby improving ad click-through rates and conversion rates.

[0034] The protection unit includes functions to protect user privacy. For example, the protection unit can anonymize data. The protection unit can also encrypt data. The protection unit can also collect data with the user's consent. This allows for the insertion of advertisements while protecting user privacy. Some or all of the above-described processes in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can have AI perform data anonymization.

[0035] The performance measurement unit measures the click-through rate and conversion rate of advertisements. For example, the performance measurement unit calculates the value obtained by dividing the number of clicks by the number of impressions. The performance measurement unit can also calculate the value obtained by dividing the number of purchases by the number of clicks. The performance measurement unit can also count the number of times an advertisement is displayed. This allows for the measurement of the effectiveness of advertisements and the development of optimal advertising strategies. Some or all of the above processes in the performance measurement unit may be performed using AI, for example, or not using AI. For example, the performance measurement unit can have AI perform the calculation of clicks and impressions.

[0036] The data collection unit analyzes the user's past behavioral data and selects the optimal data collection method. For example, the data collection unit prioritizes collecting data from websites the user has frequently visited in the past. For example, the data collection unit analyzes the user's past purchase history and collects data on related products. For example, the data collection unit collects data on topics of interest based on the user's past search history. This allows the optimal data collection method to be selected based on past behavioral data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the analysis of past behavioral data.

[0037] The data collection unit filters data based on the user's current activities and areas of interest during data collection. For example, the data collection unit collects relevant data based on the content of the web page the user is currently viewing. For example, the data collection unit collects data based on the topics of the online community the user is participating in. For example, the data collection unit collects relevant data based on the content of the video the user is currently watching. This allows the data to be filtered based on the user's current activities and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can have AI perform the filtering of current activities and areas of interest.

[0038] The data collection unit prioritizes collecting highly relevant data, taking into account the user's geographical location. For example, if the user is in a specific region, the collection unit collects event information related to that region. If the user is traveling, the collection unit prioritizes collecting tourist information for the travel destination. If the user is at home, the collection unit prioritizes collecting information about nearby shops. This allows for the collection of highly relevant data while considering geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into AI and have the AI ​​perform the collection of highly relevant data.

[0039] The data collection unit analyzes the user's social media activity and collects relevant data during data collection. For example, the data collection unit collects data based on the content of posts from accounts the user follows on social media. For example, the data collection unit collects data based on the topics of groups the user participates in on social media. For example, the data collection unit collects data related to content the user shares on social media. This allows for the collection of relevant data based on social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the analysis of social media activity.

[0040] The analysis unit adjusts the level of detail in the analysis based on the importance of the conversation. For example, the analysis unit performs a detailed analysis on important conversational content to provide deeper insights. For example, the analysis unit performs a concise analysis on general conversational content to provide only the key points. For example, the analysis unit performs a detailed analysis on topics that the user has shown particular interest in. This allows the level of detail in the analysis to be adjusted based on the importance of the conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the conversation into the AI ​​and have the AI ​​perform the adjustment of the level of detail in the analysis.

[0041] The analysis unit applies different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies a specialized analysis algorithm to business-related conversations. For example, the analysis unit applies an algorithm that emphasizes sentiment analysis to entertainment-related conversations. For example, the analysis unit applies a general analysis algorithm to everyday conversations. This allows the appropriate analysis algorithm to be applied according to the category of the conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the conversation into the AI ​​and have the AI ​​perform the application of the analysis algorithm.

[0042] The analysis unit determines the priority of analysis based on the timing of conversation submission during the analysis process. For example, the analysis unit may prioritize analyzing the most recent conversation content. For example, the analysis unit may prioritize analyzing conversations that the user had during a specific time period. For example, the analysis unit may prioritize analyzing conversations that the user had before or after an important event. This allows the analysis priority to be determined based on the timing of conversation submission. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the timing of conversation submission into the AI ​​and have the AI ​​perform the determination of analysis priority.

[0043] The analysis unit adjusts the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analyzing conversations that the user has had consecutively on a particular topic. For example, the analysis unit prioritizes analyzing conversations that the user has had with a particular person. For example, the analysis unit prioritizes analyzing conversations that the user has had in a particular location. This allows the order of analysis to be adjusted based on the relevance of the conversations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the conversations into the AI ​​and have the AI ​​perform the adjustment of the order of analysis.

[0044] The suggestion unit adjusts the level of detail in its suggestions based on the importance of the advertisements. For example, the suggestion unit provides detailed information for important advertisements, concise information for general advertisements, and detailed information for advertisements that users have shown particular interest in. This allows the level of detail in suggestions to be adjusted based on the importance of the advertisements. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input the importance of the advertisements into the AI ​​and have the AI ​​perform the adjustment of the level of detail in suggestions.

[0045] The proposal unit applies different proposal algorithms depending on the advertisement category when making proposals. For example, the proposal unit applies a specialized proposal algorithm for business-related advertisements. For example, the proposal unit applies an algorithm that emphasizes sentiment analysis for entertainment-related advertisements. For example, the proposal unit applies a general proposal algorithm for everyday life-related advertisements. This ensures that the appropriate proposal algorithm is applied according to the advertisement category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input the advertisement category into the AI ​​and have the AI ​​perform the application of the proposal algorithm.

[0046] The proposal department determines the priority of proposals based on the timing of ad submission. For example, the proposal department may prioritize the most recent ads. For example, the proposal department may prioritize ads that users showed interest in during a specific time period. For example, the proposal department may prioritize ads that users showed interest in before or after an important event. This allows the proposal department to determine the priority of proposals based on the timing of ad submission. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the timing of ad submission into the AI ​​and have the AI ​​perform the determination of proposal priority.

[0047] The suggestion unit adjusts the order of suggestions based on the relevance of the advertisements when making suggestions. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular topic. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular brand. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular product. This allows the order of suggestions to be adjusted based on the relevance of the advertisements. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit may input the relevance of the advertisements into the AI ​​and have the AI ​​perform the adjustment of the suggestion order.

[0048] The insertion unit improves the naturalness of ad insertion by considering the flow of conversation. For example, the insertion unit inserts an ad when the topic of conversation changes. For example, the insertion unit selects a way to introduce the ad naturally within the conversation. For example, the insertion unit inserts an ad when the user shows interest in the conversation. This improves the naturalness of ad insertion by considering the flow of conversation. Some or all of the above processing in the insertion unit may be performed using AI, for example, or not using AI. For example, the insertion unit can input the flow of conversation into AI and have the AI ​​perform the improvement of the naturalness of ad insertion.

[0049] The insertion unit selects the optimal insertion method by referring to the user's past response data during insertion. For example, the insertion unit prioritizes ad insertion methods that the user has previously responded favorably to. For example, the insertion unit avoids ad insertion methods that the user has previously ignored. For example, the insertion unit refers to ad insertion methods that the user has previously clicked on. This allows the system to select the optimal ad insertion method based on the user's past response data. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit can input past response data into AI and have the AI ​​select the optimal insertion method.

[0050] The insertion unit inserts the most suitable advertisements, taking into account the user's geographical location information. For example, if the user is in a specific region, the insertion unit inserts advertisements related to that region. For example, if the user is traveling, the insertion unit inserts advertisements containing tourist information about the travel destination. For example, if the user is at home, the insertion unit inserts advertisements containing information about nearby stores. This allows for the insertion of the most suitable advertisements, taking into account geographical location information. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit can input the user's geographical location information into AI and have the AI ​​perform the insertion of the most suitable advertisements.

[0051] The insertion unit analyzes the user's social media activity during insertion and proposes methods for inserting advertisements. For example, the insertion unit may insert advertisements for brands that the user follows on social media. For example, the insertion unit may insert advertisements related to content that the user has shared on social media. For example, the insertion unit may insert advertisements related to topics in groups that the user participates in on social media. This allows the insertion unit to propose the most suitable method of advertisement insertion based on social media activity. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit may have AI perform the analysis of social media activity.

[0052] The protection unit, when protecting privacy, selects the optimal protection method by referring to the user's past data usage history. For example, the protection unit suggests the optimal protection method based on the privacy settings the user has previously selected. For example, the protection unit avoids data usage methods that the user has previously rejected. For example, the protection unit prioritizes data usage methods that the user has previously permitted. This allows the protection unit to select the optimal privacy protection method based on past data usage history. Some or all of the above processing in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can input past data usage history into AI and have the AI ​​select the optimal protection method.

[0053] The protection unit selects the optimal protection method when protecting privacy, taking into account the user's geographical location. For example, if the user is in a specific region, the protection unit selects a protection method based on the privacy regulations of that region. For example, if the user is traveling, the protection unit selects a protection method based on the privacy regulations of the travel destination. For example, if the user is at home, the protection unit selects a protection method based on the local privacy regulations. This allows the protection unit to select the optimal privacy protection method while taking geographical location into consideration. Some or all of the above processing in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can input the user's geographical location information into AI and have AI select the optimal protection method.

[0054] The effectiveness measurement unit selects the optimal measurement method by referring to past advertising effectiveness data when measuring effectiveness. For example, the effectiveness measurement unit prioritizes measurement methods for advertisements that have shown high effectiveness in the past. For example, the effectiveness measurement unit avoids measurement methods for advertisements that have shown low effectiveness in the past. For example, the effectiveness measurement unit proposes new measurement methods based on past advertising effectiveness data. This allows for the selection of the optimal measurement method based on past advertising effectiveness data. Some or all of the above processes in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input past advertising effectiveness data into AI and have the AI ​​select the optimal measurement method.

[0055] The effectiveness measurement unit weights the measurement data based on the timing of ad submission during effectiveness measurement. For example, the effectiveness measurement unit may prioritize the most recent ad effectiveness data. For example, the effectiveness measurement unit may prioritize the effectiveness data of ads submitted during a specific time period. For example, the effectiveness measurement unit may prioritize the effectiveness data of ads submitted before and after an important event. This allows for weighting of the measurement data based on the timing of ad submission. Some or all of the above processing in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit may input the ad submission timing into the AI ​​and have the AI ​​perform the weighting of the measurement data.

[0056] The effectiveness measurement unit weights the measurement data based on the relevance of the advertisements when measuring effectiveness. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular topic. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular brand. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular product. This allows the measurement data to be weighted based on the relevance of the advertisements. Some or all of the above processing in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input the relevance of the advertisements into the AI ​​and have the AI ​​perform the weighting of the measurement data.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The ad insertion system may also include a device monitoring unit that monitors the user's device usage. The device monitoring unit monitors the type of device the user is using, the duration of use, and the application usage, and then suggests the most suitable ads. For example, if a user is using a smartphone for an extended period, the device monitoring unit can suggest mobile-friendly ads. If the user is using a PC, the device monitoring unit can suggest desktop-friendly ads. This allows the device monitoring unit to optimize ad suggestions based on the user's device usage.

[0059] The ad insertion system may also include a social analytics unit that analyzes the user's social network relationships. The social analytics unit analyzes the user's relationships and interaction frequency on social networks and suggests the most suitable advertisements. For example, if a user frequently interacts with a particular friend, the social analytics unit will suggest advertisements related to products or services that that friend is interested in. If a user belongs to a specific group, the social analytics unit can suggest advertisements based on the group's interests. This allows the social analytics unit to optimize ad suggestions based on the user's social network.

[0060] The ad insertion system can also include a health analysis unit that analyzes the user's health data. The health analysis unit analyzes the user's health status and fitness data to suggest the most suitable advertisements. For example, if a user is using a fitness tracker, the health analysis unit can suggest advertisements for health foods and fitness-related products based on that data. If a user is using a sleep tracker, the health analysis unit can suggest advertisements for relaxation products and sleep improvement products based on that data. This allows the health analysis unit to optimize ad suggestions based on the user's health data.

[0061] The ad insertion system may also include a purchase intent estimation unit that estimates the user's purchase intent. The purchase intent estimation unit analyzes the user's past purchase history and current behavioral data to estimate the user's purchase intent. For example, if a user frequently searches for a particular product, the purchase intent estimation unit will suggest ads related to that product. If a user has recently purchased an item in a particular category, the purchase intent estimation unit can suggest ads for additional products or accessories related to that category. This allows the purchase intent estimation unit to optimize ad suggestions based on the user's purchase intent.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The data collection unit collects user preferences and behavioral data. For example, the data collection unit collects the user's website browsing history, purchase history, and search history. Step 2: The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation content in real time. For example, the analysis unit uses generation AI, such as text generation AI, multimodal generation AI, and natural language processing technology, to analyze the conversation content. Step 3: The proposal unit proposes appropriate advertisements based on the conversation content analyzed by the analysis unit. For example, the proposal unit uses generative AI to propose advertisements using text generation AI, multimodal generation AI, and recommendation algorithms. Step 4: The insertion section seamlessly inserts the advertisement proposed by the suggestion section. For example, the insertion section inserts the advertisement in a way that does not disrupt the flow of the conversation and selects a method of introducing the advertisement that does not make the user feel uncomfortable.

[0064] (Example of form 2) An advertising insertion system according to an embodiment of the present invention is a system that naturally inserts advertisements into conversations between a user and a generative AI using generative AI. The advertising insertion system collects user hobbies, preferences, and behavioral data, and the generative AI analyzes the user's conversation in real time and proposes highly relevant advertisements at the appropriate time. Furthermore, it naturally inserts the proposed advertisements to improve the user experience. This system protects user privacy while also providing high effectiveness to advertisers. Because the generative AI analyzes the user's interests and behavior and proposes the most suitable advertisements, the click-through rate and conversion rate of advertisements are improved. For example, the advertising insertion system collects user hobbies, preferences, and behavioral data. For example, the advertising insertion system can collect behavioral data such as the user's website browsing history and purchase history. Next, the advertising insertion system uses generative AI to analyze the user's conversation in real time. The input to the generative AI is the user's conversation itself, and the generative AI performs analysis based on that content. For example, the generative AI receives a prompt such as "Understand the context of this conversation and propose relevant advertisements," analyzes the context of the conversation, and proposes appropriate advertisements. Next, the advertising insertion system naturally inserts the advertisements proposed by the generative AI. Ad insertion is performed in a way that does not disrupt the flow of conversation. For example, a generative AI selects a way to introduce ads naturally within the conversation, inserting them in a way that does not make the user feel uncomfortable. This allows the ad insertion system to maximize the effectiveness of ads while improving the user experience. In this way, the ad insertion system can achieve natural ad insertion based on the user's interests, preferences, and behavioral data, thereby improving ad click-through rates and conversion rates.

[0065] The advertising insertion system according to this embodiment comprises a collection unit, an analysis unit, a suggestion unit, and an insertion unit. The collection unit collects user hobbies, preferences, and behavioral data. For example, the collection unit collects the user's website browsing history. The collection unit can also collect, for example, the user's purchase history. The collection unit can also collect, for example, the user's search history. The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation content in real time. The analysis unit analyzes the user's conversation content using, for example, a generative AI. The generative AI analyzes the conversation content using, for example, a text generation AI (e.g., LLM). The generative AI can also analyze the conversation content using, for example, a multimodal generation AI. The generative AI can also analyze the conversation content using, for example, natural language processing technology. The suggestion unit suggests appropriate advertisements based on the conversation content analyzed by the analysis unit. The suggestion unit suggests advertisements related to the conversation content using, for example, a generative AI. The generative AI suggests advertisements using, for example, a text generation AI. The generating AI can, for example, suggest advertisements using a multimodal generating AI. The generating AI can also, for example, suggest advertisements using a recommendation algorithm. The insertion unit naturally inserts the advertisements suggested by the suggestion unit. The insertion unit inserts advertisements in a way that does not disrupt the flow of conversation, for example. The insertion unit selects a way to introduce advertisements naturally within a conversation, for example. The insertion unit can also insert advertisements in a way that does not cause discomfort to the user, for example. As a result, the advertisement insertion system according to the embodiment can achieve natural advertisement insertion based on the user's tastes, preferences and behavioral data, and can improve the click-through rate and conversion rate of advertisements.

[0066] The data collection unit collects user preferences, tastes, and behavioral data. Specifically, it collects users' website browsing history. For example, it can collect detailed data such as the URLs of web pages visited, browsing time, and links clicked. This allows for an understanding of what kind of content users are interested in. The data collection unit can also collect users' purchase history. For example, by collecting data such as purchase history on online shopping sites, categories of purchased products, price range, and purchase frequency, it is possible to analyze users' purchasing trends. Furthermore, the data collection unit can also collect users' search history. For example, by collecting data such as search keywords on search engines, click history of search results, and search date and time, it is possible to understand the topics and information that users are currently interested in. This data is centrally managed by the data collection unit and made accessible to the analysis and proposal units. By adjusting the frequency and accuracy of data collection, the data collection unit can respond flexibly to specific situations and conditions. For example, by strengthening data collection during specific time periods or event periods, more detailed user profiles can be created. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0067] The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation in real time. Specifically, it analyzes the user's conversation using a generative AI. The generative AI analyzes the conversation using, for example, a text generation AI (e.g., LLM). The text generation AI receives the user's conversation text as input and analyzes its content to identify the user's intentions and interests. For example, if a user says, "I'm looking for a new smartphone," the generative AI analyzes this statement and recognizes that the user is interested in smartphones. The generative AI can also analyze the conversation using a multimodal generative AI. A multimodal generative AI can integrate and analyze multiple data formats, such as images and audio, in addition to text. For example, if a user is sharing photos from their smartphone while talking, the generative AI can also analyze the image data to gain a more detailed understanding of the user's interests. Furthermore, the generative AI can also analyze the conversation using natural language processing technology. Natural language processing technology can perform advanced analyses such as contextual understanding and sentiment analysis, allowing for an accurate grasp of the intentions and emotions behind the user's statements. This allows the analysis unit to quickly and accurately analyze the collected data and understand users' interests and intentions in real time.

[0068] The proposal department proposes appropriate advertisements based on the conversation content analyzed by the analysis department. Specifically, it uses generative AI to propose advertisements related to the conversation content. For example, the generative AI can propose advertisements using text generation AI. Text generation AI can generate relevant advertisement text based on the user's conversation content. For example, if a user says, "I'm looking for a new smartphone," the generative AI can generate advertisement text such as, "The latest smartphone is available now at a special price." The generative AI can also propose advertisements using multimodal generative AI. Multimodal generative AI can generate not only text but also advertisement content such as images and videos. For example, if a user is sharing photos from their smartphone while talking, the generative AI can generate advertisement images and videos for smartphones based on that image data. Furthermore, the generative AI can also propose advertisements using recommendation algorithms. Recommendation algorithms can select the most suitable advertisements based on the user's past behavior data and data on similar users. This allows the proposal department to quickly propose appropriate advertisements based on the user's interests and intentions.

[0069] The insertion unit seamlessly inserts advertisements proposed by the suggestion unit. Specifically, it inserts advertisements in a way that does not disrupt the flow of conversation. For example, immediately after a user says, "I'm looking for a new smartphone," it can naturally insert an advertisement such as, "The latest smartphone is available now at a special price." The insertion unit selects the most natural way to introduce advertisements within a conversation. For example, if a user is sharing photos from their smartphone while talking, it can naturally insert advertisement images or videos related to those photos. Furthermore, the insertion unit can also insert advertisements in a way that does not make the user feel uncomfortable. For example, it can adjust the content and expression of the advertisement to match the tone and context of the user's conversation, making the advertisement feel natural. This allows the insertion unit to effectively insert advertisements without disrupting the flow of the user's conversation. In addition, the insertion unit can collect user feedback and continuously improve the accuracy and effectiveness of ad insertion. For example, it can monitor user reactions and click-through rates after ad insertion and optimize the content and timing of the advertisement. The insertion unit can also test multiple ad formats and select the most effective one. This allows the insertion section to achieve a natural and seamless ad insertion for the user, thereby improving ad click-through rates and conversion rates.

[0070] The protection unit includes functions to protect user privacy. For example, the protection unit can anonymize data. The protection unit can also encrypt data. The protection unit can also collect data with the user's consent. This allows for the insertion of advertisements while protecting user privacy. Some or all of the above-described processes in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can have AI perform data anonymization.

[0071] The performance measurement unit measures the click-through rate and conversion rate of advertisements. For example, the performance measurement unit calculates the value obtained by dividing the number of clicks by the number of impressions. The performance measurement unit can also calculate the value obtained by dividing the number of purchases by the number of clicks. The performance measurement unit can also count the number of times an advertisement is displayed. This allows for the measurement of the effectiveness of advertisements and the development of optimal advertising strategies. Some or all of the above processes in the performance measurement unit may be performed using AI, for example, or not using AI. For example, the performance measurement unit can have AI perform the calculation of clicks and impressions.

[0072] The data collection unit estimates the user's emotions and adjusts the timing of collecting hobby, preference, and behavioral data based on the estimated emotions. For example, if the user is relaxed, the data collection unit collects hobby, preference, and behavioral data more frequently. If the user is stressed, for example, the data collection unit reduces the frequency of data collection to alleviate the user's burden. If the user is excited, for example, the data collection unit prioritizes collecting specific behavioral data. This allows the timing of data collection to be adjusted 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 AI, for example, or without AI. For example, the data collection unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0073] The data collection unit analyzes the user's past behavioral data and selects the optimal data collection method. For example, the data collection unit prioritizes collecting data from websites the user has frequently visited in the past. For example, the data collection unit analyzes the user's past purchase history and collects data on related products. For example, the data collection unit collects data on topics of interest based on the user's past search history. This allows the optimal data collection method to be selected based on past behavioral data. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the analysis of past behavioral data.

[0074] The data collection unit filters data based on the user's current activities and areas of interest during data collection. For example, the data collection unit collects relevant data based on the content of the web page the user is currently viewing. For example, the data collection unit collects data based on the topics of the online community the user is participating in. For example, the data collection unit collects relevant data based on the content of the video the user is currently watching. This allows the data to be filtered based on the user's current activities and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can have AI perform the filtering of current activities and areas of interest.

[0075] The data collection unit estimates the user's emotions and determines the priority of data to collect based on the estimated user emotions. For example, if the user is relaxed, the data collection unit prioritizes collecting data related to hobbies. For example, if the user is stressed, the data collection unit prioritizes collecting data related to relaxation. For example, if the user is excited, the data collection unit prioritizes collecting data related to entertainment. This allows for data prioritization based on 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 AI, for example, or without AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0076] The data collection unit prioritizes collecting highly relevant data, taking into account the user's geographical location. For example, if the user is in a specific region, the collection unit collects event information related to that region. If the user is traveling, the collection unit prioritizes collecting tourist information for the travel destination. If the user is at home, the collection unit prioritizes collecting information about nearby shops. This allows for the collection of highly relevant data while considering geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into AI and have the AI ​​perform the collection of highly relevant data.

[0077] The data collection unit analyzes the user's social media activity and collects relevant data during data collection. For example, the data collection unit collects data based on the content of posts from accounts the user follows on social media. For example, the data collection unit collects data based on the topics of groups the user participates in on social media. For example, the data collection unit collects data related to content the user shares on social media. This allows for the collection of relevant data based on social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have AI perform the analysis of social media activity.

[0078] The analysis unit estimates the user's emotions and adjusts the conversation analysis method based on the estimated user emotions. For example, if the user is relaxed, the analysis unit performs a detailed analysis and provides deep insights. If the user is stressed, the analysis unit performs a concise analysis and provides only the important points. If the user is excited, the analysis unit performs an analysis that is sensitive to changes in emotions. This allows the conversation analysis method to be adjusted based on 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 AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0079] The analysis unit adjusts the level of detail in the analysis based on the importance of the conversation. For example, the analysis unit performs a detailed analysis on important conversational content to provide deeper insights. For example, the analysis unit performs a concise analysis on general conversational content to provide only the key points. For example, the analysis unit performs a detailed analysis on topics that the user has shown particular interest in. This allows the level of detail in the analysis to be adjusted based on the importance of the conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the conversation into the AI ​​and have the AI ​​perform the adjustment of the level of detail in the analysis.

[0080] The analysis unit applies different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit applies a specialized analysis algorithm to business-related conversations. For example, the analysis unit applies an algorithm that emphasizes sentiment analysis to entertainment-related conversations. For example, the analysis unit applies a general analysis algorithm to everyday conversations. This allows the appropriate analysis algorithm to be applied according to the category of the conversation. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the conversation into the AI ​​and have the AI ​​perform the application of the analysis algorithm.

[0081] The analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user emotions. For example, if the user is relaxed, the analysis unit displays detailed analysis results. For example, if the user is stressed, the analysis unit displays concise analysis results. For example, if the user is excited, the analysis unit provides a visually stimulating display method. This allows the display method of the analysis results to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The analysis unit determines the priority of analysis based on the timing of conversation submission during the analysis process. For example, the analysis unit may prioritize analyzing the most recent conversation content. For example, the analysis unit may prioritize analyzing conversations that the user had during a specific time period. For example, the analysis unit may prioritize analyzing conversations that the user had before or after an important event. This allows the analysis priority to be determined based on the timing of conversation submission. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit may input the timing of conversation submission into the AI ​​and have the AI ​​perform the determination of analysis priority.

[0083] The analysis unit adjusts the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analyzing conversations that the user has had consecutively on a particular topic. For example, the analysis unit prioritizes analyzing conversations that the user has had with a particular person. For example, the analysis unit prioritizes analyzing conversations that the user has had in a particular location. This allows the order of analysis to be adjusted based on the relevance of the conversations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the conversations into the AI ​​and have the AI ​​perform the adjustment of the order of analysis.

[0084] The suggestion unit estimates the user's emotions and adjusts the presentation of the ad suggestion based on the estimated emotions. For example, if the user is relaxed, the suggestion unit suggests an ad using a calm presentation. If the user is stressed, the suggestion unit suggests an ad using a simple and intuitive presentation. If the user is excited, the suggestion unit suggests an ad using a visually stimulating presentation. This allows the presentation of the ad suggestion to be adjusted based on 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 AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The suggestion unit adjusts the level of detail in its suggestions based on the importance of the advertisements. For example, the suggestion unit provides detailed information for important advertisements, concise information for general advertisements, and detailed information for advertisements that users have shown particular interest in. This allows the level of detail in suggestions to be adjusted based on the importance of the advertisements. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not. For example, the suggestion unit can input the importance of the advertisements into the AI ​​and have the AI ​​perform the adjustment of the level of detail in suggestions.

[0086] The proposal unit applies different proposal algorithms depending on the advertisement category when making proposals. For example, the proposal unit applies a specialized proposal algorithm for business-related advertisements. For example, the proposal unit applies an algorithm that emphasizes sentiment analysis for entertainment-related advertisements. For example, the proposal unit applies a general proposal algorithm for everyday life-related advertisements. This ensures that the appropriate proposal algorithm is applied according to the advertisement category. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input the advertisement category into the AI ​​and have the AI ​​perform the application of the proposal algorithm.

[0087] The suggestion unit estimates the user's emotions and adjusts the length of the suggestions based on the estimated emotions. For example, if the user is relaxed, the suggestion unit provides detailed suggestions. If the user is stressed, the suggestion unit provides concise suggestions. If the user is excited, the suggestion unit provides visually stimulating suggestions. This allows the length of suggestions to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0088] The proposal department determines the priority of proposals based on the timing of ad submission. For example, the proposal department may prioritize the most recent ads. For example, the proposal department may prioritize ads that users showed interest in during a specific time period. For example, the proposal department may prioritize ads that users showed interest in before or after an important event. This allows the proposal department to determine the priority of proposals based on the timing of ad submission. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input the timing of ad submission into the AI ​​and have the AI ​​perform the determination of proposal priority.

[0089] The suggestion unit adjusts the order of suggestions based on the relevance of the advertisements when making suggestions. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular topic. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular brand. For example, the suggestion unit may prioritize suggesting advertisements that the user has shown interest in a particular product. This allows the order of suggestions to be adjusted based on the relevance of the advertisements. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit may input the relevance of the advertisements into the AI ​​and have the AI ​​perform the adjustment of the suggestion order.

[0090] The insertion unit estimates the user's emotions and adjusts the timing of ad insertion based on the estimated emotions. For example, if the user is relaxed, the insertion unit inserts ads in line with the natural flow of the conversation. For example, if the user is stressed, the insertion unit inserts ads with minimal interruption to the conversation. For example, if the user is excited, the insertion unit inserts ads at the peak of their emotions. This allows the timing of ad insertion to be adjusted based on 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 insertion unit may be performed using AI or not using AI. For example, the insertion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The insertion unit improves the naturalness of ad insertion by considering the flow of conversation. For example, the insertion unit inserts an ad when the topic of conversation changes. For example, the insertion unit selects a way to introduce the ad naturally within the conversation. For example, the insertion unit inserts an ad when the user shows interest in the conversation. This improves the naturalness of ad insertion by considering the flow of conversation. Some or all of the above processing in the insertion unit may be performed using AI, for example, or not using AI. For example, the insertion unit can input the flow of conversation into AI and have the AI ​​perform the improvement of the naturalness of ad insertion.

[0092] The insertion unit selects the optimal insertion method by referring to the user's past response data during insertion. For example, the insertion unit prioritizes ad insertion methods that the user has previously responded favorably to. For example, the insertion unit avoids ad insertion methods that the user has previously ignored. For example, the insertion unit refers to ad insertion methods that the user has previously clicked on. This allows the system to select the optimal ad insertion method based on the user's past response data. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit can input past response data into AI and have the AI ​​select the optimal insertion method.

[0093] The insertion unit estimates the user's emotions and determines the priority of ad insertion based on the estimated user emotions. For example, if the user is relaxed, the insertion unit will prioritize inserting highly relevant ads. For example, if the user is stressed, the insertion unit will prioritize inserting less burdensome ads. For example, if the user is excited, the insertion unit will prioritize inserting visually stimulating ads. This allows the priority of ad insertion to be determined based on 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 insertion unit may be performed using AI, for example, or not using AI. For example, the insertion unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The insertion unit inserts the most suitable advertisements, taking into account the user's geographical location information. For example, if the user is in a specific region, the insertion unit inserts advertisements related to that region. For example, if the user is traveling, the insertion unit inserts advertisements containing tourist information about the travel destination. For example, if the user is at home, the insertion unit inserts advertisements containing information about nearby stores. This allows for the insertion of the most suitable advertisements, taking into account geographical location information. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit can input the user's geographical location information into AI and have the AI ​​perform the insertion of the most suitable advertisements.

[0095] The insertion unit analyzes the user's social media activity during insertion and proposes methods for inserting advertisements. For example, the insertion unit may insert advertisements for brands that the user follows on social media. For example, the insertion unit may insert advertisements related to content that the user has shared on social media. For example, the insertion unit may insert advertisements related to topics in groups that the user participates in on social media. This allows the insertion unit to propose the most suitable method of advertisement insertion based on social media activity. Some or all of the above processing in the insertion unit may be performed using AI, for example, or without AI. For example, the insertion unit may have AI perform the analysis of social media activity.

[0096] The protection unit estimates the user's emotions and adjusts the privacy protection method based on the estimated user emotions. For example, if the user is relaxed, the protection unit provides detailed privacy settings. For example, if the user is stressed, the protection unit provides simple privacy settings. For example, if the user is excited, the protection unit provides visually easy-to-understand privacy settings. This allows the privacy protection method to be adjusted based on 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 protection unit may be performed using AI, for example, or not using AI. For example, the protection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0097] The protection unit, when protecting privacy, selects the optimal protection method by referring to the user's past data usage history. For example, the protection unit suggests the optimal protection method based on the privacy settings the user has previously selected. For example, the protection unit avoids data usage methods that the user has previously rejected. For example, the protection unit prioritizes data usage methods that the user has previously permitted. This allows the protection unit to select the optimal privacy protection method based on past data usage history. Some or all of the above processing in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can input past data usage history into AI and have the AI ​​select the optimal protection method.

[0098] The protection unit estimates the user's emotions and determines the priority of privacy protection based on the estimated user emotions. For example, if the user is relaxed, the protection unit prioritizes detailed privacy protection. If the user is stressed, the protection unit prioritizes concise privacy protection. If the user is excited, the protection unit prioritizes visually clear privacy protection. This allows the protection unit to determine the priority of privacy protection based on 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 protection unit may be performed using AI or not using AI. For example, the protection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0099] The protection unit selects the optimal protection method when protecting privacy, taking into account the user's geographical location. For example, if the user is in a specific region, the protection unit selects a protection method based on the privacy regulations of that region. For example, if the user is traveling, the protection unit selects a protection method based on the privacy regulations of the travel destination. For example, if the user is at home, the protection unit selects a protection method based on the local privacy regulations. This allows the protection unit to select the optimal privacy protection method while taking geographical location into consideration. Some or all of the above processing in the protection unit may be performed using AI, for example, or without AI. For example, the protection unit can input the user's geographical location information into AI and have AI select the optimal protection method.

[0100] The effectiveness measurement unit estimates the user's emotions and adjusts the effectiveness measurement method based on the estimated user emotions. For example, if the user is relaxed, the effectiveness measurement unit performs a detailed effectiveness measurement. For example, if the user is stressed, the effectiveness measurement unit performs a concise effectiveness measurement. For example, if the user is excited, the effectiveness measurement unit performs a visually easy-to-understand effectiveness measurement. This allows the effectiveness measurement method to be adjusted based on 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 effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0101] The effectiveness measurement unit selects the optimal measurement method by referring to past advertising effectiveness data when measuring effectiveness. For example, the effectiveness measurement unit prioritizes measurement methods for advertisements that have shown high effectiveness in the past. For example, the effectiveness measurement unit avoids measurement methods for advertisements that have shown low effectiveness in the past. For example, the effectiveness measurement unit proposes new measurement methods based on past advertising effectiveness data. This allows for the selection of the optimal measurement method based on past advertising effectiveness data. Some or all of the above processes in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input past advertising effectiveness data into AI and have the AI ​​select the optimal measurement method.

[0102] The effectiveness measurement unit estimates the user's emotions and determines the priority of effectiveness measurements based on the estimated user emotions. For example, if the user is relaxed, the effectiveness measurement unit prioritizes detailed effectiveness measurements. For example, if the user is stressed, the effectiveness measurement unit prioritizes concise effectiveness measurements. For example, if the user is excited, the effectiveness measurement unit prioritizes visually easy-to-understand effectiveness measurements. This allows the effectiveness measurement unit to determine the priority of effectiveness measurements based on 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 effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0103] The effectiveness measurement unit weights the measurement data based on the timing of ad submission during effectiveness measurement. For example, the effectiveness measurement unit may prioritize the most recent ad effectiveness data. For example, the effectiveness measurement unit may prioritize the effectiveness data of ads submitted during a specific time period. For example, the effectiveness measurement unit may prioritize the effectiveness data of ads submitted before and after an important event. This allows for weighting of the measurement data based on the timing of ad submission. Some or all of the above processing in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit may input the ad submission timing into the AI ​​and have the AI ​​perform the weighting of the measurement data.

[0104] The effectiveness measurement unit weights the measurement data based on the relevance of the advertisements when measuring effectiveness. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular topic. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular brand. For example, the effectiveness measurement unit gives more weight to the effectiveness data of advertisements in which users showed interest in a particular product. This allows the measurement data to be weighted based on the relevance of the advertisements. Some or all of the above processing in the effectiveness measurement unit may be performed using AI, for example, or without AI. For example, the effectiveness measurement unit can input the relevance of the advertisements into the AI ​​and have the AI ​​perform the weighting of the measurement data.

[0105] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0106] The ad insertion system may also include a voice analysis unit that analyzes the user's voice tone. The voice analysis unit analyzes the user's voice tone, speed, volume, etc., and estimates the user's emotional state. For example, if the user is excited, the voice analysis unit can detect the change in tone and suggest an appropriate ad. If the user is calm, the voice analysis unit can detect a calm tone and suggest ads related to relaxation. In this way, the voice analysis unit can optimize ad suggestions based on the user's voice tone.

[0107] The ad insertion system may also include a device monitoring unit that monitors the user's device usage. The device monitoring unit monitors the type of device the user is using, the duration of use, and the application usage, and then suggests the most suitable ads. For example, if a user is using a smartphone for an extended period, the device monitoring unit can suggest mobile-friendly ads. If the user is using a PC, the device monitoring unit can suggest desktop-friendly ads. This allows the device monitoring unit to optimize ad suggestions based on the user's device usage.

[0108] The ad insertion system may also include a social analytics unit that analyzes the user's social network relationships. The social analytics unit analyzes the user's relationships and interaction frequency on social networks and suggests the most suitable advertisements. For example, if a user frequently interacts with a particular friend, the social analytics unit will suggest advertisements related to products or services that that friend is interested in. If a user belongs to a specific group, the social analytics unit can suggest advertisements based on the group's interests. This allows the social analytics unit to optimize ad suggestions based on the user's social network.

[0109] The ad insertion system can also include a health analysis unit that analyzes the user's health data. The health analysis unit analyzes the user's health status and fitness data to suggest the most suitable advertisements. For example, if a user is using a fitness tracker, the health analysis unit can suggest advertisements for health foods and fitness-related products based on that data. If a user is using a sleep tracker, the health analysis unit can suggest advertisements for relaxation products and sleep improvement products based on that data. This allows the health analysis unit to optimize ad suggestions based on the user's health data.

[0110] The ad insertion system may also include a purchase intent estimation unit that estimates the user's purchase intent. The purchase intent estimation unit analyzes the user's past purchase history and current behavioral data to estimate the user's purchase intent. For example, if a user frequently searches for a particular product, the purchase intent estimation unit will suggest ads related to that product. If a user has recently purchased an item in a particular category, the purchase intent estimation unit can suggest ads for additional products or accessories related to that category. This allows the purchase intent estimation unit to optimize ad suggestions based on the user's purchase intent.

[0111] The ad insertion system may further include a display adjustment unit that estimates the user's emotions and adjusts the ad display format based on those emotions. The display adjustment unit can display ads with calming colors and designs when the user is relaxed, simple and intuitive ads when the user is stressed, and visually stimulating ads when the user is excited. This allows the display adjustment unit to optimize the ad display format based on the user's emotions.

[0112] The ad insertion system may further include a content adjustment unit that estimates the user's emotions and adjusts the ad content based on those emotions. The content adjustment unit can display ads related to relaxation when the user is relaxed, ads related to stress relief when the user is stressed, and ads related to entertainment or activities when the user is excited. This allows the content adjustment unit to optimize ad content based on the user's emotions.

[0113] The ad insertion system may further include a timing adjustment unit that estimates the user's emotions and adjusts the timing of ads based on those emotions. The timing adjustment unit inserts ads in line with the natural flow of conversation when the user is relaxed. When the user is stressed, it inserts ads with minimal interruption to the conversation. When the user is excited, it can insert ads at the peak of their emotions. This allows the timing adjustment unit to optimize ad insertion timing based on the user's emotions.

[0114] The ad insertion system may further include a frequency adjustment unit that estimates the user's emotions and adjusts the frequency of ads based on those emotions. The frequency adjustment unit can increase the ad display frequency when the user is relaxed, decrease it when the user is stressed, and adjust the ad display frequency at specific times when the user is excited. This allows the frequency adjustment unit to optimize ad display frequency based on the user's emotions.

[0115] The ad insertion system may further include a type adjustment unit that estimates the user's emotions and adjusts the type of ad based on those emotions. The type adjustment unit can prioritize displaying relaxation-related ads when the user is relaxed, stress-related ads when the user is stressed, and entertainment or activity-related ads when the user is excited. This allows the type adjustment unit to optimize ad types based on the user's emotions.

[0116] The following briefly describes the processing flow for example form 2.

[0117] Step 1: The data collection unit collects user preferences and behavioral data. For example, the data collection unit collects the user's website browsing history, purchase history, and search history. Step 2: The analysis unit analyzes the data collected by the collection unit and analyzes the user's conversation content in real time. For example, the analysis unit uses generation AI, such as text generation AI, multimodal generation AI, and natural language processing technology, to analyze the conversation content. Step 3: The proposal unit proposes appropriate advertisements based on the conversation content analyzed by the analysis unit. For example, the proposal unit uses generative AI to propose advertisements using text generation AI, multimodal generation AI, and recommendation algorithms. Step 4: The insertion section seamlessly inserts the advertisement proposed by the suggestion section. For example, the insertion section inserts the advertisement in a way that does not disrupt the flow of the conversation and selects a method of introducing the advertisement that does not make the user feel uncomfortable.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, insertion unit, protection unit, and effectiveness measurement unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects user preferences and behavioral data using the camera 42 and microphone 38B of the smart device 14. The analysis unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and analyzes the user's conversation content using a generating AI. The proposal unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and proposes appropriate advertisements based on the analysis results. The insertion unit is implemented in real time using a specific processing unit 46A of the smart device 14 and inserts the proposed advertisements naturally. The protection unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The effectiveness measurement unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and measures the click-through rate and conversion rate of advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0122] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Each of the multiple elements described above, including the data collection unit, analysis unit, proposal unit, insertion unit, protection unit, and effectiveness measurement unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects user preferences and behavioral data using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and analyzes the user's conversation content using a generating AI. The proposal unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and proposes appropriate advertisements based on the analysis results. The insertion unit is implemented in real time using a specific processing unit 46A of the smart glasses 214 and inserts the proposed advertisements naturally. The protection unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and protects the user's privacy. The effectiveness measurement unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and measures the click-through rate and conversion rate of advertisements. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0138] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, insertion unit, protection unit, and effectiveness measurement unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects user preferences and behavioral data using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and analyzes the user's conversation content using a generation AI. The proposal unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and proposes appropriate advertisements based on the analysis results. The insertion unit is implemented in real time using a specific processing unit 46A of the headset terminal 314 and inserts the proposed advertisements naturally. The protection unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and protects user privacy. The effectiveness measurement unit is implemented in real time using a specific processing unit 290 of the data processing unit 12 and measures the click-through rate and conversion rate of advertisements. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0154] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, insertion unit, protection unit, and effectiveness measurement unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects user preferences and behavioral data using the camera 42 and microphone 238 of the robot 414. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and analyzes the user's conversation content in real time using generating AI. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and proposes appropriate advertisements based on the analysis results. The insertion unit is implemented by, for example, the control unit 46A of the robot 414, and inserts the proposed advertisements naturally. The protection unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and protects the user's privacy. The effectiveness measurement unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and measures the click-through rate and conversion rate of advertisements. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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."

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] (Note 1) A data collection unit that collects user hobbies, preferences, and behavioral data, The data collected by the aforementioned collection unit is analyzed by an analysis unit that analyzes the user's conversation content in real time, A proposal unit proposes an appropriate advertisement based on the conversation content analyzed by the aforementioned analysis unit, The system includes an insertion unit that naturally inserts the advertisement proposed by the proposal unit. A system characterized by the following features. (Note 2) It is equipped with a protective section to protect user privacy. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an effectiveness measurement unit that measures the click-through rate and conversion rate of advertisements. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting hobby, preference, and behavioral data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Analyze users' past behavioral data to select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting data, filtering is performed based on the user's current activities and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 7) 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 8) The aforementioned collection unit is During data collection, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and adjusts the conversation analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the conversation was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, The system estimates the user's emotions and adjusts the way ad suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the proposal based on the importance of the advertisement. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the ad category. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, When submitting proposals, prioritize them based on the timing of their ad submission. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the ads. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned insertion portion is We estimate the user's emotions and adjust the timing of ad placement based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned insertion portion is When inserting ads, we consider the flow of the conversation to improve the naturalness of the ad insertion. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned insertion portion is During insertion, the system selects the optimal insertion method by referring to the user's past response data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned insertion portion is It estimates user sentiment and determines ad placement priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned insertion portion is When inserting ads, the system considers the user's geographical location to ensure the most relevant ads are inserted. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned insertion portion is During insertion, the system analyzes the user's social media activity and suggests methods for inserting ads. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned protective part is We estimate the user's emotions and adjust our privacy protection methods based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned protective part is When protecting privacy, the system selects the most appropriate protection method by referring to the user's past data usage history. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned protective part is It estimates user sentiment and determines privacy protection priorities based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned protective part is When protecting privacy, the optimal protection method is selected by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned effect measurement unit is We estimate user emotions and adjust the effectiveness measurement method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned effect measurement unit is When measuring effectiveness, the optimal measurement method is selected by referring to past advertising effectiveness data. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned effect measurement unit is We estimate user emotions and determine the priority of effectiveness measurement based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned effect measurement unit is When measuring effectiveness, weight the measurement data based on when the advertisement was submitted. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned effect measurement unit is When measuring effectiveness, weight the measurement data based on the relevance of the advertisement. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0190] 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. A data collection unit that collects user hobbies, preferences, and behavioral data, The data collected by the aforementioned collection unit is analyzed by an analysis unit that analyzes the user's conversation content in real time, A proposal unit proposes an appropriate advertisement based on the conversation content analyzed by the aforementioned analysis unit, The system includes an insertion unit that naturally inserts the advertisement proposed by the proposal unit. A system characterized by the following features.

2. It is equipped with a protective section to protect user privacy. The system according to feature 1.

3. It includes an effectiveness measurement unit that measures the click-through rate and conversion rate of advertisements. The system according to feature 1.

4. The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of collecting hobby, preference, and behavioral data based on the estimated user emotions. The system according to feature 1.

5. The aforementioned collection unit is Analyze users' past behavioral data to select the optimal data collection method. The system according to feature 1.

6. The aforementioned collection unit is When collecting data, filtering is performed based on the user's current activities and areas of interest. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is During data collection, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system according to feature 1.

9. The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system according to feature 1.

10. The aforementioned analysis unit, It estimates the user's emotions and adjusts the conversation analysis method based on the estimated user emotions. The system according to feature 1.

Images